| 1033 1036 45 1038 10 10 7 10 10 10 7 7 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Fast batching percpu counters. */ #include <linux/percpu_counter.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/cpu.h> #include <linux/module.h> #include <linux/debugobjects.h> #ifdef CONFIG_HOTPLUG_CPU static LIST_HEAD(percpu_counters); static DEFINE_SPINLOCK(percpu_counters_lock); #endif #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER static const struct debug_obj_descr percpu_counter_debug_descr; static bool percpu_counter_fixup_free(void *addr, enum debug_obj_state state) { struct percpu_counter *fbc = addr; switch (state) { case ODEBUG_STATE_ACTIVE: percpu_counter_destroy(fbc); debug_object_free(fbc, &percpu_counter_debug_descr); return true; default: return false; } } static const struct debug_obj_descr percpu_counter_debug_descr = { .name = "percpu_counter", .fixup_free = percpu_counter_fixup_free, }; static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { debug_object_init(fbc, &percpu_counter_debug_descr); debug_object_activate(fbc, &percpu_counter_debug_descr); } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { debug_object_deactivate(fbc, &percpu_counter_debug_descr); debug_object_free(fbc, &percpu_counter_debug_descr); } #else /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ static inline void debug_percpu_counter_activate(struct percpu_counter *fbc) { } static inline void debug_percpu_counter_deactivate(struct percpu_counter *fbc) { } #endif /* CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER */ void percpu_counter_set(struct percpu_counter *fbc, s64 amount) { int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); for_each_possible_cpu(cpu) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); *pcount = 0; } fbc->count = amount; raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_set); /* * Add to a counter while respecting batch size. * * There are 2 implementations, both dealing with the following problem: * * The decision slow path/fast path and the actual update must be atomic. * Otherwise a call in process context could check the current values and * decide that the fast path can be used. If now an interrupt occurs before * the this_cpu_add(), and the interrupt updates this_cpu(*fbc->counters), * then the this_cpu_add() that is executed after the interrupt has completed * can produce values larger than "batch" or even overflows. */ #ifdef CONFIG_HAVE_CMPXCHG_LOCAL /* * Safety against interrupts is achieved in 2 ways: * 1. the fast path uses local cmpxchg (note: no lock prefix) * 2. the slow path operates with interrupts disabled */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; unsigned long flags; count = this_cpu_read(*fbc->counters); do { if (unlikely(abs(count + amount) >= batch)) { raw_spin_lock_irqsave(&fbc->lock, flags); /* * Note: by now we might have migrated to another CPU * or the value might have changed. */ count = __this_cpu_read(*fbc->counters); fbc->count += count + amount; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); return; } } while (!this_cpu_try_cmpxchg(*fbc->counters, &count, count + amount)); } #else /* * local_irq_save() is used to make the function irq safe: * - The slow path would be ok as protected by an irq-safe spinlock. * - this_cpu_add would be ok as it is irq-safe by definition. */ void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch) { s64 count; unsigned long flags; local_irq_save(flags); count = __this_cpu_read(*fbc->counters) + amount; if (abs(count) >= batch) { raw_spin_lock(&fbc->lock); fbc->count += count; __this_cpu_sub(*fbc->counters, count - amount); raw_spin_unlock(&fbc->lock); } else { this_cpu_add(*fbc->counters, amount); } local_irq_restore(flags); } #endif EXPORT_SYMBOL(percpu_counter_add_batch); /* * For percpu_counter with a big batch, the devication of its count could * be big, and there is requirement to reduce the deviation, like when the * counter's batch could be runtime decreased to get a better accuracy, * which can be achieved by running this sync function on each CPU. */ void percpu_counter_sync(struct percpu_counter *fbc) { unsigned long flags; s64 count; raw_spin_lock_irqsave(&fbc->lock, flags); count = __this_cpu_read(*fbc->counters); fbc->count += count; __this_cpu_sub(*fbc->counters, count); raw_spin_unlock_irqrestore(&fbc->lock, flags); } EXPORT_SYMBOL(percpu_counter_sync); /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive(). * * We use the cpu mask of (cpu_online_mask | cpu_dying_mask) to capture sums * from CPUs that are in the process of being taken offline. Dying cpus have * been removed from the online mask, but may not have had the hotplug dead * notifier called to fold the percpu count back into the global counter sum. * By including dying CPUs in the iteration mask, we avoid this race condition * so __percpu_counter_sum() just does the right thing when CPUs are being taken * offline. */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { s64 ret; int cpu; unsigned long flags; raw_spin_lock_irqsave(&fbc->lock, flags); ret = fbc->count; for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { s32 *pcount = per_cpu_ptr(fbc->counters, cpu); ret += *pcount; } raw_spin_unlock_irqrestore(&fbc->lock, flags); return ret; } EXPORT_SYMBOL(__percpu_counter_sum); int __percpu_counter_init_many(struct percpu_counter *fbc, s64 amount, gfp_t gfp, u32 nr_counters, struct lock_class_key *key) { unsigned long flags __maybe_unused; size_t counter_size; s32 __percpu *counters; u32 i; counter_size = ALIGN(sizeof(*counters), __alignof__(*counters)); counters = __alloc_percpu_gfp(nr_counters * counter_size, __alignof__(*counters), gfp); if (!counters) { fbc[0].counters = NULL; return -ENOMEM; } for (i = 0; i < nr_counters; i++) { raw_spin_lock_init(&fbc[i].lock); lockdep_set_class(&fbc[i].lock, key); #ifdef CONFIG_HOTPLUG_CPU INIT_LIST_HEAD(&fbc[i].list); #endif fbc[i].count = amount; fbc[i].counters = (void __percpu *)counters + i * counter_size; debug_percpu_counter_activate(&fbc[i]); } #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); for (i = 0; i < nr_counters; i++) list_add(&fbc[i].list, &percpu_counters); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif return 0; } EXPORT_SYMBOL(__percpu_counter_init_many); void percpu_counter_destroy_many(struct percpu_counter *fbc, u32 nr_counters) { unsigned long flags __maybe_unused; u32 i; if (WARN_ON_ONCE(!fbc)) return; if (!fbc[0].counters) return; for (i = 0; i < nr_counters; i++) debug_percpu_counter_deactivate(&fbc[i]); #ifdef CONFIG_HOTPLUG_CPU spin_lock_irqsave(&percpu_counters_lock, flags); for (i = 0; i < nr_counters; i++) list_del(&fbc[i].list); spin_unlock_irqrestore(&percpu_counters_lock, flags); #endif free_percpu(fbc[0].counters); for (i = 0; i < nr_counters; i++) fbc[i].counters = NULL; } EXPORT_SYMBOL(percpu_counter_destroy_many); int percpu_counter_batch __read_mostly = 32; EXPORT_SYMBOL(percpu_counter_batch); static int compute_batch_value(unsigned int cpu) { int nr = num_online_cpus(); percpu_counter_batch = max(32, nr*2); return 0; } static int percpu_counter_cpu_dead(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU struct percpu_counter *fbc; compute_batch_value(cpu); spin_lock_irq(&percpu_counters_lock); list_for_each_entry(fbc, &percpu_counters, list) { s32 *pcount; raw_spin_lock(&fbc->lock); pcount = per_cpu_ptr(fbc->counters, cpu); fbc->count += *pcount; *pcount = 0; raw_spin_unlock(&fbc->lock); } spin_unlock_irq(&percpu_counters_lock); #endif return 0; } /* * Compare counter against given value. * Return 1 if greater, 0 if equal and -1 if less */ int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch) { s64 count; count = percpu_counter_read(fbc); /* Check to see if rough count will be sufficient for comparison */ if (abs(count - rhs) > (batch * num_online_cpus())) { if (count > rhs) return 1; else return -1; } /* Need to use precise count */ count = percpu_counter_sum(fbc); if (count > rhs) return 1; else if (count < rhs) return -1; else return 0; } EXPORT_SYMBOL(__percpu_counter_compare); /* * Compare counter, and add amount if total is: less than or equal to limit if * amount is positive, or greater than or equal to limit if amount is negative. * Return true if amount is added, or false if total would be beyond the limit. * * Negative limit is allowed, but unusual. * When negative amounts (subs) are given to percpu_counter_limited_add(), * the limit would most naturally be 0 - but other limits are also allowed. * * Overflow beyond S64_MAX is not allowed for: counter, limit and amount * are all assumed to be sane (far from S64_MIN and S64_MAX). */ bool __percpu_counter_limited_add(struct percpu_counter *fbc, s64 limit, s64 amount, s32 batch) { s64 count; s64 unknown; unsigned long flags; bool good = false; if (amount == 0) return true; local_irq_save(flags); unknown = batch * num_online_cpus(); count = __this_cpu_read(*fbc->counters); /* Skip taking the lock when safe */ if (abs(count + amount) <= batch && ((amount > 0 && fbc->count + unknown <= limit) || (amount < 0 && fbc->count - unknown >= limit))) { this_cpu_add(*fbc->counters, amount); local_irq_restore(flags); return true; } raw_spin_lock(&fbc->lock); count = fbc->count + amount; /* Skip percpu_counter_sum() when safe */ if (amount > 0) { if (count - unknown > limit) goto out; if (count + unknown <= limit) good = true; } else { if (count + unknown < limit) goto out; if (count - unknown >= limit) good = true; } if (!good) { s32 *pcount; int cpu; for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { pcount = per_cpu_ptr(fbc->counters, cpu); count += *pcount; } if (amount > 0) { if (count > limit) goto out; } else { if (count < limit) goto out; } good = true; } count = __this_cpu_read(*fbc->counters); fbc->count += count + amount; __this_cpu_sub(*fbc->counters, count); out: raw_spin_unlock(&fbc->lock); local_irq_restore(flags); return good; } static int __init percpu_counter_startup(void) { int ret; ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "lib/percpu_cnt:online", compute_batch_value, NULL); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_PERCPU_CNT_DEAD, "lib/percpu_cnt:dead", NULL, percpu_counter_cpu_dead); WARN_ON(ret < 0); return 0; } module_init(percpu_counter_startup); |
| 1160 1164 | 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 | // 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)); } 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; } } #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); } } |
| 248 45 45 44 1 1 43 1 43 43 37 37 37 30 30 30 30 105 100 5 24 37 37 1 36 1 37 37 37 24 37 6 20 26 14 7 7 4 14 26 26 26 20 6 116 115 1 107 3 107 104 4 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2015, 2016 ARM Ltd. */ #include <linux/uaccess.h> #include <linux/interrupt.h> #include <linux/cpu.h> #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include "vgic.h" /* * Initialization rules: there are multiple stages to the vgic * initialization, both for the distributor and the CPU interfaces. The basic * idea is that even though the VGIC is not functional or not requested from * user space, the critical path of the run loop can still call VGIC functions * that just won't do anything, without them having to check additional * initialization flags to ensure they don't look at uninitialized data * structures. * * Distributor: * * - kvm_vgic_early_init(): initialization of static data that doesn't * depend on any sizing information or emulation type. No allocation * is allowed there. * * - vgic_init(): allocation and initialization of the generic data * structures that depend on sizing information (number of CPUs, * number of interrupts). Also initializes the vcpu specific data * structures. Can be executed lazily for GICv2. * * CPU Interface: * * - kvm_vgic_vcpu_init(): initialization of static data that doesn't depend * on any sizing information. Private interrupts are allocated if not * already allocated at vgic-creation time. */ /* EARLY INIT */ /** * kvm_vgic_early_init() - Initialize static VGIC VCPU data structures * @kvm: The VM whose VGIC districutor should be initialized * * Only do initialization of static structures that don't require any * allocation or sizing information from userspace. vgic_init() called * kvm_vgic_dist_init() which takes care of the rest. */ void kvm_vgic_early_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; xa_init(&dist->lpi_xa); } /* CREATION */ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type); /** * kvm_vgic_create: triggered by the instantiation of the VGIC device by * user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only) * or through the generic KVM_CREATE_DEVICE API ioctl. * irqchip_in_kernel() tells you if this function succeeded or not. * @kvm: kvm struct pointer * @type: KVM_DEV_TYPE_ARM_VGIC_V[23] */ int kvm_vgic_create(struct kvm *kvm, u32 type) { struct kvm_vcpu *vcpu; unsigned long i; int ret; /* * This function is also called by the KVM_CREATE_IRQCHIP handler, * which had no chance yet to check the availability of the GICv2 * emulation. So check this here again. KVM_CREATE_DEVICE does * the proper checks already. */ if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && !kvm_vgic_global_state.can_emulate_gicv2) return -ENODEV; /* * Ensure mutual exclusion with vCPU creation and any vCPU ioctls by: * * - Holding kvm->lock to prevent KVM_CREATE_VCPU from reaching * kvm_arch_vcpu_precreate() and ensuring created_vcpus is stable. * This alone is insufficient, as kvm_vm_ioctl_create_vcpu() drops * the kvm->lock before completing the vCPU creation. */ lockdep_assert_held(&kvm->lock); /* * - Acquiring the vCPU mutex for every *online* vCPU to prevent * concurrent vCPU ioctls for vCPUs already visible to userspace. */ ret = -EBUSY; if (kvm_trylock_all_vcpus(kvm)) return ret; /* * - Taking the config_lock which protects VGIC data structures such * as the per-vCPU arrays of private IRQs (SGIs, PPIs). */ mutex_lock(&kvm->arch.config_lock); /* * - Bailing on the entire thing if a vCPU is in the middle of creation, * dropped the kvm->lock, but hasn't reached kvm_arch_vcpu_create(). * * The whole combination of this guarantees that no vCPU can get into * KVM with a VGIC configuration inconsistent with the VM's VGIC. */ if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus)) goto out_unlock; if (irqchip_in_kernel(kvm)) { ret = -EEXIST; goto out_unlock; } kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu_has_run_once(vcpu)) goto out_unlock; } ret = 0; if (type == KVM_DEV_TYPE_ARM_VGIC_V2) kvm->max_vcpus = VGIC_V2_MAX_CPUS; else kvm->max_vcpus = VGIC_V3_MAX_CPUS; if (atomic_read(&kvm->online_vcpus) > kvm->max_vcpus) { ret = -E2BIG; goto out_unlock; } kvm_for_each_vcpu(i, vcpu, kvm) { ret = vgic_allocate_private_irqs_locked(vcpu, type); if (ret) break; } if (ret) { kvm_for_each_vcpu(i, vcpu, kvm) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; kfree(vgic_cpu->private_irqs); vgic_cpu->private_irqs = NULL; } goto out_unlock; } kvm->arch.vgic.in_kernel = true; kvm->arch.vgic.vgic_model = type; kvm->arch.vgic.implementation_rev = KVM_VGIC_IMP_REV_LATEST; kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; if (type == KVM_DEV_TYPE_ARM_VGIC_V2) kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; else INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); if (type == KVM_DEV_TYPE_ARM_VGIC_V3) kvm->arch.vgic.nassgicap = system_supports_direct_sgis(); out_unlock: mutex_unlock(&kvm->arch.config_lock); kvm_unlock_all_vcpus(kvm); return ret; } /* INIT/DESTROY */ /** * kvm_vgic_dist_init: initialize the dist data structures * @kvm: kvm struct pointer * @nr_spis: number of spis, frozen by caller */ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0); int i; dist->active_spis = (atomic_t)ATOMIC_INIT(0); dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL_ACCOUNT); if (!dist->spis) return -ENOMEM; /* * In the following code we do not take the irq struct lock since * no other action on irq structs can happen while the VGIC is * not initialized yet: * If someone wants to inject an interrupt or does a MMIO access, we * require prior initialization in case of a virtual GICv3 or trigger * initialization when using a virtual GICv2. */ for (i = 0; i < nr_spis; i++) { struct vgic_irq *irq = &dist->spis[i]; irq->intid = i + VGIC_NR_PRIVATE_IRQS; INIT_LIST_HEAD(&irq->ap_list); raw_spin_lock_init(&irq->irq_lock); irq->vcpu = NULL; irq->target_vcpu = vcpu0; refcount_set(&irq->refcount, 0); switch (dist->vgic_model) { case KVM_DEV_TYPE_ARM_VGIC_V2: irq->targets = 0; irq->group = 0; break; case KVM_DEV_TYPE_ARM_VGIC_V3: irq->mpidr = 0; irq->group = 1; break; default: kfree(dist->spis); dist->spis = NULL; return -EINVAL; } } return 0; } /* Default GICv3 Maintenance Interrupt INTID, as per SBSA */ #define DEFAULT_MI_INTID 25 int kvm_vgic_vcpu_nv_init(struct kvm_vcpu *vcpu) { int ret; guard(mutex)(&vcpu->kvm->arch.config_lock); /* * Matching the tradition established with the timers, provide * a default PPI for the maintenance interrupt. It makes * things easier to reason about. */ if (vcpu->kvm->arch.vgic.mi_intid == 0) vcpu->kvm->arch.vgic.mi_intid = DEFAULT_MI_INTID; ret = kvm_vgic_set_owner(vcpu, vcpu->kvm->arch.vgic.mi_intid, vcpu); return ret; } static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; int i; lockdep_assert_held(&vcpu->kvm->arch.config_lock); if (vgic_cpu->private_irqs) return 0; vgic_cpu->private_irqs = kcalloc(VGIC_NR_PRIVATE_IRQS, sizeof(struct vgic_irq), GFP_KERNEL_ACCOUNT); if (!vgic_cpu->private_irqs) return -ENOMEM; /* * Enable and configure all SGIs to be edge-triggered and * configure all PPIs as level-triggered. */ for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; INIT_LIST_HEAD(&irq->ap_list); raw_spin_lock_init(&irq->irq_lock); irq->intid = i; irq->vcpu = NULL; irq->target_vcpu = vcpu; refcount_set(&irq->refcount, 0); if (vgic_irq_is_sgi(i)) { /* SGIs */ irq->enabled = 1; irq->config = VGIC_CONFIG_EDGE; } else { /* PPIs */ irq->config = VGIC_CONFIG_LEVEL; } switch (type) { case KVM_DEV_TYPE_ARM_VGIC_V3: irq->group = 1; irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu); break; case KVM_DEV_TYPE_ARM_VGIC_V2: irq->group = 0; irq->targets = BIT(vcpu->vcpu_id); break; } } return 0; } static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu, u32 type) { int ret; mutex_lock(&vcpu->kvm->arch.config_lock); ret = vgic_allocate_private_irqs_locked(vcpu, type); mutex_unlock(&vcpu->kvm->arch.config_lock); return ret; } /** * kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data * structures and register VCPU-specific KVM iodevs * * @vcpu: pointer to the VCPU being created and initialized * * Only do initialization, but do not actually enable the * VGIC CPU interface */ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_dist *dist = &vcpu->kvm->arch.vgic; int ret = 0; vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; INIT_LIST_HEAD(&vgic_cpu->ap_list_head); raw_spin_lock_init(&vgic_cpu->ap_list_lock); atomic_set(&vgic_cpu->vgic_v3.its_vpe.vlpi_count, 0); if (!irqchip_in_kernel(vcpu->kvm)) return 0; ret = vgic_allocate_private_irqs(vcpu, dist->vgic_model); if (ret) return ret; /* * If we are creating a VCPU with a GICv3 we must also register the * KVM io device for the redistributor that belongs to this VCPU. */ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { mutex_lock(&vcpu->kvm->slots_lock); ret = vgic_register_redist_iodev(vcpu); mutex_unlock(&vcpu->kvm->slots_lock); } return ret; } static void kvm_vgic_vcpu_reset(struct kvm_vcpu *vcpu) { if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_reset(vcpu); else vgic_v3_reset(vcpu); } /* * vgic_init: allocates and initializes dist and vcpu data structures * depending on two dimensioning parameters: * - the number of spis * - the number of vcpus * The function is generally called when nr_spis has been explicitly set * by the guest through the KVM DEVICE API. If not nr_spis is set to 256. * vgic_initialized() returns true when this function has succeeded. */ int vgic_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; int ret = 0; unsigned long idx; lockdep_assert_held(&kvm->arch.config_lock); if (vgic_initialized(kvm)) return 0; /* Are we also in the middle of creating a VCPU? */ if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus)) return -EBUSY; /* freeze the number of spis */ if (!dist->nr_spis) dist->nr_spis = VGIC_NR_IRQS_LEGACY - VGIC_NR_PRIVATE_IRQS; ret = kvm_vgic_dist_init(kvm, dist->nr_spis); if (ret) goto out; /* * Ensure vPEs are allocated if direct IRQ injection (e.g. vSGIs, * vLPIs) is supported. */ if (vgic_supports_direct_irqs(kvm)) { ret = vgic_v4_init(kvm); if (ret) goto out; } kvm_for_each_vcpu(idx, vcpu, kvm) kvm_vgic_vcpu_reset(vcpu); ret = kvm_vgic_setup_default_irq_routing(kvm); if (ret) goto out; vgic_debug_init(kvm); dist->initialized = true; out: return ret; } static void kvm_vgic_dist_destroy(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_redist_region *rdreg, *next; dist->ready = false; dist->initialized = false; kfree(dist->spis); dist->spis = NULL; dist->nr_spis = 0; dist->vgic_dist_base = VGIC_ADDR_UNDEF; if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) vgic_v3_free_redist_region(kvm, rdreg); INIT_LIST_HEAD(&dist->rd_regions); } else { dist->vgic_cpu_base = VGIC_ADDR_UNDEF; } if (vgic_supports_direct_irqs(kvm)) vgic_v4_teardown(kvm); xa_destroy(&dist->lpi_xa); } static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; /* * Retire all pending LPIs on this vcpu anyway as we're * going to destroy it. */ vgic_flush_pending_lpis(vcpu); INIT_LIST_HEAD(&vgic_cpu->ap_list_head); kfree(vgic_cpu->private_irqs); vgic_cpu->private_irqs = NULL; if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { /* * If this vCPU is being destroyed because of a failed creation * then unregister the redistributor to avoid leaving behind a * dangling pointer to the vCPU struct. * * vCPUs that have been successfully created (i.e. added to * kvm->vcpu_array) get unregistered in kvm_vgic_destroy(), as * this function gets called while holding kvm->arch.config_lock * in the VM teardown path and would otherwise introduce a lock * inversion w.r.t. kvm->srcu. * * vCPUs that failed creation are torn down outside of the * kvm->arch.config_lock and do not get unregistered in * kvm_vgic_destroy(), meaning it is both safe and necessary to * do so here. */ if (kvm_get_vcpu_by_id(vcpu->kvm, vcpu->vcpu_id) != vcpu) vgic_unregister_redist_iodev(vcpu); vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; } } void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; mutex_lock(&kvm->slots_lock); __kvm_vgic_vcpu_destroy(vcpu); mutex_unlock(&kvm->slots_lock); } void kvm_vgic_destroy(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; mutex_lock(&kvm->slots_lock); mutex_lock(&kvm->arch.config_lock); vgic_debug_destroy(kvm); kvm_for_each_vcpu(i, vcpu, kvm) __kvm_vgic_vcpu_destroy(vcpu); kvm_vgic_dist_destroy(kvm); mutex_unlock(&kvm->arch.config_lock); if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) kvm_for_each_vcpu(i, vcpu, kvm) vgic_unregister_redist_iodev(vcpu); mutex_unlock(&kvm->slots_lock); } /** * vgic_lazy_init: Lazy init is only allowed if the GIC exposed to the guest * is a GICv2. A GICv3 must be explicitly initialized by userspace using the * KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEVICE group. * @kvm: kvm struct pointer */ int vgic_lazy_init(struct kvm *kvm) { int ret = 0; if (unlikely(!vgic_initialized(kvm))) { /* * We only provide the automatic initialization of the VGIC * for the legacy case of a GICv2. Any other type must * be explicitly initialized once setup with the respective * KVM device call. */ if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2) return -EBUSY; mutex_lock(&kvm->arch.config_lock); ret = vgic_init(kvm); mutex_unlock(&kvm->arch.config_lock); } return ret; } /* RESOURCE MAPPING */ /** * kvm_vgic_map_resources - map the MMIO regions * @kvm: kvm struct pointer * * Map the MMIO regions depending on the VGIC model exposed to the guest * called on the first VCPU run. * Also map the virtual CPU interface into the VM. * v2 calls vgic_init() if not already done. * v3 and derivatives return an error if the VGIC is not initialized. */ int kvm_vgic_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; enum vgic_type type; gpa_t dist_base; int ret = 0; if (likely(smp_load_acquire(&dist->ready))) return 0; mutex_lock(&kvm->slots_lock); mutex_lock(&kvm->arch.config_lock); if (dist->ready) goto out; if (!irqchip_in_kernel(kvm)) goto out; if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) { ret = vgic_v2_map_resources(kvm); type = VGIC_V2; } else { ret = vgic_v3_map_resources(kvm); type = VGIC_V3; } if (ret) goto out; dist_base = dist->vgic_dist_base; mutex_unlock(&kvm->arch.config_lock); ret = vgic_register_dist_iodev(kvm, dist_base, type); if (ret) { kvm_err("Unable to register VGIC dist MMIO regions\n"); goto out_slots; } smp_store_release(&dist->ready, true); goto out_slots; out: mutex_unlock(&kvm->arch.config_lock); out_slots: if (ret) kvm_vm_dead(kvm); mutex_unlock(&kvm->slots_lock); return ret; } /* GENERIC PROBE */ void kvm_vgic_cpu_up(void) { enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0); } void kvm_vgic_cpu_down(void) { disable_percpu_irq(kvm_vgic_global_state.maint_irq); } static irqreturn_t vgic_maintenance_handler(int irq, void *data) { struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)data; /* * We cannot rely on the vgic maintenance interrupt to be * delivered synchronously. This means we can only use it to * exit the VM, and we perform the handling of EOIed * interrupts on the exit path (see vgic_fold_lr_state). * * Of course, NV throws a wrench in this plan, and needs * something special. */ if (vcpu && vgic_state_is_nested(vcpu)) vgic_v3_handle_nested_maint_irq(vcpu); return IRQ_HANDLED; } static struct gic_kvm_info *gic_kvm_info; void __init vgic_set_kvm_info(const struct gic_kvm_info *info) { BUG_ON(gic_kvm_info != NULL); gic_kvm_info = kmalloc(sizeof(*info), GFP_KERNEL); if (gic_kvm_info) *gic_kvm_info = *info; } /** * kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware * * For a specific CPU, initialize the GIC VE hardware. */ void kvm_vgic_init_cpu_hardware(void) { BUG_ON(preemptible()); /* * We want to make sure the list registers start out clear so that we * only have the program the used registers. */ if (kvm_vgic_global_state.type == VGIC_V2) { vgic_v2_init_lrs(); } else if (kvm_vgic_global_state.type == VGIC_V3 || kvm_vgic_global_state.has_gcie_v3_compat) { kvm_call_hyp(__vgic_v3_init_lrs); } } /** * kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable * according to the host GIC model. Accordingly calls either * vgic_v2/v3_probe which registers the KVM_DEVICE that can be * instantiated by a guest later on . */ int kvm_vgic_hyp_init(void) { bool has_mask; int ret; if (!gic_kvm_info) return -ENODEV; has_mask = !gic_kvm_info->no_maint_irq_mask; if (has_mask && !gic_kvm_info->maint_irq) { kvm_err("No vgic maintenance irq\n"); return -ENXIO; } /* * If we get one of these oddball non-GICs, taint the kernel, * as we have no idea of how they *really* behave. */ if (gic_kvm_info->no_hw_deactivation) { kvm_info("Non-architectural vgic, tainting kernel\n"); add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); kvm_vgic_global_state.no_hw_deactivation = true; } switch (gic_kvm_info->type) { case GIC_V2: ret = vgic_v2_probe(gic_kvm_info); break; case GIC_V3: ret = vgic_v3_probe(gic_kvm_info); if (!ret) { static_branch_enable(&kvm_vgic_global_state.gicv3_cpuif); kvm_info("GIC system register CPU interface enabled\n"); } break; case GIC_V5: ret = vgic_v5_probe(gic_kvm_info); break; default: ret = -ENODEV; } kvm_vgic_global_state.maint_irq = gic_kvm_info->maint_irq; kfree(gic_kvm_info); gic_kvm_info = NULL; if (ret) return ret; if (!has_mask && !kvm_vgic_global_state.maint_irq) return 0; ret = request_percpu_irq(kvm_vgic_global_state.maint_irq, vgic_maintenance_handler, "vgic", kvm_get_running_vcpus()); if (ret) { kvm_err("Cannot register interrupt %d\n", kvm_vgic_global_state.maint_irq); return ret; } kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq); return 0; } |
| 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2005 Voltaire Inc. All rights reserved. * Copyright (c) 2002-2005, Network Appliance, Inc. All rights reserved. * Copyright (c) 1999-2019, Mellanox Technologies, Inc. All rights reserved. * Copyright (c) 2005-2006 Intel Corporation. All rights reserved. */ #include <linux/completion.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/mutex.h> #include <linux/random.h> #include <linux/rbtree.h> #include <linux/igmp.h> #include <linux/xarray.h> #include <linux/inetdevice.h> #include <linux/slab.h> #include <linux/module.h> #include <net/route.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netevent.h> #include <net/tcp.h> #include <net/ipv6.h> #include <net/ip_fib.h> #include <net/ip6_route.h> #include <rdma/rdma_cm.h> #include <rdma/rdma_cm_ib.h> #include <rdma/rdma_netlink.h> #include <rdma/ib.h> #include <rdma/ib_cache.h> #include <rdma/ib_cm.h> #include <rdma/ib_sa.h> #include <rdma/iw_cm.h> #include "core_priv.h" #include "cma_priv.h" #include "cma_trace.h" MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("Generic RDMA CM Agent"); MODULE_LICENSE("Dual BSD/GPL"); #define CMA_CM_RESPONSE_TIMEOUT 20 #define CMA_MAX_CM_RETRIES 15 #define CMA_IBOE_PACKET_LIFETIME 16 #define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP static const char * const cma_events[] = { [RDMA_CM_EVENT_ADDR_RESOLVED] = "address resolved", [RDMA_CM_EVENT_ADDR_ERROR] = "address error", [RDMA_CM_EVENT_ROUTE_RESOLVED] = "route resolved ", [RDMA_CM_EVENT_ROUTE_ERROR] = "route error", [RDMA_CM_EVENT_CONNECT_REQUEST] = "connect request", [RDMA_CM_EVENT_CONNECT_RESPONSE] = "connect response", [RDMA_CM_EVENT_CONNECT_ERROR] = "connect error", [RDMA_CM_EVENT_UNREACHABLE] = "unreachable", [RDMA_CM_EVENT_REJECTED] = "rejected", [RDMA_CM_EVENT_ESTABLISHED] = "established", [RDMA_CM_EVENT_DISCONNECTED] = "disconnected", [RDMA_CM_EVENT_DEVICE_REMOVAL] = "device removal", [RDMA_CM_EVENT_MULTICAST_JOIN] = "multicast join", [RDMA_CM_EVENT_MULTICAST_ERROR] = "multicast error", [RDMA_CM_EVENT_ADDR_CHANGE] = "address change", [RDMA_CM_EVENT_TIMEWAIT_EXIT] = "timewait exit", }; static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, enum ib_gid_type gid_type); static void cma_netevent_work_handler(struct work_struct *_work); const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event) { size_t index = event; return (index < ARRAY_SIZE(cma_events) && cma_events[index]) ? cma_events[index] : "unrecognized event"; } EXPORT_SYMBOL(rdma_event_msg); const char *__attribute_const__ rdma_reject_msg(struct rdma_cm_id *id, int reason) { if (rdma_ib_or_roce(id->device, id->port_num)) return ibcm_reject_msg(reason); if (rdma_protocol_iwarp(id->device, id->port_num)) return iwcm_reject_msg(reason); WARN_ON_ONCE(1); return "unrecognized transport"; } EXPORT_SYMBOL(rdma_reject_msg); /** * rdma_is_consumer_reject - return true if the consumer rejected the connect * request. * @id: Communication identifier that received the REJECT event. * @reason: Value returned in the REJECT event status field. */ static bool rdma_is_consumer_reject(struct rdma_cm_id *id, int reason) { if (rdma_ib_or_roce(id->device, id->port_num)) return reason == IB_CM_REJ_CONSUMER_DEFINED; if (rdma_protocol_iwarp(id->device, id->port_num)) return reason == -ECONNREFUSED; WARN_ON_ONCE(1); return false; } const void *rdma_consumer_reject_data(struct rdma_cm_id *id, struct rdma_cm_event *ev, u8 *data_len) { const void *p; if (rdma_is_consumer_reject(id, ev->status)) { *data_len = ev->param.conn.private_data_len; p = ev->param.conn.private_data; } else { *data_len = 0; p = NULL; } return p; } EXPORT_SYMBOL(rdma_consumer_reject_data); /** * rdma_iw_cm_id() - return the iw_cm_id pointer for this cm_id. * @id: Communication Identifier */ struct iw_cm_id *rdma_iw_cm_id(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); if (id->device->node_type == RDMA_NODE_RNIC) return id_priv->cm_id.iw; return NULL; } EXPORT_SYMBOL(rdma_iw_cm_id); static int cma_add_one(struct ib_device *device); static void cma_remove_one(struct ib_device *device, void *client_data); static struct ib_client cma_client = { .name = "cma", .add = cma_add_one, .remove = cma_remove_one }; static struct ib_sa_client sa_client; static LIST_HEAD(dev_list); static LIST_HEAD(listen_any_list); static DEFINE_MUTEX(lock); static struct rb_root id_table = RB_ROOT; /* Serialize operations of id_table tree */ static DEFINE_SPINLOCK(id_table_lock); static struct workqueue_struct *cma_wq; static unsigned int cma_pernet_id; struct cma_pernet { struct xarray tcp_ps; struct xarray udp_ps; struct xarray ipoib_ps; struct xarray ib_ps; }; static struct cma_pernet *cma_pernet(struct net *net) { return net_generic(net, cma_pernet_id); } static struct xarray *cma_pernet_xa(struct net *net, enum rdma_ucm_port_space ps) { struct cma_pernet *pernet = cma_pernet(net); switch (ps) { case RDMA_PS_TCP: return &pernet->tcp_ps; case RDMA_PS_UDP: return &pernet->udp_ps; case RDMA_PS_IPOIB: return &pernet->ipoib_ps; case RDMA_PS_IB: return &pernet->ib_ps; default: return NULL; } } struct id_table_entry { struct list_head id_list; struct rb_node rb_node; }; struct cma_device { struct list_head list; struct ib_device *device; struct completion comp; refcount_t refcount; struct list_head id_list; enum ib_gid_type *default_gid_type; u8 *default_roce_tos; }; struct rdma_bind_list { enum rdma_ucm_port_space ps; struct hlist_head owners; unsigned short port; }; static int cma_ps_alloc(struct net *net, enum rdma_ucm_port_space ps, struct rdma_bind_list *bind_list, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); return xa_insert(xa, snum, bind_list, GFP_KERNEL); } static struct rdma_bind_list *cma_ps_find(struct net *net, enum rdma_ucm_port_space ps, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); return xa_load(xa, snum); } static void cma_ps_remove(struct net *net, enum rdma_ucm_port_space ps, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); xa_erase(xa, snum); } enum { CMA_OPTION_AFONLY, }; void cma_dev_get(struct cma_device *cma_dev) { refcount_inc(&cma_dev->refcount); } void cma_dev_put(struct cma_device *cma_dev) { if (refcount_dec_and_test(&cma_dev->refcount)) complete(&cma_dev->comp); } struct cma_device *cma_enum_devices_by_ibdev(cma_device_filter filter, void *cookie) { struct cma_device *cma_dev; struct cma_device *found_cma_dev = NULL; mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) if (filter(cma_dev->device, cookie)) { found_cma_dev = cma_dev; break; } if (found_cma_dev) cma_dev_get(found_cma_dev); mutex_unlock(&lock); return found_cma_dev; } int cma_get_default_gid_type(struct cma_device *cma_dev, u32 port) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; return cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)]; } int cma_set_default_gid_type(struct cma_device *cma_dev, u32 port, enum ib_gid_type default_gid_type) { unsigned long supported_gids; if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; if (default_gid_type == IB_GID_TYPE_IB && rdma_protocol_roce_eth_encap(cma_dev->device, port)) default_gid_type = IB_GID_TYPE_ROCE; supported_gids = roce_gid_type_mask_support(cma_dev->device, port); if (!(supported_gids & 1 << default_gid_type)) return -EINVAL; cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)] = default_gid_type; return 0; } int cma_get_default_roce_tos(struct cma_device *cma_dev, u32 port) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; return cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)]; } int cma_set_default_roce_tos(struct cma_device *cma_dev, u32 port, u8 default_roce_tos) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)] = default_roce_tos; return 0; } struct ib_device *cma_get_ib_dev(struct cma_device *cma_dev) { return cma_dev->device; } /* * Device removal can occur at anytime, so we need extra handling to * serialize notifying the user of device removal with other callbacks. * We do this by disabling removal notification while a callback is in process, * and reporting it after the callback completes. */ struct cma_multicast { struct rdma_id_private *id_priv; union { struct ib_sa_multicast *sa_mc; struct { struct work_struct work; struct rdma_cm_event event; } iboe_join; }; struct list_head list; void *context; struct sockaddr_storage addr; u8 join_state; }; struct cma_work { struct work_struct work; struct rdma_id_private *id; enum rdma_cm_state old_state; enum rdma_cm_state new_state; struct rdma_cm_event event; }; union cma_ip_addr { struct in6_addr ip6; struct { __be32 pad[3]; __be32 addr; } ip4; }; struct cma_hdr { u8 cma_version; u8 ip_version; /* IP version: 7:4 */ __be16 port; union cma_ip_addr src_addr; union cma_ip_addr dst_addr; }; #define CMA_VERSION 0x00 struct cma_req_info { struct sockaddr_storage listen_addr_storage; struct sockaddr_storage src_addr_storage; struct ib_device *device; union ib_gid local_gid; __be64 service_id; int port; bool has_gid; u16 pkey; }; static int cma_comp_exch(struct rdma_id_private *id_priv, enum rdma_cm_state comp, enum rdma_cm_state exch) { unsigned long flags; int ret; /* * The FSM uses a funny double locking where state is protected by both * the handler_mutex and the spinlock. State is not allowed to change * to/from a handler_mutex protected value without also holding * handler_mutex. */ if (comp == RDMA_CM_CONNECT || exch == RDMA_CM_CONNECT) lockdep_assert_held(&id_priv->handler_mutex); spin_lock_irqsave(&id_priv->lock, flags); if ((ret = (id_priv->state == comp))) id_priv->state = exch; spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } static inline u8 cma_get_ip_ver(const struct cma_hdr *hdr) { return hdr->ip_version >> 4; } static void cma_set_ip_ver(struct cma_hdr *hdr, u8 ip_ver) { hdr->ip_version = (ip_ver << 4) | (hdr->ip_version & 0xF); } static struct sockaddr *cma_src_addr(struct rdma_id_private *id_priv) { return (struct sockaddr *)&id_priv->id.route.addr.src_addr; } static inline struct sockaddr *cma_dst_addr(struct rdma_id_private *id_priv) { return (struct sockaddr *)&id_priv->id.route.addr.dst_addr; } static int cma_igmp_send(struct net_device *ndev, union ib_gid *mgid, bool join) { struct in_device *in_dev = NULL; if (ndev) { rtnl_lock(); in_dev = __in_dev_get_rtnl(ndev); if (in_dev) { if (join) ip_mc_inc_group(in_dev, *(__be32 *)(mgid->raw + 12)); else ip_mc_dec_group(in_dev, *(__be32 *)(mgid->raw + 12)); } rtnl_unlock(); } return (in_dev) ? 0 : -ENODEV; } static int compare_netdev_and_ip(int ifindex_a, struct sockaddr *sa, struct id_table_entry *entry_b) { struct rdma_id_private *id_priv = list_first_entry( &entry_b->id_list, struct rdma_id_private, id_list_entry); int ifindex_b = id_priv->id.route.addr.dev_addr.bound_dev_if; struct sockaddr *sb = cma_dst_addr(id_priv); if (ifindex_a != ifindex_b) return (ifindex_a > ifindex_b) ? 1 : -1; if (sa->sa_family != sb->sa_family) return sa->sa_family - sb->sa_family; if (sa->sa_family == AF_INET && __builtin_object_size(sa, 0) >= sizeof(struct sockaddr_in)) { return memcmp(&((struct sockaddr_in *)sa)->sin_addr, &((struct sockaddr_in *)sb)->sin_addr, sizeof(((struct sockaddr_in *)sa)->sin_addr)); } if (sa->sa_family == AF_INET6 && __builtin_object_size(sa, 0) >= sizeof(struct sockaddr_in6)) { return ipv6_addr_cmp(&((struct sockaddr_in6 *)sa)->sin6_addr, &((struct sockaddr_in6 *)sb)->sin6_addr); } return -1; } static int cma_add_id_to_tree(struct rdma_id_private *node_id_priv) { struct rb_node **new, *parent = NULL; struct id_table_entry *this, *node; unsigned long flags; int result; node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return -ENOMEM; spin_lock_irqsave(&id_table_lock, flags); new = &id_table.rb_node; while (*new) { this = container_of(*new, struct id_table_entry, rb_node); result = compare_netdev_and_ip( node_id_priv->id.route.addr.dev_addr.bound_dev_if, cma_dst_addr(node_id_priv), this); parent = *new; if (result < 0) new = &((*new)->rb_left); else if (result > 0) new = &((*new)->rb_right); else { list_add_tail(&node_id_priv->id_list_entry, &this->id_list); kfree(node); goto unlock; } } INIT_LIST_HEAD(&node->id_list); list_add_tail(&node_id_priv->id_list_entry, &node->id_list); rb_link_node(&node->rb_node, parent, new); rb_insert_color(&node->rb_node, &id_table); unlock: spin_unlock_irqrestore(&id_table_lock, flags); return 0; } static struct id_table_entry * node_from_ndev_ip(struct rb_root *root, int ifindex, struct sockaddr *sa) { struct rb_node *node = root->rb_node; struct id_table_entry *data; int result; while (node) { data = container_of(node, struct id_table_entry, rb_node); result = compare_netdev_and_ip(ifindex, sa, data); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return data; } return NULL; } static void cma_remove_id_from_tree(struct rdma_id_private *id_priv) { struct id_table_entry *data; unsigned long flags; spin_lock_irqsave(&id_table_lock, flags); if (list_empty(&id_priv->id_list_entry)) goto out; data = node_from_ndev_ip(&id_table, id_priv->id.route.addr.dev_addr.bound_dev_if, cma_dst_addr(id_priv)); if (!data) goto out; list_del_init(&id_priv->id_list_entry); if (list_empty(&data->id_list)) { rb_erase(&data->rb_node, &id_table); kfree(data); } out: spin_unlock_irqrestore(&id_table_lock, flags); } static void _cma_attach_to_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev) { cma_dev_get(cma_dev); id_priv->cma_dev = cma_dev; id_priv->id.device = cma_dev->device; id_priv->id.route.addr.dev_addr.transport = rdma_node_get_transport(cma_dev->device->node_type); list_add_tail(&id_priv->device_item, &cma_dev->id_list); trace_cm_id_attach(id_priv, cma_dev->device); } static void cma_attach_to_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev) { _cma_attach_to_dev(id_priv, cma_dev); id_priv->gid_type = cma_dev->default_gid_type[id_priv->id.port_num - rdma_start_port(cma_dev->device)]; } static void cma_release_dev(struct rdma_id_private *id_priv) { mutex_lock(&lock); list_del_init(&id_priv->device_item); cma_dev_put(id_priv->cma_dev); id_priv->cma_dev = NULL; id_priv->id.device = NULL; if (id_priv->id.route.addr.dev_addr.sgid_attr) { rdma_put_gid_attr(id_priv->id.route.addr.dev_addr.sgid_attr); id_priv->id.route.addr.dev_addr.sgid_attr = NULL; } mutex_unlock(&lock); } static inline unsigned short cma_family(struct rdma_id_private *id_priv) { return id_priv->id.route.addr.src_addr.ss_family; } static int cma_set_default_qkey(struct rdma_id_private *id_priv) { struct ib_sa_mcmember_rec rec; int ret = 0; switch (id_priv->id.ps) { case RDMA_PS_UDP: case RDMA_PS_IB: id_priv->qkey = RDMA_UDP_QKEY; break; case RDMA_PS_IPOIB: ib_addr_get_mgid(&id_priv->id.route.addr.dev_addr, &rec.mgid); ret = ib_sa_get_mcmember_rec(id_priv->id.device, id_priv->id.port_num, &rec.mgid, &rec); if (!ret) id_priv->qkey = be32_to_cpu(rec.qkey); break; default: break; } return ret; } static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) { if (!qkey || (id_priv->qkey && (id_priv->qkey != qkey))) return -EINVAL; id_priv->qkey = qkey; return 0; } static void cma_translate_ib(struct sockaddr_ib *sib, struct rdma_dev_addr *dev_addr) { dev_addr->dev_type = ARPHRD_INFINIBAND; rdma_addr_set_sgid(dev_addr, (union ib_gid *) &sib->sib_addr); ib_addr_set_pkey(dev_addr, ntohs(sib->sib_pkey)); } static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_addr) { int ret; if (addr->sa_family != AF_IB) { ret = rdma_translate_ip(addr, dev_addr); } else { cma_translate_ib((struct sockaddr_ib *) addr, dev_addr); ret = 0; } return ret; } static const struct ib_gid_attr * cma_validate_port(struct ib_device *device, u32 port, enum ib_gid_type gid_type, union ib_gid *gid, struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr = ERR_PTR(-ENODEV); int bound_if_index = dev_addr->bound_dev_if; int dev_type = dev_addr->dev_type; struct net_device *ndev = NULL; struct net_device *pdev = NULL; if (!rdma_dev_access_netns(device, id_priv->id.route.addr.dev_addr.net)) goto out; if ((dev_type == ARPHRD_INFINIBAND) && !rdma_protocol_ib(device, port)) goto out; if ((dev_type != ARPHRD_INFINIBAND) && rdma_protocol_ib(device, port)) goto out; /* * For drivers that do not associate more than one net device with * their gid tables, such as iWARP drivers, it is sufficient to * return the first table entry. * * Other driver classes might be included in the future. */ if (rdma_protocol_iwarp(device, port)) { sgid_attr = rdma_get_gid_attr(device, port, 0); if (IS_ERR(sgid_attr)) goto out; rcu_read_lock(); ndev = rcu_dereference(sgid_attr->ndev); if (ndev->ifindex != bound_if_index) { pdev = dev_get_by_index_rcu(dev_addr->net, bound_if_index); if (pdev) { if (is_vlan_dev(pdev)) { pdev = vlan_dev_real_dev(pdev); if (ndev->ifindex == pdev->ifindex) bound_if_index = pdev->ifindex; } if (is_vlan_dev(ndev)) { pdev = vlan_dev_real_dev(ndev); if (bound_if_index == pdev->ifindex) bound_if_index = ndev->ifindex; } } } if (!net_eq(dev_net(ndev), dev_addr->net) || ndev->ifindex != bound_if_index) { rdma_put_gid_attr(sgid_attr); sgid_attr = ERR_PTR(-ENODEV); } rcu_read_unlock(); goto out; } /* * For a RXE device, it should work with TUN device and normal ethernet * devices. Use driver_id to check if a device is a RXE device or not. * ARPHDR_NONE means a TUN device. */ if (device->ops.driver_id == RDMA_DRIVER_RXE) { if ((dev_type == ARPHRD_NONE || dev_type == ARPHRD_ETHER) && rdma_protocol_roce(device, port)) { ndev = dev_get_by_index(dev_addr->net, bound_if_index); if (!ndev) goto out; } } else { if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) { ndev = dev_get_by_index(dev_addr->net, bound_if_index); if (!ndev) goto out; } else { gid_type = IB_GID_TYPE_IB; } } sgid_attr = rdma_find_gid_by_port(device, gid, gid_type, port, ndev); dev_put(ndev); out: return sgid_attr; } static void cma_bind_sgid_attr(struct rdma_id_private *id_priv, const struct ib_gid_attr *sgid_attr) { WARN_ON(id_priv->id.route.addr.dev_addr.sgid_attr); id_priv->id.route.addr.dev_addr.sgid_attr = sgid_attr; } /** * cma_acquire_dev_by_src_ip - Acquire cma device, port, gid attribute * based on source ip address. * @id_priv: cm_id which should be bound to cma device * * cma_acquire_dev_by_src_ip() binds cm id to cma device, port and GID attribute * based on source IP address. It returns 0 on success or error code otherwise. * It is applicable to active and passive side cm_id. */ static int cma_acquire_dev_by_src_ip(struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; union ib_gid gid, iboe_gid, *gidp; struct cma_device *cma_dev; enum ib_gid_type gid_type; int ret = -ENODEV; u32 port; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &iboe_gid); memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) { rdma_for_each_port (cma_dev->device, port) { gidp = rdma_protocol_roce(cma_dev->device, port) ? &iboe_gid : &gid; gid_type = cma_dev->default_gid_type[port - 1]; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, gidp, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); cma_attach_to_dev(id_priv, cma_dev); ret = 0; goto out; } } } out: mutex_unlock(&lock); return ret; } /** * cma_ib_acquire_dev - Acquire cma device, port and SGID attribute * @id_priv: cm id to bind to cma device * @listen_id_priv: listener cm id to match against * @req: Pointer to req structure containaining incoming * request information * cma_ib_acquire_dev() acquires cma device, port and SGID attribute when * rdma device matches for listen_id and incoming request. It also verifies * that a GID table entry is present for the source address. * Returns 0 on success, or returns error code otherwise. */ static int cma_ib_acquire_dev(struct rdma_id_private *id_priv, const struct rdma_id_private *listen_id_priv, struct cma_req_info *req) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; enum ib_gid_type gid_type; union ib_gid gid; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; if (rdma_protocol_roce(req->device, req->port)) rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &gid); else memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); gid_type = listen_id_priv->cma_dev->default_gid_type[req->port - 1]; sgid_attr = cma_validate_port(req->device, req->port, gid_type, &gid, id_priv); if (IS_ERR(sgid_attr)) return PTR_ERR(sgid_attr); id_priv->id.port_num = req->port; cma_bind_sgid_attr(id_priv, sgid_attr); /* Need to acquire lock to protect against reader * of cma_dev->id_list such as cma_netdev_callback() and * cma_process_remove(). */ mutex_lock(&lock); cma_attach_to_dev(id_priv, listen_id_priv->cma_dev); mutex_unlock(&lock); rdma_restrack_add(&id_priv->res); return 0; } static int cma_iw_acquire_dev(struct rdma_id_private *id_priv, const struct rdma_id_private *listen_id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; struct cma_device *cma_dev; enum ib_gid_type gid_type; int ret = -ENODEV; union ib_gid gid; u32 port; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); mutex_lock(&lock); cma_dev = listen_id_priv->cma_dev; port = listen_id_priv->id.port_num; gid_type = listen_id_priv->gid_type; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, &gid, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); ret = 0; goto out; } list_for_each_entry(cma_dev, &dev_list, list) { rdma_for_each_port (cma_dev->device, port) { if (listen_id_priv->cma_dev == cma_dev && listen_id_priv->id.port_num == port) continue; gid_type = cma_dev->default_gid_type[port - 1]; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, &gid, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); ret = 0; goto out; } } } out: if (!ret) { cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); } mutex_unlock(&lock); return ret; } /* * Select the source IB device and address to reach the destination IB address. */ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) { struct cma_device *cma_dev, *cur_dev; struct sockaddr_ib *addr; union ib_gid gid, sgid, *dgid; unsigned int p; u16 pkey, index; enum ib_port_state port_state; int ret; int i; cma_dev = NULL; addr = (struct sockaddr_ib *) cma_dst_addr(id_priv); dgid = (union ib_gid *) &addr->sib_addr; pkey = ntohs(addr->sib_pkey); mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { rdma_for_each_port (cur_dev->device, p) { if (!rdma_cap_af_ib(cur_dev->device, p)) continue; if (ib_find_cached_pkey(cur_dev->device, p, pkey, &index)) continue; if (ib_get_cached_port_state(cur_dev->device, p, &port_state)) continue; for (i = 0; i < cur_dev->device->port_data[p].immutable.gid_tbl_len; ++i) { ret = rdma_query_gid(cur_dev->device, p, i, &gid); if (ret) continue; if (!memcmp(&gid, dgid, sizeof(gid))) { cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; goto found; } if (!cma_dev && (gid.global.subnet_prefix == dgid->global.subnet_prefix) && port_state == IB_PORT_ACTIVE) { cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; goto found; } } } } mutex_unlock(&lock); return -ENODEV; found: cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); mutex_unlock(&lock); addr = (struct sockaddr_ib *)cma_src_addr(id_priv); memcpy(&addr->sib_addr, &sgid, sizeof(sgid)); cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr); return 0; } static void cma_id_get(struct rdma_id_private *id_priv) { refcount_inc(&id_priv->refcount); } static void cma_id_put(struct rdma_id_private *id_priv) { if (refcount_dec_and_test(&id_priv->refcount)) complete(&id_priv->comp); } static struct rdma_id_private * __rdma_create_id(struct net *net, rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type, const struct rdma_id_private *parent) { struct rdma_id_private *id_priv; id_priv = kzalloc(sizeof *id_priv, GFP_KERNEL); if (!id_priv) return ERR_PTR(-ENOMEM); id_priv->state = RDMA_CM_IDLE; id_priv->id.context = context; id_priv->id.event_handler = event_handler; id_priv->id.ps = ps; id_priv->id.qp_type = qp_type; id_priv->tos_set = false; id_priv->timeout_set = false; id_priv->min_rnr_timer_set = false; id_priv->gid_type = IB_GID_TYPE_IB; spin_lock_init(&id_priv->lock); mutex_init(&id_priv->qp_mutex); init_completion(&id_priv->comp); refcount_set(&id_priv->refcount, 1); mutex_init(&id_priv->handler_mutex); INIT_LIST_HEAD(&id_priv->device_item); INIT_LIST_HEAD(&id_priv->id_list_entry); INIT_LIST_HEAD(&id_priv->listen_list); INIT_LIST_HEAD(&id_priv->mc_list); get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num); id_priv->id.route.addr.dev_addr.net = get_net(net); id_priv->seq_num &= 0x00ffffff; INIT_WORK(&id_priv->id.net_work, cma_netevent_work_handler); rdma_restrack_new(&id_priv->res, RDMA_RESTRACK_CM_ID); if (parent) rdma_restrack_parent_name(&id_priv->res, &parent->res); return id_priv; } struct rdma_cm_id * __rdma_create_kernel_id(struct net *net, rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type, const char *caller) { struct rdma_id_private *ret; ret = __rdma_create_id(net, event_handler, context, ps, qp_type, NULL); if (IS_ERR(ret)) return ERR_CAST(ret); rdma_restrack_set_name(&ret->res, caller); return &ret->id; } EXPORT_SYMBOL(__rdma_create_kernel_id); struct rdma_cm_id *rdma_create_user_id(rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type) { struct rdma_id_private *ret; ret = __rdma_create_id(current->nsproxy->net_ns, event_handler, context, ps, qp_type, NULL); if (IS_ERR(ret)) return ERR_CAST(ret); rdma_restrack_set_name(&ret->res, NULL); return &ret->id; } EXPORT_SYMBOL(rdma_create_user_id); static int cma_init_ud_qp(struct rdma_id_private *id_priv, struct ib_qp *qp) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) return ret; ret = ib_modify_qp(qp, &qp_attr, qp_attr_mask); if (ret) return ret; qp_attr.qp_state = IB_QPS_RTR; ret = ib_modify_qp(qp, &qp_attr, IB_QP_STATE); if (ret) return ret; qp_attr.qp_state = IB_QPS_RTS; qp_attr.sq_psn = 0; ret = ib_modify_qp(qp, &qp_attr, IB_QP_STATE | IB_QP_SQ_PSN); return ret; } static int cma_init_conn_qp(struct rdma_id_private *id_priv, struct ib_qp *qp) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) return ret; return ib_modify_qp(qp, &qp_attr, qp_attr_mask); } int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr) { struct rdma_id_private *id_priv; struct ib_qp *qp; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (id->device != pd->device) { ret = -EINVAL; goto out_err; } qp_init_attr->port_num = id->port_num; qp = ib_create_qp(pd, qp_init_attr); if (IS_ERR(qp)) { ret = PTR_ERR(qp); goto out_err; } if (id->qp_type == IB_QPT_UD) ret = cma_init_ud_qp(id_priv, qp); else ret = cma_init_conn_qp(id_priv, qp); if (ret) goto out_destroy; id->qp = qp; id_priv->qp_num = qp->qp_num; id_priv->srq = (qp->srq != NULL); trace_cm_qp_create(id_priv, pd, qp_init_attr, 0); return 0; out_destroy: ib_destroy_qp(qp); out_err: trace_cm_qp_create(id_priv, pd, qp_init_attr, ret); return ret; } EXPORT_SYMBOL(rdma_create_qp); void rdma_destroy_qp(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); trace_cm_qp_destroy(id_priv); mutex_lock(&id_priv->qp_mutex); ib_destroy_qp(id_priv->id.qp); id_priv->id.qp = NULL; mutex_unlock(&id_priv->qp_mutex); } EXPORT_SYMBOL(rdma_destroy_qp); static int cma_modify_qp_rtr(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } /* Need to update QP attributes from default values. */ qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); if (ret) goto out; qp_attr.qp_state = IB_QPS_RTR; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; BUG_ON(id_priv->cma_dev->device != id_priv->id.device); if (conn_param) qp_attr.max_dest_rd_atomic = conn_param->responder_resources; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_modify_qp_rts(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } qp_attr.qp_state = IB_QPS_RTS; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; if (conn_param) qp_attr.max_rd_atomic = conn_param->initiator_depth; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_modify_qp_err(struct rdma_id_private *id_priv) { struct ib_qp_attr qp_attr; int ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } qp_attr.qp_state = IB_QPS_ERR; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, IB_QP_STATE); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int ret; u16 pkey; if (rdma_cap_eth_ah(id_priv->id.device, id_priv->id.port_num)) pkey = 0xffff; else pkey = ib_addr_get_pkey(dev_addr); ret = ib_find_cached_pkey(id_priv->id.device, id_priv->id.port_num, pkey, &qp_attr->pkey_index); if (ret) return ret; qp_attr->port_num = id_priv->id.port_num; *qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT; if (id_priv->id.qp_type == IB_QPT_UD) { ret = cma_set_default_qkey(id_priv); if (ret) return ret; qp_attr->qkey = id_priv->qkey; *qp_attr_mask |= IB_QP_QKEY; } else { qp_attr->qp_access_flags = 0; *qp_attr_mask |= IB_QP_ACCESS_FLAGS; } return 0; } int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { struct rdma_id_private *id_priv; int ret = 0; id_priv = container_of(id, struct rdma_id_private, id); if (rdma_cap_ib_cm(id->device, id->port_num)) { if (!id_priv->cm_id.ib || (id_priv->id.qp_type == IB_QPT_UD)) ret = cma_ib_init_qp_attr(id_priv, qp_attr, qp_attr_mask); else ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, qp_attr, qp_attr_mask); if (qp_attr->qp_state == IB_QPS_RTR) qp_attr->rq_psn = id_priv->seq_num; } else if (rdma_cap_iw_cm(id->device, id->port_num)) { if (!id_priv->cm_id.iw) { qp_attr->qp_access_flags = 0; *qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS; } else ret = iw_cm_init_qp_attr(id_priv->cm_id.iw, qp_attr, qp_attr_mask); qp_attr->port_num = id_priv->id.port_num; *qp_attr_mask |= IB_QP_PORT; } else { ret = -ENOSYS; } if ((*qp_attr_mask & IB_QP_TIMEOUT) && id_priv->timeout_set) qp_attr->timeout = id_priv->timeout; if ((*qp_attr_mask & IB_QP_MIN_RNR_TIMER) && id_priv->min_rnr_timer_set) qp_attr->min_rnr_timer = id_priv->min_rnr_timer; return ret; } EXPORT_SYMBOL(rdma_init_qp_attr); static inline bool cma_zero_addr(const struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: return ipv4_is_zeronet(((struct sockaddr_in *)addr)->sin_addr.s_addr); case AF_INET6: return ipv6_addr_any(&((struct sockaddr_in6 *)addr)->sin6_addr); case AF_IB: return ib_addr_any(&((struct sockaddr_ib *)addr)->sib_addr); default: return false; } } static inline bool cma_loopback_addr(const struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: return ipv4_is_loopback( ((struct sockaddr_in *)addr)->sin_addr.s_addr); case AF_INET6: return ipv6_addr_loopback( &((struct sockaddr_in6 *)addr)->sin6_addr); case AF_IB: return ib_addr_loopback( &((struct sockaddr_ib *)addr)->sib_addr); default: return false; } } static inline bool cma_any_addr(const struct sockaddr *addr) { return cma_zero_addr(addr) || cma_loopback_addr(addr); } static int cma_addr_cmp(const struct sockaddr *src, const struct sockaddr *dst) { if (src->sa_family != dst->sa_family) return -1; switch (src->sa_family) { case AF_INET: return ((struct sockaddr_in *)src)->sin_addr.s_addr != ((struct sockaddr_in *)dst)->sin_addr.s_addr; case AF_INET6: { struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *)src; struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *)dst; bool link_local; if (ipv6_addr_cmp(&src_addr6->sin6_addr, &dst_addr6->sin6_addr)) return 1; link_local = ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL; /* Link local must match their scope_ids */ return link_local ? (src_addr6->sin6_scope_id != dst_addr6->sin6_scope_id) : 0; } default: return ib_addr_cmp(&((struct sockaddr_ib *) src)->sib_addr, &((struct sockaddr_ib *) dst)->sib_addr); } } static __be16 cma_port(const struct sockaddr *addr) { struct sockaddr_ib *sib; switch (addr->sa_family) { case AF_INET: return ((struct sockaddr_in *) addr)->sin_port; case AF_INET6: return ((struct sockaddr_in6 *) addr)->sin6_port; case AF_IB: sib = (struct sockaddr_ib *) addr; return htons((u16) (be64_to_cpu(sib->sib_sid) & be64_to_cpu(sib->sib_sid_mask))); default: return 0; } } static inline int cma_any_port(const struct sockaddr *addr) { return !cma_port(addr); } static void cma_save_ib_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct rdma_cm_id *listen_id, const struct sa_path_rec *path) { struct sockaddr_ib *listen_ib, *ib; listen_ib = (struct sockaddr_ib *) &listen_id->route.addr.src_addr; if (src_addr) { ib = (struct sockaddr_ib *)src_addr; ib->sib_family = AF_IB; if (path) { ib->sib_pkey = path->pkey; ib->sib_flowinfo = path->flow_label; memcpy(&ib->sib_addr, &path->sgid, 16); ib->sib_sid = path->service_id; ib->sib_scope_id = 0; } else { ib->sib_pkey = listen_ib->sib_pkey; ib->sib_flowinfo = listen_ib->sib_flowinfo; ib->sib_addr = listen_ib->sib_addr; ib->sib_sid = listen_ib->sib_sid; ib->sib_scope_id = listen_ib->sib_scope_id; } ib->sib_sid_mask = cpu_to_be64(0xffffffffffffffffULL); } if (dst_addr) { ib = (struct sockaddr_ib *)dst_addr; ib->sib_family = AF_IB; if (path) { ib->sib_pkey = path->pkey; ib->sib_flowinfo = path->flow_label; memcpy(&ib->sib_addr, &path->dgid, 16); } } } static void cma_save_ip4_info(struct sockaddr_in *src_addr, struct sockaddr_in *dst_addr, struct cma_hdr *hdr, __be16 local_port) { if (src_addr) { *src_addr = (struct sockaddr_in) { .sin_family = AF_INET, .sin_addr.s_addr = hdr->dst_addr.ip4.addr, .sin_port = local_port, }; } if (dst_addr) { *dst_addr = (struct sockaddr_in) { .sin_family = AF_INET, .sin_addr.s_addr = hdr->src_addr.ip4.addr, .sin_port = hdr->port, }; } } static void cma_save_ip6_info(struct sockaddr_in6 *src_addr, struct sockaddr_in6 *dst_addr, struct cma_hdr *hdr, __be16 local_port) { if (src_addr) { *src_addr = (struct sockaddr_in6) { .sin6_family = AF_INET6, .sin6_addr = hdr->dst_addr.ip6, .sin6_port = local_port, }; } if (dst_addr) { *dst_addr = (struct sockaddr_in6) { .sin6_family = AF_INET6, .sin6_addr = hdr->src_addr.ip6, .sin6_port = hdr->port, }; } } static u16 cma_port_from_service_id(__be64 service_id) { return (u16)be64_to_cpu(service_id); } static int cma_save_ip_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct ib_cm_event *ib_event, __be64 service_id) { struct cma_hdr *hdr; __be16 port; hdr = ib_event->private_data; if (hdr->cma_version != CMA_VERSION) return -EINVAL; port = htons(cma_port_from_service_id(service_id)); switch (cma_get_ip_ver(hdr)) { case 4: cma_save_ip4_info((struct sockaddr_in *)src_addr, (struct sockaddr_in *)dst_addr, hdr, port); break; case 6: cma_save_ip6_info((struct sockaddr_in6 *)src_addr, (struct sockaddr_in6 *)dst_addr, hdr, port); break; default: return -EAFNOSUPPORT; } return 0; } static int cma_save_net_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, sa_family_t sa_family, __be64 service_id) { if (sa_family == AF_IB) { if (ib_event->event == IB_CM_REQ_RECEIVED) cma_save_ib_info(src_addr, dst_addr, listen_id, ib_event->param.req_rcvd.primary_path); else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) cma_save_ib_info(src_addr, dst_addr, listen_id, NULL); return 0; } return cma_save_ip_info(src_addr, dst_addr, ib_event, service_id); } static int cma_save_req_info(const struct ib_cm_event *ib_event, struct cma_req_info *req) { const struct ib_cm_req_event_param *req_param = &ib_event->param.req_rcvd; const struct ib_cm_sidr_req_event_param *sidr_param = &ib_event->param.sidr_req_rcvd; switch (ib_event->event) { case IB_CM_REQ_RECEIVED: req->device = req_param->listen_id->device; req->port = req_param->port; memcpy(&req->local_gid, &req_param->primary_path->sgid, sizeof(req->local_gid)); req->has_gid = true; req->service_id = req_param->primary_path->service_id; req->pkey = be16_to_cpu(req_param->primary_path->pkey); if (req->pkey != req_param->bth_pkey) pr_warn_ratelimited("RDMA CMA: got different BTH P_Key (0x%x) and primary path P_Key (0x%x)\n" "RDMA CMA: in the future this may cause the request to be dropped\n", req_param->bth_pkey, req->pkey); break; case IB_CM_SIDR_REQ_RECEIVED: req->device = sidr_param->listen_id->device; req->port = sidr_param->port; req->has_gid = false; req->service_id = sidr_param->service_id; req->pkey = sidr_param->pkey; if (req->pkey != sidr_param->bth_pkey) pr_warn_ratelimited("RDMA CMA: got different BTH P_Key (0x%x) and SIDR request payload P_Key (0x%x)\n" "RDMA CMA: in the future this may cause the request to be dropped\n", sidr_param->bth_pkey, req->pkey); break; default: return -EINVAL; } return 0; } static bool validate_ipv4_net_dev(struct net_device *net_dev, const struct sockaddr_in *dst_addr, const struct sockaddr_in *src_addr) { __be32 daddr = dst_addr->sin_addr.s_addr, saddr = src_addr->sin_addr.s_addr; struct fib_result res; struct flowi4 fl4; int err; bool ret; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || ipv4_is_lbcast(daddr) || ipv4_is_zeronet(saddr) || ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr) || ipv4_is_loopback(saddr)) return false; memset(&fl4, 0, sizeof(fl4)); fl4.flowi4_oif = net_dev->ifindex; fl4.daddr = daddr; fl4.saddr = saddr; rcu_read_lock(); err = fib_lookup(dev_net(net_dev), &fl4, &res, 0); ret = err == 0 && FIB_RES_DEV(res) == net_dev; rcu_read_unlock(); return ret; } static bool validate_ipv6_net_dev(struct net_device *net_dev, const struct sockaddr_in6 *dst_addr, const struct sockaddr_in6 *src_addr) { #if IS_ENABLED(CONFIG_IPV6) const int strict = ipv6_addr_type(&dst_addr->sin6_addr) & IPV6_ADDR_LINKLOCAL; struct rt6_info *rt = rt6_lookup(dev_net(net_dev), &dst_addr->sin6_addr, &src_addr->sin6_addr, net_dev->ifindex, NULL, strict); bool ret; if (!rt) return false; ret = rt->rt6i_idev->dev == net_dev; ip6_rt_put(rt); return ret; #else return false; #endif } static bool validate_net_dev(struct net_device *net_dev, const struct sockaddr *daddr, const struct sockaddr *saddr) { const struct sockaddr_in *daddr4 = (const struct sockaddr_in *)daddr; const struct sockaddr_in *saddr4 = (const struct sockaddr_in *)saddr; const struct sockaddr_in6 *daddr6 = (const struct sockaddr_in6 *)daddr; const struct sockaddr_in6 *saddr6 = (const struct sockaddr_in6 *)saddr; switch (daddr->sa_family) { case AF_INET: return saddr->sa_family == AF_INET && validate_ipv4_net_dev(net_dev, daddr4, saddr4); case AF_INET6: return saddr->sa_family == AF_INET6 && validate_ipv6_net_dev(net_dev, daddr6, saddr6); default: return false; } } static struct net_device * roce_get_net_dev_by_cm_event(const struct ib_cm_event *ib_event) { const struct ib_gid_attr *sgid_attr = NULL; struct net_device *ndev; if (ib_event->event == IB_CM_REQ_RECEIVED) sgid_attr = ib_event->param.req_rcvd.ppath_sgid_attr; else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) sgid_attr = ib_event->param.sidr_req_rcvd.sgid_attr; if (!sgid_attr) return NULL; rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(sgid_attr); if (IS_ERR(ndev)) ndev = NULL; else dev_hold(ndev); rcu_read_unlock(); return ndev; } static struct net_device *cma_get_net_dev(const struct ib_cm_event *ib_event, struct cma_req_info *req) { struct sockaddr *listen_addr = (struct sockaddr *)&req->listen_addr_storage; struct sockaddr *src_addr = (struct sockaddr *)&req->src_addr_storage; struct net_device *net_dev; const union ib_gid *gid = req->has_gid ? &req->local_gid : NULL; int err; err = cma_save_ip_info(listen_addr, src_addr, ib_event, req->service_id); if (err) return ERR_PTR(err); if (rdma_protocol_roce(req->device, req->port)) net_dev = roce_get_net_dev_by_cm_event(ib_event); else net_dev = ib_get_net_dev_by_params(req->device, req->port, req->pkey, gid, listen_addr); if (!net_dev) return ERR_PTR(-ENODEV); return net_dev; } static enum rdma_ucm_port_space rdma_ps_from_service_id(__be64 service_id) { return (be64_to_cpu(service_id) >> 16) & 0xffff; } static bool cma_match_private_data(struct rdma_id_private *id_priv, const struct cma_hdr *hdr) { struct sockaddr *addr = cma_src_addr(id_priv); __be32 ip4_addr; struct in6_addr ip6_addr; if (cma_any_addr(addr) && !id_priv->afonly) return true; switch (addr->sa_family) { case AF_INET: ip4_addr = ((struct sockaddr_in *)addr)->sin_addr.s_addr; if (cma_get_ip_ver(hdr) != 4) return false; if (!cma_any_addr(addr) && hdr->dst_addr.ip4.addr != ip4_addr) return false; break; case AF_INET6: ip6_addr = ((struct sockaddr_in6 *)addr)->sin6_addr; if (cma_get_ip_ver(hdr) != 6) return false; if (!cma_any_addr(addr) && memcmp(&hdr->dst_addr.ip6, &ip6_addr, sizeof(ip6_addr))) return false; break; case AF_IB: return true; default: return false; } return true; } static bool cma_protocol_roce(const struct rdma_cm_id *id) { struct ib_device *device = id->device; const u32 port_num = id->port_num ?: rdma_start_port(device); return rdma_protocol_roce(device, port_num); } static bool cma_is_req_ipv6_ll(const struct cma_req_info *req) { const struct sockaddr *daddr = (const struct sockaddr *)&req->listen_addr_storage; const struct sockaddr_in6 *daddr6 = (const struct sockaddr_in6 *)daddr; /* Returns true if the req is for IPv6 link local */ return (daddr->sa_family == AF_INET6 && (ipv6_addr_type(&daddr6->sin6_addr) & IPV6_ADDR_LINKLOCAL)); } static bool cma_match_net_dev(const struct rdma_cm_id *id, const struct net_device *net_dev, const struct cma_req_info *req) { const struct rdma_addr *addr = &id->route.addr; if (!net_dev) /* This request is an AF_IB request */ return (!id->port_num || id->port_num == req->port) && (addr->src_addr.ss_family == AF_IB); /* * If the request is not for IPv6 link local, allow matching * request to any netdevice of the one or multiport rdma device. */ if (!cma_is_req_ipv6_ll(req)) return true; /* * Net namespaces must match, and if the listner is listening * on a specific netdevice than netdevice must match as well. */ if (net_eq(dev_net(net_dev), addr->dev_addr.net) && (!!addr->dev_addr.bound_dev_if == (addr->dev_addr.bound_dev_if == net_dev->ifindex))) return true; else return false; } static struct rdma_id_private *cma_find_listener( const struct rdma_bind_list *bind_list, const struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event, const struct cma_req_info *req, const struct net_device *net_dev) { struct rdma_id_private *id_priv, *id_priv_dev; lockdep_assert_held(&lock); if (!bind_list) return ERR_PTR(-EINVAL); hlist_for_each_entry(id_priv, &bind_list->owners, node) { if (cma_match_private_data(id_priv, ib_event->private_data)) { if (id_priv->id.device == cm_id->device && cma_match_net_dev(&id_priv->id, net_dev, req)) return id_priv; list_for_each_entry(id_priv_dev, &id_priv->listen_list, listen_item) { if (id_priv_dev->id.device == cm_id->device && cma_match_net_dev(&id_priv_dev->id, net_dev, req)) return id_priv_dev; } } } return ERR_PTR(-EINVAL); } static struct rdma_id_private * cma_ib_id_from_event(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event, struct cma_req_info *req, struct net_device **net_dev) { struct rdma_bind_list *bind_list; struct rdma_id_private *id_priv; int err; err = cma_save_req_info(ib_event, req); if (err) return ERR_PTR(err); *net_dev = cma_get_net_dev(ib_event, req); if (IS_ERR(*net_dev)) { if (PTR_ERR(*net_dev) == -EAFNOSUPPORT) { /* Assuming the protocol is AF_IB */ *net_dev = NULL; } else { return ERR_CAST(*net_dev); } } mutex_lock(&lock); /* * Net namespace might be getting deleted while route lookup, * cm_id lookup is in progress. Therefore, perform netdevice * validation, cm_id lookup under rcu lock. * RCU lock along with netdevice state check, synchronizes with * netdevice migrating to different net namespace and also avoids * case where net namespace doesn't get deleted while lookup is in * progress. * If the device state is not IFF_UP, its properties such as ifindex * and nd_net cannot be trusted to remain valid without rcu lock. * net/core/dev.c change_net_namespace() ensures to synchronize with * ongoing operations on net device after device is closed using * synchronize_net(). */ rcu_read_lock(); if (*net_dev) { /* * If netdevice is down, it is likely that it is administratively * down or it might be migrating to different namespace. * In that case avoid further processing, as the net namespace * or ifindex may change. */ if (((*net_dev)->flags & IFF_UP) == 0) { id_priv = ERR_PTR(-EHOSTUNREACH); goto err; } if (!validate_net_dev(*net_dev, (struct sockaddr *)&req->src_addr_storage, (struct sockaddr *)&req->listen_addr_storage)) { id_priv = ERR_PTR(-EHOSTUNREACH); goto err; } } bind_list = cma_ps_find(*net_dev ? dev_net(*net_dev) : &init_net, rdma_ps_from_service_id(req->service_id), cma_port_from_service_id(req->service_id)); id_priv = cma_find_listener(bind_list, cm_id, ib_event, req, *net_dev); err: rcu_read_unlock(); mutex_unlock(&lock); if (IS_ERR(id_priv) && *net_dev) { dev_put(*net_dev); *net_dev = NULL; } return id_priv; } static inline u8 cma_user_data_offset(struct rdma_id_private *id_priv) { return cma_family(id_priv) == AF_IB ? 0 : sizeof(struct cma_hdr); } static void cma_cancel_route(struct rdma_id_private *id_priv) { if (rdma_cap_ib_sa(id_priv->id.device, id_priv->id.port_num)) { if (id_priv->query) ib_sa_cancel_query(id_priv->query_id, id_priv->query); } } static void _cma_cancel_listens(struct rdma_id_private *id_priv) { struct rdma_id_private *dev_id_priv; lockdep_assert_held(&lock); /* * Remove from listen_any_list to prevent added devices from spawning * additional listen requests. */ list_del_init(&id_priv->listen_any_item); while (!list_empty(&id_priv->listen_list)) { dev_id_priv = list_first_entry(&id_priv->listen_list, struct rdma_id_private, listen_item); /* sync with device removal to avoid duplicate destruction */ list_del_init(&dev_id_priv->device_item); list_del_init(&dev_id_priv->listen_item); mutex_unlock(&lock); rdma_destroy_id(&dev_id_priv->id); mutex_lock(&lock); } } static void cma_cancel_listens(struct rdma_id_private *id_priv) { mutex_lock(&lock); _cma_cancel_listens(id_priv); mutex_unlock(&lock); } static void cma_cancel_operation(struct rdma_id_private *id_priv, enum rdma_cm_state state) { switch (state) { case RDMA_CM_ADDR_QUERY: /* * We can avoid doing the rdma_addr_cancel() based on state, * only RDMA_CM_ADDR_QUERY has a work that could still execute. * Notice that the addr_handler work could still be exiting * outside this state, however due to the interaction with the * handler_mutex the work is guaranteed not to touch id_priv * during exit. */ rdma_addr_cancel(&id_priv->id.route.addr.dev_addr); break; case RDMA_CM_ROUTE_QUERY: cma_cancel_route(id_priv); break; case RDMA_CM_LISTEN: if (cma_any_addr(cma_src_addr(id_priv)) && !id_priv->cma_dev) cma_cancel_listens(id_priv); break; default: break; } } static void cma_release_port(struct rdma_id_private *id_priv) { struct rdma_bind_list *bind_list = id_priv->bind_list; struct net *net = id_priv->id.route.addr.dev_addr.net; if (!bind_list) return; mutex_lock(&lock); hlist_del(&id_priv->node); if (hlist_empty(&bind_list->owners)) { cma_ps_remove(net, bind_list->ps, bind_list->port); kfree(bind_list); } mutex_unlock(&lock); } static void destroy_mc(struct rdma_id_private *id_priv, struct cma_multicast *mc) { bool send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); if (rdma_cap_ib_mcast(id_priv->id.device, id_priv->id.port_num)) ib_sa_free_multicast(mc->sa_mc); if (rdma_protocol_roce(id_priv->id.device, id_priv->id.port_num)) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct net_device *ndev = NULL; if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (ndev && !send_only) { enum ib_gid_type gid_type; union ib_gid mgid; gid_type = id_priv->cma_dev->default_gid_type [id_priv->id.port_num - rdma_start_port( id_priv->cma_dev->device)]; cma_iboe_set_mgid((struct sockaddr *)&mc->addr, &mgid, gid_type); cma_igmp_send(ndev, &mgid, false); } dev_put(ndev); cancel_work_sync(&mc->iboe_join.work); } kfree(mc); } static void cma_leave_mc_groups(struct rdma_id_private *id_priv) { struct cma_multicast *mc; while (!list_empty(&id_priv->mc_list)) { mc = list_first_entry(&id_priv->mc_list, struct cma_multicast, list); list_del(&mc->list); destroy_mc(id_priv, mc); } } static void _destroy_id(struct rdma_id_private *id_priv, enum rdma_cm_state state) { cma_cancel_operation(id_priv, state); rdma_restrack_del(&id_priv->res); cma_remove_id_from_tree(id_priv); if (id_priv->cma_dev) { if (rdma_cap_ib_cm(id_priv->id.device, 1)) { if (id_priv->cm_id.ib) ib_destroy_cm_id(id_priv->cm_id.ib); } else if (rdma_cap_iw_cm(id_priv->id.device, 1)) { if (id_priv->cm_id.iw) iw_destroy_cm_id(id_priv->cm_id.iw); } cma_leave_mc_groups(id_priv); cma_release_dev(id_priv); } cma_release_port(id_priv); cma_id_put(id_priv); wait_for_completion(&id_priv->comp); if (id_priv->internal_id) cma_id_put(id_priv->id.context); kfree(id_priv->id.route.path_rec); kfree(id_priv->id.route.path_rec_inbound); kfree(id_priv->id.route.path_rec_outbound); kfree(id_priv->id.route.service_recs); put_net(id_priv->id.route.addr.dev_addr.net); kfree(id_priv); } /* * destroy an ID from within the handler_mutex. This ensures that no other * handlers can start running concurrently. */ static void destroy_id_handler_unlock(struct rdma_id_private *id_priv) __releases(&idprv->handler_mutex) { enum rdma_cm_state state; unsigned long flags; trace_cm_id_destroy(id_priv); /* * Setting the state to destroyed under the handler mutex provides a * fence against calling handler callbacks. If this is invoked due to * the failure of a handler callback then it guarentees that no future * handlers will be called. */ lockdep_assert_held(&id_priv->handler_mutex); spin_lock_irqsave(&id_priv->lock, flags); state = id_priv->state; id_priv->state = RDMA_CM_DESTROYING; spin_unlock_irqrestore(&id_priv->lock, flags); mutex_unlock(&id_priv->handler_mutex); _destroy_id(id_priv, state); } void rdma_destroy_id(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->handler_mutex); destroy_id_handler_unlock(id_priv); } EXPORT_SYMBOL(rdma_destroy_id); static int cma_rep_recv(struct rdma_id_private *id_priv) { int ret; ret = cma_modify_qp_rtr(id_priv, NULL); if (ret) goto reject; ret = cma_modify_qp_rts(id_priv, NULL); if (ret) goto reject; trace_cm_send_rtu(id_priv); ret = ib_send_cm_rtu(id_priv->cm_id.ib, NULL, 0); if (ret) goto reject; return 0; reject: pr_debug_ratelimited("RDMA CM: CONNECT_ERROR: failed to handle reply. status %d\n", ret); cma_modify_qp_err(id_priv); trace_cm_send_rej(id_priv); ib_send_cm_rej(id_priv->cm_id.ib, IB_CM_REJ_CONSUMER_DEFINED, NULL, 0, NULL, 0); return ret; } static void cma_set_rep_event_data(struct rdma_cm_event *event, const struct ib_cm_rep_event_param *rep_data, void *private_data) { event->param.conn.private_data = private_data; event->param.conn.private_data_len = IB_CM_REP_PRIVATE_DATA_SIZE; event->param.conn.responder_resources = rep_data->responder_resources; event->param.conn.initiator_depth = rep_data->initiator_depth; event->param.conn.flow_control = rep_data->flow_control; event->param.conn.rnr_retry_count = rep_data->rnr_retry_count; event->param.conn.srq = rep_data->srq; event->param.conn.qp_num = rep_data->remote_qpn; event->ece.vendor_id = rep_data->ece.vendor_id; event->ece.attr_mod = rep_data->ece.attr_mod; } static int cma_cm_event_handler(struct rdma_id_private *id_priv, struct rdma_cm_event *event) { int ret; lockdep_assert_held(&id_priv->handler_mutex); trace_cm_event_handler(id_priv, event); ret = id_priv->id.event_handler(&id_priv->id, event); trace_cm_event_done(id_priv, event, ret); return ret; } static int cma_ib_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *id_priv = cm_id->context; struct rdma_cm_event event = {}; enum rdma_cm_state state; int ret; mutex_lock(&id_priv->handler_mutex); state = READ_ONCE(id_priv->state); if ((ib_event->event != IB_CM_TIMEWAIT_EXIT && state != RDMA_CM_CONNECT) || (ib_event->event == IB_CM_TIMEWAIT_EXIT && state != RDMA_CM_DISCONNECT)) goto out; switch (ib_event->event) { case IB_CM_REQ_ERROR: case IB_CM_REP_ERROR: event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; break; case IB_CM_REP_RECEIVED: if (state == RDMA_CM_CONNECT && (id_priv->id.qp_type != IB_QPT_UD)) { trace_cm_prepare_mra(id_priv); ib_prepare_cm_mra(cm_id); } if (id_priv->id.qp) { event.status = cma_rep_recv(id_priv); event.event = event.status ? RDMA_CM_EVENT_CONNECT_ERROR : RDMA_CM_EVENT_ESTABLISHED; } else { event.event = RDMA_CM_EVENT_CONNECT_RESPONSE; } cma_set_rep_event_data(&event, &ib_event->param.rep_rcvd, ib_event->private_data); break; case IB_CM_RTU_RECEIVED: case IB_CM_USER_ESTABLISHED: event.event = RDMA_CM_EVENT_ESTABLISHED; break; case IB_CM_DREQ_ERROR: event.status = -ETIMEDOUT; fallthrough; case IB_CM_DREQ_RECEIVED: case IB_CM_DREP_RECEIVED: if (!cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_DISCONNECT)) goto out; event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IB_CM_TIMEWAIT_EXIT: event.event = RDMA_CM_EVENT_TIMEWAIT_EXIT; break; case IB_CM_MRA_RECEIVED: /* ignore event */ goto out; case IB_CM_REJ_RECEIVED: pr_debug_ratelimited("RDMA CM: REJECTED: %s\n", rdma_reject_msg(&id_priv->id, ib_event->param.rej_rcvd.reason)); cma_modify_qp_err(id_priv); event.status = ib_event->param.rej_rcvd.reason; event.event = RDMA_CM_EVENT_REJECTED; event.param.conn.private_data = ib_event->private_data; event.param.conn.private_data_len = IB_CM_REJ_PRIVATE_DATA_SIZE; break; default: pr_err("RDMA CMA: unexpected IB CM event: %d\n", ib_event->event); goto out; } ret = cma_cm_event_handler(id_priv, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return 0; } static struct rdma_id_private * cma_ib_new_conn_id(const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, struct net_device *net_dev) { struct rdma_id_private *listen_id_priv; struct rdma_id_private *id_priv; struct rdma_cm_id *id; struct rdma_route *rt; const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family; struct sa_path_rec *path = ib_event->param.req_rcvd.primary_path; const __be64 service_id = ib_event->param.req_rcvd.primary_path->service_id; int ret; listen_id_priv = container_of(listen_id, struct rdma_id_private, id); id_priv = __rdma_create_id(listen_id->route.addr.dev_addr.net, listen_id->event_handler, listen_id->context, listen_id->ps, ib_event->param.req_rcvd.qp_type, listen_id_priv); if (IS_ERR(id_priv)) return NULL; id = &id_priv->id; if (cma_save_net_info((struct sockaddr *)&id->route.addr.src_addr, (struct sockaddr *)&id->route.addr.dst_addr, listen_id, ib_event, ss_family, service_id)) goto err; rt = &id->route; rt->num_pri_alt_paths = ib_event->param.req_rcvd.alternate_path ? 2 : 1; rt->path_rec = kmalloc_array(rt->num_pri_alt_paths, sizeof(*rt->path_rec), GFP_KERNEL); if (!rt->path_rec) goto err; rt->path_rec[0] = *path; if (rt->num_pri_alt_paths == 2) rt->path_rec[1] = *ib_event->param.req_rcvd.alternate_path; if (net_dev) { rdma_copy_src_l2_addr(&rt->addr.dev_addr, net_dev); } else { if (!cma_protocol_roce(listen_id) && cma_any_addr(cma_src_addr(id_priv))) { rt->addr.dev_addr.dev_type = ARPHRD_INFINIBAND; rdma_addr_set_sgid(&rt->addr.dev_addr, &rt->path_rec[0].sgid); ib_addr_set_pkey(&rt->addr.dev_addr, be16_to_cpu(rt->path_rec[0].pkey)); } else if (!cma_any_addr(cma_src_addr(id_priv))) { ret = cma_translate_addr(cma_src_addr(id_priv), &rt->addr.dev_addr); if (ret) goto err; } } rdma_addr_set_dgid(&rt->addr.dev_addr, &rt->path_rec[0].dgid); id_priv->state = RDMA_CM_CONNECT; return id_priv; err: rdma_destroy_id(id); return NULL; } static struct rdma_id_private * cma_ib_new_udp_id(const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, struct net_device *net_dev) { const struct rdma_id_private *listen_id_priv; struct rdma_id_private *id_priv; struct rdma_cm_id *id; const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family; struct net *net = listen_id->route.addr.dev_addr.net; int ret; listen_id_priv = container_of(listen_id, struct rdma_id_private, id); id_priv = __rdma_create_id(net, listen_id->event_handler, listen_id->context, listen_id->ps, IB_QPT_UD, listen_id_priv); if (IS_ERR(id_priv)) return NULL; id = &id_priv->id; if (cma_save_net_info((struct sockaddr *)&id->route.addr.src_addr, (struct sockaddr *)&id->route.addr.dst_addr, listen_id, ib_event, ss_family, ib_event->param.sidr_req_rcvd.service_id)) goto err; if (net_dev) { rdma_copy_src_l2_addr(&id->route.addr.dev_addr, net_dev); } else { if (!cma_any_addr(cma_src_addr(id_priv))) { ret = cma_translate_addr(cma_src_addr(id_priv), &id->route.addr.dev_addr); if (ret) goto err; } } id_priv->state = RDMA_CM_CONNECT; return id_priv; err: rdma_destroy_id(id); return NULL; } static void cma_set_req_event_data(struct rdma_cm_event *event, const struct ib_cm_req_event_param *req_data, void *private_data, int offset) { event->param.conn.private_data = private_data + offset; event->param.conn.private_data_len = IB_CM_REQ_PRIVATE_DATA_SIZE - offset; event->param.conn.responder_resources = req_data->responder_resources; event->param.conn.initiator_depth = req_data->initiator_depth; event->param.conn.flow_control = req_data->flow_control; event->param.conn.retry_count = req_data->retry_count; event->param.conn.rnr_retry_count = req_data->rnr_retry_count; event->param.conn.srq = req_data->srq; event->param.conn.qp_num = req_data->remote_qpn; event->ece.vendor_id = req_data->ece.vendor_id; event->ece.attr_mod = req_data->ece.attr_mod; } static int cma_ib_check_req_qp_type(const struct rdma_cm_id *id, const struct ib_cm_event *ib_event) { return (((ib_event->event == IB_CM_REQ_RECEIVED) && (ib_event->param.req_rcvd.qp_type == id->qp_type)) || ((ib_event->event == IB_CM_SIDR_REQ_RECEIVED) && (id->qp_type == IB_QPT_UD)) || (!id->qp_type)); } static int cma_ib_req_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *listen_id, *conn_id = NULL; struct rdma_cm_event event = {}; struct cma_req_info req = {}; struct net_device *net_dev; u8 offset; int ret; listen_id = cma_ib_id_from_event(cm_id, ib_event, &req, &net_dev); if (IS_ERR(listen_id)) return PTR_ERR(listen_id); trace_cm_req_handler(listen_id, ib_event->event); if (!cma_ib_check_req_qp_type(&listen_id->id, ib_event)) { ret = -EINVAL; goto net_dev_put; } mutex_lock(&listen_id->handler_mutex); if (READ_ONCE(listen_id->state) != RDMA_CM_LISTEN) { ret = -ECONNABORTED; goto err_unlock; } offset = cma_user_data_offset(listen_id); event.event = RDMA_CM_EVENT_CONNECT_REQUEST; if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) { conn_id = cma_ib_new_udp_id(&listen_id->id, ib_event, net_dev); event.param.ud.private_data = ib_event->private_data + offset; event.param.ud.private_data_len = IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE - offset; } else { conn_id = cma_ib_new_conn_id(&listen_id->id, ib_event, net_dev); cma_set_req_event_data(&event, &ib_event->param.req_rcvd, ib_event->private_data, offset); } if (!conn_id) { ret = -ENOMEM; goto err_unlock; } mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING); ret = cma_ib_acquire_dev(conn_id, listen_id, &req); if (ret) { destroy_id_handler_unlock(conn_id); goto err_unlock; } conn_id->cm_id.ib = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_ib_handler; ret = cma_cm_event_handler(conn_id, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ conn_id->cm_id.ib = NULL; mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); goto net_dev_put; } if (READ_ONCE(conn_id->state) == RDMA_CM_CONNECT && conn_id->id.qp_type != IB_QPT_UD) { trace_cm_prepare_mra(cm_id->context); ib_prepare_cm_mra(cm_id); } mutex_unlock(&conn_id->handler_mutex); err_unlock: mutex_unlock(&listen_id->handler_mutex); net_dev_put: dev_put(net_dev); return ret; } __be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr) { if (addr->sa_family == AF_IB) return ((struct sockaddr_ib *) addr)->sib_sid; return cpu_to_be64(((u64)id->ps << 16) + be16_to_cpu(cma_port(addr))); } EXPORT_SYMBOL(rdma_get_service_id); void rdma_read_gids(struct rdma_cm_id *cm_id, union ib_gid *sgid, union ib_gid *dgid) { struct rdma_addr *addr = &cm_id->route.addr; if (!cm_id->device) { if (sgid) memset(sgid, 0, sizeof(*sgid)); if (dgid) memset(dgid, 0, sizeof(*dgid)); return; } if (rdma_protocol_roce(cm_id->device, cm_id->port_num)) { if (sgid) rdma_ip2gid((struct sockaddr *)&addr->src_addr, sgid); if (dgid) rdma_ip2gid((struct sockaddr *)&addr->dst_addr, dgid); } else { if (sgid) rdma_addr_get_sgid(&addr->dev_addr, sgid); if (dgid) rdma_addr_get_dgid(&addr->dev_addr, dgid); } } EXPORT_SYMBOL(rdma_read_gids); static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) { struct rdma_id_private *id_priv = iw_id->context; struct rdma_cm_event event = {}; int ret = 0; struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) goto out; switch (iw_event->event) { case IW_CM_EVENT_CLOSE: event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IW_CM_EVENT_CONNECT_REPLY: memcpy(cma_src_addr(id_priv), laddr, rdma_addr_size(laddr)); memcpy(cma_dst_addr(id_priv), raddr, rdma_addr_size(raddr)); switch (iw_event->status) { case 0: event.event = RDMA_CM_EVENT_ESTABLISHED; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; break; case -ECONNRESET: case -ECONNREFUSED: event.event = RDMA_CM_EVENT_REJECTED; break; case -ETIMEDOUT: event.event = RDMA_CM_EVENT_UNREACHABLE; break; default: event.event = RDMA_CM_EVENT_CONNECT_ERROR; break; } break; case IW_CM_EVENT_ESTABLISHED: event.event = RDMA_CM_EVENT_ESTABLISHED; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; break; default: goto out; } event.status = iw_event->status; event.param.conn.private_data = iw_event->private_data; event.param.conn.private_data_len = iw_event->private_data_len; ret = cma_cm_event_handler(id_priv, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.iw = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return ret; } static int iw_conn_req_handler(struct iw_cm_id *cm_id, struct iw_cm_event *iw_event) { struct rdma_id_private *listen_id, *conn_id; struct rdma_cm_event event = {}; int ret = -ECONNABORTED; struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; event.event = RDMA_CM_EVENT_CONNECT_REQUEST; event.param.conn.private_data = iw_event->private_data; event.param.conn.private_data_len = iw_event->private_data_len; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; listen_id = cm_id->context; mutex_lock(&listen_id->handler_mutex); if (READ_ONCE(listen_id->state) != RDMA_CM_LISTEN) goto out; /* Create a new RDMA id for the new IW CM ID */ conn_id = __rdma_create_id(listen_id->id.route.addr.dev_addr.net, listen_id->id.event_handler, listen_id->id.context, RDMA_PS_TCP, IB_QPT_RC, listen_id); if (IS_ERR(conn_id)) { ret = -ENOMEM; goto out; } mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING); conn_id->state = RDMA_CM_CONNECT; ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr); if (ret) { mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } ret = cma_iw_acquire_dev(conn_id, listen_id); if (ret) { mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } conn_id->cm_id.iw = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_iw_handler; memcpy(cma_src_addr(conn_id), laddr, rdma_addr_size(laddr)); memcpy(cma_dst_addr(conn_id), raddr, rdma_addr_size(raddr)); ret = cma_cm_event_handler(conn_id, &event); if (ret) { /* User wants to destroy the CM ID */ conn_id->cm_id.iw = NULL; mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } mutex_unlock(&conn_id->handler_mutex); out: mutex_unlock(&listen_id->handler_mutex); return ret; } static int cma_ib_listen(struct rdma_id_private *id_priv) { struct sockaddr *addr; struct ib_cm_id *id; __be64 svc_id; addr = cma_src_addr(id_priv); svc_id = rdma_get_service_id(&id_priv->id, addr); id = ib_cm_insert_listen(id_priv->id.device, cma_ib_req_handler, svc_id); if (IS_ERR(id)) return PTR_ERR(id); id_priv->cm_id.ib = id; return 0; } static int cma_iw_listen(struct rdma_id_private *id_priv, int backlog) { int ret; struct iw_cm_id *id; id = iw_create_cm_id(id_priv->id.device, iw_conn_req_handler, id_priv); if (IS_ERR(id)) return PTR_ERR(id); mutex_lock(&id_priv->qp_mutex); id->tos = id_priv->tos; id->tos_set = id_priv->tos_set; mutex_unlock(&id_priv->qp_mutex); id->afonly = id_priv->afonly; id_priv->cm_id.iw = id; memcpy(&id_priv->cm_id.iw->local_addr, cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); ret = iw_cm_listen(id_priv->cm_id.iw, backlog); if (ret) { iw_destroy_cm_id(id_priv->cm_id.iw); id_priv->cm_id.iw = NULL; } return ret; } static int cma_listen_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) { struct rdma_id_private *id_priv = id->context; /* Listening IDs are always destroyed on removal */ if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) return -1; id->context = id_priv->id.context; id->event_handler = id_priv->id.event_handler; trace_cm_event_handler(id_priv, event); return id_priv->id.event_handler(id, event); } static int cma_listen_on_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev, struct rdma_id_private **to_destroy) { struct rdma_id_private *dev_id_priv; struct net *net = id_priv->id.route.addr.dev_addr.net; int ret; lockdep_assert_held(&lock); *to_destroy = NULL; if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1)) return 0; dev_id_priv = __rdma_create_id(net, cma_listen_handler, id_priv, id_priv->id.ps, id_priv->id.qp_type, id_priv); if (IS_ERR(dev_id_priv)) return PTR_ERR(dev_id_priv); dev_id_priv->state = RDMA_CM_ADDR_BOUND; memcpy(cma_src_addr(dev_id_priv), cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); _cma_attach_to_dev(dev_id_priv, cma_dev); rdma_restrack_add(&dev_id_priv->res); cma_id_get(id_priv); dev_id_priv->internal_id = 1; dev_id_priv->afonly = id_priv->afonly; mutex_lock(&id_priv->qp_mutex); dev_id_priv->tos_set = id_priv->tos_set; dev_id_priv->tos = id_priv->tos; mutex_unlock(&id_priv->qp_mutex); ret = rdma_listen(&dev_id_priv->id, id_priv->backlog); if (ret) goto err_listen; list_add_tail(&dev_id_priv->listen_item, &id_priv->listen_list); return 0; err_listen: /* Caller must destroy this after releasing lock */ *to_destroy = dev_id_priv; dev_warn(&cma_dev->device->dev, "RDMA CMA: %s, error %d\n", __func__, ret); return ret; } static int cma_listen_on_all(struct rdma_id_private *id_priv) { struct rdma_id_private *to_destroy; struct cma_device *cma_dev; int ret; mutex_lock(&lock); list_add_tail(&id_priv->listen_any_item, &listen_any_list); list_for_each_entry(cma_dev, &dev_list, list) { ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy); if (ret) { /* Prevent racing with cma_process_remove() */ if (to_destroy) list_del_init(&to_destroy->device_item); goto err_listen; } } mutex_unlock(&lock); return 0; err_listen: _cma_cancel_listens(id_priv); mutex_unlock(&lock); if (to_destroy) rdma_destroy_id(&to_destroy->id); return ret; } void rdma_set_service_type(struct rdma_cm_id *id, int tos) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->tos = (u8) tos; id_priv->tos_set = true; mutex_unlock(&id_priv->qp_mutex); } EXPORT_SYMBOL(rdma_set_service_type); /** * rdma_set_ack_timeout() - Set the ack timeout of QP associated * with a connection identifier. * @id: Communication identifier to associated with service type. * @timeout: Ack timeout to set a QP, expressed as 4.096 * 2^(timeout) usec. * * This function should be called before rdma_connect() on active side, * and on passive side before rdma_accept(). It is applicable to primary * path only. The timeout will affect the local side of the QP, it is not * negotiated with remote side and zero disables the timer. In case it is * set before rdma_resolve_route, the value will also be used to determine * PacketLifeTime for RoCE. * * Return: 0 for success */ int rdma_set_ack_timeout(struct rdma_cm_id *id, u8 timeout) { struct rdma_id_private *id_priv; if (id->qp_type != IB_QPT_RC && id->qp_type != IB_QPT_XRC_INI) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->timeout = timeout; id_priv->timeout_set = true; mutex_unlock(&id_priv->qp_mutex); return 0; } EXPORT_SYMBOL(rdma_set_ack_timeout); /** * rdma_set_min_rnr_timer() - Set the minimum RNR Retry timer of the * QP associated with a connection identifier. * @id: Communication identifier to associated with service type. * @min_rnr_timer: 5-bit value encoded as Table 45: "Encoding for RNR NAK * Timer Field" in the IBTA specification. * * This function should be called before rdma_connect() on active * side, and on passive side before rdma_accept(). The timer value * will be associated with the local QP. When it receives a send it is * not read to handle, typically if the receive queue is empty, an RNR * Retry NAK is returned to the requester with the min_rnr_timer * encoded. The requester will then wait at least the time specified * in the NAK before retrying. The default is zero, which translates * to a minimum RNR Timer value of 655 ms. * * Return: 0 for success */ int rdma_set_min_rnr_timer(struct rdma_cm_id *id, u8 min_rnr_timer) { struct rdma_id_private *id_priv; /* It is a five-bit value */ if (min_rnr_timer & 0xe0) return -EINVAL; if (WARN_ON(id->qp_type != IB_QPT_RC && id->qp_type != IB_QPT_XRC_TGT)) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->min_rnr_timer = min_rnr_timer; id_priv->min_rnr_timer_set = true; mutex_unlock(&id_priv->qp_mutex); return 0; } EXPORT_SYMBOL(rdma_set_min_rnr_timer); static int route_set_path_rec_inbound(struct cma_work *work, struct sa_path_rec *path_rec) { struct rdma_route *route = &work->id->id.route; if (!route->path_rec_inbound) { route->path_rec_inbound = kzalloc(sizeof(*route->path_rec_inbound), GFP_KERNEL); if (!route->path_rec_inbound) return -ENOMEM; } *route->path_rec_inbound = *path_rec; return 0; } static int route_set_path_rec_outbound(struct cma_work *work, struct sa_path_rec *path_rec) { struct rdma_route *route = &work->id->id.route; if (!route->path_rec_outbound) { route->path_rec_outbound = kzalloc(sizeof(*route->path_rec_outbound), GFP_KERNEL); if (!route->path_rec_outbound) return -ENOMEM; } *route->path_rec_outbound = *path_rec; return 0; } static void cma_query_handler(int status, struct sa_path_rec *path_rec, unsigned int num_prs, void *context) { struct cma_work *work = context; struct rdma_route *route; int i; route = &work->id->id.route; if (status) goto fail; for (i = 0; i < num_prs; i++) { if (!path_rec[i].flags || (path_rec[i].flags & IB_PATH_GMP)) *route->path_rec = path_rec[i]; else if (path_rec[i].flags & IB_PATH_INBOUND) status = route_set_path_rec_inbound(work, &path_rec[i]); else if (path_rec[i].flags & IB_PATH_OUTBOUND) status = route_set_path_rec_outbound(work, &path_rec[i]); else status = -EINVAL; if (status) goto fail; } route->num_pri_alt_paths = 1; queue_work(cma_wq, &work->work); return; fail: work->old_state = RDMA_CM_ROUTE_QUERY; work->new_state = RDMA_CM_ADDR_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_ERROR; work->event.status = status; pr_debug_ratelimited("RDMA CM: ROUTE_ERROR: failed to query path. status %d\n", status); queue_work(cma_wq, &work->work); } static int cma_query_ib_route(struct rdma_id_private *id_priv, unsigned long timeout_ms, struct cma_work *work) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct sa_path_rec path_rec; ib_sa_comp_mask comp_mask; struct sockaddr_in6 *sin6; struct sockaddr_ib *sib; memset(&path_rec, 0, sizeof path_rec); if (rdma_cap_opa_ah(id_priv->id.device, id_priv->id.port_num)) path_rec.rec_type = SA_PATH_REC_TYPE_OPA; else path_rec.rec_type = SA_PATH_REC_TYPE_IB; rdma_addr_get_sgid(dev_addr, &path_rec.sgid); rdma_addr_get_dgid(dev_addr, &path_rec.dgid); path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); path_rec.numb_path = 1; path_rec.reversible = 1; path_rec.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH | IB_SA_PATH_REC_REVERSIBLE | IB_SA_PATH_REC_SERVICE_ID; switch (cma_family(id_priv)) { case AF_INET: path_rec.qos_class = cpu_to_be16((u16) id_priv->tos); comp_mask |= IB_SA_PATH_REC_QOS_CLASS; break; case AF_INET6: sin6 = (struct sockaddr_in6 *) cma_src_addr(id_priv); path_rec.traffic_class = (u8) (be32_to_cpu(sin6->sin6_flowinfo) >> 20); comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS; break; case AF_IB: sib = (struct sockaddr_ib *) cma_src_addr(id_priv); path_rec.traffic_class = (u8) (be32_to_cpu(sib->sib_flowinfo) >> 20); comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS; break; } id_priv->query_id = ib_sa_path_rec_get(&sa_client, id_priv->id.device, id_priv->id.port_num, &path_rec, comp_mask, timeout_ms, GFP_KERNEL, cma_query_handler, work, &id_priv->query); return (id_priv->query_id < 0) ? id_priv->query_id : 0; } static void cma_iboe_join_work_handler(struct work_struct *work) { struct cma_multicast *mc = container_of(work, struct cma_multicast, iboe_join.work); struct rdma_cm_event *event = &mc->iboe_join.event; struct rdma_id_private *id_priv = mc->id_priv; int ret; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; ret = cma_cm_event_handler(id_priv, event); WARN_ON(ret); out_unlock: mutex_unlock(&id_priv->handler_mutex); if (event->event == RDMA_CM_EVENT_MULTICAST_JOIN) rdma_destroy_ah_attr(&event->param.ud.ah_attr); } static void cma_work_handler(struct work_struct *_work) { struct cma_work *work = container_of(_work, struct cma_work, work); struct rdma_id_private *id_priv = work->id; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; if (work->old_state != 0 || work->new_state != 0) { if (!cma_comp_exch(id_priv, work->old_state, work->new_state)) goto out_unlock; } if (cma_cm_event_handler(id_priv, &work->event)) { cma_id_put(id_priv); destroy_id_handler_unlock(id_priv); goto out_free; } out_unlock: mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); out_free: if (work->event.event == RDMA_CM_EVENT_MULTICAST_JOIN) rdma_destroy_ah_attr(&work->event.param.ud.ah_attr); kfree(work); } static void cma_init_resolve_route_work(struct cma_work *work, struct rdma_id_private *id_priv) { work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ROUTE_QUERY; work->new_state = RDMA_CM_ROUTE_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; } static void enqueue_resolve_addr_work(struct cma_work *work, struct rdma_id_private *id_priv) { /* Balances with cma_id_put() in cma_work_handler */ cma_id_get(id_priv); work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ADDR_QUERY; work->new_state = RDMA_CM_ADDR_RESOLVED; work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED; queue_work(cma_wq, &work->work); } static int cma_resolve_ib_route(struct rdma_id_private *id_priv, unsigned long timeout_ms) { struct rdma_route *route = &id_priv->id.route; struct cma_work *work; int ret; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; cma_init_resolve_route_work(work, id_priv); if (!route->path_rec) route->path_rec = kmalloc(sizeof *route->path_rec, GFP_KERNEL); if (!route->path_rec) { ret = -ENOMEM; goto err1; } ret = cma_query_ib_route(id_priv, timeout_ms, work); if (ret) goto err2; return 0; err2: kfree(route->path_rec); route->path_rec = NULL; err1: kfree(work); return ret; } static enum ib_gid_type cma_route_gid_type(enum rdma_network_type network_type, unsigned long supported_gids, enum ib_gid_type default_gid) { if ((network_type == RDMA_NETWORK_IPV4 || network_type == RDMA_NETWORK_IPV6) && test_bit(IB_GID_TYPE_ROCE_UDP_ENCAP, &supported_gids)) return IB_GID_TYPE_ROCE_UDP_ENCAP; return default_gid; } /* * cma_iboe_set_path_rec_l2_fields() is helper function which sets * path record type based on GID type. * It also sets up other L2 fields which includes destination mac address * netdev ifindex, of the path record. * It returns the netdev of the bound interface for this path record entry. */ static struct net_device * cma_iboe_set_path_rec_l2_fields(struct rdma_id_private *id_priv) { struct rdma_route *route = &id_priv->id.route; enum ib_gid_type gid_type = IB_GID_TYPE_ROCE; struct rdma_addr *addr = &route->addr; unsigned long supported_gids; struct net_device *ndev; if (!addr->dev_addr.bound_dev_if) return NULL; ndev = dev_get_by_index(addr->dev_addr.net, addr->dev_addr.bound_dev_if); if (!ndev) return NULL; supported_gids = roce_gid_type_mask_support(id_priv->id.device, id_priv->id.port_num); gid_type = cma_route_gid_type(addr->dev_addr.network, supported_gids, id_priv->gid_type); /* Use the hint from IP Stack to select GID Type */ if (gid_type < ib_network_to_gid_type(addr->dev_addr.network)) gid_type = ib_network_to_gid_type(addr->dev_addr.network); route->path_rec->rec_type = sa_conv_gid_to_pathrec_type(gid_type); route->path_rec->roce.route_resolved = true; sa_path_set_dmac(route->path_rec, addr->dev_addr.dst_dev_addr); return ndev; } int rdma_set_ib_path(struct rdma_cm_id *id, struct sa_path_rec *path_rec) { struct rdma_id_private *id_priv; struct net_device *ndev; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ROUTE_RESOLVED)) return -EINVAL; id->route.path_rec = kmemdup(path_rec, sizeof(*path_rec), GFP_KERNEL); if (!id->route.path_rec) { ret = -ENOMEM; goto err; } if (rdma_protocol_roce(id->device, id->port_num)) { ndev = cma_iboe_set_path_rec_l2_fields(id_priv); if (!ndev) { ret = -ENODEV; goto err_free; } dev_put(ndev); } id->route.num_pri_alt_paths = 1; return 0; err_free: kfree(id->route.path_rec); id->route.path_rec = NULL; err: cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_ADDR_RESOLVED); return ret; } EXPORT_SYMBOL(rdma_set_ib_path); static int cma_resolve_iw_route(struct rdma_id_private *id_priv) { struct cma_work *work; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; cma_init_resolve_route_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; } static int get_vlan_ndev_tc(struct net_device *vlan_ndev, int prio) { struct net_device *dev; dev = vlan_dev_real_dev(vlan_ndev); if (dev->num_tc) return netdev_get_prio_tc_map(dev, prio); return (vlan_dev_get_egress_qos_mask(vlan_ndev, prio) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } struct iboe_prio_tc_map { int input_prio; int output_tc; bool found; }; static int get_lower_vlan_dev_tc(struct net_device *dev, struct netdev_nested_priv *priv) { struct iboe_prio_tc_map *map = (struct iboe_prio_tc_map *)priv->data; if (is_vlan_dev(dev)) map->output_tc = get_vlan_ndev_tc(dev, map->input_prio); else if (dev->num_tc) map->output_tc = netdev_get_prio_tc_map(dev, map->input_prio); else map->output_tc = 0; /* We are interested only in first level VLAN device, so always * return 1 to stop iterating over next level devices. */ map->found = true; return 1; } static int iboe_tos_to_sl(struct net_device *ndev, int tos) { struct iboe_prio_tc_map prio_tc_map = {}; int prio = rt_tos2priority(tos); struct netdev_nested_priv priv; /* If VLAN device, get it directly from the VLAN netdev */ if (is_vlan_dev(ndev)) return get_vlan_ndev_tc(ndev, prio); prio_tc_map.input_prio = prio; priv.data = (void *)&prio_tc_map; rcu_read_lock(); netdev_walk_all_lower_dev_rcu(ndev, get_lower_vlan_dev_tc, &priv); rcu_read_unlock(); /* If map is found from lower device, use it; Otherwise * continue with the current netdevice to get priority to tc map. */ if (prio_tc_map.found) return prio_tc_map.output_tc; else if (ndev->num_tc) return netdev_get_prio_tc_map(ndev, prio); else return 0; } static __be32 cma_get_roce_udp_flow_label(struct rdma_id_private *id_priv) { struct sockaddr_in6 *addr6; u16 dport, sport; u32 hash, fl; addr6 = (struct sockaddr_in6 *)cma_src_addr(id_priv); fl = be32_to_cpu(addr6->sin6_flowinfo) & IB_GRH_FLOWLABEL_MASK; if ((cma_family(id_priv) != AF_INET6) || !fl) { dport = be16_to_cpu(cma_port(cma_dst_addr(id_priv))); sport = be16_to_cpu(cma_port(cma_src_addr(id_priv))); hash = (u32)sport * 31 + dport; fl = hash & IB_GRH_FLOWLABEL_MASK; } return cpu_to_be32(fl); } static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) { struct rdma_route *route = &id_priv->id.route; struct rdma_addr *addr = &route->addr; struct cma_work *work; int ret; struct net_device *ndev; u8 default_roce_tos = id_priv->cma_dev->default_roce_tos[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; u8 tos; mutex_lock(&id_priv->qp_mutex); tos = id_priv->tos_set ? id_priv->tos : default_roce_tos; mutex_unlock(&id_priv->qp_mutex); work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; route->path_rec = kzalloc(sizeof *route->path_rec, GFP_KERNEL); if (!route->path_rec) { ret = -ENOMEM; goto err1; } route->num_pri_alt_paths = 1; ndev = cma_iboe_set_path_rec_l2_fields(id_priv); if (!ndev) { ret = -ENODEV; goto err2; } rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &route->path_rec->sgid); rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.dst_addr, &route->path_rec->dgid); if (((struct sockaddr *)&id_priv->id.route.addr.dst_addr)->sa_family != AF_IB) /* TODO: get the hoplimit from the inet/inet6 device */ route->path_rec->hop_limit = addr->dev_addr.hoplimit; else route->path_rec->hop_limit = 1; route->path_rec->reversible = 1; route->path_rec->pkey = cpu_to_be16(0xffff); route->path_rec->mtu_selector = IB_SA_EQ; route->path_rec->sl = iboe_tos_to_sl(ndev, tos); route->path_rec->traffic_class = tos; route->path_rec->mtu = iboe_get_mtu(ndev->mtu); route->path_rec->rate_selector = IB_SA_EQ; route->path_rec->rate = IB_RATE_PORT_CURRENT; dev_put(ndev); route->path_rec->packet_life_time_selector = IB_SA_EQ; /* In case ACK timeout is set, use this value to calculate * PacketLifeTime. As per IBTA 12.7.34, * local ACK timeout = (2 * PacketLifeTime + Local CA’s ACK delay). * Assuming a negligible local ACK delay, we can use * PacketLifeTime = local ACK timeout/2 * as a reasonable approximation for RoCE networks. */ mutex_lock(&id_priv->qp_mutex); if (id_priv->timeout_set && id_priv->timeout) route->path_rec->packet_life_time = id_priv->timeout - 1; else route->path_rec->packet_life_time = CMA_IBOE_PACKET_LIFETIME; mutex_unlock(&id_priv->qp_mutex); if (!route->path_rec->mtu) { ret = -EINVAL; goto err2; } if (rdma_protocol_roce_udp_encap(id_priv->id.device, id_priv->id.port_num)) route->path_rec->flow_label = cma_get_roce_udp_flow_label(id_priv); cma_init_resolve_route_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; err2: kfree(route->path_rec); route->path_rec = NULL; route->num_pri_alt_paths = 0; err1: kfree(work); return ret; } int rdma_resolve_route(struct rdma_cm_id *id, unsigned long timeout_ms) { struct rdma_id_private *id_priv; enum rdma_cm_state state; int ret; if (!timeout_ms) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); state = id_priv->state; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ROUTE_QUERY) && !cma_comp_exch(id_priv, RDMA_CM_ADDRINFO_RESOLVED, RDMA_CM_ROUTE_QUERY)) return -EINVAL; cma_id_get(id_priv); if (rdma_cap_ib_sa(id->device, id->port_num)) ret = cma_resolve_ib_route(id_priv, timeout_ms); else if (rdma_protocol_roce(id->device, id->port_num)) { ret = cma_resolve_iboe_route(id_priv); if (!ret) cma_add_id_to_tree(id_priv); } else if (rdma_protocol_iwarp(id->device, id->port_num)) ret = cma_resolve_iw_route(id_priv); else ret = -ENOSYS; if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ROUTE_QUERY, state); cma_id_put(id_priv); return ret; } EXPORT_SYMBOL(rdma_resolve_route); static void cma_set_loopback(struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: ((struct sockaddr_in *) addr)->sin_addr.s_addr = htonl(INADDR_LOOPBACK); break; case AF_INET6: ipv6_addr_set(&((struct sockaddr_in6 *) addr)->sin6_addr, 0, 0, 0, htonl(1)); break; default: ib_addr_set(&((struct sockaddr_ib *) addr)->sib_addr, 0, 0, 0, htonl(1)); break; } } static int cma_bind_loopback(struct rdma_id_private *id_priv) { struct cma_device *cma_dev, *cur_dev; union ib_gid gid; enum ib_port_state port_state; unsigned int p; u16 pkey; int ret; cma_dev = NULL; mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cur_dev->device, 1)) continue; if (!cma_dev) cma_dev = cur_dev; rdma_for_each_port (cur_dev->device, p) { if (!ib_get_cached_port_state(cur_dev->device, p, &port_state) && port_state == IB_PORT_ACTIVE) { cma_dev = cur_dev; goto port_found; } } } if (!cma_dev) { ret = -ENODEV; goto out; } p = 1; port_found: ret = rdma_query_gid(cma_dev->device, p, 0, &gid); if (ret) goto out; ret = ib_get_cached_pkey(cma_dev->device, p, 0, &pkey); if (ret) goto out; id_priv->id.route.addr.dev_addr.dev_type = (rdma_protocol_ib(cma_dev->device, p)) ? ARPHRD_INFINIBAND : ARPHRD_ETHER; rdma_addr_set_sgid(&id_priv->id.route.addr.dev_addr, &gid); ib_addr_set_pkey(&id_priv->id.route.addr.dev_addr, pkey); id_priv->id.port_num = p; cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); cma_set_loopback(cma_src_addr(id_priv)); out: mutex_unlock(&lock); return ret; } static void addr_handler(int status, struct sockaddr *src_addr, struct rdma_dev_addr *dev_addr, void *context) { struct rdma_id_private *id_priv = context; struct rdma_cm_event event = {}; struct sockaddr *addr; struct sockaddr_storage old_addr; mutex_lock(&id_priv->handler_mutex); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_RESOLVED)) goto out; /* * Store the previous src address, so that if we fail to acquire * matching rdma device, old address can be restored back, which helps * to cancel the cma listen operation correctly. */ addr = cma_src_addr(id_priv); memcpy(&old_addr, addr, rdma_addr_size(addr)); memcpy(addr, src_addr, rdma_addr_size(src_addr)); if (!status && !id_priv->cma_dev) { status = cma_acquire_dev_by_src_ip(id_priv); if (status) pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to acquire device. status %d\n", status); rdma_restrack_add(&id_priv->res); } else if (status) { pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to resolve IP. status %d\n", status); } if (status) { memcpy(addr, &old_addr, rdma_addr_size((struct sockaddr *)&old_addr)); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ADDR_BOUND)) goto out; event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = status; } else event.event = RDMA_CM_EVENT_ADDR_RESOLVED; if (cma_cm_event_handler(id_priv, &event)) { destroy_id_handler_unlock(id_priv); return; } out: mutex_unlock(&id_priv->handler_mutex); } static int cma_resolve_loopback(struct rdma_id_private *id_priv) { struct cma_work *work; union ib_gid gid; int ret; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; if (!id_priv->cma_dev) { ret = cma_bind_loopback(id_priv); if (ret) goto err; } rdma_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid); rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid); enqueue_resolve_addr_work(work, id_priv); return 0; err: kfree(work); return ret; } static int cma_resolve_ib_addr(struct rdma_id_private *id_priv) { struct cma_work *work; int ret; work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; if (!id_priv->cma_dev) { ret = cma_resolve_ib_dev(id_priv); if (ret) goto err; } rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *) &(((struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr)->sib_addr)); enqueue_resolve_addr_work(work, id_priv); return 0; err: kfree(work); return ret; } int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse) { struct rdma_id_private *id_priv; unsigned long flags; int ret; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irqsave(&id_priv->lock, flags); if ((reuse && id_priv->state != RDMA_CM_LISTEN) || id_priv->state == RDMA_CM_IDLE) { id_priv->reuseaddr = reuse; ret = 0; } else { ret = -EINVAL; } spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } EXPORT_SYMBOL(rdma_set_reuseaddr); int rdma_set_afonly(struct rdma_cm_id *id, int afonly) { struct rdma_id_private *id_priv; unsigned long flags; int ret; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irqsave(&id_priv->lock, flags); if (id_priv->state == RDMA_CM_IDLE || id_priv->state == RDMA_CM_ADDR_BOUND) { id_priv->options |= (1 << CMA_OPTION_AFONLY); id_priv->afonly = afonly; ret = 0; } else { ret = -EINVAL; } spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } EXPORT_SYMBOL(rdma_set_afonly); static void cma_bind_port(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv) { struct sockaddr *addr; struct sockaddr_ib *sib; u64 sid, mask; __be16 port; lockdep_assert_held(&lock); addr = cma_src_addr(id_priv); port = htons(bind_list->port); switch (addr->sa_family) { case AF_INET: ((struct sockaddr_in *) addr)->sin_port = port; break; case AF_INET6: ((struct sockaddr_in6 *) addr)->sin6_port = port; break; case AF_IB: sib = (struct sockaddr_ib *) addr; sid = be64_to_cpu(sib->sib_sid); mask = be64_to_cpu(sib->sib_sid_mask); sib->sib_sid = cpu_to_be64((sid & mask) | (u64) ntohs(port)); sib->sib_sid_mask = cpu_to_be64(~0ULL); break; } id_priv->bind_list = bind_list; hlist_add_head(&id_priv->node, &bind_list->owners); } static int cma_alloc_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv, unsigned short snum) { struct rdma_bind_list *bind_list; int ret; lockdep_assert_held(&lock); bind_list = kzalloc(sizeof *bind_list, GFP_KERNEL); if (!bind_list) return -ENOMEM; ret = cma_ps_alloc(id_priv->id.route.addr.dev_addr.net, ps, bind_list, snum); if (ret < 0) goto err; bind_list->ps = ps; bind_list->port = snum; cma_bind_port(bind_list, id_priv); return 0; err: kfree(bind_list); return ret == -ENOSPC ? -EADDRNOTAVAIL : ret; } static int cma_port_is_unique(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv) { struct rdma_id_private *cur_id; struct sockaddr *daddr = cma_dst_addr(id_priv); struct sockaddr *saddr = cma_src_addr(id_priv); __be16 dport = cma_port(daddr); lockdep_assert_held(&lock); hlist_for_each_entry(cur_id, &bind_list->owners, node) { struct sockaddr *cur_daddr = cma_dst_addr(cur_id); struct sockaddr *cur_saddr = cma_src_addr(cur_id); __be16 cur_dport = cma_port(cur_daddr); if (id_priv == cur_id) continue; /* different dest port -> unique */ if (!cma_any_port(daddr) && !cma_any_port(cur_daddr) && (dport != cur_dport)) continue; /* different src address -> unique */ if (!cma_any_addr(saddr) && !cma_any_addr(cur_saddr) && cma_addr_cmp(saddr, cur_saddr)) continue; /* different dst address -> unique */ if (!cma_any_addr(daddr) && !cma_any_addr(cur_daddr) && cma_addr_cmp(daddr, cur_daddr)) continue; return -EADDRNOTAVAIL; } return 0; } static int cma_alloc_any_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv) { static unsigned int last_used_port; int low, high, remaining; unsigned int rover; struct net *net = id_priv->id.route.addr.dev_addr.net; lockdep_assert_held(&lock); inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; rover = get_random_u32_inclusive(low, remaining + low - 1); retry: if (last_used_port != rover) { struct rdma_bind_list *bind_list; int ret; bind_list = cma_ps_find(net, ps, (unsigned short)rover); if (!bind_list) { ret = cma_alloc_port(ps, id_priv, rover); } else { ret = cma_port_is_unique(bind_list, id_priv); if (!ret) cma_bind_port(bind_list, id_priv); } /* * Remember previously used port number in order to avoid * re-using same port immediately after it is closed. */ if (!ret) last_used_port = rover; if (ret != -EADDRNOTAVAIL) return ret; } if (--remaining) { rover++; if ((rover < low) || (rover > high)) rover = low; goto retry; } return -EADDRNOTAVAIL; } /* * Check that the requested port is available. This is called when trying to * bind to a specific port, or when trying to listen on a bound port. In * the latter case, the provided id_priv may already be on the bind_list, but * we still need to check that it's okay to start listening. */ static int cma_check_port(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv, uint8_t reuseaddr) { struct rdma_id_private *cur_id; struct sockaddr *addr, *cur_addr; lockdep_assert_held(&lock); addr = cma_src_addr(id_priv); hlist_for_each_entry(cur_id, &bind_list->owners, node) { if (id_priv == cur_id) continue; if (reuseaddr && cur_id->reuseaddr) continue; cur_addr = cma_src_addr(cur_id); if (id_priv->afonly && cur_id->afonly && (addr->sa_family != cur_addr->sa_family)) continue; if (cma_any_addr(addr) || cma_any_addr(cur_addr)) return -EADDRNOTAVAIL; if (!cma_addr_cmp(addr, cur_addr)) return -EADDRINUSE; } return 0; } static int cma_use_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv) { struct rdma_bind_list *bind_list; unsigned short snum; int ret; lockdep_assert_held(&lock); snum = ntohs(cma_port(cma_src_addr(id_priv))); if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; bind_list = cma_ps_find(id_priv->id.route.addr.dev_addr.net, ps, snum); if (!bind_list) { ret = cma_alloc_port(ps, id_priv, snum); } else { ret = cma_check_port(bind_list, id_priv, id_priv->reuseaddr); if (!ret) cma_bind_port(bind_list, id_priv); } return ret; } static enum rdma_ucm_port_space cma_select_inet_ps(struct rdma_id_private *id_priv) { switch (id_priv->id.ps) { case RDMA_PS_TCP: case RDMA_PS_UDP: case RDMA_PS_IPOIB: case RDMA_PS_IB: return id_priv->id.ps; default: return 0; } } static enum rdma_ucm_port_space cma_select_ib_ps(struct rdma_id_private *id_priv) { enum rdma_ucm_port_space ps = 0; struct sockaddr_ib *sib; u64 sid_ps, mask, sid; sib = (struct sockaddr_ib *) cma_src_addr(id_priv); mask = be64_to_cpu(sib->sib_sid_mask) & RDMA_IB_IP_PS_MASK; sid = be64_to_cpu(sib->sib_sid) & mask; if ((id_priv->id.ps == RDMA_PS_IB) && (sid == (RDMA_IB_IP_PS_IB & mask))) { sid_ps = RDMA_IB_IP_PS_IB; ps = RDMA_PS_IB; } else if (((id_priv->id.ps == RDMA_PS_IB) || (id_priv->id.ps == RDMA_PS_TCP)) && (sid == (RDMA_IB_IP_PS_TCP & mask))) { sid_ps = RDMA_IB_IP_PS_TCP; ps = RDMA_PS_TCP; } else if (((id_priv->id.ps == RDMA_PS_IB) || (id_priv->id.ps == RDMA_PS_UDP)) && (sid == (RDMA_IB_IP_PS_UDP & mask))) { sid_ps = RDMA_IB_IP_PS_UDP; ps = RDMA_PS_UDP; } if (ps) { sib->sib_sid = cpu_to_be64(sid_ps | ntohs(cma_port((struct sockaddr *) sib))); sib->sib_sid_mask = cpu_to_be64(RDMA_IB_IP_PS_MASK | be64_to_cpu(sib->sib_sid_mask)); } return ps; } static int cma_get_port(struct rdma_id_private *id_priv) { enum rdma_ucm_port_space ps; int ret; if (cma_family(id_priv) != AF_IB) ps = cma_select_inet_ps(id_priv); else ps = cma_select_ib_ps(id_priv); if (!ps) return -EPROTONOSUPPORT; mutex_lock(&lock); if (cma_any_port(cma_src_addr(id_priv))) ret = cma_alloc_any_port(ps, id_priv); else ret = cma_use_port(ps, id_priv); mutex_unlock(&lock); return ret; } static int cma_check_linklocal(struct rdma_dev_addr *dev_addr, struct sockaddr *addr) { #if IS_ENABLED(CONFIG_IPV6) struct sockaddr_in6 *sin6; if (addr->sa_family != AF_INET6) return 0; sin6 = (struct sockaddr_in6 *) addr; if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)) return 0; if (!sin6->sin6_scope_id) return -EINVAL; dev_addr->bound_dev_if = sin6->sin6_scope_id; #endif return 0; } int rdma_listen(struct rdma_cm_id *id, int backlog) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN)) { struct sockaddr_in any_in = { .sin_family = AF_INET, .sin_addr.s_addr = htonl(INADDR_ANY), }; /* For a well behaved ULP state will be RDMA_CM_IDLE */ ret = rdma_bind_addr(id, (struct sockaddr *)&any_in); if (ret) return ret; if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN))) return -EINVAL; } /* * Once the ID reaches RDMA_CM_LISTEN it is not allowed to be reusable * any more, and has to be unique in the bind list. */ if (id_priv->reuseaddr) { mutex_lock(&lock); ret = cma_check_port(id_priv->bind_list, id_priv, 0); if (!ret) id_priv->reuseaddr = 0; mutex_unlock(&lock); if (ret) goto err; } id_priv->backlog = backlog; if (id_priv->cma_dev) { if (rdma_cap_ib_cm(id->device, 1)) { ret = cma_ib_listen(id_priv); if (ret) goto err; } else if (rdma_cap_iw_cm(id->device, 1)) { ret = cma_iw_listen(id_priv, backlog); if (ret) goto err; } else { ret = -ENOSYS; goto err; } } else { ret = cma_listen_on_all(id_priv); if (ret) goto err; } return 0; err: id_priv->backlog = 0; /* * All the failure paths that lead here will not allow the req_handler's * to have run. */ cma_comp_exch(id_priv, RDMA_CM_LISTEN, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_listen); static int rdma_bind_addr_dst(struct rdma_id_private *id_priv, struct sockaddr *addr, const struct sockaddr *daddr) { struct sockaddr *id_daddr; int ret; if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6 && addr->sa_family != AF_IB) return -EAFNOSUPPORT; if (!cma_comp_exch(id_priv, RDMA_CM_IDLE, RDMA_CM_ADDR_BOUND)) return -EINVAL; ret = cma_check_linklocal(&id_priv->id.route.addr.dev_addr, addr); if (ret) goto err1; memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr)); if (!cma_any_addr(addr)) { ret = cma_translate_addr(addr, &id_priv->id.route.addr.dev_addr); if (ret) goto err1; ret = cma_acquire_dev_by_src_ip(id_priv); if (ret) goto err1; } if (!(id_priv->options & (1 << CMA_OPTION_AFONLY))) { if (addr->sa_family == AF_INET) id_priv->afonly = 1; #if IS_ENABLED(CONFIG_IPV6) else if (addr->sa_family == AF_INET6) { struct net *net = id_priv->id.route.addr.dev_addr.net; id_priv->afonly = net->ipv6.sysctl.bindv6only; } #endif } id_daddr = cma_dst_addr(id_priv); if (daddr != id_daddr) memcpy(id_daddr, daddr, rdma_addr_size(addr)); id_daddr->sa_family = addr->sa_family; ret = cma_get_port(id_priv); if (ret) goto err2; if (!cma_any_addr(addr)) rdma_restrack_add(&id_priv->res); return 0; err2: if (id_priv->cma_dev) cma_release_dev(id_priv); err1: cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_IDLE); return ret; } static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, const struct sockaddr *dst_addr) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); struct sockaddr_storage zero_sock = {}; if (src_addr && src_addr->sa_family) return rdma_bind_addr_dst(id_priv, src_addr, dst_addr); /* * When the src_addr is not specified, automatically supply an any addr */ zero_sock.ss_family = dst_addr->sa_family; if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) { struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *)&zero_sock; struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *)dst_addr; src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) id->route.addr.dev_addr.bound_dev_if = dst_addr6->sin6_scope_id; } else if (dst_addr->sa_family == AF_IB) { ((struct sockaddr_ib *)&zero_sock)->sib_pkey = ((struct sockaddr_ib *)dst_addr)->sib_pkey; } return rdma_bind_addr_dst(id_priv, (struct sockaddr *)&zero_sock, dst_addr); } /* * If required, resolve the source address for bind and leave the id_priv in * state RDMA_CM_ADDR_BOUND. This oddly uses the state to determine the prior * calls made by ULP, a previously bound ID will not be re-bound and src_addr is * ignored. */ static int resolve_prepare_src(struct rdma_id_private *id_priv, struct sockaddr *src_addr, const struct sockaddr *dst_addr) { int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) { /* For a well behaved ULP state will be RDMA_CM_IDLE */ ret = cma_bind_addr(&id_priv->id, src_addr, dst_addr); if (ret) return ret; if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY))) return -EINVAL; } else { memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr)); } if (cma_family(id_priv) != dst_addr->sa_family) { ret = -EINVAL; goto err_state; } return 0; err_state: cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); return ret; } int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, const struct sockaddr *dst_addr, unsigned long timeout_ms) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; ret = resolve_prepare_src(id_priv, src_addr, dst_addr); if (ret) return ret; if (cma_any_addr(dst_addr)) { ret = cma_resolve_loopback(id_priv); } else { if (dst_addr->sa_family == AF_IB) { ret = cma_resolve_ib_addr(id_priv); } else { /* * The FSM can return back to RDMA_CM_ADDR_BOUND after * rdma_resolve_ip() is called, eg through the error * path in addr_handler(). If this happens the existing * request must be canceled before issuing a new one. * Since canceling a request is a bit slow and this * oddball path is rare, keep track once a request has * been issued. The track turns out to be a permanent * state since this is the only cancel as it is * immediately before rdma_resolve_ip(). */ if (id_priv->used_resolve_ip) rdma_addr_cancel(&id->route.addr.dev_addr); else id_priv->used_resolve_ip = 1; ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr, &id->route.addr.dev_addr, timeout_ms, addr_handler, false, id_priv); } } if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_resolve_addr); int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); return rdma_bind_addr_dst(id_priv, addr, cma_dst_addr(id_priv)); } EXPORT_SYMBOL(rdma_bind_addr); static int cma_format_hdr(void *hdr, struct rdma_id_private *id_priv) { struct cma_hdr *cma_hdr; cma_hdr = hdr; cma_hdr->cma_version = CMA_VERSION; if (cma_family(id_priv) == AF_INET) { struct sockaddr_in *src4, *dst4; src4 = (struct sockaddr_in *) cma_src_addr(id_priv); dst4 = (struct sockaddr_in *) cma_dst_addr(id_priv); cma_set_ip_ver(cma_hdr, 4); cma_hdr->src_addr.ip4.addr = src4->sin_addr.s_addr; cma_hdr->dst_addr.ip4.addr = dst4->sin_addr.s_addr; cma_hdr->port = src4->sin_port; } else if (cma_family(id_priv) == AF_INET6) { struct sockaddr_in6 *src6, *dst6; src6 = (struct sockaddr_in6 *) cma_src_addr(id_priv); dst6 = (struct sockaddr_in6 *) cma_dst_addr(id_priv); cma_set_ip_ver(cma_hdr, 6); cma_hdr->src_addr.ip6 = src6->sin6_addr; cma_hdr->dst_addr.ip6 = dst6->sin6_addr; cma_hdr->port = src6->sin6_port; } return 0; } static int cma_sidr_rep_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *id_priv = cm_id->context; struct rdma_cm_event event = {}; const struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd; int ret; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) goto out; switch (ib_event->event) { case IB_CM_SIDR_REQ_ERROR: event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; break; case IB_CM_SIDR_REP_RECEIVED: event.param.ud.private_data = ib_event->private_data; event.param.ud.private_data_len = IB_CM_SIDR_REP_PRIVATE_DATA_SIZE; if (rep->status != IB_SIDR_SUCCESS) { event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = ib_event->param.sidr_rep_rcvd.status; pr_debug_ratelimited("RDMA CM: UNREACHABLE: bad SIDR reply. status %d\n", event.status); break; } ret = cma_set_qkey(id_priv, rep->qkey); if (ret) { pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to set qkey. status %d\n", ret); event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = ret; break; } ib_init_ah_attr_from_path(id_priv->id.device, id_priv->id.port_num, id_priv->id.route.path_rec, &event.param.ud.ah_attr, rep->sgid_attr); event.param.ud.qp_num = rep->qpn; event.param.ud.qkey = rep->qkey; event.event = RDMA_CM_EVENT_ESTABLISHED; event.status = 0; break; default: pr_err("RDMA CMA: unexpected IB CM event: %d\n", ib_event->event); goto out; } ret = cma_cm_event_handler(id_priv, &event); rdma_destroy_ah_attr(&event.param.ud.ah_attr); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return 0; } static int cma_resolve_ib_udp(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_sidr_req_param req; struct ib_cm_id *id; void *private_data; u8 offset; int ret; memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); if (check_add_overflow(offset, conn_param->private_data_len, &req.private_data_len)) return -EINVAL; if (req.private_data_len) { private_data = kzalloc(req.private_data_len, GFP_ATOMIC); if (!private_data) return -ENOMEM; } else { private_data = NULL; } if (conn_param->private_data && conn_param->private_data_len) memcpy(private_data + offset, conn_param->private_data, conn_param->private_data_len); if (private_data) { ret = cma_format_hdr(private_data, id_priv); if (ret) goto out; req.private_data = private_data; } id = ib_create_cm_id(id_priv->id.device, cma_sidr_rep_handler, id_priv); if (IS_ERR(id)) { ret = PTR_ERR(id); goto out; } id_priv->cm_id.ib = id; req.path = id_priv->id.route.path_rec; req.sgid_attr = id_priv->id.route.addr.dev_addr.sgid_attr; req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); req.timeout_ms = 1 << (CMA_CM_RESPONSE_TIMEOUT - 8); req.max_cm_retries = CMA_MAX_CM_RETRIES; trace_cm_send_sidr_req(id_priv); ret = ib_send_cm_sidr_req(id_priv->cm_id.ib, &req); if (ret) { ib_destroy_cm_id(id_priv->cm_id.ib); id_priv->cm_id.ib = NULL; } out: kfree(private_data); return ret; } static int cma_connect_ib(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_req_param req; struct rdma_route *route; void *private_data; struct ib_cm_id *id; u8 offset; int ret; memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); if (check_add_overflow(offset, conn_param->private_data_len, &req.private_data_len)) return -EINVAL; if (req.private_data_len) { private_data = kzalloc(req.private_data_len, GFP_ATOMIC); if (!private_data) return -ENOMEM; } else { private_data = NULL; } if (conn_param->private_data && conn_param->private_data_len) memcpy(private_data + offset, conn_param->private_data, conn_param->private_data_len); id = ib_create_cm_id(id_priv->id.device, cma_ib_handler, id_priv); if (IS_ERR(id)) { ret = PTR_ERR(id); goto out; } id_priv->cm_id.ib = id; route = &id_priv->id.route; if (private_data) { ret = cma_format_hdr(private_data, id_priv); if (ret) goto out; req.private_data = private_data; } req.primary_path = &route->path_rec[0]; req.primary_path_inbound = route->path_rec_inbound; req.primary_path_outbound = route->path_rec_outbound; if (route->num_pri_alt_paths == 2) req.alternate_path = &route->path_rec[1]; req.ppath_sgid_attr = id_priv->id.route.addr.dev_addr.sgid_attr; /* Alternate path SGID attribute currently unsupported */ req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); req.qp_num = id_priv->qp_num; req.qp_type = id_priv->id.qp_type; req.starting_psn = id_priv->seq_num; req.responder_resources = conn_param->responder_resources; req.initiator_depth = conn_param->initiator_depth; req.flow_control = conn_param->flow_control; req.retry_count = min_t(u8, 7, conn_param->retry_count); req.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count); req.remote_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT; req.local_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT; req.max_cm_retries = CMA_MAX_CM_RETRIES; req.srq = id_priv->srq ? 1 : 0; req.ece.vendor_id = id_priv->ece.vendor_id; req.ece.attr_mod = id_priv->ece.attr_mod; trace_cm_send_req(id_priv); ret = ib_send_cm_req(id_priv->cm_id.ib, &req); out: if (ret && !IS_ERR(id)) { ib_destroy_cm_id(id); id_priv->cm_id.ib = NULL; } kfree(private_data); return ret; } static int cma_connect_iw(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct iw_cm_id *cm_id; int ret; struct iw_cm_conn_param iw_param; cm_id = iw_create_cm_id(id_priv->id.device, cma_iw_handler, id_priv); if (IS_ERR(cm_id)) return PTR_ERR(cm_id); mutex_lock(&id_priv->qp_mutex); cm_id->tos = id_priv->tos; cm_id->tos_set = id_priv->tos_set; mutex_unlock(&id_priv->qp_mutex); id_priv->cm_id.iw = cm_id; memcpy(&cm_id->local_addr, cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); memcpy(&cm_id->remote_addr, cma_dst_addr(id_priv), rdma_addr_size(cma_dst_addr(id_priv))); ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) goto out; if (conn_param) { iw_param.ord = conn_param->initiator_depth; iw_param.ird = conn_param->responder_resources; iw_param.private_data = conn_param->private_data; iw_param.private_data_len = conn_param->private_data_len; iw_param.qpn = id_priv->id.qp ? id_priv->qp_num : conn_param->qp_num; } else { memset(&iw_param, 0, sizeof iw_param); iw_param.qpn = id_priv->qp_num; } ret = iw_cm_connect(cm_id, &iw_param); out: if (ret) { iw_destroy_cm_id(cm_id); id_priv->cm_id.iw = NULL; } return ret; } /** * rdma_connect_locked - Initiate an active connection request. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * * Same as rdma_connect() but can only be called from the * RDMA_CM_EVENT_ROUTE_RESOLVED handler callback. */ int rdma_connect_locked(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT)) return -EINVAL; if (!id->qp) { id_priv->qp_num = conn_param->qp_num; id_priv->srq = conn_param->srq; } if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) ret = cma_resolve_ib_udp(id_priv, conn_param); else ret = cma_connect_ib(id_priv, conn_param); } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = cma_connect_iw(id_priv, conn_param); } else { ret = -ENOSYS; } if (ret) goto err_state; return 0; err_state: cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_ROUTE_RESOLVED); return ret; } EXPORT_SYMBOL(rdma_connect_locked); /** * rdma_connect - Initiate an active connection request. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * * Users must have resolved a route for the rdma_cm_id to connect with by having * called rdma_resolve_route before calling this routine. * * This call will either connect to a remote QP or obtain remote QP information * for unconnected rdma_cm_id's. The actual operation is based on the * rdma_cm_id's port space. */ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; mutex_lock(&id_priv->handler_mutex); ret = rdma_connect_locked(id, conn_param); mutex_unlock(&id_priv->handler_mutex); return ret; } EXPORT_SYMBOL(rdma_connect); /** * rdma_connect_ece - Initiate an active connection request with ECE data. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * @ece: ECE parameters * * See rdma_connect() explanation. */ int rdma_connect_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, struct rdma_ucm_ece *ece) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); id_priv->ece.vendor_id = ece->vendor_id; id_priv->ece.attr_mod = ece->attr_mod; return rdma_connect(id, conn_param); } EXPORT_SYMBOL(rdma_connect_ece); static int cma_accept_ib(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_rep_param rep; int ret; ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) goto out; ret = cma_modify_qp_rts(id_priv, conn_param); if (ret) goto out; memset(&rep, 0, sizeof rep); rep.qp_num = id_priv->qp_num; rep.starting_psn = id_priv->seq_num; rep.private_data = conn_param->private_data; rep.private_data_len = conn_param->private_data_len; rep.responder_resources = conn_param->responder_resources; rep.initiator_depth = conn_param->initiator_depth; rep.failover_accepted = 0; rep.flow_control = conn_param->flow_control; rep.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count); rep.srq = id_priv->srq ? 1 : 0; rep.ece.vendor_id = id_priv->ece.vendor_id; rep.ece.attr_mod = id_priv->ece.attr_mod; trace_cm_send_rep(id_priv); ret = ib_send_cm_rep(id_priv->cm_id.ib, &rep); out: return ret; } static int cma_accept_iw(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct iw_cm_conn_param iw_param; int ret; if (!conn_param) return -EINVAL; ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) return ret; iw_param.ord = conn_param->initiator_depth; iw_param.ird = conn_param->responder_resources; iw_param.private_data = conn_param->private_data; iw_param.private_data_len = conn_param->private_data_len; if (id_priv->id.qp) iw_param.qpn = id_priv->qp_num; else iw_param.qpn = conn_param->qp_num; return iw_cm_accept(id_priv->cm_id.iw, &iw_param); } static int cma_send_sidr_rep(struct rdma_id_private *id_priv, enum ib_cm_sidr_status status, u32 qkey, const void *private_data, int private_data_len) { struct ib_cm_sidr_rep_param rep; int ret; memset(&rep, 0, sizeof rep); rep.status = status; if (status == IB_SIDR_SUCCESS) { if (qkey) ret = cma_set_qkey(id_priv, qkey); else ret = cma_set_default_qkey(id_priv); if (ret) return ret; rep.qp_num = id_priv->qp_num; rep.qkey = id_priv->qkey; rep.ece.vendor_id = id_priv->ece.vendor_id; rep.ece.attr_mod = id_priv->ece.attr_mod; } rep.private_data = private_data; rep.private_data_len = private_data_len; trace_cm_send_sidr_rep(id_priv); return ib_send_cm_sidr_rep(id_priv->cm_id.ib, &rep); } /** * rdma_accept - Called to accept a connection request or response. * @id: Connection identifier associated with the request. * @conn_param: Information needed to establish the connection. This must be * provided if accepting a connection request. If accepting a connection * response, this parameter must be NULL. * * Typically, this routine is only called by the listener to accept a connection * request. It must also be called on the active side of a connection if the * user is performing their own QP transitions. * * In the case of error, a reject message is sent to the remote side and the * state of the qp associated with the id is modified to error, such that any * previously posted receive buffers would be flushed. * * This function is for use by kernel ULPs and must be called from under the * handler callback. */ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; lockdep_assert_held(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) return -EINVAL; if (!id->qp && conn_param) { id_priv->qp_num = conn_param->qp_num; id_priv->srq = conn_param->srq; } if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) { if (conn_param) ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, conn_param->qkey, conn_param->private_data, conn_param->private_data_len); else ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, 0, NULL, 0); } else { if (conn_param) ret = cma_accept_ib(id_priv, conn_param); else ret = cma_rep_recv(id_priv); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = cma_accept_iw(id_priv, conn_param); } else { ret = -ENOSYS; } if (ret) goto reject; return 0; reject: cma_modify_qp_err(id_priv); rdma_reject(id, NULL, 0, IB_CM_REJ_CONSUMER_DEFINED); return ret; } EXPORT_SYMBOL(rdma_accept); int rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, struct rdma_ucm_ece *ece) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); id_priv->ece.vendor_id = ece->vendor_id; id_priv->ece.attr_mod = ece->attr_mod; return rdma_accept(id, conn_param); } EXPORT_SYMBOL(rdma_accept_ece); void rdma_lock_handler(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->handler_mutex); } EXPORT_SYMBOL(rdma_lock_handler); void rdma_unlock_handler(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_unlock(&id_priv->handler_mutex); } EXPORT_SYMBOL(rdma_unlock_handler); int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; switch (id->device->node_type) { case RDMA_NODE_IB_CA: ret = ib_cm_notify(id_priv->cm_id.ib, event); break; default: ret = 0; break; } return ret; } EXPORT_SYMBOL(rdma_notify); int rdma_reject(struct rdma_cm_id *id, const void *private_data, u8 private_data_len, u8 reason) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) { ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, 0, private_data, private_data_len); } else { trace_cm_send_rej(id_priv); ret = ib_send_cm_rej(id_priv->cm_id.ib, reason, NULL, 0, private_data, private_data_len); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = iw_cm_reject(id_priv->cm_id.iw, private_data, private_data_len); } else { ret = -ENOSYS; } return ret; } EXPORT_SYMBOL(rdma_reject); int rdma_disconnect(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; if (rdma_cap_ib_cm(id->device, id->port_num)) { ret = cma_modify_qp_err(id_priv); if (ret) goto out; /* Initiate or respond to a disconnect. */ trace_cm_disconnect(id_priv); if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0)) { if (!ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0)) trace_cm_sent_drep(id_priv); } else { trace_cm_sent_dreq(id_priv); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = iw_cm_disconnect(id_priv->cm_id.iw, 0); } else ret = -EINVAL; out: return ret; } EXPORT_SYMBOL(rdma_disconnect); static void cma_make_mc_event(int status, struct rdma_id_private *id_priv, struct ib_sa_multicast *multicast, struct rdma_cm_event *event, struct cma_multicast *mc) { struct rdma_dev_addr *dev_addr; enum ib_gid_type gid_type; struct net_device *ndev; if (status) pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to join multicast. status %d\n", status); event->status = status; event->param.ud.private_data = mc->context; if (status) { event->event = RDMA_CM_EVENT_MULTICAST_ERROR; return; } dev_addr = &id_priv->id.route.addr.dev_addr; ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); gid_type = id_priv->cma_dev ->default_gid_type[id_priv->id.port_num - rdma_start_port( id_priv->cma_dev->device)]; event->event = RDMA_CM_EVENT_MULTICAST_JOIN; if (ib_init_ah_from_mcmember(id_priv->id.device, id_priv->id.port_num, &multicast->rec, ndev, gid_type, &event->param.ud.ah_attr)) { event->event = RDMA_CM_EVENT_MULTICAST_ERROR; goto out; } event->param.ud.qp_num = 0xFFFFFF; event->param.ud.qkey = id_priv->qkey; out: dev_put(ndev); } static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) { struct cma_multicast *mc = multicast->context; struct rdma_id_private *id_priv = mc->id_priv; struct rdma_cm_event event = {}; int ret = 0; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL || READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING) goto out; ret = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); if (!ret) { cma_make_mc_event(status, id_priv, multicast, &event, mc); ret = cma_cm_event_handler(id_priv, &event); } rdma_destroy_ah_attr(&event.param.ud.ah_attr); WARN_ON(ret); out: mutex_unlock(&id_priv->handler_mutex); return 0; } static void cma_set_mgid(struct rdma_id_private *id_priv, struct sockaddr *addr, union ib_gid *mgid) { unsigned char mc_map[MAX_ADDR_LEN]; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct sockaddr_in *sin = (struct sockaddr_in *) addr; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) addr; if (cma_any_addr(addr)) { memset(mgid, 0, sizeof *mgid); } else if ((addr->sa_family == AF_INET6) && ((be32_to_cpu(sin6->sin6_addr.s6_addr32[0]) & 0xFFF0FFFF) == 0xFF10A01B)) { /* IPv6 address is an SA assigned MGID. */ memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); } else if (addr->sa_family == AF_IB) { memcpy(mgid, &((struct sockaddr_ib *) addr)->sib_addr, sizeof *mgid); } else if (addr->sa_family == AF_INET6) { ipv6_ib_mc_map(&sin6->sin6_addr, dev_addr->broadcast, mc_map); if (id_priv->id.ps == RDMA_PS_UDP) mc_map[7] = 0x01; /* Use RDMA CM signature */ *mgid = *(union ib_gid *) (mc_map + 4); } else { ip_ib_mc_map(sin->sin_addr.s_addr, dev_addr->broadcast, mc_map); if (id_priv->id.ps == RDMA_PS_UDP) mc_map[7] = 0x01; /* Use RDMA CM signature */ *mgid = *(union ib_gid *) (mc_map + 4); } } static int cma_join_ib_multicast(struct rdma_id_private *id_priv, struct cma_multicast *mc) { struct ib_sa_mcmember_rec rec; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; ib_sa_comp_mask comp_mask; int ret; ib_addr_get_mgid(dev_addr, &rec.mgid); ret = ib_sa_get_mcmember_rec(id_priv->id.device, id_priv->id.port_num, &rec.mgid, &rec); if (ret) return ret; if (!id_priv->qkey) { ret = cma_set_default_qkey(id_priv); if (ret) return ret; } cma_set_mgid(id_priv, (struct sockaddr *) &mc->addr, &rec.mgid); rec.qkey = cpu_to_be32(id_priv->qkey); rdma_addr_get_sgid(dev_addr, &rec.port_gid); rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); rec.join_state = mc->join_state; comp_mask = IB_SA_MCMEMBER_REC_MGID | IB_SA_MCMEMBER_REC_PORT_GID | IB_SA_MCMEMBER_REC_PKEY | IB_SA_MCMEMBER_REC_JOIN_STATE | IB_SA_MCMEMBER_REC_QKEY | IB_SA_MCMEMBER_REC_SL | IB_SA_MCMEMBER_REC_FLOW_LABEL | IB_SA_MCMEMBER_REC_TRAFFIC_CLASS; if (id_priv->id.ps == RDMA_PS_IPOIB) comp_mask |= IB_SA_MCMEMBER_REC_RATE | IB_SA_MCMEMBER_REC_RATE_SELECTOR | IB_SA_MCMEMBER_REC_MTU_SELECTOR | IB_SA_MCMEMBER_REC_MTU | IB_SA_MCMEMBER_REC_HOP_LIMIT; mc->sa_mc = ib_sa_join_multicast(&sa_client, id_priv->id.device, id_priv->id.port_num, &rec, comp_mask, GFP_KERNEL, cma_ib_mc_handler, mc); return PTR_ERR_OR_ZERO(mc->sa_mc); } static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, enum ib_gid_type gid_type) { struct sockaddr_in *sin = (struct sockaddr_in *)addr; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; if (cma_any_addr(addr)) { memset(mgid, 0, sizeof *mgid); } else if (addr->sa_family == AF_INET6) { memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); } else { mgid->raw[0] = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ? 0 : 0xff; mgid->raw[1] = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ? 0 : 0x0e; mgid->raw[2] = 0; mgid->raw[3] = 0; mgid->raw[4] = 0; mgid->raw[5] = 0; mgid->raw[6] = 0; mgid->raw[7] = 0; mgid->raw[8] = 0; mgid->raw[9] = 0; mgid->raw[10] = 0xff; mgid->raw[11] = 0xff; *(__be32 *)(&mgid->raw[12]) = sin->sin_addr.s_addr; } } static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, struct cma_multicast *mc) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int err = 0; struct sockaddr *addr = (struct sockaddr *)&mc->addr; struct net_device *ndev = NULL; struct ib_sa_multicast ib = {}; enum ib_gid_type gid_type; bool send_only; send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); if (cma_zero_addr(addr)) return -EINVAL; gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; cma_iboe_set_mgid(addr, &ib.rec.mgid, gid_type); ib.rec.pkey = cpu_to_be16(0xffff); if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (!ndev) return -ENODEV; ib.rec.rate = IB_RATE_PORT_CURRENT; ib.rec.hop_limit = 1; ib.rec.mtu = iboe_get_mtu(ndev->mtu); if (addr->sa_family == AF_INET) { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) { ib.rec.hop_limit = IPV6_DEFAULT_HOPLIMIT; if (!send_only) { err = cma_igmp_send(ndev, &ib.rec.mgid, true); } } } else { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) err = -ENOTSUPP; } dev_put(ndev); if (err || !ib.rec.mtu) return err ?: -EINVAL; if (!id_priv->qkey) cma_set_default_qkey(id_priv); rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &ib.rec.port_gid); INIT_WORK(&mc->iboe_join.work, cma_iboe_join_work_handler); cma_make_mc_event(0, id_priv, &ib, &mc->iboe_join.event, mc); queue_work(cma_wq, &mc->iboe_join.work); return 0; } int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, u8 join_state, void *context) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); struct cma_multicast *mc; int ret; /* Not supported for kernel QPs */ if (WARN_ON(id->qp)) return -EINVAL; /* ULP is calling this wrong. */ if (!id->device || (READ_ONCE(id_priv->state) != RDMA_CM_ADDR_BOUND && READ_ONCE(id_priv->state) != RDMA_CM_ADDR_RESOLVED)) return -EINVAL; if (id_priv->id.qp_type != IB_QPT_UD) return -EINVAL; mc = kzalloc(sizeof(*mc), GFP_KERNEL); if (!mc) return -ENOMEM; memcpy(&mc->addr, addr, rdma_addr_size(addr)); mc->context = context; mc->id_priv = id_priv; mc->join_state = join_state; if (rdma_protocol_roce(id->device, id->port_num)) { ret = cma_iboe_join_multicast(id_priv, mc); if (ret) goto out_err; } else if (rdma_cap_ib_mcast(id->device, id->port_num)) { ret = cma_join_ib_multicast(id_priv, mc); if (ret) goto out_err; } else { ret = -ENOSYS; goto out_err; } spin_lock(&id_priv->lock); list_add(&mc->list, &id_priv->mc_list); spin_unlock(&id_priv->lock); return 0; out_err: kfree(mc); return ret; } EXPORT_SYMBOL(rdma_join_multicast); void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv; struct cma_multicast *mc; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irq(&id_priv->lock); list_for_each_entry(mc, &id_priv->mc_list, list) { if (memcmp(&mc->addr, addr, rdma_addr_size(addr)) != 0) continue; list_del(&mc->list); spin_unlock_irq(&id_priv->lock); WARN_ON(id_priv->cma_dev->device != id->device); destroy_mc(id_priv, mc); return; } spin_unlock_irq(&id_priv->lock); } EXPORT_SYMBOL(rdma_leave_multicast); static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr; struct cma_work *work; dev_addr = &id_priv->id.route.addr.dev_addr; if ((dev_addr->bound_dev_if == ndev->ifindex) && (net_eq(dev_net(ndev), dev_addr->net)) && memcmp(dev_addr->src_dev_addr, ndev->dev_addr, ndev->addr_len)) { pr_info("RDMA CM addr change for ndev %s used by id %p\n", ndev->name, &id_priv->id); work = kzalloc(sizeof *work, GFP_KERNEL); if (!work) return -ENOMEM; INIT_WORK(&work->work, cma_work_handler); work->id = id_priv; work->event.event = RDMA_CM_EVENT_ADDR_CHANGE; cma_id_get(id_priv); queue_work(cma_wq, &work->work); } return 0; } static int cma_netdev_callback(struct notifier_block *self, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct cma_device *cma_dev; struct rdma_id_private *id_priv; int ret = NOTIFY_DONE; if (event != NETDEV_BONDING_FAILOVER) return NOTIFY_DONE; if (!netif_is_bond_master(ndev)) return NOTIFY_DONE; mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) list_for_each_entry(id_priv, &cma_dev->id_list, device_item) { ret = cma_netdev_change(ndev, id_priv); if (ret) goto out; } out: mutex_unlock(&lock); return ret; } static void cma_netevent_work_handler(struct work_struct *_work) { struct rdma_id_private *id_priv = container_of(_work, struct rdma_id_private, id.net_work); struct rdma_cm_event event = {}; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; if (cma_cm_event_handler(id_priv, &event)) { __acquire(&id_priv->handler_mutex); id_priv->cm_id.ib = NULL; cma_id_put(id_priv); destroy_id_handler_unlock(id_priv); return; } out_unlock: mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); } static int cma_netevent_callback(struct notifier_block *self, unsigned long event, void *ctx) { struct id_table_entry *ips_node = NULL; struct rdma_id_private *current_id; struct neighbour *neigh = ctx; unsigned long flags; if (event != NETEVENT_NEIGH_UPDATE) return NOTIFY_DONE; spin_lock_irqsave(&id_table_lock, flags); if (neigh->tbl->family == AF_INET6) { struct sockaddr_in6 neigh_sock_6; neigh_sock_6.sin6_family = AF_INET6; neigh_sock_6.sin6_addr = *(struct in6_addr *)neigh->primary_key; ips_node = node_from_ndev_ip(&id_table, neigh->dev->ifindex, (struct sockaddr *)&neigh_sock_6); } else if (neigh->tbl->family == AF_INET) { struct sockaddr_in neigh_sock_4; neigh_sock_4.sin_family = AF_INET; neigh_sock_4.sin_addr.s_addr = *(__be32 *)(neigh->primary_key); ips_node = node_from_ndev_ip(&id_table, neigh->dev->ifindex, (struct sockaddr *)&neigh_sock_4); } else goto out; if (!ips_node) goto out; list_for_each_entry(current_id, &ips_node->id_list, id_list_entry) { if (!memcmp(current_id->id.route.addr.dev_addr.dst_dev_addr, neigh->ha, ETH_ALEN)) continue; cma_id_get(current_id); if (!queue_work(cma_wq, ¤t_id->id.net_work)) cma_id_put(current_id); } out: spin_unlock_irqrestore(&id_table_lock, flags); return NOTIFY_DONE; } static struct notifier_block cma_nb = { .notifier_call = cma_netdev_callback }; static struct notifier_block cma_netevent_cb = { .notifier_call = cma_netevent_callback }; static void cma_send_device_removal_put(struct rdma_id_private *id_priv) { struct rdma_cm_event event = { .event = RDMA_CM_EVENT_DEVICE_REMOVAL }; enum rdma_cm_state state; unsigned long flags; mutex_lock(&id_priv->handler_mutex); /* Record that we want to remove the device */ spin_lock_irqsave(&id_priv->lock, flags); state = id_priv->state; if (state == RDMA_CM_DESTROYING || state == RDMA_CM_DEVICE_REMOVAL) { spin_unlock_irqrestore(&id_priv->lock, flags); mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); return; } id_priv->state = RDMA_CM_DEVICE_REMOVAL; spin_unlock_irqrestore(&id_priv->lock, flags); if (cma_cm_event_handler(id_priv, &event)) { /* * At this point the ULP promises it won't call * rdma_destroy_id() concurrently */ cma_id_put(id_priv); mutex_unlock(&id_priv->handler_mutex); trace_cm_id_destroy(id_priv); _destroy_id(id_priv, state); return; } mutex_unlock(&id_priv->handler_mutex); /* * If this races with destroy then the thread that first assigns state * to a destroying does the cancel. */ cma_cancel_operation(id_priv, state); cma_id_put(id_priv); } static void cma_process_remove(struct cma_device *cma_dev) { mutex_lock(&lock); while (!list_empty(&cma_dev->id_list)) { struct rdma_id_private *id_priv = list_first_entry( &cma_dev->id_list, struct rdma_id_private, device_item); list_del_init(&id_priv->listen_item); list_del_init(&id_priv->device_item); cma_id_get(id_priv); mutex_unlock(&lock); cma_send_device_removal_put(id_priv); mutex_lock(&lock); } mutex_unlock(&lock); cma_dev_put(cma_dev); wait_for_completion(&cma_dev->comp); } static bool cma_supported(struct ib_device *device) { u32 i; rdma_for_each_port(device, i) { if (rdma_cap_ib_cm(device, i) || rdma_cap_iw_cm(device, i)) return true; } return false; } static int cma_add_one(struct ib_device *device) { struct rdma_id_private *to_destroy; struct cma_device *cma_dev; struct rdma_id_private *id_priv; unsigned long supported_gids = 0; int ret; u32 i; if (!cma_supported(device)) return -EOPNOTSUPP; cma_dev = kmalloc(sizeof(*cma_dev), GFP_KERNEL); if (!cma_dev) return -ENOMEM; cma_dev->device = device; cma_dev->default_gid_type = kcalloc(device->phys_port_cnt, sizeof(*cma_dev->default_gid_type), GFP_KERNEL); if (!cma_dev->default_gid_type) { ret = -ENOMEM; goto free_cma_dev; } cma_dev->default_roce_tos = kcalloc(device->phys_port_cnt, sizeof(*cma_dev->default_roce_tos), GFP_KERNEL); if (!cma_dev->default_roce_tos) { ret = -ENOMEM; goto free_gid_type; } rdma_for_each_port (device, i) { supported_gids = roce_gid_type_mask_support(device, i); WARN_ON(!supported_gids); if (supported_gids & (1 << CMA_PREFERRED_ROCE_GID_TYPE)) cma_dev->default_gid_type[i - rdma_start_port(device)] = CMA_PREFERRED_ROCE_GID_TYPE; else cma_dev->default_gid_type[i - rdma_start_port(device)] = find_first_bit(&supported_gids, BITS_PER_LONG); cma_dev->default_roce_tos[i - rdma_start_port(device)] = 0; } init_completion(&cma_dev->comp); refcount_set(&cma_dev->refcount, 1); INIT_LIST_HEAD(&cma_dev->id_list); ib_set_client_data(device, &cma_client, cma_dev); mutex_lock(&lock); list_add_tail(&cma_dev->list, &dev_list); list_for_each_entry(id_priv, &listen_any_list, listen_any_item) { ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy); if (ret) goto free_listen; } mutex_unlock(&lock); trace_cm_add_one(device); return 0; free_listen: list_del(&cma_dev->list); mutex_unlock(&lock); /* cma_process_remove() will delete to_destroy */ cma_process_remove(cma_dev); kfree(cma_dev->default_roce_tos); free_gid_type: kfree(cma_dev->default_gid_type); free_cma_dev: kfree(cma_dev); return ret; } static void cma_remove_one(struct ib_device *device, void *client_data) { struct cma_device *cma_dev = client_data; trace_cm_remove_one(device); mutex_lock(&lock); list_del(&cma_dev->list); mutex_unlock(&lock); cma_process_remove(cma_dev); kfree(cma_dev->default_roce_tos); kfree(cma_dev->default_gid_type); kfree(cma_dev); } static int cma_init_net(struct net *net) { struct cma_pernet *pernet = cma_pernet(net); xa_init(&pernet->tcp_ps); xa_init(&pernet->udp_ps); xa_init(&pernet->ipoib_ps); xa_init(&pernet->ib_ps); return 0; } static void cma_exit_net(struct net *net) { struct cma_pernet *pernet = cma_pernet(net); WARN_ON(!xa_empty(&pernet->tcp_ps)); WARN_ON(!xa_empty(&pernet->udp_ps)); WARN_ON(!xa_empty(&pernet->ipoib_ps)); WARN_ON(!xa_empty(&pernet->ib_ps)); } static struct pernet_operations cma_pernet_operations = { .init = cma_init_net, .exit = cma_exit_net, .id = &cma_pernet_id, .size = sizeof(struct cma_pernet), }; static int __init cma_init(void) { int ret; /* * There is a rare lock ordering dependency in cma_netdev_callback() * that only happens when bonding is enabled. Teach lockdep that rtnl * must never be nested under lock so it can find these without having * to test with bonding. */ if (IS_ENABLED(CONFIG_LOCKDEP)) { rtnl_lock(); mutex_lock(&lock); mutex_unlock(&lock); rtnl_unlock(); } cma_wq = alloc_ordered_workqueue("rdma_cm", WQ_MEM_RECLAIM); if (!cma_wq) return -ENOMEM; ret = register_pernet_subsys(&cma_pernet_operations); if (ret) goto err_wq; ib_sa_register_client(&sa_client); register_netdevice_notifier(&cma_nb); register_netevent_notifier(&cma_netevent_cb); ret = ib_register_client(&cma_client); if (ret) goto err; ret = cma_configfs_init(); if (ret) goto err_ib; return 0; err_ib: ib_unregister_client(&cma_client); err: unregister_netevent_notifier(&cma_netevent_cb); unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); unregister_pernet_subsys(&cma_pernet_operations); err_wq: destroy_workqueue(cma_wq); return ret; } static void __exit cma_cleanup(void) { cma_configfs_exit(); ib_unregister_client(&cma_client); unregister_netevent_notifier(&cma_netevent_cb); unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); unregister_pernet_subsys(&cma_pernet_operations); destroy_workqueue(cma_wq); } module_init(cma_init); module_exit(cma_cleanup); static void cma_query_ib_service_handler(int status, struct sa_service_rec *recs, unsigned int num_recs, void *context) { struct cma_work *work = context; struct rdma_id_private *id_priv = work->id; struct sockaddr_ib *addr; if (status) goto fail; if (!num_recs) { status = -ENOENT; goto fail; } if (id_priv->id.route.service_recs) { status = -EALREADY; goto fail; } id_priv->id.route.service_recs = kmalloc_array(num_recs, sizeof(*recs), GFP_KERNEL); if (!id_priv->id.route.service_recs) { status = -ENOMEM; goto fail; } id_priv->id.route.num_service_recs = num_recs; memcpy(id_priv->id.route.service_recs, recs, sizeof(*recs) * num_recs); addr = (struct sockaddr_ib *)&id_priv->id.route.addr.dst_addr; addr->sib_family = AF_IB; addr->sib_addr = *(struct ib_addr *)&recs->gid; addr->sib_pkey = recs->pkey; addr->sib_sid = recs->id; rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *)&addr->sib_addr); ib_addr_set_pkey(&id_priv->id.route.addr.dev_addr, ntohs(addr->sib_pkey)); queue_work(cma_wq, &work->work); return; fail: work->old_state = RDMA_CM_ADDRINFO_QUERY; work->new_state = RDMA_CM_ADDR_BOUND; work->event.event = RDMA_CM_EVENT_ADDRINFO_ERROR; work->event.status = status; pr_debug_ratelimited( "RDMA CM: SERVICE_ERROR: failed to query service record. status %d\n", status); queue_work(cma_wq, &work->work); } static int cma_resolve_ib_service(struct rdma_id_private *id_priv, struct rdma_ucm_ib_service *ibs) { struct sa_service_rec sr = {}; ib_sa_comp_mask mask = 0; struct cma_work *work; work = kzalloc(sizeof(*work), GFP_KERNEL); if (!work) return -ENOMEM; cma_id_get(id_priv); work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ADDRINFO_QUERY; work->new_state = RDMA_CM_ADDRINFO_RESOLVED; work->event.event = RDMA_CM_EVENT_ADDRINFO_RESOLVED; if (ibs->flags & RDMA_USER_CM_IB_SERVICE_FLAG_ID) { sr.id = cpu_to_be64(ibs->service_id); mask |= IB_SA_SERVICE_REC_SERVICE_ID; } if (ibs->flags & RDMA_USER_CM_IB_SERVICE_FLAG_NAME) { strscpy(sr.name, ibs->service_name, sizeof(sr.name)); mask |= IB_SA_SERVICE_REC_SERVICE_NAME; } id_priv->query_id = ib_sa_service_rec_get(&sa_client, id_priv->id.device, id_priv->id.port_num, &sr, mask, 2000, GFP_KERNEL, cma_query_ib_service_handler, work, &id_priv->query); if (id_priv->query_id < 0) { cma_id_put(id_priv); kfree(work); return id_priv->query_id; } return 0; } int rdma_resolve_ib_service(struct rdma_cm_id *id, struct rdma_ucm_ib_service *ibs) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cma_dev || !cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDRINFO_QUERY)) return -EINVAL; if (rdma_cap_ib_sa(id->device, id->port_num)) ret = cma_resolve_ib_service(id_priv, ibs); else ret = -EOPNOTSUPP; if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ADDRINFO_QUERY, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_resolve_ib_service); |
| 928 928 7 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_PAGE_EXT_H #define __LINUX_PAGE_EXT_H #include <linux/types.h> #include <linux/mmzone.h> #include <linux/stacktrace.h> struct pglist_data; #ifdef CONFIG_PAGE_EXTENSION /** * struct page_ext_operations - per page_ext client operations * @offset: Offset to the client's data within page_ext. Offset is returned to * the client by page_ext_init. * @size: The size of the client data within page_ext. * @need: Function that returns true if client requires page_ext. * @init: (optional) Called to initialize client once page_exts are allocated. * @need_shared_flags: True when client is using shared page_ext->flags * field. * * Each Page Extension client must define page_ext_operations in * page_ext_ops array. */ struct page_ext_operations { size_t offset; size_t size; bool (*need)(void); void (*init)(void); bool need_shared_flags; }; /* * The page_ext_flags users must set need_shared_flags to true. */ enum page_ext_flags { PAGE_EXT_OWNER, PAGE_EXT_OWNER_ALLOCATED, #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) PAGE_EXT_YOUNG, PAGE_EXT_IDLE, #endif }; /* * Page Extension can be considered as an extended mem_map. * A page_ext page is associated with every page descriptor. The * page_ext helps us add more information about the page. * All page_ext are allocated at boot or memory hotplug event, * then the page_ext for pfn always exists. */ struct page_ext { unsigned long flags; }; extern bool early_page_ext; extern unsigned long page_ext_size; extern void pgdat_page_ext_init(struct pglist_data *pgdat); static inline bool early_page_ext_enabled(void) { return early_page_ext; } #ifdef CONFIG_SPARSEMEM static inline void page_ext_init_flatmem(void) { } extern void page_ext_init(void); static inline void page_ext_init_flatmem_late(void) { } static inline bool page_ext_iter_next_fast_possible(unsigned long next_pfn) { /* * page_ext is allocated per memory section. Once we cross a * memory section, we have to fetch the new pointer. */ return next_pfn % PAGES_PER_SECTION; } #else extern void page_ext_init_flatmem(void); extern void page_ext_init_flatmem_late(void); static inline void page_ext_init(void) { } static inline bool page_ext_iter_next_fast_possible(unsigned long next_pfn) { return true; } #endif extern struct page_ext *page_ext_get(const struct page *page); extern void page_ext_put(struct page_ext *page_ext); extern struct page_ext *page_ext_lookup(unsigned long pfn); static inline void *page_ext_data(struct page_ext *page_ext, struct page_ext_operations *ops) { return (void *)(page_ext) + ops->offset; } static inline struct page_ext *page_ext_next(struct page_ext *curr) { void *next = curr; next += page_ext_size; return next; } struct page_ext_iter { unsigned long index; unsigned long start_pfn; struct page_ext *page_ext; }; /** * page_ext_iter_begin() - Prepare for iterating through page extensions. * @iter: page extension iterator. * @pfn: PFN of the page we're interested in. * * Must be called with RCU read lock taken. * * Return: NULL if no page_ext exists for this page. */ static inline struct page_ext *page_ext_iter_begin(struct page_ext_iter *iter, unsigned long pfn) { iter->index = 0; iter->start_pfn = pfn; iter->page_ext = page_ext_lookup(pfn); return iter->page_ext; } /** * page_ext_iter_next() - Get next page extension * @iter: page extension iterator. * * Must be called with RCU read lock taken. * * Return: NULL if no next page_ext exists. */ static inline struct page_ext *page_ext_iter_next(struct page_ext_iter *iter) { unsigned long pfn; if (WARN_ON_ONCE(!iter->page_ext)) return NULL; iter->index++; pfn = iter->start_pfn + iter->index; if (page_ext_iter_next_fast_possible(pfn)) iter->page_ext = page_ext_next(iter->page_ext); else iter->page_ext = page_ext_lookup(pfn); return iter->page_ext; } /** * page_ext_iter_get() - Get current page extension * @iter: page extension iterator. * * Return: NULL if no page_ext exists for this iterator. */ static inline struct page_ext *page_ext_iter_get(const struct page_ext_iter *iter) { return iter->page_ext; } /** * for_each_page_ext(): iterate through page_ext objects. * @__page: the page we're interested in * @__pgcount: how many pages to iterate through * @__page_ext: struct page_ext pointer where the current page_ext * object is returned * @__iter: struct page_ext_iter object (defined in the stack) * * IMPORTANT: must be called with RCU read lock taken. */ #define for_each_page_ext(__page, __pgcount, __page_ext, __iter) \ for (__page_ext = page_ext_iter_begin(&__iter, page_to_pfn(__page));\ __page_ext && __iter.index < __pgcount; \ __page_ext = page_ext_iter_next(&__iter)) #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; static inline bool early_page_ext_enabled(void) { return false; } static inline void pgdat_page_ext_init(struct pglist_data *pgdat) { } static inline void page_ext_init(void) { } static inline void page_ext_init_flatmem_late(void) { } static inline void page_ext_init_flatmem(void) { } static inline struct page_ext *page_ext_get(const struct page *page) { return NULL; } static inline void page_ext_put(struct page_ext *page_ext) { } #endif /* CONFIG_PAGE_EXTENSION */ #endif /* __LINUX_PAGE_EXT_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2023 Arm Ltd. * * Based on arch/x86/include/asm/pkeys.h */ #ifndef _ASM_ARM64_PKEYS_H #define _ASM_ARM64_PKEYS_H #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2) #define arch_max_pkey() 8 int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val); static inline bool arch_pkeys_enabled(void) { return system_supports_poe(); } static inline int vma_pkey(struct vm_area_struct *vma) { return (vma->vm_flags & ARCH_VM_PKEY_FLAGS) >> VM_PKEY_SHIFT; } static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey) { if (pkey != -1) return pkey; return vma_pkey(vma); } static inline int execute_only_pkey(struct mm_struct *mm) { // Execute-only mappings are handled by EPAN/FEAT_PAN3. return -1; } #define mm_pkey_allocation_map(mm) (mm)->context.pkey_allocation_map #define mm_set_pkey_allocated(mm, pkey) do { \ mm_pkey_allocation_map(mm) |= (1U << pkey); \ } while (0) #define mm_set_pkey_free(mm, pkey) do { \ mm_pkey_allocation_map(mm) &= ~(1U << pkey); \ } while (0) static inline bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) { /* * "Allocated" pkeys are those that have been returned * from pkey_alloc() or pkey 0 which is allocated * implicitly when the mm is created. */ if (pkey < 0 || pkey >= arch_max_pkey()) return false; return mm_pkey_allocation_map(mm) & (1U << pkey); } /* * Returns a positive, 3-bit key on success, or -1 on failure. */ static inline int mm_pkey_alloc(struct mm_struct *mm) { /* * Note: this is the one and only place we make sure * that the pkey is valid as far as the hardware is * concerned. The rest of the kernel trusts that * only good, valid pkeys come out of here. */ u8 all_pkeys_mask = GENMASK(arch_max_pkey() - 1, 0); int ret; if (!arch_pkeys_enabled()) return -1; /* * Are we out of pkeys? We must handle this specially * because ffz() behavior is undefined if there are no * zeros. */ if (mm_pkey_allocation_map(mm) == all_pkeys_mask) return -1; ret = ffz(mm_pkey_allocation_map(mm)); mm_set_pkey_allocated(mm, ret); return ret; } static inline int mm_pkey_free(struct mm_struct *mm, int pkey) { if (!mm_pkey_is_allocated(mm, pkey)) return -EINVAL; mm_set_pkey_free(mm, pkey); return 0; } #endif /* _ASM_ARM64_PKEYS_H */ |
| 108 248 248 218 127 248 127 218 217 1 218 248 18 18 18 17 26 26 22 25 26 24 22 22 22 25 26 250 252 252 252 252 252 252 250 252 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 | // SPDX-License-Identifier: GPL-2.0-only /* * jump label support * * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> * Copyright (C) 2011 Peter Zijlstra * */ #include <linux/memory.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/sort.h> #include <linux/err.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/bug.h> #include <linux/cpu.h> #include <asm/sections.h> /* mutex to protect coming/going of the jump_label table */ static DEFINE_MUTEX(jump_label_mutex); void jump_label_lock(void) { mutex_lock(&jump_label_mutex); } void jump_label_unlock(void) { mutex_unlock(&jump_label_mutex); } static int jump_label_cmp(const void *a, const void *b) { const struct jump_entry *jea = a; const struct jump_entry *jeb = b; /* * Entrires are sorted by key. */ if (jump_entry_key(jea) < jump_entry_key(jeb)) return -1; if (jump_entry_key(jea) > jump_entry_key(jeb)) return 1; /* * In the batching mode, entries should also be sorted by the code * inside the already sorted list of entries, enabling a bsearch in * the vector. */ if (jump_entry_code(jea) < jump_entry_code(jeb)) return -1; if (jump_entry_code(jea) > jump_entry_code(jeb)) return 1; return 0; } static void jump_label_swap(void *a, void *b, int size) { long delta = (unsigned long)a - (unsigned long)b; struct jump_entry *jea = a; struct jump_entry *jeb = b; struct jump_entry tmp = *jea; jea->code = jeb->code - delta; jea->target = jeb->target - delta; jea->key = jeb->key - delta; jeb->code = tmp.code + delta; jeb->target = tmp.target + delta; jeb->key = tmp.key + delta; } static void jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) { unsigned long size; void *swapfn = NULL; if (IS_ENABLED(CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE)) swapfn = jump_label_swap; size = (((unsigned long)stop - (unsigned long)start) / sizeof(struct jump_entry)); sort(start, size, sizeof(struct jump_entry), jump_label_cmp, swapfn); } static void jump_label_update(struct static_key *key); /* * There are similar definitions for the !CONFIG_JUMP_LABEL case in jump_label.h. * The use of 'atomic_read()' requires atomic.h and its problematic for some * kernel headers such as kernel.h and others. Since static_key_count() is not * used in the branch statements as it is for the !CONFIG_JUMP_LABEL case its ok * to have it be a function here. Similarly, for 'static_key_enable()' and * 'static_key_disable()', which require bug.h. This should allow jump_label.h * to be included from most/all places for CONFIG_JUMP_LABEL. */ int static_key_count(struct static_key *key) { /* * -1 means the first static_key_slow_inc() is in progress. * static_key_enabled() must return true, so return 1 here. */ int n = atomic_read(&key->enabled); return n >= 0 ? n : 1; } EXPORT_SYMBOL_GPL(static_key_count); /* * static_key_fast_inc_not_disabled - adds a user for a static key * @key: static key that must be already enabled * * The caller must make sure that the static key can't get disabled while * in this function. It doesn't patch jump labels, only adds a user to * an already enabled static key. * * Returns true if the increment was done. Unlike refcount_t the ref counter * is not saturated, but will fail to increment on overflow. */ bool static_key_fast_inc_not_disabled(struct static_key *key) { int v; STATIC_KEY_CHECK_USE(key); /* * Negative key->enabled has a special meaning: it sends * static_key_slow_inc/dec() down the slow path, and it is non-zero * so it counts as "enabled" in jump_label_update(). * * The INT_MAX overflow condition is either used by the networking * code to reset or detected in the slow path of * static_key_slow_inc_cpuslocked(). */ v = atomic_read(&key->enabled); do { if (v <= 0 || v == INT_MAX) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); return true; } EXPORT_SYMBOL_GPL(static_key_fast_inc_not_disabled); bool static_key_slow_inc_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); /* * Careful if we get concurrent static_key_slow_inc/dec() calls; * later calls must wait for the first one to _finish_ the * jump_label_update() process. At the same time, however, * the jump_label_update() call below wants to see * static_key_enabled(&key) for jumps to be updated properly. */ if (static_key_fast_inc_not_disabled(key)) return true; guard(mutex)(&jump_label_mutex); /* Try to mark it as 'enabling in progress. */ if (!atomic_cmpxchg(&key->enabled, 0, -1)) { jump_label_update(key); /* * Ensure that when static_key_fast_inc_not_disabled() or * static_key_dec_not_one() observe the positive value, * they must also observe all the text changes. */ atomic_set_release(&key->enabled, 1); } else { /* * While holding the mutex this should never observe * anything else than a value >= 1 and succeed */ if (WARN_ON_ONCE(!static_key_fast_inc_not_disabled(key))) return false; } return true; } bool static_key_slow_inc(struct static_key *key) { bool ret; cpus_read_lock(); ret = static_key_slow_inc_cpuslocked(key); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(static_key_slow_inc); void static_key_enable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) > 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); return; } jump_label_lock(); if (atomic_read(&key->enabled) == 0) { atomic_set(&key->enabled, -1); jump_label_update(key); /* * See static_key_slow_inc(). */ atomic_set_release(&key->enabled, 1); } jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable_cpuslocked); void static_key_enable(struct static_key *key) { cpus_read_lock(); static_key_enable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable); void static_key_disable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); return; } jump_label_lock(); if (atomic_cmpxchg(&key->enabled, 1, 0) == 1) jump_label_update(key); jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable_cpuslocked); void static_key_disable(struct static_key *key) { cpus_read_lock(); static_key_disable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable); static bool static_key_dec_not_one(struct static_key *key) { int v; /* * Go into the slow path if key::enabled is less than or equal than * one. One is valid to shut down the key, anything less than one * is an imbalance, which is handled at the call site. * * That includes the special case of '-1' which is set in * static_key_slow_inc_cpuslocked(), but that's harmless as it is * fully serialized in the slow path below. By the time this task * acquires the jump label lock the value is back to one and the * retry under the lock must succeed. */ v = atomic_read(&key->enabled); do { /* * Warn about the '-1' case though; since that means a * decrement is concurrent with a first (0->1) increment. IOW * people are trying to disable something that wasn't yet fully * enabled. This suggests an ordering problem on the user side. */ WARN_ON_ONCE(v < 0); /* * Warn about underflow, and lie about success in an attempt to * not make things worse. */ if (WARN_ON_ONCE(v == 0)) return true; if (v <= 1) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v - 1))); return true; } static void __static_key_slow_dec_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); int val; if (static_key_dec_not_one(key)) return; guard(mutex)(&jump_label_mutex); val = atomic_read(&key->enabled); /* * It should be impossible to observe -1 with jump_label_mutex held, * see static_key_slow_inc_cpuslocked(). */ if (WARN_ON_ONCE(val == -1)) return; /* * Cannot already be 0, something went sideways. */ if (WARN_ON_ONCE(val == 0)) return; if (atomic_dec_and_test(&key->enabled)) jump_label_update(key); } static void __static_key_slow_dec(struct static_key *key) { cpus_read_lock(); __static_key_slow_dec_cpuslocked(key); cpus_read_unlock(); } void jump_label_update_timeout(struct work_struct *work) { struct static_key_deferred *key = container_of(work, struct static_key_deferred, work.work); __static_key_slow_dec(&key->key); } EXPORT_SYMBOL_GPL(jump_label_update_timeout); void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec(key); } EXPORT_SYMBOL_GPL(static_key_slow_dec); void static_key_slow_dec_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec_cpuslocked(key); } void __static_key_slow_dec_deferred(struct static_key *key, struct delayed_work *work, unsigned long timeout) { STATIC_KEY_CHECK_USE(key); if (static_key_dec_not_one(key)) return; schedule_delayed_work(work, timeout); } EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred); void __static_key_deferred_flush(void *key, struct delayed_work *work) { STATIC_KEY_CHECK_USE(key); flush_delayed_work(work); } EXPORT_SYMBOL_GPL(__static_key_deferred_flush); void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { STATIC_KEY_CHECK_USE(key); key->timeout = rl; INIT_DELAYED_WORK(&key->work, jump_label_update_timeout); } EXPORT_SYMBOL_GPL(jump_label_rate_limit); static int addr_conflict(struct jump_entry *entry, void *start, void *end) { if (jump_entry_code(entry) <= (unsigned long)end && jump_entry_code(entry) + jump_entry_size(entry) > (unsigned long)start) return 1; return 0; } static int __jump_label_text_reserved(struct jump_entry *iter_start, struct jump_entry *iter_stop, void *start, void *end, bool init) { struct jump_entry *iter; iter = iter_start; while (iter < iter_stop) { if (init || !jump_entry_is_init(iter)) { if (addr_conflict(iter, start, end)) return 1; } iter++; } return 0; } #ifndef arch_jump_label_transform_static static void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type) { /* nothing to do on most architectures */ } #endif static inline struct jump_entry *static_key_entries(struct static_key *key) { WARN_ON_ONCE(key->type & JUMP_TYPE_LINKED); return (struct jump_entry *)(key->type & ~JUMP_TYPE_MASK); } static inline bool static_key_type(struct static_key *key) { return key->type & JUMP_TYPE_TRUE; } static inline bool static_key_linked(struct static_key *key) { return key->type & JUMP_TYPE_LINKED; } static inline void static_key_clear_linked(struct static_key *key) { key->type &= ~JUMP_TYPE_LINKED; } static inline void static_key_set_linked(struct static_key *key) { key->type |= JUMP_TYPE_LINKED; } /*** * A 'struct static_key' uses a union such that it either points directly * to a table of 'struct jump_entry' or to a linked list of modules which in * turn point to 'struct jump_entry' tables. * * The two lower bits of the pointer are used to keep track of which pointer * type is in use and to store the initial branch direction, we use an access * function which preserves these bits. */ static void static_key_set_entries(struct static_key *key, struct jump_entry *entries) { unsigned long type; WARN_ON_ONCE((unsigned long)entries & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->entries = entries; key->type |= type; } static enum jump_label_type jump_label_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool enabled = static_key_enabled(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return enabled ^ branch; } static bool jump_label_can_update(struct jump_entry *entry, bool init) { /* * Cannot update code that was in an init text area. */ if (!init && jump_entry_is_init(entry)) return false; if (!kernel_text_address(jump_entry_code(entry))) { /* * This skips patching built-in __exit, which * is part of init_section_contains() but is * not part of kernel_text_address(). * * Skipping built-in __exit is fine since it * will never be executed. */ WARN_ONCE(!jump_entry_is_init(entry), "can't patch jump_label at %pS", (void *)jump_entry_code(entry)); return false; } return true; } #ifndef HAVE_JUMP_LABEL_BATCH static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (jump_label_can_update(entry, init)) arch_jump_label_transform(entry, jump_label_type(entry)); } } #else static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (!jump_label_can_update(entry, init)) continue; if (!arch_jump_label_transform_queue(entry, jump_label_type(entry))) { /* * Queue is full: Apply the current queue and try again. */ arch_jump_label_transform_apply(); BUG_ON(!arch_jump_label_transform_queue(entry, jump_label_type(entry))); } } arch_jump_label_transform_apply(); } #endif void __init jump_label_init(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct static_key *key = NULL; struct jump_entry *iter; /* * Since we are initializing the static_key.enabled field with * with the 'raw' int values (to avoid pulling in atomic.h) in * jump_label.h, let's make sure that is safe. There are only two * cases to check since we initialize to 0 or 1. */ BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0); BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1); if (static_key_initialized) return; cpus_read_lock(); jump_label_lock(); jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; /* rewrite NOPs */ if (jump_label_type(iter) == JUMP_LABEL_NOP) arch_jump_label_transform_static(iter, JUMP_LABEL_NOP); in_init = init_section_contains((void *)jump_entry_code(iter), 1); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; static_key_set_entries(key, iter); } static_key_initialized = true; jump_label_unlock(); cpus_read_unlock(); } static inline bool static_key_sealed(struct static_key *key) { return (key->type & JUMP_TYPE_LINKED) && !(key->type & ~JUMP_TYPE_MASK); } static inline void static_key_seal(struct static_key *key) { unsigned long type = key->type & JUMP_TYPE_TRUE; key->type = JUMP_TYPE_LINKED | type; } void jump_label_init_ro(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct jump_entry *iter; if (WARN_ON_ONCE(!static_key_initialized)) return; cpus_read_lock(); jump_label_lock(); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk = jump_entry_key(iter); if (!is_kernel_ro_after_init((unsigned long)iterk)) continue; if (static_key_sealed(iterk)) continue; static_key_seal(iterk); } jump_label_unlock(); cpus_read_unlock(); } #ifdef CONFIG_MODULES enum jump_label_type jump_label_init_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool type = static_key_type(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return type ^ branch; } struct static_key_mod { struct static_key_mod *next; struct jump_entry *entries; struct module *mod; }; static inline struct static_key_mod *static_key_mod(struct static_key *key) { WARN_ON_ONCE(!static_key_linked(key)); return (struct static_key_mod *)(key->type & ~JUMP_TYPE_MASK); } /*** * key->type and key->next are the same via union. * This sets key->next and preserves the type bits. * * See additional comments above static_key_set_entries(). */ static void static_key_set_mod(struct static_key *key, struct static_key_mod *mod) { unsigned long type; WARN_ON_ONCE((unsigned long)mod & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->next = mod; key->type |= type; } static int __jump_label_mod_text_reserved(void *start, void *end) { struct module *mod; int ret; scoped_guard(rcu) { mod = __module_text_address((unsigned long)start); WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); if (!try_module_get(mod)) mod = NULL; } if (!mod) return 0; ret = __jump_label_text_reserved(mod->jump_entries, mod->jump_entries + mod->num_jump_entries, start, end, mod->state == MODULE_STATE_COMING); module_put(mod); return ret; } static void __jump_label_mod_update(struct static_key *key) { struct static_key_mod *mod; for (mod = static_key_mod(key); mod; mod = mod->next) { struct jump_entry *stop; struct module *m; /* * NULL if the static_key is defined in a module * that does not use it */ if (!mod->entries) continue; m = mod->mod; if (!m) stop = __stop___jump_table; else stop = m->jump_entries + m->num_jump_entries; __jump_label_update(key, mod->entries, stop, m && m->state == MODULE_STATE_COMING); } } static int jump_label_add_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, *jlm2; /* if the module doesn't have jump label entries, just return */ if (iter_start == iter_stop) return 0; jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; in_init = within_module_init(jump_entry_code(iter), mod); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; if (within_module((unsigned long)key, mod)) { static_key_set_entries(key, iter); continue; } /* * If the key was sealed at init, then there's no need to keep a * reference to its module entries - just patch them now and be * done with it. */ if (static_key_sealed(key)) goto do_poke; jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm) return -ENOMEM; if (!static_key_linked(key)) { jlm2 = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm2) { kfree(jlm); return -ENOMEM; } scoped_guard(rcu) jlm2->mod = __module_address((unsigned long)key); jlm2->entries = static_key_entries(key); jlm2->next = NULL; static_key_set_mod(key, jlm2); static_key_set_linked(key); } jlm->mod = mod; jlm->entries = iter; jlm->next = static_key_mod(key); static_key_set_mod(key, jlm); static_key_set_linked(key); /* Only update if we've changed from our initial state */ do_poke: if (jump_label_type(iter) != jump_label_init_type(iter)) __jump_label_update(key, iter, iter_stop, true); } return 0; } static void jump_label_del_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, **prev; for (iter = iter_start; iter < iter_stop; iter++) { if (jump_entry_key(iter) == key) continue; key = jump_entry_key(iter); if (within_module((unsigned long)key, mod)) continue; /* No @jlm allocated because key was sealed at init. */ if (static_key_sealed(key)) continue; /* No memory during module load */ if (WARN_ON(!static_key_linked(key))) continue; prev = &key->next; jlm = static_key_mod(key); while (jlm && jlm->mod != mod) { prev = &jlm->next; jlm = jlm->next; } /* No memory during module load */ if (WARN_ON(!jlm)) continue; if (prev == &key->next) static_key_set_mod(key, jlm->next); else *prev = jlm->next; kfree(jlm); jlm = static_key_mod(key); /* if only one etry is left, fold it back into the static_key */ if (jlm->next == NULL) { static_key_set_entries(key, jlm->entries); static_key_clear_linked(key); kfree(jlm); } } } static int jump_label_module_notify(struct notifier_block *self, unsigned long val, void *data) { struct module *mod = data; int ret = 0; cpus_read_lock(); jump_label_lock(); switch (val) { case MODULE_STATE_COMING: ret = jump_label_add_module(mod); if (ret) { WARN(1, "Failed to allocate memory: jump_label may not work properly.\n"); jump_label_del_module(mod); } break; case MODULE_STATE_GOING: jump_label_del_module(mod); break; } jump_label_unlock(); cpus_read_unlock(); return notifier_from_errno(ret); } static struct notifier_block jump_label_module_nb = { .notifier_call = jump_label_module_notify, .priority = 1, /* higher than tracepoints */ }; static __init int jump_label_init_module(void) { return register_module_notifier(&jump_label_module_nb); } early_initcall(jump_label_init_module); #endif /* CONFIG_MODULES */ /*** * jump_label_text_reserved - check if addr range is reserved * @start: start text addr * @end: end text addr * * checks if the text addr located between @start and @end * overlaps with any of the jump label patch addresses. Code * that wants to modify kernel text should first verify that * it does not overlap with any of the jump label addresses. * Caller must hold jump_label_mutex. * * returns 1 if there is an overlap, 0 otherwise */ int jump_label_text_reserved(void *start, void *end) { bool init = system_state < SYSTEM_RUNNING; int ret = __jump_label_text_reserved(__start___jump_table, __stop___jump_table, start, end, init); if (ret) return ret; #ifdef CONFIG_MODULES ret = __jump_label_mod_text_reserved(start, end); #endif return ret; } static void jump_label_update(struct static_key *key) { struct jump_entry *stop = __stop___jump_table; bool init = system_state < SYSTEM_RUNNING; struct jump_entry *entry; #ifdef CONFIG_MODULES struct module *mod; if (static_key_linked(key)) { __jump_label_mod_update(key); return; } scoped_guard(rcu) { mod = __module_address((unsigned long)key); if (mod) { stop = mod->jump_entries + mod->num_jump_entries; init = mod->state == MODULE_STATE_COMING; } } #endif entry = static_key_entries(key); /* if there are no users, entry can be NULL */ if (entry) __jump_label_update(key, entry, stop, init); } #ifdef CONFIG_STATIC_KEYS_SELFTEST static DEFINE_STATIC_KEY_TRUE(sk_true); static DEFINE_STATIC_KEY_FALSE(sk_false); static __init int jump_label_test(void) { int i; for (i = 0; i < 2; i++) { WARN_ON(static_key_enabled(&sk_true.key) != true); WARN_ON(static_key_enabled(&sk_false.key) != false); WARN_ON(!static_branch_likely(&sk_true)); WARN_ON(!static_branch_unlikely(&sk_true)); WARN_ON(static_branch_likely(&sk_false)); WARN_ON(static_branch_unlikely(&sk_false)); static_branch_disable(&sk_true); static_branch_enable(&sk_false); WARN_ON(static_key_enabled(&sk_true.key) == true); WARN_ON(static_key_enabled(&sk_false.key) == false); WARN_ON(static_branch_likely(&sk_true)); WARN_ON(static_branch_unlikely(&sk_true)); WARN_ON(!static_branch_likely(&sk_false)); WARN_ON(!static_branch_unlikely(&sk_false)); static_branch_enable(&sk_true); static_branch_disable(&sk_false); } return 0; } early_initcall(jump_label_test); #endif /* STATIC_KEYS_SELFTEST */ |
| 9 9 106 106 348 348 347 3 3 106 274 107 106 108 43 90 108 271 272 272 272 272 110 252 106 274 26 274 347 347 1 348 348 108 253 349 114 267 106 274 348 348 348 348 347 109 252 538 539 538 538 37 538 468 348 7 7 26 26 26 25 26 26 26 26 26 26 26 26 26 26 26 26 528 6 520 6 529 529 5 5 6 499 376 137 248 373 430 427 376 523 523 524 523 523 524 524 520 523 1 436 437 251 1 197 293 294 10 293 295 295 295 251 1 13 295 294 294 294 294 294 294 294 294 294 295 295 295 295 294 3 294 295 1 295 295 295 295 295 295 295 295 3 294 294 294 294 294 294 294 294 5 5 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/dcache.c * * Complete reimplementation * (C) 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ /* * Notes on the allocation strategy: * * The dcache is a master of the icache - whenever a dcache entry * exists, the inode will always exist. "iput()" is done either when * the dcache entry is deleted or garbage collected. */ #include <linux/ratelimit.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/hash.h> #include <linux/cache.h> #include <linux/export.h> #include <linux/security.h> #include <linux/seqlock.h> #include <linux/memblock.h> #include <linux/bit_spinlock.h> #include <linux/rculist_bl.h> #include <linux/list_lru.h> #include "internal.h" #include "mount.h" #include <asm/runtime-const.h> /* * Usage: * dcache->d_inode->i_lock protects: * - i_dentry, d_u.d_alias, d_inode of aliases * dcache_hash_bucket lock protects: * - the dcache hash table * s_roots bl list spinlock protects: * - the s_roots list (see __d_drop) * dentry->d_sb->s_dentry_lru_lock protects: * - the dcache lru lists and counters * d_lock protects: * - d_flags * - d_name * - d_lru * - d_count * - d_unhashed() * - d_parent and d_chilren * - childrens' d_sib and d_parent * - d_u.d_alias, d_inode * * Ordering: * dentry->d_inode->i_lock * dentry->d_lock * dentry->d_sb->s_dentry_lru_lock * dcache_hash_bucket lock * s_roots lock * * If there is an ancestor relationship: * dentry->d_parent->...->d_parent->d_lock * ... * dentry->d_parent->d_lock * dentry->d_lock * * If no ancestor relationship: * arbitrary, since it's serialized on rename_lock */ static int sysctl_vfs_cache_pressure __read_mostly = 100; static int sysctl_vfs_cache_pressure_denom __read_mostly = 100; unsigned long vfs_pressure_ratio(unsigned long val) { return mult_frac(val, sysctl_vfs_cache_pressure, sysctl_vfs_cache_pressure_denom); } EXPORT_SYMBOL_GPL(vfs_pressure_ratio); __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock); EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __ro_after_init; const struct qstr empty_name = QSTR_INIT("", 0); EXPORT_SYMBOL(empty_name); const struct qstr slash_name = QSTR_INIT("/", 1); EXPORT_SYMBOL(slash_name); const struct qstr dotdot_name = QSTR_INIT("..", 2); EXPORT_SYMBOL(dotdot_name); /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try * to make this good - I've just made it work. * * This hash-function tries to avoid losing too many bits of hash * information, yet avoid using a prime hash-size or similar. * * Marking the variables "used" ensures that the compiler doesn't * optimize them away completely on architectures with runtime * constant infrastructure, this allows debuggers to see their * values. But updating these values has no effect on those arches. */ static unsigned int d_hash_shift __ro_after_init __used; static struct hlist_bl_head *dentry_hashtable __ro_after_init __used; static inline struct hlist_bl_head *d_hash(unsigned long hashlen) { return runtime_const_ptr(dentry_hashtable) + runtime_const_shift_right_32(hashlen, d_hash_shift); } #define IN_LOOKUP_SHIFT 10 static struct hlist_bl_head in_lookup_hashtable[1 << IN_LOOKUP_SHIFT]; static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, unsigned int hash) { hash += (unsigned long) parent / L1_CACHE_BYTES; return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); } struct dentry_stat_t { long nr_dentry; long nr_unused; long age_limit; /* age in seconds */ long want_pages; /* pages requested by system */ long nr_negative; /* # of unused negative dentries */ long dummy; /* Reserved for future use */ }; static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); static int dentry_negative_policy; #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) /* Statistics gathering. */ static struct dentry_stat_t dentry_stat = { .age_limit = 45, }; /* * Here we resort to our own counters instead of using generic per-cpu counters * for consistency with what the vfs inode code does. We are expected to harvest * better code and performance by having our own specialized counters. * * Please note that the loop is done over all possible CPUs, not over all online * CPUs. The reason for this is that we don't want to play games with CPUs going * on and off. If one of them goes off, we will just keep their counters. * * glommer: See cffbc8a for details, and if you ever intend to change this, * please update all vfs counters to match. */ static long get_nr_dentry(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_unused, i); return sum < 0 ? 0 : sum; } static long get_nr_dentry_negative(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_dentry_negative, i); return sum < 0 ? 0 : sum; } static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static const struct ctl_table fs_dcache_sysctls[] = { { .procname = "dentry-state", .data = &dentry_stat, .maxlen = 6*sizeof(long), .mode = 0444, .proc_handler = proc_nr_dentry, }, { .procname = "dentry-negative", .data = &dentry_negative_policy, .maxlen = sizeof(dentry_negative_policy), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; static const struct ctl_table vm_dcache_sysctls[] = { { .procname = "vfs_cache_pressure", .data = &sysctl_vfs_cache_pressure, .maxlen = sizeof(sysctl_vfs_cache_pressure), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, { .procname = "vfs_cache_pressure_denom", .data = &sysctl_vfs_cache_pressure_denom, .maxlen = sizeof(sysctl_vfs_cache_pressure_denom), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE_HUNDRED, }, }; static int __init init_fs_dcache_sysctls(void) { register_sysctl_init("vm", vm_dcache_sysctls); register_sysctl_init("fs", fs_dcache_sysctls); return 0; } fs_initcall(init_fs_dcache_sysctls); #endif /* * Compare 2 name strings, return 0 if they match, otherwise non-zero. * The strings are both count bytes long, and count is non-zero. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> /* * NOTE! 'cs' and 'scount' come from a dentry, so it has a * aligned allocation for this particular component. We don't * strictly need the load_unaligned_zeropad() safety, but it * doesn't hurt either. * * In contrast, 'ct' and 'tcount' can be from a pathname, and do * need the careful unaligned handling. */ static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { unsigned long a,b,mask; for (;;) { a = read_word_at_a_time(cs); b = load_unaligned_zeropad(ct); if (tcount < sizeof(unsigned long)) break; if (unlikely(a != b)) return 1; cs += sizeof(unsigned long); ct += sizeof(unsigned long); tcount -= sizeof(unsigned long); if (!tcount) return 0; } mask = bytemask_from_count(tcount); return unlikely(!!((a ^ b) & mask)); } #else static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) { do { if (*cs != *ct) return 1; cs++; ct++; tcount--; } while (tcount); return 0; } #endif static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) { /* * Be careful about RCU walk racing with rename: * use 'READ_ONCE' to fetch the name pointer. * * NOTE! Even if a rename will mean that the length * was not loaded atomically, we don't care. The * RCU walk will check the sequence count eventually, * and catch it. And we won't overrun the buffer, * because we're reading the name pointer atomically, * and a dentry name is guaranteed to be properly * terminated with a NUL byte. * * End result: even if 'len' is wrong, we'll exit * early because the data cannot match (there can * be no NUL in the ct/tcount data) */ const unsigned char *cs = READ_ONCE(dentry->d_name.name); return dentry_string_cmp(cs, ct, tcount); } /* * long names are allocated separately from dentry and never modified. * Refcounted, freeing is RCU-delayed. See take_dentry_name_snapshot() * for the reason why ->count and ->head can't be combined into a union. * dentry_string_cmp() relies upon ->name[] being word-aligned. */ struct external_name { atomic_t count; struct rcu_head head; unsigned char name[] __aligned(sizeof(unsigned long)); }; static inline struct external_name *external_name(struct dentry *dentry) { return container_of(dentry->d_name.name, struct external_name, name[0]); } static void __d_free(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kmem_cache_free(dentry_cache, dentry); } static void __d_free_external(struct rcu_head *head) { struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu); kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); } static inline int dname_external(const struct dentry *dentry) { return dentry->d_name.name != dentry->d_shortname.string; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { unsigned seq; const unsigned char *s; rcu_read_lock(); retry: seq = read_seqcount_begin(&dentry->d_seq); s = READ_ONCE(dentry->d_name.name); name->name.hash_len = dentry->d_name.hash_len; name->name.name = name->inline_name.string; if (likely(s == dentry->d_shortname.string)) { name->inline_name = dentry->d_shortname; } else { struct external_name *p; p = container_of(s, struct external_name, name[0]); // get a valid reference if (unlikely(!atomic_inc_not_zero(&p->count))) goto retry; name->name.name = s; } if (read_seqcount_retry(&dentry->d_seq, seq)) { release_dentry_name_snapshot(name); goto retry; } rcu_read_unlock(); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { if (unlikely(name->name.name != name->inline_name.string)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); if (unlikely(atomic_dec_and_test(&p->count))) kfree_rcu(p, head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) { unsigned flags; dentry->d_inode = inode; flags = READ_ONCE(dentry->d_flags); flags &= ~DCACHE_ENTRY_TYPE; flags |= type_flags; smp_store_release(&dentry->d_flags, flags); } static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~DCACHE_ENTRY_TYPE; WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; /* * The negative counter only tracks dentries on the LRU. Don't inc if * d_lru is on another list. */ if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) { WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); if (likely(atomic_dec_and_test(&p->count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external); return; } } /* if dentry was never visible to RCU, immediate free is OK */ if (dentry->d_flags & DCACHE_NORCU) __d_free(&dentry->d_u.d_rcu); else call_rcu(&dentry->d_u.d_rcu, __d_free); } /* * Release the dentry's inode, using the filesystem * d_iput() operation if defined. */ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_lock) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) fsnotify_inoderemove(inode); if (dentry->d_op && dentry->d_op->d_iput) dentry->d_op->d_iput(dentry, inode); else iput(inode); } /* * The DCACHE_LRU_LIST bit is set whenever the 'd_lru' entry * is in use - which includes both the "real" per-superblock * LRU list _and_ the DCACHE_SHRINK_LIST use. * * The DCACHE_SHRINK_LIST bit is set whenever the dentry is * on the shrink list (ie not on the superblock LRU list). * * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * * The per-cpu "nr_dentry_negative" counters are only updated * when deleted from or added to the per-superblock LRU list, not * from/to the shrink list. That is to avoid an unneeded dec/inc * pair when moving from LRU to shrink list in select_collect(). * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ #define D_FLAG_VERIFY(dentry,x) WARN_ON_ONCE(((dentry)->d_flags & (DCACHE_LRU_LIST | DCACHE_SHRINK_LIST)) != (x)) static void d_lru_add(struct dentry *dentry) { D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add_obj( &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_lru_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del_obj( &dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } static void d_shrink_del(struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); list_del_init(&dentry->d_lru); dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST); this_cpu_dec(nr_dentry_unused); } static void d_shrink_add(struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, 0); list_add(&dentry->d_lru, list); dentry->d_flags |= DCACHE_SHRINK_LIST | DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); } /* * These can only be called under the global LRU lock, ie during the * callback for freeing the LRU list. "isolate" removes it from the * LRU lists entirely, while shrink_move moves it to the indicated * private list. */ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, struct list_head *list) { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; if (d_is_negative(dentry)) this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } static void ___d_drop(struct dentry *dentry) { struct hlist_bl_head *b; /* * Hashed dentries are normally on the dentry hashtable, * with the exception of those newly allocated by * d_obtain_root, which are always IS_ROOT: */ if (unlikely(IS_ROOT(dentry))) b = &dentry->d_sb->s_roots; else b = d_hash(dentry->d_name.hash); hlist_bl_lock(b); __hlist_bl_del(&dentry->d_hash); hlist_bl_unlock(b); } void __d_drop(struct dentry *dentry) { if (!d_unhashed(dentry)) { ___d_drop(dentry); dentry->d_hash.pprev = NULL; write_seqcount_invalidate(&dentry->d_seq); } } EXPORT_SYMBOL(__d_drop); /** * d_drop - drop a dentry * @dentry: dentry to drop * * d_drop() unhashes the entry from the parent dentry hashes, so that it won't * be found through a VFS lookup any more. Note that this is different from * deleting the dentry - d_delete will try to mark the dentry negative if * possible, giving a successful _negative_ lookup, while d_drop will * just make the cache lookup fail. * * d_drop() is used mainly for stuff that wants to invalidate a dentry for some * reason (NFS timeouts or autofs deletes). * * __d_drop requires dentry->d_lock * * ___d_drop doesn't mark dentry as "unhashed" * (dentry->d_hash.pprev will be LIST_POISON2, not NULL). */ void d_drop(struct dentry *dentry) { spin_lock(&dentry->d_lock); __d_drop(dentry); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(d_drop); static inline void dentry_unlist(struct dentry *dentry) { struct dentry *next; /* * Inform d_walk() and shrink_dentry_list() that we are no longer * attached to the dentry tree */ dentry->d_flags |= DCACHE_DENTRY_KILLED; if (unlikely(hlist_unhashed(&dentry->d_sib))) return; __hlist_del(&dentry->d_sib); /* * Cursors can move around the list of children. While we'd been * a normal list member, it didn't matter - ->d_sib.next would've * been updated. However, from now on it won't be and for the * things like d_walk() it might end up with a nasty surprise. * Normally d_walk() doesn't care about cursors moving around - * ->d_lock on parent prevents that and since a cursor has no children * of its own, we get through it without ever unlocking the parent. * There is one exception, though - if we ascend from a child that * gets killed as soon as we unlock it, the next sibling is found * using the value left in its ->d_sib.next. And if _that_ * pointed to a cursor, and cursor got moved (e.g. by lseek()) * before d_walk() regains parent->d_lock, we'll end up skipping * everything the cursor had been moved past. * * Solution: make sure that the pointer left behind in ->d_sib.next * points to something that won't be moving around. I.e. skip the * cursors. */ while (dentry->d_sib.next) { next = hlist_entry(dentry->d_sib.next, struct dentry, d_sib); if (likely(!(next->d_flags & DCACHE_DENTRY_CURSOR))) break; dentry->d_sib.next = next->d_sib.next; } } static struct dentry *__dentry_kill(struct dentry *dentry) { struct dentry *parent = NULL; bool can_free = true; /* * The dentry is now unrecoverably dead to the world. */ lockref_mark_dead(&dentry->d_lockref); /* * inform the fs via d_prune that this dentry is about to be * unhashed and destroyed. */ if (dentry->d_flags & DCACHE_OP_PRUNE) dentry->d_op->d_prune(dentry); if (dentry->d_flags & DCACHE_LRU_LIST) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) d_lru_del(dentry); } /* if it was on the hash then remove it */ __d_drop(dentry); if (dentry->d_inode) dentry_unlink_inode(dentry); else spin_unlock(&dentry->d_lock); this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); cond_resched(); /* now that it's negative, ->d_parent is stable */ if (!IS_ROOT(dentry)) { parent = dentry->d_parent; spin_lock(&parent->d_lock); } spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry_unlist(dentry); if (dentry->d_flags & DCACHE_SHRINK_LIST) can_free = false; spin_unlock(&dentry->d_lock); if (likely(can_free)) dentry_free(dentry); if (parent && --parent->d_lockref.count) { spin_unlock(&parent->d_lock); return NULL; } return parent; } /* * Lock a dentry for feeding it to __dentry_kill(). * Called under rcu_read_lock() and dentry->d_lock; the former * guarantees that nothing we access will be freed under us. * Note that dentry is *not* protected from concurrent dentry_kill(), * d_delete(), etc. * * Return false if dentry is busy. Otherwise, return true and have * that dentry's inode locked. */ static bool lock_for_kill(struct dentry *dentry) { struct inode *inode = dentry->d_inode; if (unlikely(dentry->d_lockref.count)) return false; if (!inode || likely(spin_trylock(&inode->i_lock))) return true; do { spin_unlock(&dentry->d_lock); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); if (likely(inode == dentry->d_inode)) break; spin_unlock(&inode->i_lock); inode = dentry->d_inode; } while (inode); if (likely(!dentry->d_lockref.count)) return true; if (inode) spin_unlock(&inode->i_lock); return false; } /* * Decide if dentry is worth retaining. Usually this is called with dentry * locked; if not locked, we are more limited and might not be able to tell * without a lock. False in this case means "punt to locked path and recheck". * * In case we aren't locked, these predicates are not "stable". However, it is * sufficient that at some point after we dropped the reference the dentry was * hashed and the flags had the proper value. Other dentry users may have * re-gotten a reference to the dentry and change that, but our work is done - * we can leave the dentry around with a zero refcount. */ static inline bool retain_dentry(struct dentry *dentry, bool locked) { unsigned int d_flags; smp_rmb(); d_flags = READ_ONCE(dentry->d_flags); // Unreachable? Nobody would be able to look it up, no point retaining if (unlikely(d_unhashed(dentry))) return false; // Same if it's disconnected if (unlikely(d_flags & DCACHE_DISCONNECTED)) return false; // ->d_delete() might tell us not to bother, but that requires // ->d_lock; can't decide without it if (unlikely(d_flags & DCACHE_OP_DELETE)) { if (!locked || dentry->d_op->d_delete(dentry)) return false; } // Explicitly told not to bother if (unlikely(d_flags & DCACHE_DONTCACHE)) return false; // At this point it looks like we ought to keep it. We also might // need to do something - put it on LRU if it wasn't there already // and mark it referenced if it was on LRU, but not marked yet. // Unfortunately, both actions require ->d_lock, so in lockless // case we'd have to punt rather than doing those. if (unlikely(!(d_flags & DCACHE_LRU_LIST))) { if (!locked) return false; d_lru_add(dentry); } else if (unlikely(!(d_flags & DCACHE_REFERENCED))) { if (!locked) return false; dentry->d_flags |= DCACHE_REFERENCED; } return true; } void d_mark_dontcache(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); hlist_for_each_entry(de, &inode->i_dentry, d_u.d_alias) { spin_lock(&de->d_lock); de->d_flags |= DCACHE_DONTCACHE; spin_unlock(&de->d_lock); } inode->i_state |= I_DONTCACHE; spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_mark_dontcache); /* * Try to do a lockless dput(), and return whether that was successful. * * If unsuccessful, we return false, having already taken the dentry lock. * In that case refcount is guaranteed to be zero and we have already * decided that it's not worth keeping around. * * The caller needs to hold the RCU read lock, so that the dentry is * guaranteed to stay around even if the refcount goes down to zero! */ static inline bool fast_dput(struct dentry *dentry) { int ret; /* * try to decrement the lockref optimistically. */ ret = lockref_put_return(&dentry->d_lockref); /* * If the lockref_put_return() failed due to the lock being held * by somebody else, the fast path has failed. We will need to * get the lock, and then check the count again. */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } dentry->d_lockref.count--; goto locked; } /* * If we weren't the last ref, we're done. */ if (ret) return true; /* * Can we decide that decrement of refcount is all we needed without * taking the lock? There's a very common case when it's all we need - * dentry looks like it ought to be retained and there's nothing else * to do. */ if (retain_dentry(dentry, false)) return true; /* * Either not worth retaining or we can't tell without the lock. * Get the lock, then. We've already decremented the refcount to 0, * but we'll need to re-check the situation after getting the lock. */ spin_lock(&dentry->d_lock); /* * Did somebody else grab a reference to it in the meantime, and * we're no longer the last user after all? Alternatively, somebody * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ locked: if (dentry->d_lockref.count || retain_dentry(dentry, true)) { spin_unlock(&dentry->d_lock); return true; } return false; } /* * This is dput * * This is complicated by the fact that we do not want to put * dentries that are no longer on any hash chain on the unused * list: we'd much rather just get rid of them immediately. * * However, that implies that we have to traverse the dentry * tree upwards to the parents which might _also_ now be * scheduled for deletion (it may have been only waiting for * its last child to go away). * * This tail recursion is done by hand as we don't want to depend * on the compiler to always get this right (gcc generally doesn't). * Real recursion would eat up our stack space. */ /* * dput - release a dentry * @dentry: dentry to release * * Release a dentry. This will drop the usage count and if appropriate * call the dentry unlink method as well as removing it from the queues and * releasing its resources. If the parent dentries were scheduled for release * they too may now get deleted. */ void dput(struct dentry *dentry) { if (!dentry) return; might_sleep(); rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } while (lock_for_kill(dentry)) { rcu_read_unlock(); dentry = __dentry_kill(dentry); if (!dentry) return; if (retain_dentry(dentry, true)) { spin_unlock(&dentry->d_lock); return; } rcu_read_lock(); } rcu_read_unlock(); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(dput); static void to_shrink_list(struct dentry *dentry, struct list_head *list) __must_hold(&dentry->d_lock) { if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { if (dentry->d_flags & DCACHE_LRU_LIST) d_lru_del(dentry); d_shrink_add(dentry, list); } } void dput_to_list(struct dentry *dentry, struct list_head *list) { rcu_read_lock(); if (likely(fast_dput(dentry))) { rcu_read_unlock(); return; } rcu_read_unlock(); to_shrink_list(dentry, list); spin_unlock(&dentry->d_lock); } struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; unsigned seq; /* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); } repeat: /* * Don't need rcu_dereference because we re-check it was correct under * the lock. */ rcu_read_lock(); ret = dentry->d_parent; spin_lock(&ret->d_lock); if (unlikely(ret != dentry->d_parent)) { spin_unlock(&ret->d_lock); rcu_read_unlock(); goto repeat; } rcu_read_unlock(); BUG_ON(!ret->d_lockref.count); ret->d_lockref.count++; spin_unlock(&ret->d_lock); return ret; } EXPORT_SYMBOL(dget_parent); static struct dentry * __d_find_any_alias(struct inode *inode) { struct dentry *alias; if (hlist_empty(&inode->i_dentry)) return NULL; alias = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias); lockref_get(&alias->d_lockref); return alias; } /** * d_find_any_alias - find any alias for a given inode * @inode: inode to find an alias for * * If any aliases exist for the given inode, take and return a * reference for one of them. If no aliases exist, return %NULL. */ struct dentry *d_find_any_alias(struct inode *inode) { struct dentry *de; spin_lock(&inode->i_lock); de = __d_find_any_alias(inode); spin_unlock(&inode->i_lock); return de; } EXPORT_SYMBOL(d_find_any_alias); static struct dentry *__d_find_alias(struct inode *inode) { struct dentry *alias; if (S_ISDIR(inode->i_mode)) return __d_find_any_alias(inode); hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { spin_lock(&alias->d_lock); if (!d_unhashed(alias)) { dget_dlock(alias); spin_unlock(&alias->d_lock); return alias; } spin_unlock(&alias->d_lock); } return NULL; } /** * d_find_alias - grab a hashed alias of inode * @inode: inode in question * * If inode has a hashed alias, or is a directory and has any alias, * acquire the reference to alias and return it. Otherwise return NULL. * Notice that if inode is a directory there can be only one alias and * it can be unhashed only if it has no children, or if it is the root * of a filesystem, or if the directory was renamed and d_revalidate * was the first vfs operation to notice. * * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer * any other hashed alias over that one. */ struct dentry *d_find_alias(struct inode *inode) { struct dentry *de = NULL; if (!hlist_empty(&inode->i_dentry)) { spin_lock(&inode->i_lock); de = __d_find_alias(inode); spin_unlock(&inode->i_lock); } return de; } EXPORT_SYMBOL(d_find_alias); /* * Caller MUST be holding rcu_read_lock() and be guaranteed * that inode won't get freed until rcu_read_unlock(). */ struct dentry *d_find_alias_rcu(struct inode *inode) { struct hlist_head *l = &inode->i_dentry; struct dentry *de = NULL; spin_lock(&inode->i_lock); // ->i_dentry and ->i_rcu are colocated, but the latter won't be // used without having I_FREEING set, which means no aliases left if (likely(!(inode->i_state & I_FREEING) && !hlist_empty(l))) { if (S_ISDIR(inode->i_mode)) { de = hlist_entry(l->first, struct dentry, d_u.d_alias); } else { hlist_for_each_entry(de, l, d_u.d_alias) if (!d_unhashed(de)) break; } } spin_unlock(&inode->i_lock); return de; } /* * Try to kill dentries associated with this inode. * WARNING: you must own a reference to inode. */ void d_prune_aliases(struct inode *inode) { LIST_HEAD(dispose); struct dentry *dentry; spin_lock(&inode->i_lock); hlist_for_each_entry(dentry, &inode->i_dentry, d_u.d_alias) { spin_lock(&dentry->d_lock); if (!dentry->d_lockref.count) to_shrink_list(dentry, &dispose); spin_unlock(&dentry->d_lock); } spin_unlock(&inode->i_lock); shrink_dentry_list(&dispose); } EXPORT_SYMBOL(d_prune_aliases); static inline void shrink_kill(struct dentry *victim) { do { rcu_read_unlock(); victim = __dentry_kill(victim); rcu_read_lock(); } while (victim && lock_for_kill(victim)); rcu_read_unlock(); if (victim) spin_unlock(&victim->d_lock); } void shrink_dentry_list(struct list_head *list) { while (!list_empty(list)) { struct dentry *dentry; dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); rcu_read_lock(); if (!lock_for_kill(dentry)) { bool can_free; rcu_read_unlock(); d_shrink_del(dentry); can_free = dentry->d_flags & DCACHE_DENTRY_KILLED; spin_unlock(&dentry->d_lock); if (can_free) dentry_free(dentry); continue; } d_shrink_del(dentry); shrink_kill(dentry); } } static enum lru_status dentry_lru_isolate(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; /* * Referenced dentries are still in use. If they have active * counts, just remove them from the LRU. Otherwise give them * another pass through the LRU. */ if (dentry->d_lockref.count) { d_lru_isolate(lru, dentry); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } if (dentry->d_flags & DCACHE_REFERENCED) { dentry->d_flags &= ~DCACHE_REFERENCED; spin_unlock(&dentry->d_lock); /* * The list move itself will be made by the common LRU code. At * this point, we've dropped the dentry->d_lock but keep the * lru lock. This is safe to do, since every list movement is * protected by the lru lock even if both locks are held. * * This is guaranteed by the fact that all LRU management * functions are intermediated by the LRU API calls like * list_lru_add_obj and list_lru_del_obj. List movement in this file * only ever occur through this functions or through callbacks * like this one, that are called from the LRU API. * * The only exceptions to this are functions like * shrink_dentry_list, and code that first checks for the * DCACHE_SHRINK_LIST flag. Those are guaranteed to be * operating only with stack provided lists after they are * properly isolated from the main list. It is thus, always a * local access. */ return LRU_ROTATE; } d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * prune_dcache_sb - shrink the dcache * @sb: superblock * @sc: shrink control, passed to list_lru_shrink_walk() * * Attempt to shrink the superblock dcache LRU by @sc->nr_to_scan entries. This * is done when we need more memory and called from the superblock shrinker * function. * * This function may fail to free any resources if all the dentries are in * use. */ long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(dispose); long freed; freed = list_lru_shrink_walk(&sb->s_dentry_lru, sc, dentry_lru_isolate, &dispose); shrink_dentry_list(&dispose); return freed; } static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, struct list_lru_one *lru, void *arg) { struct list_head *freeable = arg; struct dentry *dentry = container_of(item, struct dentry, d_lru); /* * we are inverting the lru lock/dentry->d_lock here, * so use a trylock. If we fail to get the lock, just skip * it */ if (!spin_trylock(&dentry->d_lock)) return LRU_SKIP; d_lru_shrink_move(lru, dentry, freeable); spin_unlock(&dentry->d_lock); return LRU_REMOVED; } /** * shrink_dcache_sb - shrink dcache for a superblock * @sb: superblock * * Shrink the dcache for the specified super block. This is used to free * the dcache before unmounting a file system. */ void shrink_dcache_sb(struct super_block *sb) { do { LIST_HEAD(dispose); list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); /** * enum d_walk_ret - action to talke during tree walk * @D_WALK_CONTINUE: contrinue walk * @D_WALK_QUIT: quit walk * @D_WALK_NORETRY: quit when retry is needed * @D_WALK_SKIP: skip this dentry and its children */ enum d_walk_ret { D_WALK_CONTINUE, D_WALK_QUIT, D_WALK_NORETRY, D_WALK_SKIP, }; /** * d_walk - walk the dentry tree * @parent: start of walk * @data: data passed to @enter() and @finish() * @enter: callback when first entering the dentry * * The @enter() callbacks are called with d_lock held. */ static void d_walk(struct dentry *parent, void *data, enum d_walk_ret (*enter)(void *, struct dentry *)) { struct dentry *this_parent, *dentry; unsigned seq = 0; enum d_walk_ret ret; bool retry = true; again: read_seqbegin_or_lock(&rename_lock, &seq); this_parent = parent; spin_lock(&this_parent->d_lock); ret = enter(data, this_parent); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: case D_WALK_SKIP: goto out_unlock; case D_WALK_NORETRY: retry = false; break; } repeat: dentry = d_first_child(this_parent); resume: hlist_for_each_entry_from(dentry, d_sib) { if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); ret = enter(data, dentry); switch (ret) { case D_WALK_CONTINUE: break; case D_WALK_QUIT: spin_unlock(&dentry->d_lock); goto out_unlock; case D_WALK_NORETRY: retry = false; break; case D_WALK_SKIP: spin_unlock(&dentry->d_lock); continue; } if (!hlist_empty(&dentry->d_children)) { spin_unlock(&this_parent->d_lock); spin_release(&dentry->d_lock.dep_map, _RET_IP_); this_parent = dentry; spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); goto repeat; } spin_unlock(&dentry->d_lock); } /* * All done at this level ... ascend and resume the search. */ rcu_read_lock(); ascend: if (this_parent != parent) { dentry = this_parent; this_parent = dentry->d_parent; spin_unlock(&dentry->d_lock); spin_lock(&this_parent->d_lock); /* might go back up the wrong parent if we have had a rename. */ if (need_seqretry(&rename_lock, seq)) goto rename_retry; /* go into the first sibling still alive */ hlist_for_each_entry_continue(dentry, d_sib) { if (likely(!(dentry->d_flags & DCACHE_DENTRY_KILLED))) { rcu_read_unlock(); goto resume; } } goto ascend; } if (need_seqretry(&rename_lock, seq)) goto rename_retry; rcu_read_unlock(); out_unlock: spin_unlock(&this_parent->d_lock); done_seqretry(&rename_lock, seq); return; rename_retry: spin_unlock(&this_parent->d_lock); rcu_read_unlock(); BUG_ON(seq & 1); if (!retry) return; seq = 1; goto again; } struct check_mount { struct vfsmount *mnt; unsigned int mounted; }; /* locks: mount_locked_reader && dentry->d_lock */ static enum d_walk_ret path_check_mount(void *data, struct dentry *dentry) { struct check_mount *info = data; struct path path = { .mnt = info->mnt, .dentry = dentry }; if (likely(!d_mountpoint(dentry))) return D_WALK_CONTINUE; if (__path_is_mountpoint(&path)) { info->mounted = 1; return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * path_has_submounts - check for mounts over a dentry in the * current namespace. * @parent: path to check. * * Return true if the parent or its subdirectories contain * a mount point in the current namespace. */ int path_has_submounts(const struct path *parent) { struct check_mount data = { .mnt = parent->mnt, .mounted = 0 }; guard(mount_locked_reader)(); d_walk(parent->dentry, &data, path_check_mount); return data.mounted; } EXPORT_SYMBOL(path_has_submounts); /* * Called by mount code to set a mountpoint and check if the mountpoint is * reachable (e.g. NFS can unhash a directory dentry and then the complete * subtree can become unreachable). * * Only one of d_invalidate() and d_set_mounted() must succeed. For * this reason take rename_lock and d_lock on dentry and ancestors. */ int d_set_mounted(struct dentry *dentry) { struct dentry *p; int ret = -ENOENT; read_seqlock_excl(&rename_lock); for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) { /* Need exclusion wrt. d_invalidate() */ spin_lock(&p->d_lock); if (unlikely(d_unhashed(p))) { spin_unlock(&p->d_lock); goto out; } spin_unlock(&p->d_lock); } spin_lock(&dentry->d_lock); if (!d_unlinked(dentry)) { ret = -EBUSY; if (!d_mountpoint(dentry)) { dentry->d_flags |= DCACHE_MOUNTED; ret = 0; } } spin_unlock(&dentry->d_lock); out: read_sequnlock_excl(&rename_lock); return ret; } /* * Search the dentry child list of the specified parent, * and move any unused dentries to the end of the unused * list for prune_dcache(). We descend to the next level * whenever the d_children list is non-empty and continue * searching. * * It returns zero iff there are no unused children, * otherwise it returns the number of children moved to * the end of the unused list. This may not be the total * number of unused children, because select_parent can * drop the lock and return early due to latency * constraints. */ struct select_data { struct dentry *start; union { long found; struct dentry *victim; }; struct list_head dispose; }; static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (dentry->d_flags & DCACHE_SHRINK_LIST) { data->found++; } else if (!dentry->d_lockref.count) { to_shrink_list(dentry, &data->dispose); data->found++; } else if (dentry->d_lockref.count < 0) { data->found++; } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry) { struct select_data *data = _data; enum d_walk_ret ret = D_WALK_CONTINUE; if (data->start == dentry) goto out; if (!dentry->d_lockref.count) { if (dentry->d_flags & DCACHE_SHRINK_LIST) { rcu_read_lock(); data->victim = dentry; return D_WALK_QUIT; } to_shrink_list(dentry, &data->dispose); } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ if (!list_empty(&data->dispose)) ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } /** * shrink_dcache_parent - prune dcache * @parent: parent of entries to prune * * Prune the dcache to remove unused children of the parent dentry. */ void shrink_dcache_parent(struct dentry *parent) { for (;;) { struct select_data data = {.start = parent}; INIT_LIST_HEAD(&data.dispose); d_walk(parent, &data, select_collect); if (!list_empty(&data.dispose)) { shrink_dentry_list(&data.dispose); continue; } cond_resched(); if (!data.found) break; data.victim = NULL; d_walk(parent, &data, select_collect2); if (data.victim) { spin_lock(&data.victim->d_lock); if (!lock_for_kill(data.victim)) { spin_unlock(&data.victim->d_lock); rcu_read_unlock(); } else { shrink_kill(data.victim); } } if (!list_empty(&data.dispose)) shrink_dentry_list(&data.dispose); } } EXPORT_SYMBOL(shrink_dcache_parent); static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { /* it has busy descendents; complain about those instead */ if (!hlist_empty(&dentry->d_children)) return D_WALK_CONTINUE; /* root with refcount 1 is fine */ if (dentry == _data && dentry->d_lockref.count == 1) return D_WALK_CONTINUE; WARN(1, "BUG: Dentry %p{i=%lx,n=%pd} " " still in use (%d) [unmount of %s %s]\n", dentry, dentry->d_inode ? dentry->d_inode->i_ino : 0UL, dentry, dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); return D_WALK_CONTINUE; } static void do_one_tree(struct dentry *dentry) { shrink_dcache_parent(dentry); d_walk(dentry, dentry, umount_check); d_drop(dentry); dput(dentry); } /* * destroy the dentries attached to a superblock on unmounting */ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; rwsem_assert_held_write(&sb->s_umount); dentry = sb->s_root; sb->s_root = NULL; do_one_tree(dentry); while (!hlist_bl_empty(&sb->s_roots)) { dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_roots), struct dentry, d_hash)); do_one_tree(dentry); } } static enum d_walk_ret find_submount(void *_data, struct dentry *dentry) { struct dentry **victim = _data; if (d_mountpoint(dentry)) { *victim = dget_dlock(dentry); return D_WALK_QUIT; } return D_WALK_CONTINUE; } /** * d_invalidate - detach submounts, prune dcache, and drop * @dentry: dentry to invalidate (aka detach, prune and drop) */ void d_invalidate(struct dentry *dentry) { bool had_submounts = false; spin_lock(&dentry->d_lock); if (d_unhashed(dentry)) { spin_unlock(&dentry->d_lock); return; } __d_drop(dentry); spin_unlock(&dentry->d_lock); /* Negative dentries can be dropped without further checks */ if (!dentry->d_inode) return; shrink_dcache_parent(dentry); for (;;) { struct dentry *victim = NULL; d_walk(dentry, &victim, find_submount); if (!victim) { if (had_submounts) shrink_dcache_parent(dentry); return; } had_submounts = true; detach_mounts(victim); dput(victim); } } EXPORT_SYMBOL(d_invalidate); /** * __d_alloc - allocate a dcache entry * @sb: filesystem it will belong to * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) { struct dentry *dentry; char *dname; int err; dentry = kmem_cache_alloc_lru(dentry_cache, &sb->s_dentry_lru, GFP_KERNEL); if (!dentry) return NULL; /* * We guarantee that the inline name is always NUL-terminated. * This way the memcpy() done by the name switching in rename * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ dentry->d_shortname.string[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; dname = dentry->d_shortname.string; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT | __GFP_RECLAIMABLE); if (!p) { kmem_cache_free(dentry_cache, dentry); return NULL; } atomic_set(&p->count, 1); dname = p->name; } else { dname = dentry->d_shortname.string; } dentry->__d_name.len = name->len; dentry->__d_name.hash = name->hash; memcpy(dname, name->name, name->len); dname[name->len] = 0; /* Make sure we always see the terminating NUL character */ smp_store_release(&dentry->__d_name.name, dname); /* ^^^ */ dentry->d_flags = 0; lockref_init(&dentry->d_lockref); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; dentry->d_sb = sb; dentry->d_op = sb->__s_d_op; dentry->d_flags = sb->s_d_flags; dentry->d_fsdata = NULL; INIT_HLIST_BL_NODE(&dentry->d_hash); INIT_LIST_HEAD(&dentry->d_lru); INIT_HLIST_HEAD(&dentry->d_children); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_HLIST_NODE(&dentry->d_sib); if (dentry->d_op && dentry->d_op->d_init) { err = dentry->d_op->d_init(dentry); if (err) { if (dname_external(dentry)) kfree(external_name(dentry)); kmem_cache_free(dentry_cache, dentry); return NULL; } } this_cpu_inc(nr_dentry); return dentry; } /** * d_alloc - allocate a dcache entry * @parent: parent of entry to allocate * @name: qstr of the name * * Allocates a dentry. It returns %NULL if there is insufficient memory * available. On a success the dentry is returned. The name passed in is * copied and the copy passed in may be reused after this call. */ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) { struct dentry *dentry = __d_alloc(parent->d_sb, name); if (!dentry) return NULL; spin_lock(&parent->d_lock); /* * don't need child lock because it is not subject * to concurrency here */ dentry->d_parent = dget_dlock(parent); hlist_add_head(&dentry->d_sib, &parent->d_children); spin_unlock(&parent->d_lock); return dentry; } EXPORT_SYMBOL(d_alloc); struct dentry *d_alloc_anon(struct super_block *sb) { return __d_alloc(sb, NULL); } EXPORT_SYMBOL(d_alloc_anon); struct dentry *d_alloc_cursor(struct dentry * parent) { struct dentry *dentry = d_alloc_anon(parent->d_sb); if (dentry) { dentry->d_flags |= DCACHE_DENTRY_CURSOR; dentry->d_parent = dget(parent); } return dentry; } /** * d_alloc_pseudo - allocate a dentry (for lookup-less filesystems) * @sb: the superblock * @name: qstr of the name * * For a filesystem that just pins its dentries in memory and never * performs lookups at all, return an unhashed IS_ROOT dentry. * This is used for pipes, sockets et.al. - the stuff that should * never be anyone's children or parents. Unlike all other * dentries, these will not have RCU delay between dropping the * last reference and freeing them. * * The only user is alloc_file_pseudo() and that's what should * be considered a public interface. Don't use directly. */ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name) { static const struct dentry_operations anon_ops = { .d_dname = simple_dname }; struct dentry *dentry = __d_alloc(sb, name); if (likely(dentry)) { dentry->d_flags |= DCACHE_NORCU; /* d_op_flags(&anon_ops) is 0 */ if (!dentry->d_op) dentry->d_op = &anon_ops; } return dentry; } struct dentry *d_alloc_name(struct dentry *parent, const char *name) { struct qstr q; q.name = name; q.hash_len = hashlen_string(parent, name); return d_alloc(parent, &q); } EXPORT_SYMBOL(d_alloc_name); #define DCACHE_OP_FLAGS \ (DCACHE_OP_HASH | DCACHE_OP_COMPARE | DCACHE_OP_REVALIDATE | \ DCACHE_OP_WEAK_REVALIDATE | DCACHE_OP_DELETE | DCACHE_OP_PRUNE | \ DCACHE_OP_REAL) static unsigned int d_op_flags(const struct dentry_operations *op) { unsigned int flags = 0; if (op) { if (op->d_hash) flags |= DCACHE_OP_HASH; if (op->d_compare) flags |= DCACHE_OP_COMPARE; if (op->d_revalidate) flags |= DCACHE_OP_REVALIDATE; if (op->d_weak_revalidate) flags |= DCACHE_OP_WEAK_REVALIDATE; if (op->d_delete) flags |= DCACHE_OP_DELETE; if (op->d_prune) flags |= DCACHE_OP_PRUNE; if (op->d_real) flags |= DCACHE_OP_REAL; } return flags; } static void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op) { unsigned int flags = d_op_flags(op); WARN_ON_ONCE(dentry->d_op); WARN_ON_ONCE(dentry->d_flags & DCACHE_OP_FLAGS); dentry->d_op = op; if (flags) dentry->d_flags |= flags; } void set_default_d_op(struct super_block *s, const struct dentry_operations *ops) { unsigned int flags = d_op_flags(ops); s->__s_d_op = ops; s->s_d_flags = (s->s_d_flags & ~DCACHE_OP_FLAGS) | flags; } EXPORT_SYMBOL(set_default_d_op); static unsigned d_flags_for_inode(struct inode *inode) { unsigned add_flags = DCACHE_REGULAR_TYPE; if (!inode) return DCACHE_MISS_TYPE; if (S_ISDIR(inode->i_mode)) { add_flags = DCACHE_DIRECTORY_TYPE; if (unlikely(!(inode->i_opflags & IOP_LOOKUP))) { if (unlikely(!inode->i_op->lookup)) add_flags = DCACHE_AUTODIR_TYPE; else inode->i_opflags |= IOP_LOOKUP; } goto type_determined; } if (unlikely(!(inode->i_opflags & IOP_NOFOLLOW))) { if (unlikely(inode->i_op->get_link)) { add_flags = DCACHE_SYMLINK_TYPE; goto type_determined; } inode->i_opflags |= IOP_NOFOLLOW; } if (unlikely(!S_ISREG(inode->i_mode))) add_flags = DCACHE_SPECIAL_TYPE; type_determined: if (unlikely(IS_AUTOMOUNT(inode))) add_flags |= DCACHE_NEED_AUTOMOUNT; return add_flags; } static void __d_instantiate(struct dentry *dentry, struct inode *inode) { unsigned add_flags = d_flags_for_inode(inode); WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); /* * The negative counter only tracks dentries on the LRU. Don't dec if * d_lru is on another list. */ if ((dentry->d_flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); spin_unlock(&dentry->d_lock); } /** * d_instantiate - fill in inode information for a dentry * @entry: dentry to complete * @inode: inode to attach to this dentry * * Fill in inode information in the entry. * * This turns negative dentries into productive full members * of society. * * NOTE! This assumes that the inode count has been incremented * (or otherwise set) by the caller to indicate that it is now * in use by the dcache. */ void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_instantiate); /* * This should be equivalent to d_instantiate() + unlock_new_inode(), * with lockdep-related part of unlock_new_inode() done before * anything else. Use that instead of open-coding d_instantiate()/ * unlock_new_inode() combinations. */ void d_instantiate_new(struct dentry *entry, struct inode *inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); BUG_ON(!inode); lockdep_annotate_inode_mutex_key(inode); security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); __d_instantiate(entry, inode); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; /* * Pairs with the barrier in prepare_to_wait_event() to make sure * ___wait_var_event() either sees the bit cleared or * waitqueue_active() check in wake_up_var() sees the waiter. */ smp_mb(); inode_wake_up_bit(inode, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(d_instantiate_new); struct dentry *d_make_root(struct inode *root_inode) { struct dentry *res = NULL; if (root_inode) { res = d_alloc_anon(root_inode->i_sb); if (res) d_instantiate(res, root_inode); else iput(root_inode); } return res; } EXPORT_SYMBOL(d_make_root); static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected) { struct super_block *sb; struct dentry *new, *res; if (!inode) return ERR_PTR(-ESTALE); if (IS_ERR(inode)) return ERR_CAST(inode); sb = inode->i_sb; res = d_find_any_alias(inode); /* existing alias? */ if (res) goto out; new = d_alloc_anon(sb); if (!new) { res = ERR_PTR(-ENOMEM); goto out; } security_d_instantiate(new, inode); spin_lock(&inode->i_lock); res = __d_find_any_alias(inode); /* recheck under lock */ if (likely(!res)) { /* still no alias, attach a disconnected dentry */ unsigned add_flags = d_flags_for_inode(inode); if (disconnected) add_flags |= DCACHE_DISCONNECTED; spin_lock(&new->d_lock); __d_set_inode_and_type(new, inode, add_flags); hlist_add_head(&new->d_u.d_alias, &inode->i_dentry); if (!disconnected) { hlist_bl_lock(&sb->s_roots); hlist_bl_add_head(&new->d_hash, &sb->s_roots); hlist_bl_unlock(&sb->s_roots); } spin_unlock(&new->d_lock); spin_unlock(&inode->i_lock); inode = NULL; /* consumed by new->d_inode */ res = new; } else { spin_unlock(&inode->i_lock); dput(new); } out: iput(inode); return res; } /** * d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain a dentry for an inode resulting from NFS filehandle conversion or * similar open by handle operations. The returned dentry may be anonymous, * or may have a full name (if the inode was already in the cache). * * When called on a directory inode, we must ensure that the inode only ever * has one dentry. If a dentry is found, that is returned instead of * allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is released. * To make it easier to use in export operations a %NULL or IS_ERR inode may * be passed in and the error will be propagated to the return value, * with a %NULL @inode replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_alias(struct inode *inode) { return __d_obtain_alias(inode, true); } EXPORT_SYMBOL(d_obtain_alias); /** * d_obtain_root - find or allocate a dentry for a given inode * @inode: inode to allocate the dentry for * * Obtain an IS_ROOT dentry for the root of a filesystem. * * We must ensure that directory inodes only ever have one dentry. If a * dentry is found, that is returned instead of allocating a new one. * * On successful return, the reference to the inode has been transferred * to the dentry. In case of an error the reference on the inode is * released. A %NULL or IS_ERR inode may be passed in and will be the * error will be propagate to the return value, with a %NULL @inode * replaced by ERR_PTR(-ESTALE). */ struct dentry *d_obtain_root(struct inode *inode) { return __d_obtain_alias(inode, false); } EXPORT_SYMBOL(d_obtain_root); /** * d_add_ci - lookup or allocate new dentry with case-exact name * @dentry: the negative dentry that was passed to the parent's lookup func * @inode: the inode case-insensitive lookup has found * @name: the case-exact name to be associated with the returned dentry * * This is to avoid filling the dcache with case-insensitive names to the * same inode, only the actual correct case is stored in the dcache for * case-insensitive filesystems. * * For a case-insensitive lookup match and if the case-exact dentry * already exists in the dcache, use it and return it. * * If no entry exists with the exact case name, allocate new dentry with * the exact case, and return the spliced entry. */ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, struct qstr *name) { struct dentry *found, *res; /* * First check if a dentry matching the name already exists, * if not go ahead and create it now. */ found = d_hash_and_lookup(dentry->d_parent, name); if (found) { iput(inode); return found; } if (d_in_lookup(dentry)) { found = d_alloc_parallel(dentry->d_parent, name, dentry->d_wait); if (IS_ERR(found) || !d_in_lookup(found)) { iput(inode); return found; } } else { found = d_alloc(dentry->d_parent, name); if (!found) { iput(inode); return ERR_PTR(-ENOMEM); } } res = d_splice_alias(inode, found); if (res) { d_lookup_done(found); dput(found); return res; } return found; } EXPORT_SYMBOL(d_add_ci); /** * d_same_name - compare dentry name with case-exact name * @dentry: the negative dentry that was passed to the parent's lookup func * @parent: parent dentry * @name: the case-exact name to be associated with the returned dentry * * Return: true if names are same, or false */ bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name) { if (likely(!(parent->d_flags & DCACHE_OP_COMPARE))) { if (dentry->d_name.len != name->len) return false; return dentry_cmp(dentry, name->name, name->len) == 0; } return parent->d_op->d_compare(dentry, dentry->d_name.len, dentry->d_name.name, name) == 0; } EXPORT_SYMBOL_GPL(d_same_name); /* * This is __d_lookup_rcu() when the parent dentry has * DCACHE_OP_COMPARE, which makes things much nastier. */ static noinline struct dentry *__d_lookup_rcu_op_compare( const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { int tlen; const char *tname; unsigned seq; seqretry: seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; tlen = dentry->d_name.len; tname = dentry->d_name.name; /* we want a consistent (name,len) pair */ if (read_seqcount_retry(&dentry->d_seq, seq)) { cpu_relax(); goto seqretry; } if (parent->d_op->d_compare(dentry, tlen, tname, name) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry * @name: qstr of name we wish to find * @seqp: returns d_seq value at the point where the dentry was found * Returns: dentry, or NULL * * __d_lookup_rcu is the dcache lookup function for rcu-walk name * resolution (store-free path walking) design described in * Documentation/filesystems/path-lookup.txt. * * This is not to be used outside core vfs. * * __d_lookup_rcu must only be used in rcu-walk mode, ie. with vfsmount lock * held, and rcu_read_lock held. The returned dentry must not be stored into * without taking d_lock and checking d_seq sequence count against @seq * returned here. * * Alternatively, __d_lookup_rcu may be called again to look up the child of * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks * is formed, giving integrity down the path walk. * * NOTE! The caller *has* to check the resulting dentry against the sequence * number we've returned before using any of the resulting dentry state! */ struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seqp) { u64 hashlen = name->hash_len; const unsigned char *str = name->name; struct hlist_bl_head *b = d_hash(hashlen); struct hlist_bl_node *node; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) return __d_lookup_rcu_op_compare(parent, name, seqp); /* * The hash list is protected using RCU. * * Carefully use d_seq when comparing a candidate dentry, to avoid * races with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; /* * The dentry sequence count protects us from concurrent * renames, and thus protects parent and name fields. * * The caller must perform a seqcount check in order * to do anything useful with the returned dentry. * * NOTE! We do a "raw" seqcount_begin here. That means that * we don't wait for the sequence count to stabilize if it * is in the middle of a sequence change. If we do the slow * dentry compare, we will do seqretries until it is stable, * and if we end up with a successful lookup, we actually * want to exit RCU lookup anyway. * * Note that raw_seqcount_begin still *does* smp_rmb(), so * we are still guaranteed NUL-termination of ->d_name.name. */ seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; if (dentry->d_name.hash_len != hashlen) continue; if (dentry_cmp(dentry, str, hashlen_len(hashlen)) != 0) continue; *seqp = seq; return dentry; } return NULL; } /** * d_lookup - search for a dentry * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * d_lookup searches the children of the parent dentry for the name in * question. If the dentry is found its reference count is incremented and the * dentry is returned. The caller must use dput to free the entry when it has * finished using it. %NULL is returned if the dentry does not exist. */ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name) { struct dentry *dentry; unsigned seq; do { seq = read_seqbegin(&rename_lock); dentry = __d_lookup(parent, name); if (dentry) break; } while (read_seqretry(&rename_lock, seq)); return dentry; } EXPORT_SYMBOL(d_lookup); /** * __d_lookup - search for a dentry (racy) * @parent: parent dentry * @name: qstr of name we wish to find * Returns: dentry, or NULL * * __d_lookup is like d_lookup, however it may (rarely) return a * false-negative result due to unrelated rename activity. * * __d_lookup is slightly faster by avoiding rename_lock read seqlock, * however it must be used carefully, eg. with a following d_lookup in * the case of failure. * * __d_lookup callers must be commented. */ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name) { unsigned int hash = name->hash; struct hlist_bl_head *b = d_hash(hash); struct hlist_bl_node *node; struct dentry *found = NULL; struct dentry *dentry; /* * Note: There is significant duplication with __d_lookup_rcu which is * required to prevent single threaded performance regressions * especially on architectures where smp_rmb (in seqcounts) are costly. * Keep the two functions in sync. */ /* * The hash list is protected using RCU. * * Take d_lock when comparing a candidate dentry, to avoid races * with d_move(). * * It is possible that concurrent renames can mess up our list * walk here and result in missing our dentry, resulting in the * false-negative result. d_lookup() protects against concurrent * renames using rename_lock seqlock. * * See Documentation/filesystems/path-lookup.txt for more details. */ rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { if (dentry->d_name.hash != hash) continue; spin_lock(&dentry->d_lock); if (dentry->d_parent != parent) goto next; if (d_unhashed(dentry)) goto next; if (!d_same_name(dentry, parent, name)) goto next; dentry->d_lockref.count++; found = dentry; spin_unlock(&dentry->d_lock); break; next: spin_unlock(&dentry->d_lock); } rcu_read_unlock(); return found; } /** * d_hash_and_lookup - hash the qstr then search for a dentry * @dir: Directory to search in * @name: qstr of name we wish to find * * On lookup failure NULL is returned; on bad name - ERR_PTR(-error) */ struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name) { /* * Check for a fs-specific hash function. Note that we must * calculate the standard hash first, as the d_op->d_hash() * routine may choose to leave the hash value unchanged. */ name->hash = full_name_hash(dir, name->name, name->len); if (dir->d_flags & DCACHE_OP_HASH) { int err = dir->d_op->d_hash(dir, name); if (unlikely(err < 0)) return ERR_PTR(err); } return d_lookup(dir, name); } /* * When a file is deleted, we have two options: * - turn this dentry into a negative dentry * - unhash this dentry and free it. * * Usually, we want to just turn this into * a negative dentry, but if anybody else is * currently using the dentry or the inode * we can't do that and we fall back on removing * it from the hash queues and waiting for * it to be deleted later when it has no users */ /** * d_delete - delete a dentry * @dentry: The dentry to delete * * Turn the dentry into a negative dentry if possible, otherwise * remove it from the hash queues so it can be deleted later */ void d_delete(struct dentry * dentry) { struct inode *inode = dentry->d_inode; spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); /* * Are we the only user? */ if (dentry->d_lockref.count == 1) { if (dentry_negative_policy) __d_drop(dentry); dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } } EXPORT_SYMBOL(d_delete); static void __d_rehash(struct dentry *entry) { struct hlist_bl_head *b = d_hash(entry->d_name.hash); hlist_bl_lock(b); hlist_bl_add_head_rcu(&entry->d_hash, b); hlist_bl_unlock(b); } /** * d_rehash - add an entry back to the hash * @entry: dentry to add to the hash * * Adds a dentry to the hash according to its name. */ void d_rehash(struct dentry * entry) { spin_lock(&entry->d_lock); __d_rehash(entry); spin_unlock(&entry->d_lock); } EXPORT_SYMBOL(d_rehash); static inline unsigned start_dir_add(struct inode *dir) { preempt_disable_nested(); for (;;) { unsigned n = READ_ONCE(dir->i_dir_seq); if (!(n & 1) && try_cmpxchg(&dir->i_dir_seq, &n, n + 1)) return n; cpu_relax(); } } static inline void end_dir_add(struct inode *dir, unsigned int n, wait_queue_head_t *d_wait) { smp_store_release(&dir->i_dir_seq, n + 2); preempt_enable_nested(); if (wq_has_sleeper(d_wait)) wake_up_all(d_wait); } static void d_wait_lookup(struct dentry *dentry) { if (d_in_lookup(dentry)) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(dentry->d_wait, &wait); do { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&dentry->d_lock); schedule(); spin_lock(&dentry->d_lock); } while (d_in_lookup(dentry)); } } struct dentry *d_alloc_parallel(struct dentry *parent, const struct qstr *name, wait_queue_head_t *wq) { unsigned int hash = name->hash; struct hlist_bl_head *b = in_lookup_hash(parent, hash); struct hlist_bl_node *node; struct dentry *new = __d_alloc(parent->d_sb, name); struct dentry *dentry; unsigned seq, r_seq, d_seq; if (unlikely(!new)) return ERR_PTR(-ENOMEM); new->d_flags |= DCACHE_PAR_LOOKUP; spin_lock(&parent->d_lock); new->d_parent = dget_dlock(parent); hlist_add_head(&new->d_sib, &parent->d_children); if (parent->d_flags & DCACHE_DISCONNECTED) new->d_flags |= DCACHE_DISCONNECTED; spin_unlock(&parent->d_lock); retry: rcu_read_lock(); seq = smp_load_acquire(&parent->d_inode->i_dir_seq); r_seq = read_seqbegin(&rename_lock); dentry = __d_lookup_rcu(parent, name, &d_seq); if (unlikely(dentry)) { if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } if (read_seqcount_retry(&dentry->d_seq, d_seq)) { rcu_read_unlock(); dput(dentry); goto retry; } rcu_read_unlock(); dput(new); return dentry; } if (unlikely(read_seqretry(&rename_lock, r_seq))) { rcu_read_unlock(); goto retry; } if (unlikely(seq & 1)) { rcu_read_unlock(); goto retry; } hlist_bl_lock(b); if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { hlist_bl_unlock(b); rcu_read_unlock(); goto retry; } /* * No changes for the parent since the beginning of d_lookup(). * Since all removals from the chain happen with hlist_bl_lock(), * any potential in-lookup matches are going to stay here until * we unlock the chain. All fields are stable in everything * we encounter. */ hlist_bl_for_each_entry(dentry, node, b, d_u.d_in_lookup_hash) { if (dentry->d_name.hash != hash) continue; if (dentry->d_parent != parent) continue; if (!d_same_name(dentry, parent, name)) continue; hlist_bl_unlock(b); /* now we can try to grab a reference */ if (!lockref_get_not_dead(&dentry->d_lockref)) { rcu_read_unlock(); goto retry; } rcu_read_unlock(); /* * somebody is likely to be still doing lookup for it; * wait for them to finish */ spin_lock(&dentry->d_lock); d_wait_lookup(dentry); /* * it's not in-lookup anymore; in principle we should repeat * everything from dcache lookup, but it's likely to be what * d_lookup() would've found anyway. If it is, just return it; * otherwise we really have to repeat the whole thing. */ if (unlikely(dentry->d_name.hash != hash)) goto mismatch; if (unlikely(dentry->d_parent != parent)) goto mismatch; if (unlikely(d_unhashed(dentry))) goto mismatch; if (unlikely(!d_same_name(dentry, parent, name))) goto mismatch; /* OK, it *is* a hashed match; return it */ spin_unlock(&dentry->d_lock); dput(new); return dentry; } rcu_read_unlock(); new->d_wait = wq; hlist_bl_add_head(&new->d_u.d_in_lookup_hash, b); hlist_bl_unlock(b); return new; mismatch: spin_unlock(&dentry->d_lock); dput(dentry); goto retry; } EXPORT_SYMBOL(d_alloc_parallel); /* * - Unhash the dentry * - Retrieve and clear the waitqueue head in dentry * - Return the waitqueue head */ static wait_queue_head_t *__d_lookup_unhash(struct dentry *dentry) { wait_queue_head_t *d_wait; struct hlist_bl_head *b; lockdep_assert_held(&dentry->d_lock); b = in_lookup_hash(dentry->d_parent, dentry->d_name.hash); hlist_bl_lock(b); dentry->d_flags &= ~DCACHE_PAR_LOOKUP; __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); d_wait = dentry->d_wait; dentry->d_wait = NULL; hlist_bl_unlock(b); INIT_HLIST_NODE(&dentry->d_u.d_alias); INIT_LIST_HEAD(&dentry->d_lru); return d_wait; } void __d_lookup_unhash_wake(struct dentry *dentry) { spin_lock(&dentry->d_lock); wake_up_all(__d_lookup_unhash(dentry)); spin_unlock(&dentry->d_lock); } EXPORT_SYMBOL(__d_lookup_unhash_wake); /* inode->i_lock held if inode is non-NULL */ static inline void __d_add(struct dentry *dentry, struct inode *inode, const struct dentry_operations *ops) { wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; spin_lock(&dentry->d_lock); if (unlikely(d_in_lookup(dentry))) { dir = dentry->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(dentry); } if (unlikely(ops)) d_set_d_op(dentry, ops); if (inode) { unsigned add_flags = d_flags_for_inode(inode); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); raw_write_seqcount_end(&dentry->d_seq); fsnotify_update_flags(dentry); } __d_rehash(dentry); if (dir) end_dir_add(dir, n, d_wait); spin_unlock(&dentry->d_lock); if (inode) spin_unlock(&inode->i_lock); } /** * d_add - add dentry to hash queues * @entry: dentry to add * @inode: The inode to attach to this dentry * * This adds the entry to the hash queues and initializes @inode. * The entry was actually filled in earlier during d_alloc(). */ void d_add(struct dentry *entry, struct inode *inode) { if (inode) { security_d_instantiate(entry, inode); spin_lock(&inode->i_lock); } __d_add(entry, inode, NULL); } EXPORT_SYMBOL(d_add); static void swap_names(struct dentry *dentry, struct dentry *target) { if (unlikely(dname_external(target))) { if (unlikely(dname_external(dentry))) { /* * Both external: swap the pointers */ swap(target->__d_name.name, dentry->__d_name.name); } else { /* * dentry:internal, target:external. Steal target's * storage and make target internal. */ dentry->__d_name.name = target->__d_name.name; target->d_shortname = dentry->d_shortname; target->__d_name.name = target->d_shortname.string; } } else { if (unlikely(dname_external(dentry))) { /* * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ target->__d_name.name = dentry->__d_name.name; dentry->d_shortname = target->d_shortname; dentry->__d_name.name = dentry->d_shortname.string; } else { /* * Both are internal. */ for (int i = 0; i < DNAME_INLINE_WORDS; i++) swap(dentry->d_shortname.words[i], target->d_shortname.words[i]); } } swap(dentry->__d_name.hash_len, target->__d_name.hash_len); } static void copy_name(struct dentry *dentry, struct dentry *target) { struct external_name *old_name = NULL; if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { atomic_inc(&external_name(target)->count); dentry->__d_name = target->__d_name; } else { dentry->d_shortname = target->d_shortname; dentry->__d_name.name = dentry->d_shortname.string; dentry->__d_name.hash_len = target->__d_name.hash_len; } if (old_name && likely(atomic_dec_and_test(&old_name->count))) kfree_rcu(old_name, head); } /* * __d_move - move a dentry * @dentry: entry to move * @target: new dentry * @exchange: exchange the two dentries * * Update the dcache to reflect the move of a file name. Negative dcache * entries should not be moved in this way. Caller must hold rename_lock, the * i_rwsem of the source and target directories (exclusively), and the sb-> * s_vfs_rename_mutex if they differ. See lock_rename(). */ static void __d_move(struct dentry *dentry, struct dentry *target, bool exchange) { struct dentry *old_parent, *p; wait_queue_head_t *d_wait; struct inode *dir = NULL; unsigned n; WARN_ON(!dentry->d_inode); if (WARN_ON(dentry == target)) return; BUG_ON(d_ancestor(target, dentry)); old_parent = dentry->d_parent; p = d_ancestor(old_parent, target); if (IS_ROOT(dentry)) { BUG_ON(p); spin_lock(&target->d_parent->d_lock); } else if (!p) { /* target is not a descendent of dentry->d_parent */ spin_lock(&target->d_parent->d_lock); spin_lock_nested(&old_parent->d_lock, DENTRY_D_LOCK_NESTED); } else { BUG_ON(p == dentry); spin_lock(&old_parent->d_lock); if (p != target) spin_lock_nested(&target->d_parent->d_lock, DENTRY_D_LOCK_NESTED); } spin_lock_nested(&dentry->d_lock, 2); spin_lock_nested(&target->d_lock, 3); if (unlikely(d_in_lookup(target))) { dir = target->d_parent->d_inode; n = start_dir_add(dir); d_wait = __d_lookup_unhash(target); } write_seqcount_begin(&dentry->d_seq); write_seqcount_begin_nested(&target->d_seq, DENTRY_D_LOCK_NESTED); /* unhash both */ if (!d_unhashed(dentry)) ___d_drop(dentry); if (!d_unhashed(target)) ___d_drop(target); /* ... and switch them in the tree */ dentry->d_parent = target->d_parent; if (!exchange) { copy_name(dentry, target); target->d_hash.pprev = NULL; dentry->d_parent->d_lockref.count++; if (dentry != old_parent) /* wasn't IS_ROOT */ WARN_ON(!--old_parent->d_lockref.count); } else { target->d_parent = old_parent; swap_names(dentry, target); if (!hlist_unhashed(&target->d_sib)) __hlist_del(&target->d_sib); hlist_add_head(&target->d_sib, &target->d_parent->d_children); __d_rehash(target); fsnotify_update_flags(target); } if (!hlist_unhashed(&dentry->d_sib)) __hlist_del(&dentry->d_sib); hlist_add_head(&dentry->d_sib, &dentry->d_parent->d_children); __d_rehash(dentry); fsnotify_update_flags(dentry); fscrypt_handle_d_move(dentry); write_seqcount_end(&target->d_seq); write_seqcount_end(&dentry->d_seq); if (dir) end_dir_add(dir, n, d_wait); if (dentry->d_parent != old_parent) spin_unlock(&dentry->d_parent->d_lock); if (dentry != old_parent) spin_unlock(&old_parent->d_lock); spin_unlock(&target->d_lock); spin_unlock(&dentry->d_lock); } /* * d_move - move a dentry * @dentry: entry to move * @target: new dentry * * Update the dcache to reflect the move of a file name. Negative * dcache entries should not be moved in this way. See the locking * requirements for __d_move. */ void d_move(struct dentry *dentry, struct dentry *target) { write_seqlock(&rename_lock); __d_move(dentry, target, false); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_move); /* * d_exchange - exchange two dentries * @dentry1: first dentry * @dentry2: second dentry */ void d_exchange(struct dentry *dentry1, struct dentry *dentry2) { write_seqlock(&rename_lock); WARN_ON(!dentry1->d_inode); WARN_ON(!dentry2->d_inode); WARN_ON(IS_ROOT(dentry1)); WARN_ON(IS_ROOT(dentry2)); __d_move(dentry1, dentry2, true); write_sequnlock(&rename_lock); } EXPORT_SYMBOL(d_exchange); /** * d_ancestor - search for an ancestor * @p1: ancestor dentry * @p2: child dentry * * Returns the ancestor dentry of p2 which is a child of p1, if p1 is * an ancestor of p2, else NULL. */ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2) { struct dentry *p; for (p = p2; !IS_ROOT(p); p = p->d_parent) { if (p->d_parent == p1) return p; } return NULL; } /* * This helper attempts to cope with remotely renamed directories * * It assumes that the caller is already holding * dentry->d_parent->d_inode->i_rwsem, and rename_lock * * Note: If ever the locking in lock_rename() changes, then please * remember to update this too... */ static int __d_unalias(struct dentry *dentry, struct dentry *alias) { struct mutex *m1 = NULL; struct rw_semaphore *m2 = NULL; int ret = -ESTALE; /* If alias and dentry share a parent, then no extra locks required */ if (alias->d_parent == dentry->d_parent) goto out_unalias; /* See lock_rename() */ if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex)) goto out_err; m1 = &dentry->d_sb->s_vfs_rename_mutex; if (!inode_trylock_shared(alias->d_parent->d_inode)) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: if (alias->d_op && alias->d_op->d_unalias_trylock && !alias->d_op->d_unalias_trylock(alias)) goto out_err; __d_move(alias, dentry, false); if (alias->d_op && alias->d_op->d_unalias_unlock) alias->d_op->d_unalias_unlock(alias); ret = 0; out_err: if (m2) up_read(m2); if (m1) mutex_unlock(m1); return ret; } struct dentry *d_splice_alias_ops(struct inode *inode, struct dentry *dentry, const struct dentry_operations *ops) { if (IS_ERR(inode)) return ERR_CAST(inode); BUG_ON(!d_unhashed(dentry)); if (!inode) goto out; security_d_instantiate(dentry, inode); spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); if (unlikely(new)) { /* The reference to new ensures it remains an alias */ spin_unlock(&inode->i_lock); write_seqlock(&rename_lock); if (unlikely(d_ancestor(new, dentry))) { write_sequnlock(&rename_lock); dput(new); new = ERR_PTR(-ELOOP); pr_warn_ratelimited( "VFS: Lookup of '%s' in %s %s" " would have caused loop\n", dentry->d_name.name, inode->i_sb->s_type->name, inode->i_sb->s_id); } else if (!IS_ROOT(new)) { struct dentry *old_parent = dget(new->d_parent); int err = __d_unalias(dentry, new); write_sequnlock(&rename_lock); if (err) { dput(new); new = ERR_PTR(err); } dput(old_parent); } else { __d_move(new, dentry, false); write_sequnlock(&rename_lock); } iput(inode); return new; } } out: __d_add(dentry, inode, ops); return NULL; } /** * d_splice_alias - splice a disconnected dentry into the tree if one exists * @inode: the inode which may have a disconnected dentry * @dentry: a negative dentry which we want to point to the inode. * * If inode is a directory and has an IS_ROOT alias, then d_move that in * place of the given dentry and return it, else simply d_add the inode * to the dentry and return NULL. * * If a non-IS_ROOT directory is found, the filesystem is corrupt, and * we should error out: directories can't have multiple aliases. * * This is needed in the lookup routine of any filesystem that is exportable * (via knfsd) so that we can build dcache paths to directories effectively. * * If a dentry was found and moved, then it is returned. Otherwise NULL * is returned. This matches the expected return value of ->lookup. * * Cluster filesystems may call this function with a negative, hashed dentry. * In that case, we know that the inode will be a regular file, and also this * will only occur during atomic_open. So we need to check for the dentry * being already hashed only in the final case. */ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) { return d_splice_alias_ops(inode, dentry, NULL); } EXPORT_SYMBOL(d_splice_alias); /* * Test whether new_dentry is a subdirectory of old_dentry. * * Trivially implemented using the dcache structure */ /** * is_subdir - is new dentry a subdirectory of old_dentry * @new_dentry: new dentry * @old_dentry: old dentry * * Returns true if new_dentry is a subdirectory of the parent (at any depth). * Returns false otherwise. * Caller must ensure that "new_dentry" is pinned before calling is_subdir() */ bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry) { bool subdir; unsigned seq; if (new_dentry == old_dentry) return true; /* Access d_parent under rcu as d_move() may change it. */ rcu_read_lock(); seq = read_seqbegin(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); /* Try lockless once... */ if (read_seqretry(&rename_lock, seq)) { /* ...else acquire lock for progress even on deep chains. */ read_seqlock_excl(&rename_lock); subdir = d_ancestor(old_dentry, new_dentry); read_sequnlock_excl(&rename_lock); } rcu_read_unlock(); return subdir; } EXPORT_SYMBOL(is_subdir); static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry) { struct dentry *root = data; if (dentry != root) { if (d_unhashed(dentry) || !dentry->d_inode) return D_WALK_SKIP; if (!(dentry->d_flags & DCACHE_GENOCIDE)) { dentry->d_flags |= DCACHE_GENOCIDE; dentry->d_lockref.count--; } } return D_WALK_CONTINUE; } void d_genocide(struct dentry *parent) { d_walk(parent, parent, d_genocide_kill); } void d_mark_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; BUG_ON(dname_external(dentry) || !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); dentry->__d_name.len = sprintf(dentry->d_shortname.string, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); } EXPORT_SYMBOL(d_mark_tmpfile); void d_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; inode_dec_link_count(inode); d_mark_tmpfile(file, inode); d_instantiate(dentry, inode); } EXPORT_SYMBOL(d_tmpfile); /* * Obtain inode number of the parent dentry. */ ino_t d_parent_ino(struct dentry *dentry) { struct dentry *parent; struct inode *iparent; unsigned seq; ino_t ret; scoped_guard(rcu) { seq = raw_seqcount_begin(&dentry->d_seq); parent = READ_ONCE(dentry->d_parent); iparent = d_inode_rcu(parent); if (likely(iparent)) { ret = iparent->i_ino; if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; } } spin_lock(&dentry->d_lock); ret = dentry->d_parent->d_inode->i_ino; spin_unlock(&dentry->d_lock); return ret; } EXPORT_SYMBOL(d_parent_ino); static __initdata unsigned long dhash_entries; static int __init set_dhash_entries(char *str) { if (!str) return 0; dhash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_EARLY | HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; runtime_const_init(shift, d_hash_shift); runtime_const_init(ptr, dentry_hashtable); } static void __init dcache_init(void) { /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature * of the dcache. */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT, d_shortname.string); /* Hash may have been set up in dcache_init_early */ if (!hashdist) return; dentry_hashtable = alloc_large_system_hash("Dentry cache", sizeof(struct hlist_bl_head), dhash_entries, 13, HASH_ZERO, &d_hash_shift, NULL, 0, 0); d_hash_shift = 32 - d_hash_shift; runtime_const_init(shift, d_hash_shift); runtime_const_init(ptr, dentry_hashtable); } /* SLAB cache for __getname() consumers */ struct kmem_cache *names_cachep __ro_after_init; EXPORT_SYMBOL(names_cachep); void __init vfs_caches_init_early(void) { int i; for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++) INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]); dcache_init_early(); inode_init_early(); } void __init vfs_caches_init(void) { names_cachep = kmem_cache_create_usercopy("names_cache", PATH_MAX, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, 0, PATH_MAX, NULL); dcache_init(); inode_init(); files_init(); files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); } |
| 510 211 205 203 290 87 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* audit.h -- Auditing support * * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> */ #ifndef _LINUX_AUDIT_H_ #define _LINUX_AUDIT_H_ #include <linux/sched.h> #include <linux/ptrace.h> #include <linux/audit_arch.h> #include <uapi/linux/audit.h> #include <uapi/linux/netfilter/nf_tables.h> #include <uapi/linux/fanotify.h> #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) struct audit_sig_info { uid_t uid; pid_t pid; char ctx[]; }; struct audit_buffer; struct audit_context; struct inode; struct netlink_skb_parms; struct path; struct linux_binprm; struct mq_attr; struct mqstat; struct audit_watch; struct audit_tree; struct sk_buff; struct kern_ipc_perm; struct lsm_id; struct lsm_prop; struct audit_krule { u32 pflags; u32 flags; u32 listnr; u32 action; u32 mask[AUDIT_BITMASK_SIZE]; u32 buflen; /* for data alloc on list rules */ u32 field_count; char *filterkey; /* ties events to rules */ struct audit_field *fields; struct audit_field *arch_f; /* quick access to arch field */ struct audit_field *inode_f; /* quick access to an inode field */ struct audit_watch *watch; /* associated watch */ struct audit_tree *tree; /* associated watched tree */ struct audit_fsnotify_mark *exe; struct list_head rlist; /* entry in audit_{watch,tree}.rules list */ struct list_head list; /* for AUDIT_LIST* purposes only */ u64 prio; }; /* Flag to indicate legacy AUDIT_LOGINUID unset usage */ #define AUDIT_LOGINUID_LEGACY 0x1 struct audit_field { u32 type; union { u32 val; kuid_t uid; kgid_t gid; struct { char *lsm_str; void *lsm_rule; }; }; u32 op; }; enum audit_ntp_type { AUDIT_NTP_OFFSET, AUDIT_NTP_FREQ, AUDIT_NTP_STATUS, AUDIT_NTP_TAI, AUDIT_NTP_TICK, AUDIT_NTP_ADJUST, AUDIT_NTP_NVALS /* count */ }; #ifdef CONFIG_AUDITSYSCALL struct audit_ntp_val { long long oldval, newval; }; struct audit_ntp_data { struct audit_ntp_val vals[AUDIT_NTP_NVALS]; }; #else struct audit_ntp_data {}; #endif enum audit_nfcfgop { AUDIT_XT_OP_REGISTER, AUDIT_XT_OP_REPLACE, AUDIT_XT_OP_UNREGISTER, AUDIT_NFT_OP_TABLE_REGISTER, AUDIT_NFT_OP_TABLE_UNREGISTER, AUDIT_NFT_OP_CHAIN_REGISTER, AUDIT_NFT_OP_CHAIN_UNREGISTER, AUDIT_NFT_OP_RULE_REGISTER, AUDIT_NFT_OP_RULE_UNREGISTER, AUDIT_NFT_OP_SET_REGISTER, AUDIT_NFT_OP_SET_UNREGISTER, AUDIT_NFT_OP_SETELEM_REGISTER, AUDIT_NFT_OP_SETELEM_UNREGISTER, AUDIT_NFT_OP_GEN_REGISTER, AUDIT_NFT_OP_OBJ_REGISTER, AUDIT_NFT_OP_OBJ_UNREGISTER, AUDIT_NFT_OP_OBJ_RESET, AUDIT_NFT_OP_FLOWTABLE_REGISTER, AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, AUDIT_NFT_OP_SETELEM_RESET, AUDIT_NFT_OP_RULE_RESET, AUDIT_NFT_OP_INVALID, }; extern int __init audit_register_class(int class, unsigned *list); extern int audit_classify_syscall(int abi, unsigned syscall); extern int audit_classify_arch(int arch); /* only for compat system calls */ extern unsigned compat_write_class[]; extern unsigned compat_read_class[]; extern unsigned compat_dir_class[]; extern unsigned compat_chattr_class[]; extern unsigned compat_signal_class[]; /* audit_names->type values */ #define AUDIT_TYPE_UNKNOWN 0 /* we don't know yet */ #define AUDIT_TYPE_NORMAL 1 /* a "normal" audit record */ #define AUDIT_TYPE_PARENT 2 /* a parent audit record */ #define AUDIT_TYPE_CHILD_DELETE 3 /* a child being deleted */ #define AUDIT_TYPE_CHILD_CREATE 4 /* a child being created */ /* maximized args number that audit_socketcall can process */ #define AUDITSC_ARGS 6 /* bit values for ->signal->audit_tty */ #define AUDIT_TTY_ENABLE BIT(0) #define AUDIT_TTY_LOG_PASSWD BIT(1) /* bit values for audit_cfg_lsm */ #define AUDIT_CFG_LSM_SECCTX_SUBJECT BIT(0) #define AUDIT_CFG_LSM_SECCTX_OBJECT BIT(1) struct filename; #define AUDIT_OFF 0 #define AUDIT_ON 1 #define AUDIT_LOCKED 2 #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ extern __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...); extern struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type); extern __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...); extern void audit_log_end(struct audit_buffer *ab); extern bool audit_string_contains_control(const char *string, size_t len); extern void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len); extern void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n); extern void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n); extern void audit_log_untrustedstring(struct audit_buffer *ab, const char *string); extern void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path); extern void audit_log_key(struct audit_buffer *ab, char *key); extern void audit_log_path_denied(int type, const char *operation); extern void audit_log_lost(const char *message); extern int audit_log_subj_ctx(struct audit_buffer *ab, struct lsm_prop *prop); extern int audit_log_obj_ctx(struct audit_buffer *ab, struct lsm_prop *prop); extern int audit_log_task_context(struct audit_buffer *ab); extern void audit_log_task_info(struct audit_buffer *ab); extern int audit_update_lsm_rules(void); /* Private API (for audit.c only) */ extern int audit_rule_change(int type, int seq, void *data, size_t datasz); extern int audit_list_rules_send(struct sk_buff *request_skb, int seq); extern int audit_set_loginuid(kuid_t loginuid); static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return tsk->loginuid; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return tsk->sessionid; } extern u32 audit_enabled; extern int audit_signal_info(int sig, struct task_struct *t); extern void audit_cfg_lsm(const struct lsm_id *lsmid, int flags); #else /* CONFIG_AUDIT */ static inline __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { } static inline struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { return NULL; } static inline __printf(2, 3) void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { } static inline void audit_log_end(struct audit_buffer *ab) { } static inline void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { } static inline void audit_log_n_string(struct audit_buffer *ab, const char *buf, size_t n) { } static inline void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t n) { } static inline void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { } static inline void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { } static inline void audit_log_key(struct audit_buffer *ab, char *key) { } static inline void audit_log_path_denied(int type, const char *operation) { } static inline int audit_log_subj_ctx(struct audit_buffer *ab, struct lsm_prop *prop) { return 0; } static inline int audit_log_obj_ctx(struct audit_buffer *ab, struct lsm_prop *prop) { return 0; } static inline int audit_log_task_context(struct audit_buffer *ab) { return 0; } static inline void audit_log_task_info(struct audit_buffer *ab) { } static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { return INVALID_UID; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { return AUDIT_SID_UNSET; } #define audit_enabled AUDIT_OFF static inline int audit_signal_info(int sig, struct task_struct *t) { return 0; } static inline void audit_cfg_lsm(const struct lsm_id *lsmid, int flags) { } #endif /* CONFIG_AUDIT */ #ifdef CONFIG_AUDIT_COMPAT_GENERIC #define audit_is_compat(arch) (!((arch) & __AUDIT_ARCH_64BIT)) #else #define audit_is_compat(arch) false #endif #define AUDIT_INODE_PARENT 1 /* dentry represents the parent */ #define AUDIT_INODE_HIDDEN 2 /* audit record should be hidden */ #define AUDIT_INODE_NOEVAL 4 /* audit record incomplete */ #ifdef CONFIG_AUDITSYSCALL #include <asm/syscall.h> /* for syscall_get_arch() */ /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); extern void __audit_free(struct task_struct *task); extern void __audit_uring_entry(u8 op); extern void __audit_uring_exit(int success, long code); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); extern struct filename *__audit_reusename(const __user char *uptr); extern void __audit_getname(struct filename *name); extern void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags); extern void __audit_file(const struct file *); extern void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type); extern void audit_seccomp(unsigned long syscall, long signr, int code); extern void audit_seccomp_actions_logged(const char *names, const char *old_names, int res); extern void __audit_ptrace(struct task_struct *t); static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { task->audit_context = ctx; } static inline struct audit_context *audit_context(void) { return current->audit_context; } static inline bool audit_dummy_context(void) { void *p = audit_context(); return !p || *(int *)p; } static inline void audit_free(struct task_struct *task) { if (unlikely(task->audit_context)) __audit_free(task); } static inline void audit_uring_entry(u8 op) { /* * We intentionally check audit_context() before audit_enabled as most * Linux systems (as of ~2021) rely on systemd which forces audit to * be enabled regardless of the user's audit configuration. */ if (unlikely(audit_context() && audit_enabled)) __audit_uring_entry(op); } static inline void audit_uring_exit(int success, long code) { if (unlikely(audit_context())) __audit_uring_exit(success, code); } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { if (unlikely(audit_context())) __audit_syscall_entry(major, a0, a1, a2, a3); } static inline void audit_syscall_exit(void *pt_regs) { if (unlikely(audit_context())) { int success = is_syscall_success(pt_regs); long return_code = regs_return_value(pt_regs); __audit_syscall_exit(success, return_code); } } static inline struct filename *audit_reusename(const __user char *name) { if (unlikely(!audit_dummy_context())) return __audit_reusename(name); return NULL; } static inline void audit_getname(struct filename *name) { if (unlikely(!audit_dummy_context())) __audit_getname(name); } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, aflags); } static inline void audit_file(struct file *file) { if (unlikely(!audit_dummy_context())) __audit_file(file); } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { if (unlikely(!audit_dummy_context())) __audit_inode(name, dentry, AUDIT_INODE_PARENT | AUDIT_INODE_HIDDEN); } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { if (unlikely(!audit_dummy_context())) __audit_inode_child(parent, dentry, type); } void audit_core_dumps(long signr); static inline void audit_ptrace(struct task_struct *t) { if (unlikely(!audit_dummy_context())) __audit_ptrace(t); } /* Private API (for audit.c only) */ extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp); extern void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode); extern void __audit_bprm(struct linux_binprm *bprm); extern int __audit_socketcall(int nargs, unsigned long *args); extern int __audit_sockaddr(int len, void *addr); extern void __audit_fd_pair(int fd1, int fd2); extern void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr); extern void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout); extern void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification); extern void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); extern void __audit_openat2_how(struct open_how *how); extern void __audit_log_kern_module(const char *name); extern void __audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar); extern void __audit_tk_injoffset(struct timespec64 offset); extern void __audit_ntp_log(const struct audit_ntp_data *ad); extern void __audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp); static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { if (unlikely(!audit_dummy_context())) __audit_ipc_obj(ipcp); } static inline void audit_fd_pair(int fd1, int fd2) { if (unlikely(!audit_dummy_context())) __audit_fd_pair(fd1, fd2); } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { if (unlikely(!audit_dummy_context())) __audit_ipc_set_perm(qbytes, uid, gid, mode); } static inline void audit_bprm(struct linux_binprm *bprm) { if (unlikely(!audit_dummy_context())) __audit_bprm(bprm); } static inline int audit_socketcall(int nargs, unsigned long *args) { if (unlikely(!audit_dummy_context())) return __audit_socketcall(nargs, args); return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { unsigned long a[AUDITSC_ARGS]; int i; if (audit_dummy_context()) return 0; for (i = 0; i < nargs; i++) a[i] = (unsigned long)args[i]; return __audit_socketcall(nargs, a); } static inline int audit_sockaddr(int len, void *addr) { if (unlikely(!audit_dummy_context())) return __audit_sockaddr(len, addr); return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { if (unlikely(!audit_dummy_context())) __audit_mq_open(oflag, mode, attr); } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { if (unlikely(!audit_dummy_context())) __audit_mq_sendrecv(mqdes, msg_len, msg_prio, abs_timeout); } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { if (unlikely(!audit_dummy_context())) __audit_mq_notify(mqdes, notification); } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { if (unlikely(!audit_dummy_context())) __audit_mq_getsetattr(mqdes, mqstat); } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) return __audit_log_bprm_fcaps(bprm, new, old); return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { if (unlikely(!audit_dummy_context())) __audit_log_capset(new, old); } static inline void audit_mmap_fd(int fd, int flags) { if (unlikely(!audit_dummy_context())) __audit_mmap_fd(fd, flags); } static inline void audit_openat2_how(struct open_how *how) { if (unlikely(!audit_dummy_context())) __audit_openat2_how(how); } static inline void audit_log_kern_module(const char *name) { if (!audit_dummy_context()) __audit_log_kern_module(name); } static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { if (audit_enabled) __audit_fanotify(response, friar); } static inline void audit_tk_injoffset(struct timespec64 offset) { /* ignore no-op events */ if (offset.tv_sec == 0 && offset.tv_nsec == 0) return; if (!audit_dummy_context()) __audit_tk_injoffset(offset); } static inline void audit_ntp_init(struct audit_ntp_data *ad) { memset(ad, 0, sizeof(*ad)); } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].oldval = val; } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { ad->vals[type].newval = val; } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { if (!audit_dummy_context()) __audit_ntp_log(ad); } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { if (audit_enabled) __audit_log_nfcfg(name, af, nentries, op, gfp); } extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ static inline int audit_alloc(struct task_struct *task) { return 0; } static inline void audit_free(struct task_struct *task) { } static inline void audit_uring_entry(u8 op) { } static inline void audit_uring_exit(int success, long code) { } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { } static inline void audit_syscall_exit(void *pt_regs) { } static inline bool audit_dummy_context(void) { return true; } static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { } static inline struct audit_context *audit_context(void) { return NULL; } static inline struct filename *audit_reusename(const __user char *name) { return NULL; } static inline void audit_getname(struct filename *name) { } static inline void audit_inode(struct filename *name, const struct dentry *dentry, unsigned int aflags) { } static inline void audit_file(struct file *file) { } static inline void audit_inode_parent_hidden(struct filename *name, const struct dentry *dentry) { } static inline void audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { } static inline void audit_core_dumps(long signr) { } static inline void audit_seccomp(unsigned long syscall, long signr, int code) { } static inline void audit_seccomp_actions_logged(const char *names, const char *old_names, int res) { } static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp) { } static inline void audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode) { } static inline void audit_bprm(struct linux_binprm *bprm) { } static inline int audit_socketcall(int nargs, unsigned long *args) { return 0; } static inline int audit_socketcall_compat(int nargs, u32 *args) { return 0; } static inline void audit_fd_pair(int fd1, int fd2) { } static inline int audit_sockaddr(int len, void *addr) { return 0; } static inline void audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr) { } static inline void audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio, const struct timespec64 *abs_timeout) { } static inline void audit_mq_notify(mqd_t mqdes, const struct sigevent *notification) { } static inline void audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) { } static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *new, const struct cred *old) { return 0; } static inline void audit_log_capset(const struct cred *new, const struct cred *old) { } static inline void audit_mmap_fd(int fd, int flags) { } static inline void audit_openat2_how(struct open_how *how) { } static inline void audit_log_kern_module(const char *name) { } static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { } static inline void audit_tk_injoffset(struct timespec64 offset) { } static inline void audit_ntp_init(struct audit_ntp_data *ad) { } static inline void audit_ntp_set_old(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_set_new(struct audit_ntp_data *ad, enum audit_ntp_type type, long long val) { } static inline void audit_ntp_log(const struct audit_ntp_data *ad) { } static inline void audit_ptrace(struct task_struct *t) { } static inline void audit_log_nfcfg(const char *name, u8 af, unsigned int nentries, enum audit_nfcfgop op, gfp_t gfp) { } #define audit_n_rules 0 #define audit_signals 0 #endif /* CONFIG_AUDITSYSCALL */ static inline bool audit_loginuid_set(struct task_struct *tsk) { return uid_valid(audit_get_loginuid(tsk)); } #endif |
| 121 121 7 47 39 20 26 14 18 18 6 18 22 20 20 19 5 19 3 15 14 15 15 5 7 2 2 2 2 29 5 22 2 2 105 14 14 14 14 42 41 15 14 6 2 1 41 2 41 4 41 41 7 41 41 42 42 42 8 38 41 42 7 186 185 167 160 8 42 41 41 42 5 4 1 1 1 1 1 18 8 5 13 13 4 13 7 7 6 7 7 41 41 41 40 41 18 18 18 22 22 22 16 17 17 21 18 18 18 18 18 18 18 7 7 18 18 2 1 1 2 1 1 1 1 41 41 41 41 43 2 3 39 1 1 1 3 3 3 2 3 23 21 21 20 20 18 18 18 4 1 1 2 1 2 1 1 32 32 1 1 1 1 5 1 1 1 3 12 12 1 1 1 2 7 5 4 5 4 2 1 5 3 1 1 1 3 1 2 18 18 45 45 45 | 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 | // 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) 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); bool kvm_supports_guest_pmuv3(void) { guard(mutex)(&arm_pmus_lock); return !list_empty(&arm_pmus); } 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) { 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_assign_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) { kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx), val, false); } /** * kvm_pmu_set_counter_value_user - set PMU counter value from user * @vcpu: The vcpu pointer * @select_idx: The counter index * @val: The counter value */ void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu, u64 select_idx, u64 val) { kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, select_idx)); __vcpu_assign_sys_reg(vcpu, counter_index_to_reg(select_idx), val); kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); } /** * 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_assign_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_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.nr_pmu_counters; /* * 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 (!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; 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_assign_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_rmw_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_rmw_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; /* 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_assign_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) { unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu) & ~BIT(ARMV8_PMU_CYCLE_IDX); if (!vcpu_is_el2(vcpu)) mask &= ~kvm_pmu_hyp_counter_mask(vcpu); 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; } static int kvm_map_pmu_event(struct kvm *kvm, unsigned int eventsel) { struct arm_pmu *pmu = kvm->arch.arm_pmu; /* * The CPU PMU likely isn't PMUv3; let the driver provide a mapping * for the guest's PMUv3 event ID. */ if (unlikely(pmu->map_pmuv3_event)) return pmu->map_pmuv3_event(eventsel); return eventsel; } /** * 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; int eventsel; u64 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; /* * Don't create an event if we're running on hardware that requires * PMUv3 event translation and we couldn't find a valid mapping. */ eventsel = kvm_map_pmu_event(vcpu->kvm, eventsel); if (eventsel < 0) 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; reg = counter_index_to_evtreg(pmc->idx); __vcpu_assign_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; guard(mutex)(&arm_pmus_lock); entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return; entry->arm_pmu = pmu; list_add_tail(&entry->entry, &arm_pmus); } static struct arm_pmu *kvm_pmu_probe_armpmu(void) { struct arm_pmu_entry *entry; struct arm_pmu *pmu; int cpu; guard(mutex)(&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) { pmu = entry->arm_pmu; if (cpumask_test_cpu(cpu, &pmu->supported_cpus)) return pmu; } return NULL; } static u64 __compute_pmceid(struct arm_pmu *pmu, bool pmceid1) { u32 hi[2], lo[2]; bitmap_to_arr32(lo, pmu->pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); bitmap_to_arr32(hi, pmu->pmceid_ext_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS); return ((u64)hi[pmceid1] << 32) | lo[pmceid1]; } static u64 compute_pmceid0(struct arm_pmu *pmu) { u64 val = __compute_pmceid(pmu, 0); /* always support SW_INCR */ val |= BIT(ARMV8_PMUV3_PERFCTR_SW_INCR); /* always support CHAIN */ val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN); return val; } static u64 compute_pmceid1(struct arm_pmu *pmu) { u64 val = __compute_pmceid(pmu, 1); /* * 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)); return val; } u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) { struct arm_pmu *cpu_pmu = vcpu->kvm->arch.arm_pmu; unsigned long *bmap = vcpu->kvm->arch.pmu_filter; u64 val, mask = 0; int base, i, nr_events; if (!pmceid1) { val = compute_pmceid0(cpu_pmu); base = 0; } else { val = compute_pmceid1(cpu_pmu); 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_rmw_sys_reg(vcpu, PMOVSSET_EL0, &=, mask); __vcpu_rmw_sys_reg(vcpu, PMINTENSET_EL1, &=, mask); __vcpu_rmw_sys_reg(vcpu, PMCNTENSET_EL0, &=, mask); kvm_pmu_reprogram_counter_mask(vcpu, mask); } int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) { 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; } 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; /* * PMUv3 requires that all event counters are capable of counting any * event, though the same may not be true of non-PMUv3 hardware. */ if (cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS)) return 1; /* * 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_nr_counters(struct kvm *kvm, unsigned int nr) { kvm->arch.nr_pmu_counters = nr; /* Reset MDCR_EL2.HPMN behind the vcpus' back... */ if (test_bit(KVM_ARM_VCPU_HAS_EL2, kvm->arch.vcpu_features)) { struct kvm_vcpu *vcpu; unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { u64 val = __vcpu_sys_reg(vcpu, MDCR_EL2); val &= ~MDCR_EL2_HPMN; val |= FIELD_PREP(MDCR_EL2_HPMN, kvm->arch.nr_pmu_counters); __vcpu_assign_sys_reg(vcpu, MDCR_EL2, val); } } } 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_arm_set_nr_counters(kvm, 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; } static int kvm_arm_pmu_v3_set_nr_counters(struct kvm_vcpu *vcpu, unsigned int n) { struct kvm *kvm = vcpu->kvm; if (!kvm->arch.arm_pmu) return -EINVAL; if (n > kvm_arm_pmu_get_max_counters(kvm)) return -EINVAL; kvm_arm_set_nr_counters(kvm, n); return 0; } 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_SET_NR_COUNTERS: { unsigned int __user *uaddr = (unsigned int __user *)(long)attr->addr; unsigned int n; if (get_user(n, uaddr)) return -EFAULT; return kvm_arm_pmu_v3_set_nr_counters(vcpu, n); } 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: case KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS: if (kvm_vcpu_has_pmu(vcpu)) return 0; } return -ENXIO; } u8 kvm_arm_pmu_get_pmuver_limit(void) { unsigned int pmuver; pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer, read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1)); /* * Spoof a barebones PMUv3 implementation if the system supports IMPDEF * traps of the PMUv3 sysregs */ if (cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS)) return ID_AA64DFR0_EL1_PMUVer_IMP; /* * Otherwise, treat IMPLEMENTATION DEFINED functionality as * unimplemented */ if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF) return 0; return min(pmuver, ID_AA64DFR0_EL1_PMUVer_V3P5); } /** * 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); u64 n = vcpu->kvm->arch.nr_pmu_counters; if (vcpu_has_nv(vcpu) && !vcpu_is_el2(vcpu)) n = FIELD_GET(MDCR_EL2_HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2)); return u64_replace_bits(pmcr, n, ARMV8_PMU_PMCR_N); } void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu) { bool reprogrammed = false; unsigned long mask; int i; 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); } |
| 408 407 408 408 408 406 65 111 276 298 300 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/flush.c * * Copyright (C) 1995-2002 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/export.h> #include <linux/mm.h> #include <linux/libnvdimm.h> #include <linux/pagemap.h> #include <asm/cacheflush.h> #include <asm/cache.h> #include <asm/tlbflush.h> void sync_icache_aliases(unsigned long start, unsigned long end) { if (icache_is_aliasing()) { dcache_clean_pou(start, end); icache_inval_all_pou(); } else { /* * Don't issue kick_all_cpus_sync() after I-cache invalidation * for user mappings. */ caches_clean_inval_pou(start, end); } } static void flush_ptrace_access(struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (vma->vm_flags & VM_EXEC) sync_icache_aliases(start, end); } /* * Copy user data from/to a page which is mapped into a different processes * address space. Really, we want to allow our "user space" model to handle * this. */ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *dst, const void *src, unsigned long len) { memcpy(dst, src, len); flush_ptrace_access(vma, (unsigned long)dst, (unsigned long)dst + len); } void __sync_icache_dcache(pte_t pte) { struct folio *folio = page_folio(pte_page(pte)); if (!test_bit(PG_dcache_clean, &folio->flags.f)) { sync_icache_aliases((unsigned long)folio_address(folio), (unsigned long)folio_address(folio) + folio_size(folio)); set_bit(PG_dcache_clean, &folio->flags.f); } } EXPORT_SYMBOL_GPL(__sync_icache_dcache); /* * This function is called when a page has been modified by the kernel. Mark * it as dirty for later flushing when mapped in user space (if executable, * see __sync_icache_dcache). */ void flush_dcache_folio(struct folio *folio) { if (test_bit(PG_dcache_clean, &folio->flags.f)) clear_bit(PG_dcache_clean, &folio->flags.f); } EXPORT_SYMBOL(flush_dcache_folio); void flush_dcache_page(struct page *page) { flush_dcache_folio(page_folio(page)); } EXPORT_SYMBOL(flush_dcache_page); /* * Additional functions defined in assembly. */ EXPORT_SYMBOL(caches_clean_inval_pou); #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size) { /* Ensure order against any prior non-cacheable writes */ dmb(osh); dcache_clean_pop((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_wb_cache_pmem); void arch_invalidate_pmem(void *addr, size_t size) { dcache_inval_poc((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_invalidate_pmem); #endif |
| 48 35 34 49 21 21 32 49 20 21 32 4 13 12 4 13 30 22 9 61 32 16 16 16 16 16 16 16 16 16 16 16 35 35 39 5 5 91 92 35 34 35 35 10 39 5 40 37 53 52 51 49 15 35 38 37 37 14 14 14 14 14 14 14 38 38 31 7 7 38 37 38 38 37 38 37 38 37 37 38 38 35 35 14 17 17 17 5 17 17 17 17 17 4 13 13 17 17 31 15 17 17 17 31 15 17 17 38 38 15 7 31 38 52 52 52 52 52 52 92 87 92 9 5 9 5 13 14 14 14 9 5 5 35 35 29 27 2 17 13 13 2 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 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 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic hugetlb support. * (C) Nadia Yvette Chambers, April 2004 */ #include <linux/list.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/seq_file.h> #include <linux/sysctl.h> #include <linux/highmem.h> #include <linux/mmu_notifier.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <linux/mempolicy.h> #include <linux/compiler.h> #include <linux/cpumask.h> #include <linux/cpuset.h> #include <linux/mutex.h> #include <linux/memblock.h> #include <linux/minmax.h> #include <linux/sysfs.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/mmdebug.h> #include <linux/sched/signal.h> #include <linux/rmap.h> #include <linux/string_choices.h> #include <linux/string_helpers.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/jhash.h> #include <linux/numa.h> #include <linux/llist.h> #include <linux/cma.h> #include <linux/migrate.h> #include <linux/nospec.h> #include <linux/delayacct.h> #include <linux/memory.h> #include <linux/mm_inline.h> #include <linux/padata.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/setup.h> #include <linux/io.h> #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> #include <linux/node.h> #include <linux/page_owner.h> #include "internal.h" #include "hugetlb_vmemmap.h" #include "hugetlb_cma.h" #include <linux/page-isolation.h> int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; __initdata nodemask_t hugetlb_bootmem_nodes; __initdata struct list_head huge_boot_pages[MAX_NUMNODES]; static unsigned long hstate_boot_nrinvalid[HUGE_MAX_HSTATE] __initdata; /* * Due to ordering constraints across the init code for various * architectures, hugetlb hstate cmdline parameters can't simply * be early_param. early_param might call the setup function * before valid hugetlb page sizes are determined, leading to * incorrect rejection of valid hugepagesz= options. * * So, record the parameters early and consume them whenever the * init code is ready for them, by calling hugetlb_parse_params(). */ /* one (hugepagesz=,hugepages=) pair per hstate, one default_hugepagesz */ #define HUGE_MAX_CMDLINE_ARGS (2 * HUGE_MAX_HSTATE + 1) struct hugetlb_cmdline { char *val; int (*setup)(char *val); }; /* for command line parsing */ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static bool __initdata parsed_valid_hugepagesz = true; static bool __initdata parsed_default_hugepagesz; static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata; static unsigned long hugepage_allocation_threads __initdata; static char hstate_cmdline_buf[COMMAND_LINE_SIZE] __initdata; static int hstate_cmdline_index __initdata; static struct hugetlb_cmdline hugetlb_params[HUGE_MAX_CMDLINE_ARGS] __initdata; static int hugetlb_param_index __initdata; static __init int hugetlb_add_param(char *s, int (*setup)(char *val)); static __init void hugetlb_parse_params(void); #define hugetlb_early_param(str, func) \ static __init int func##args(char *s) \ { \ return hugetlb_add_param(s, func); \ } \ early_param(str, func##args) /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, * free_huge_pages, and surplus_huge_pages. */ __cacheline_aligned_in_smp DEFINE_SPINLOCK(hugetlb_lock); /* * Serializes faults on the same logical page. This is used to * prevent spurious OOMs when the hugepage pool is fully utilized. */ static int num_fault_mutexes __ro_after_init; struct mutex *hugetlb_fault_mutex_table __ro_after_init; /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); static void hugetlb_vma_lock_free(struct vm_area_struct *vma); static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool take_locks); static struct resv_map *vma_resv_map(struct vm_area_struct *vma); static void hugetlb_free_folio(struct folio *folio) { if (folio_test_hugetlb_cma(folio)) { hugetlb_cma_free_folio(folio); return; } folio_put(folio); } static inline bool subpool_is_free(struct hugepage_subpool *spool) { if (spool->count) return false; if (spool->max_hpages != -1) return spool->used_hpages == 0; if (spool->min_hpages != -1) return spool->rsv_hpages == spool->min_hpages; return true; } static inline void unlock_or_release_subpool(struct hugepage_subpool *spool, unsigned long irq_flags) { spin_unlock_irqrestore(&spool->lock, irq_flags); /* If no pages are used, and no other handles to the subpool * remain, give up any reservations based on minimum size and * free the subpool */ if (subpool_is_free(spool)) { if (spool->min_hpages != -1) hugetlb_acct_memory(spool->hstate, -spool->min_hpages); kfree(spool); } } struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages) { struct hugepage_subpool *spool; spool = kzalloc(sizeof(*spool), GFP_KERNEL); if (!spool) return NULL; spin_lock_init(&spool->lock); spool->count = 1; spool->max_hpages = max_hpages; spool->hstate = h; spool->min_hpages = min_hpages; if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) { kfree(spool); return NULL; } spool->rsv_hpages = min_hpages; return spool; } void hugepage_put_subpool(struct hugepage_subpool *spool) { unsigned long flags; spin_lock_irqsave(&spool->lock, flags); BUG_ON(!spool->count); spool->count--; unlock_or_release_subpool(spool, flags); } /* * Subpool accounting for allocating and reserving pages. * Return -ENOMEM if there are not enough resources to satisfy the * request. Otherwise, return the number of pages by which the * global pools must be adjusted (upward). The returned value may * only be different than the passed value (delta) in the case where * a subpool minimum size must be maintained. */ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; if (!spool) return ret; spin_lock_irq(&spool->lock); if (spool->max_hpages != -1) { /* maximum size accounting */ if ((spool->used_hpages + delta) <= spool->max_hpages) spool->used_hpages += delta; else { ret = -ENOMEM; goto unlock_ret; } } /* minimum size accounting */ if (spool->min_hpages != -1 && spool->rsv_hpages) { if (delta > spool->rsv_hpages) { /* * Asking for more reserves than those already taken on * behalf of subpool. Return difference. */ ret = delta - spool->rsv_hpages; spool->rsv_hpages = 0; } else { ret = 0; /* reserves already accounted for */ spool->rsv_hpages -= delta; } } unlock_ret: spin_unlock_irq(&spool->lock); return ret; } /* * Subpool accounting for freeing and unreserving pages. * Return the number of global page reservations that must be dropped. * The return value may only be different than the passed value (delta) * in the case where a subpool minimum size must be maintained. */ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; unsigned long flags; if (!spool) return delta; spin_lock_irqsave(&spool->lock, flags); if (spool->max_hpages != -1) /* maximum size accounting */ spool->used_hpages -= delta; /* minimum size accounting */ if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) { if (spool->rsv_hpages + delta <= spool->min_hpages) ret = 0; else ret = spool->rsv_hpages + delta - spool->min_hpages; spool->rsv_hpages += delta; if (spool->rsv_hpages > spool->min_hpages) spool->rsv_hpages = spool->min_hpages; } /* * If hugetlbfs_put_super couldn't free spool due to an outstanding * quota reference, free it now. */ unlock_or_release_subpool(spool, flags); return ret; } static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) { return subpool_inode(file_inode(vma->vm_file)); } /* * hugetlb vma_lock helper routines */ void hugetlb_vma_lock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); down_read(&resv_map->rw_sema); } } void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); up_read(&resv_map->rw_sema); } } void hugetlb_vma_lock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); down_write(&resv_map->rw_sema); } } void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); up_write(&resv_map->rw_sema); } } int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; return down_write_trylock(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); return down_write_trylock(&resv_map->rw_sema); } return 1; } void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; lockdep_assert_held(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); lockdep_assert_held(&resv_map->rw_sema); } } void hugetlb_vma_lock_release(struct kref *kref) { struct hugetlb_vma_lock *vma_lock = container_of(kref, struct hugetlb_vma_lock, refs); kfree(vma_lock); } static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) { struct vm_area_struct *vma = vma_lock->vma; /* * vma_lock structure may or not be released as a result of put, * it certainly will no longer be attached to vma so clear pointer. * Semaphore synchronizes access to vma_lock->vma field. */ vma_lock->vma = NULL; vma->vm_private_data = NULL; up_write(&vma_lock->rw_sema); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); } static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; __hugetlb_vma_unlock_write_put(vma_lock); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); /* no free for anon vmas, but still need to unlock */ up_write(&resv_map->rw_sema); } } static void hugetlb_vma_lock_free(struct vm_area_struct *vma) { /* * Only present in sharable vmas. */ if (!vma || !__vma_shareable_lock(vma)) return; if (vma->vm_private_data) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); __hugetlb_vma_unlock_write_put(vma_lock); } } static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma) { struct hugetlb_vma_lock *vma_lock; /* Only establish in (flags) sharable vmas */ if (!vma || !(vma->vm_flags & VM_MAYSHARE)) return; /* Should never get here with non-NULL vm_private_data */ if (vma->vm_private_data) return; vma_lock = kmalloc(sizeof(*vma_lock), GFP_KERNEL); if (!vma_lock) { /* * If we can not allocate structure, then vma can not * participate in pmd sharing. This is only a possible * performance enhancement and memory saving issue. * However, the lock is also used to synchronize page * faults with truncation. If the lock is not present, * unlikely races could leave pages in a file past i_size * until the file is removed. Warn in the unlikely case of * allocation failure. */ pr_warn_once("HugeTLB: unable to allocate vma specific lock\n"); return; } kref_init(&vma_lock->refs); init_rwsem(&vma_lock->rw_sema); vma_lock->vma = vma; vma->vm_private_data = vma_lock; } /* Helper that removes a struct file_region from the resv_map cache and returns * it for use. */ static struct file_region * get_file_region_entry_from_cache(struct resv_map *resv, long from, long to) { struct file_region *nrg; VM_BUG_ON(resv->region_cache_count <= 0); resv->region_cache_count--; nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); nrg->from = from; nrg->to = to; return nrg; } static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg, struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB nrg->reservation_counter = rg->reservation_counter; nrg->css = rg->css; if (rg->css) css_get(rg->css); #endif } /* Helper that records hugetlb_cgroup uncharge info. */ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, struct hstate *h, struct resv_map *resv, struct file_region *nrg) { #ifdef CONFIG_CGROUP_HUGETLB if (h_cg) { nrg->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; /* * The caller will hold exactly one h_cg->css reference for the * whole contiguous reservation region. But this area might be * scattered when there are already some file_regions reside in * it. As a result, many file_regions may share only one css * reference. In order to ensure that one file_region must hold * exactly one h_cg->css reference, we should do css_get for * each file_region and leave the reference held by caller * untouched. */ css_get(&h_cg->css); if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h); /* pages_per_hpage should be the same for all entries in * a resv_map. */ VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h)); } else { nrg->reservation_counter = NULL; nrg->css = NULL; } #endif } static void put_uncharge_info(struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB if (rg->css) css_put(rg->css); #endif } static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { #ifdef CONFIG_CGROUP_HUGETLB return rg->reservation_counter == org->reservation_counter && rg->css == org->css; #else return true; #endif } static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) { struct file_region *nrg, *prg; prg = list_prev_entry(rg, link); if (&prg->link != &resv->regions && prg->to == rg->from && has_same_uncharge_info(prg, rg)) { prg->to = rg->to; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); rg = prg; } nrg = list_next_entry(rg, link); if (&nrg->link != &resv->regions && nrg->from == rg->to && has_same_uncharge_info(nrg, rg)) { nrg->from = rg->from; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); } } static inline long hugetlb_resv_map_add(struct resv_map *map, struct list_head *rg, long from, long to, struct hstate *h, struct hugetlb_cgroup *cg, long *regions_needed) { struct file_region *nrg; if (!regions_needed) { nrg = get_file_region_entry_from_cache(map, from, to); record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg); list_add(&nrg->link, rg); coalesce_file_region(map, nrg); } else *regions_needed += 1; return to - from; } /* * Must be called with resv->lock held. * * Calling this with regions_needed != NULL will count the number of pages * to be added but will not modify the linked list. And regions_needed will * indicate the number of file_regions needed in the cache to carry out to add * the regions for this range. */ static long add_reservation_in_range(struct resv_map *resv, long f, long t, struct hugetlb_cgroup *h_cg, struct hstate *h, long *regions_needed) { long add = 0; struct list_head *head = &resv->regions; long last_accounted_offset = f; struct file_region *iter, *trg = NULL; struct list_head *rg = NULL; if (regions_needed) *regions_needed = 0; /* In this loop, we essentially handle an entry for the range * [last_accounted_offset, iter->from), at every iteration, with some * bounds checking. */ list_for_each_entry_safe(iter, trg, head, link) { /* Skip irrelevant regions that start before our range. */ if (iter->from < f) { /* If this region ends after the last accounted offset, * then we need to update last_accounted_offset. */ if (iter->to > last_accounted_offset) last_accounted_offset = iter->to; continue; } /* When we find a region that starts beyond our range, we've * finished. */ if (iter->from >= t) { rg = iter->link.prev; break; } /* Add an entry for last_accounted_offset -> iter->from, and * update last_accounted_offset. */ if (iter->from > last_accounted_offset) add += hugetlb_resv_map_add(resv, iter->link.prev, last_accounted_offset, iter->from, h, h_cg, regions_needed); last_accounted_offset = iter->to; } /* Handle the case where our range extends beyond * last_accounted_offset. */ if (!rg) rg = head->prev; if (last_accounted_offset < t) add += hugetlb_resv_map_add(resv, rg, last_accounted_offset, t, h, h_cg, regions_needed); return add; } /* Must be called with resv->lock acquired. Will drop lock to allocate entries. */ static int allocate_file_region_entries(struct resv_map *resv, int regions_needed) __must_hold(&resv->lock) { LIST_HEAD(allocated_regions); int to_allocate = 0, i = 0; struct file_region *trg = NULL, *rg = NULL; VM_BUG_ON(regions_needed < 0); /* * Check for sufficient descriptors in the cache to accommodate * the number of in progress add operations plus regions_needed. * * This is a while loop because when we drop the lock, some other call * to region_add or region_del may have consumed some region_entries, * so we keep looping here until we finally have enough entries for * (adds_in_progress + regions_needed). */ while (resv->region_cache_count < (resv->adds_in_progress + regions_needed)) { to_allocate = resv->adds_in_progress + regions_needed - resv->region_cache_count; /* At this point, we should have enough entries in the cache * for all the existing adds_in_progress. We should only be * needing to allocate for regions_needed. */ VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress); spin_unlock(&resv->lock); for (i = 0; i < to_allocate; i++) { trg = kmalloc(sizeof(*trg), GFP_KERNEL); if (!trg) goto out_of_memory; list_add(&trg->link, &allocated_regions); } spin_lock(&resv->lock); list_splice(&allocated_regions, &resv->region_cache); resv->region_cache_count += to_allocate; } return 0; out_of_memory: list_for_each_entry_safe(rg, trg, &allocated_regions, link) { list_del(&rg->link); kfree(rg); } return -ENOMEM; } /* * Add the huge page range represented by [f, t) to the reserve * map. Regions will be taken from the cache to fill in this range. * Sufficient regions should exist in the cache due to the previous * call to region_chg with the same range, but in some cases the cache will not * have sufficient entries due to races with other code doing region_add or * region_del. The extra needed entries will be allocated. * * regions_needed is the out value provided by a previous call to region_chg. * * Return the number of new huge pages added to the map. This number is greater * than or equal to zero. If file_region entries needed to be allocated for * this operation and we were not able to allocate, it returns -ENOMEM. * region_add of regions of length 1 never allocate file_regions and cannot * fail; region_chg will always allocate at least 1 entry and a region_add for * 1 page will only require at most 1 entry. */ static long region_add(struct resv_map *resv, long f, long t, long in_regions_needed, struct hstate *h, struct hugetlb_cgroup *h_cg) { long add = 0, actual_regions_needed = 0; spin_lock(&resv->lock); retry: /* Count how many regions are actually needed to execute this add. */ add_reservation_in_range(resv, f, t, NULL, NULL, &actual_regions_needed); /* * Check for sufficient descriptors in the cache to accommodate * this add operation. Note that actual_regions_needed may be greater * than in_regions_needed, as the resv_map may have been modified since * the region_chg call. In this case, we need to make sure that we * allocate extra entries, such that we have enough for all the * existing adds_in_progress, plus the excess needed for this * operation. */ if (actual_regions_needed > in_regions_needed && resv->region_cache_count < resv->adds_in_progress + (actual_regions_needed - in_regions_needed)) { /* region_add operation of range 1 should never need to * allocate file_region entries. */ VM_BUG_ON(t - f <= 1); if (allocate_file_region_entries( resv, actual_regions_needed - in_regions_needed)) { return -ENOMEM; } goto retry; } add = add_reservation_in_range(resv, f, t, h_cg, h, NULL); resv->adds_in_progress -= in_regions_needed; spin_unlock(&resv->lock); return add; } /* * Examine the existing reserve map and determine how many * huge pages in the specified range [f, t) are NOT currently * represented. This routine is called before a subsequent * call to region_add that will actually modify the reserve * map to add the specified range [f, t). region_chg does * not change the number of huge pages represented by the * map. A number of new file_region structures is added to the cache as a * placeholder, for the subsequent region_add call to use. At least 1 * file_region structure is added. * * out_regions_needed is the number of regions added to the * resv->adds_in_progress. This value needs to be provided to a follow up call * to region_add or region_abort for proper accounting. * * Returns the number of huge pages that need to be added to the existing * reservation map for the range [f, t). This number is greater or equal to * zero. -ENOMEM is returned if a new file_region structure or cache entry * is needed and can not be allocated. */ static long region_chg(struct resv_map *resv, long f, long t, long *out_regions_needed) { long chg = 0; spin_lock(&resv->lock); /* Count how many hugepages in this range are NOT represented. */ chg = add_reservation_in_range(resv, f, t, NULL, NULL, out_regions_needed); if (*out_regions_needed == 0) *out_regions_needed = 1; if (allocate_file_region_entries(resv, *out_regions_needed)) return -ENOMEM; resv->adds_in_progress += *out_regions_needed; spin_unlock(&resv->lock); return chg; } /* * Abort the in progress add operation. The adds_in_progress field * of the resv_map keeps track of the operations in progress between * calls to region_chg and region_add. Operations are sometimes * aborted after the call to region_chg. In such cases, region_abort * is called to decrement the adds_in_progress counter. regions_needed * is the value returned by the region_chg call, it is used to decrement * the adds_in_progress counter. * * NOTE: The range arguments [f, t) are not needed or used in this * routine. They are kept to make reading the calling code easier as * arguments will match the associated region_chg call. */ static void region_abort(struct resv_map *resv, long f, long t, long regions_needed) { spin_lock(&resv->lock); VM_BUG_ON(!resv->region_cache_count); resv->adds_in_progress -= regions_needed; spin_unlock(&resv->lock); } /* * Delete the specified range [f, t) from the reserve map. If the * t parameter is LONG_MAX, this indicates that ALL regions after f * should be deleted. Locate the regions which intersect [f, t) * and either trim, delete or split the existing regions. * * Returns the number of huge pages deleted from the reserve map. * In the normal case, the return value is zero or more. In the * case where a region must be split, a new region descriptor must * be allocated. If the allocation fails, -ENOMEM will be returned. * NOTE: If the parameter t == LONG_MAX, then we will never split * a region and possibly return -ENOMEM. Callers specifying * t == LONG_MAX do not need to check for -ENOMEM error. */ static long region_del(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg, *trg; struct file_region *nrg = NULL; long del = 0; retry: spin_lock(&resv->lock); list_for_each_entry_safe(rg, trg, head, link) { /* * Skip regions before the range to be deleted. file_region * ranges are normally of the form [from, to). However, there * may be a "placeholder" entry in the map which is of the form * (from, to) with from == to. Check for placeholder entries * at the beginning of the range to be deleted. */ if (rg->to <= f && (rg->to != rg->from || rg->to != f)) continue; if (rg->from >= t) break; if (f > rg->from && t < rg->to) { /* Must split region */ /* * Check for an entry in the cache before dropping * lock and attempting allocation. */ if (!nrg && resv->region_cache_count > resv->adds_in_progress) { nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); resv->region_cache_count--; } if (!nrg) { spin_unlock(&resv->lock); nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); if (!nrg) return -ENOMEM; goto retry; } del += t - f; hugetlb_cgroup_uncharge_file_region( resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; nrg->to = rg->to; copy_hugetlb_cgroup_uncharge_info(nrg, rg); INIT_LIST_HEAD(&nrg->link); /* Original entry is trimmed */ rg->to = f; list_add(&nrg->link, &rg->link); nrg = NULL; break; } if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; } if (f <= rg->from) { /* Trim beginning of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, t - rg->from, false); del += t - rg->from; rg->from = t; } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - f, false); del += rg->to - f; rg->to = f; } } spin_unlock(&resv->lock); kfree(nrg); return del; } /* * A rare out of memory error was encountered which prevented removal of * the reserve map region for a page. The huge page itself was free'ed * and removed from the page cache. This routine will adjust the subpool * usage count, and the global reserve count if needed. By incrementing * these counts, the reserve map entry which could not be deleted will * appear as a "reserved" entry instead of simply dangling with incorrect * counts. */ void hugetlb_fix_reserve_counts(struct inode *inode) { struct hugepage_subpool *spool = subpool_inode(inode); long rsv_adjust; bool reserved = false; rsv_adjust = hugepage_subpool_get_pages(spool, 1); if (rsv_adjust > 0) { struct hstate *h = hstate_inode(inode); if (!hugetlb_acct_memory(h, 1)) reserved = true; } else if (!rsv_adjust) { reserved = true; } if (!reserved) pr_warn("hugetlb: Huge Page Reserved count may go negative.\n"); } /* * Count and return the number of huge pages in the reserve map * that intersect with the range [f, t). */ static long region_count(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg; long chg = 0; spin_lock(&resv->lock); /* Locate each segment we overlap with, and count that overlap. */ list_for_each_entry(rg, head, link) { long seg_from; long seg_to; if (rg->to <= f) continue; if (rg->from >= t) break; seg_from = max(rg->from, f); seg_to = min(rg->to, t); chg += seg_to - seg_from; } spin_unlock(&resv->lock); return chg; } /* * Convert the address within this vma to the page offset within * the mapping, huge page units here. */ static pgoff_t vma_hugecache_offset(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return ((address - vma->vm_start) >> huge_page_shift(h)) + (vma->vm_pgoff >> huge_page_order(h)); } /** * vma_kernel_pagesize - Page size granularity for this VMA. * @vma: The user mapping. * * Folios in this VMA will be aligned to, and at least the size of the * number of bytes returned by this function. * * Return: The default size of the folios allocated when backing a VMA. */ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { if (vma->vm_ops && vma->vm_ops->pagesize) return vma->vm_ops->pagesize(vma); return PAGE_SIZE; } EXPORT_SYMBOL_GPL(vma_kernel_pagesize); /* * Return the page size being used by the MMU to back a VMA. In the majority * of cases, the page size used by the kernel matches the MMU size. On * architectures where it differs, an architecture-specific 'strong' * version of this symbol is required. */ __weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return vma_kernel_pagesize(vma); } /* * Flags for MAP_PRIVATE reservations. These are stored in the bottom * bits of the reservation map pointer, which are always clear due to * alignment. */ #define HPAGE_RESV_OWNER (1UL << 0) #define HPAGE_RESV_UNMAPPED (1UL << 1) #define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED) /* * These helpers are used to track how many pages are reserved for * faults in a MAP_PRIVATE mapping. Only the process that called mmap() * is guaranteed to have their future faults succeed. * * With the exception of hugetlb_dup_vma_private() which is called at fork(), * the reserve counters are updated with the hugetlb_lock held. It is safe * to reset the VMA at fork() time as it is not in use yet and there is no * chance of the global counters getting corrupted as a result of the values. * * The private mapping reservation is represented in a subtly different * manner to a shared mapping. A shared mapping has a region map associated * with the underlying file, this region map represents the backing file * pages which have ever had a reservation assigned which this persists even * after the page is instantiated. A private mapping has a region map * associated with the original mmap which is attached to all VMAs which * reference it, this region map represents those offsets which have consumed * reservation ie. where pages have been instantiated. */ static unsigned long get_vma_private_data(struct vm_area_struct *vma) { return (unsigned long)vma->vm_private_data; } static void set_vma_private_data(struct vm_area_struct *vma, unsigned long value) { vma->vm_private_data = (void *)value; } static void resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map, struct hugetlb_cgroup *h_cg, struct hstate *h) { #ifdef CONFIG_CGROUP_HUGETLB if (!h_cg || !h) { resv_map->reservation_counter = NULL; resv_map->pages_per_hpage = 0; resv_map->css = NULL; } else { resv_map->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; resv_map->pages_per_hpage = pages_per_huge_page(h); resv_map->css = &h_cg->css; } #endif } struct resv_map *resv_map_alloc(void) { struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL); struct file_region *rg = kmalloc(sizeof(*rg), GFP_KERNEL); if (!resv_map || !rg) { kfree(resv_map); kfree(rg); return NULL; } kref_init(&resv_map->refs); spin_lock_init(&resv_map->lock); INIT_LIST_HEAD(&resv_map->regions); init_rwsem(&resv_map->rw_sema); resv_map->adds_in_progress = 0; /* * Initialize these to 0. On shared mappings, 0's here indicate these * fields don't do cgroup accounting. On private mappings, these will be * re-initialized to the proper values, to indicate that hugetlb cgroup * reservations are to be un-charged from here. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL); INIT_LIST_HEAD(&resv_map->region_cache); list_add(&rg->link, &resv_map->region_cache); resv_map->region_cache_count = 1; return resv_map; } void resv_map_release(struct kref *ref) { struct resv_map *resv_map = container_of(ref, struct resv_map, refs); struct list_head *head = &resv_map->region_cache; struct file_region *rg, *trg; /* Clear out any active regions before we release the map. */ region_del(resv_map, 0, LONG_MAX); /* ... and any entries left in the cache */ list_for_each_entry_safe(rg, trg, head, link) { list_del(&rg->link); kfree(rg); } VM_BUG_ON(resv_map->adds_in_progress); kfree(resv_map); } static inline struct resv_map *inode_resv_map(struct inode *inode) { /* * At inode evict time, i_mapping may not point to the original * address space within the inode. This original address space * contains the pointer to the resv_map. So, always use the * address space embedded within the inode. * The VERY common case is inode->mapping == &inode->i_data but, * this may not be true for device special inodes. */ return (struct resv_map *)(&inode->i_data)->i_private_data; } static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); if (vma->vm_flags & VM_MAYSHARE) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; return inode_resv_map(inode); } else { return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); } } static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, (unsigned long)map); } static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, get_vma_private_data(vma) | flags); } static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); return (get_vma_private_data(vma) & flag) != 0; } bool __vma_private_lock(struct vm_area_struct *vma) { return !(vma->vm_flags & VM_MAYSHARE) && get_vma_private_data(vma) & ~HPAGE_RESV_MASK && is_vma_resv_set(vma, HPAGE_RESV_OWNER); } void hugetlb_dup_vma_private(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); /* * Clear vm_private_data * - For shared mappings this is a per-vma semaphore that may be * allocated in a subsequent call to hugetlb_vm_op_open. * Before clearing, make sure pointer is not associated with vma * as this will leak the structure. This is the case when called * via clear_vma_resv_huge_pages() and hugetlb_vm_op_open has already * been called to allocate a new structure. * - For MAP_PRIVATE mappings, this is the reserve map which does * not apply to children. Faults generated by the children are * not guaranteed to succeed, even if read-only. */ if (vma->vm_flags & VM_MAYSHARE) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; if (vma_lock && vma_lock->vma != vma) vma->vm_private_data = NULL; } else vma->vm_private_data = NULL; } /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. * This function should be only used by mremap and operate on * same sized vma. It should never come here with last ref on the * reservation. */ void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { /* * Clear the old hugetlb private page reservation. * It has already been transferred to new_vma. * * During a mremap() operation of a hugetlb vma we call move_vma() * which copies vma into new_vma and unmaps vma. After the copy * operation both new_vma and vma share a reference to the resv_map * struct, and at that point vma is about to be unmapped. We don't * want to return the reservation to the pool at unmap of vma because * the reservation still lives on in new_vma, so simply decrement the * ref here and remove the resv_map reference from this vma. */ struct resv_map *reservations = vma_resv_map(vma); if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_put_hugetlb_cgroup_uncharge_info(reservations); kref_put(&reservations->refs, resv_map_release); } hugetlb_dup_vma_private(vma); } static void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio) { int nid = folio_nid(folio); lockdep_assert_held(&hugetlb_lock); VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); list_move(&folio->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; folio_set_hugetlb_freed(folio); } static struct folio *dequeue_hugetlb_folio_node_exact(struct hstate *h, int nid) { struct folio *folio; bool pin = !!(current->flags & PF_MEMALLOC_PIN); lockdep_assert_held(&hugetlb_lock); list_for_each_entry(folio, &h->hugepage_freelists[nid], lru) { if (pin && !folio_is_longterm_pinnable(folio)) continue; if (folio_test_hwpoison(folio)) continue; if (is_migrate_isolate_page(&folio->page)) continue; list_move(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); folio_clear_hugetlb_freed(folio); h->free_huge_pages--; h->free_huge_pages_node[nid]--; return folio; } return NULL; } static struct folio *dequeue_hugetlb_folio_nodemask(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { unsigned int cpuset_mems_cookie; struct zonelist *zonelist; struct zone *zone; struct zoneref *z; int node = NUMA_NO_NODE; /* 'nid' should not be NUMA_NO_NODE. Try to catch any misuse of it and rectifiy. */ if (nid == NUMA_NO_NODE) nid = numa_node_id(); zonelist = node_zonelist(nid, gfp_mask); retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) { struct folio *folio; if (!cpuset_zone_allowed(zone, gfp_mask)) continue; /* * no need to ask again on the same node. Pool is node rather than * zone aware */ if (zone_to_nid(zone) == node) continue; node = zone_to_nid(zone); folio = dequeue_hugetlb_folio_node_exact(h, node); if (folio) return folio; } if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return NULL; } static unsigned long available_huge_pages(struct hstate *h) { return h->free_huge_pages - h->resv_huge_pages; } static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, long gbl_chg) { struct folio *folio = NULL; struct mempolicy *mpol; gfp_t gfp_mask; nodemask_t *nodemask; int nid; /* * gbl_chg==1 means the allocation requires a new page that was not * reserved before. Making sure there's at least one free page. */ if (gbl_chg && !available_huge_pages(h)) goto err; gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); mpol_cond_put(mpol); return folio; err: return NULL; } /* * common helper functions for hstate_next_node_to_{alloc|free}. * We may have allocated or freed a huge page based on a different * nodes_allowed previously, so h->next_node_to_{alloc|free} might * be outside of *nodes_allowed. Ensure that we use an allowed * node for alloc or free. */ static int next_node_allowed(int nid, nodemask_t *nodes_allowed) { nid = next_node_in(nid, *nodes_allowed); VM_BUG_ON(nid >= MAX_NUMNODES); return nid; } static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed) { if (!node_isset(nid, *nodes_allowed)) nid = next_node_allowed(nid, nodes_allowed); return nid; } /* * returns the previously saved node ["this node"] from which to * allocate a persistent huge page for the pool and advance the * next node from which to allocate, handling wrap at end of node * mask. */ static int hstate_next_node_to_alloc(int *next_node, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(*next_node, nodes_allowed); *next_node = next_node_allowed(nid, nodes_allowed); return nid; } /* * helper for remove_pool_hugetlb_folio() - return the previously saved * node ["this node"] from which to free a huge page. Advance the * next node id whether or not we find a free huge page to free so * that the next attempt to free addresses the next node. */ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) { int nid; VM_BUG_ON(!nodes_allowed); nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed); h->next_nid_to_free = next_node_allowed(nid, nodes_allowed); return nid; } #define for_each_node_mask_to_alloc(next_node, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_alloc(next_node, mask)) || 1); \ nr_nodes--) #define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \ for (nr_nodes = nodes_weight(*mask); \ nr_nodes > 0 && \ ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE #ifdef CONFIG_CONTIG_ALLOC static struct folio *alloc_gigantic_folio(int order, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { struct folio *folio; bool retried = false; retry: folio = hugetlb_cma_alloc_folio(order, gfp_mask, nid, nodemask); if (!folio) { if (hugetlb_cma_exclusive_alloc()) return NULL; folio = folio_alloc_gigantic(order, gfp_mask, nid, nodemask); if (!folio) return NULL; } if (folio_ref_freeze(folio, 1)) return folio; pr_warn("HugeTLB: unexpected refcount on PFN %lu\n", folio_pfn(folio)); hugetlb_free_folio(folio); if (!retried) { retried = true; goto retry; } return NULL; } #else /* !CONFIG_CONTIG_ALLOC */ static struct folio *alloc_gigantic_folio(int order, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } #endif /* CONFIG_CONTIG_ALLOC */ #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */ static struct folio *alloc_gigantic_folio(int order, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } #endif /* * Remove hugetlb folio from lists. * If vmemmap exists for the folio, clear the hugetlb flag so that the * folio appears as just a compound page. Otherwise, wait until after * allocating vmemmap to clear the flag. * * Must be called with hugetlb lock held. */ static void remove_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { int nid = folio_nid(folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio(folio), folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio_rsvd(folio), folio); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; list_del(&folio->lru); if (folio_test_hugetlb_freed(folio)) { folio_clear_hugetlb_freed(folio); h->free_huge_pages--; h->free_huge_pages_node[nid]--; } if (adjust_surplus) { h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; } /* * We can only clear the hugetlb flag after allocating vmemmap * pages. Otherwise, someone (memory error handling) may try to write * to tail struct pages. */ if (!folio_test_hugetlb_vmemmap_optimized(folio)) __folio_clear_hugetlb(folio); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; } static void add_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { int nid = folio_nid(folio); VM_BUG_ON_FOLIO(!folio_test_hugetlb_vmemmap_optimized(folio), folio); lockdep_assert_held(&hugetlb_lock); INIT_LIST_HEAD(&folio->lru); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; if (adjust_surplus) { h->surplus_huge_pages++; h->surplus_huge_pages_node[nid]++; } __folio_set_hugetlb(folio); folio_change_private(folio, NULL); /* * We have to set hugetlb_vmemmap_optimized again as above * folio_change_private(folio, NULL) cleared it. */ folio_set_hugetlb_vmemmap_optimized(folio); arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); } static void __update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio) { bool clear_flag = folio_test_hugetlb_vmemmap_optimized(folio); if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; /* * If we don't know which subpages are hwpoisoned, we can't free * the hugepage, so it's leaked intentionally. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return; /* * If folio is not vmemmap optimized (!clear_flag), then the folio * is no longer identified as a hugetlb page. hugetlb_vmemmap_restore_folio * can only be passed hugetlb pages and will BUG otherwise. */ if (clear_flag && hugetlb_vmemmap_restore_folio(h, folio)) { spin_lock_irq(&hugetlb_lock); /* * If we cannot allocate vmemmap pages, just refuse to free the * page and put the page back on the hugetlb free list and treat * as a surplus page. */ add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); return; } /* * If vmemmap pages were allocated above, then we need to clear the * hugetlb flag under the hugetlb lock. */ if (folio_test_hugetlb(folio)) { spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } /* * Move PageHWPoison flag from head page to the raw error pages, * which makes any healthy subpages reusable. */ if (unlikely(folio_test_hwpoison(folio))) folio_clear_hugetlb_hwpoison(folio); folio_ref_unfreeze(folio, 1); hugetlb_free_folio(folio); } /* * As update_and_free_hugetlb_folio() can be called under any context, so we cannot * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate * the vmemmap pages. * * free_hpage_workfn() locklessly retrieves the linked list of pages to be * freed and frees them one-by-one. As the page->mapping pointer is going * to be cleared in free_hpage_workfn() anyway, it is reused as the llist_node * structure of a lockless linked list of huge pages to be freed. */ static LLIST_HEAD(hpage_freelist); static void free_hpage_workfn(struct work_struct *work) { struct llist_node *node; node = llist_del_all(&hpage_freelist); while (node) { struct folio *folio; struct hstate *h; folio = container_of((struct address_space **)node, struct folio, mapping); node = node->next; folio->mapping = NULL; /* * The VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio) in * folio_hstate() is going to trigger because a previous call to * remove_hugetlb_folio() will clear the hugetlb bit, so do * not use folio_hstate() directly. */ h = size_to_hstate(folio_size(folio)); __update_and_free_hugetlb_folio(h, folio); cond_resched(); } } static DECLARE_WORK(free_hpage_work, free_hpage_workfn); static inline void flush_free_hpage_work(struct hstate *h) { if (hugetlb_vmemmap_optimizable(h)) flush_work(&free_hpage_work); } static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio, bool atomic) { if (!folio_test_hugetlb_vmemmap_optimized(folio) || !atomic) { __update_and_free_hugetlb_folio(h, folio); return; } /* * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages. * * Only call schedule_work() if hpage_freelist is previously * empty. Otherwise, schedule_work() had been called but the workfn * hasn't retrieved the list yet. */ if (llist_add((struct llist_node *)&folio->mapping, &hpage_freelist)) schedule_work(&free_hpage_work); } static void bulk_vmemmap_restore_error(struct hstate *h, struct list_head *folio_list, struct list_head *non_hvo_folios) { struct folio *folio, *t_folio; if (!list_empty(non_hvo_folios)) { /* * Free any restored hugetlb pages so that restore of the * entire list can be retried. * The idea is that in the common case of ENOMEM errors freeing * hugetlb pages with vmemmap we will free up memory so that we * can allocate vmemmap for more hugetlb pages. */ list_for_each_entry_safe(folio, t_folio, non_hvo_folios, lru) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } else { /* * In the case where there are no folios which can be * immediately freed, we loop through the list trying to restore * vmemmap individually in the hope that someone elsewhere may * have done something to cause success (such as freeing some * memory). If unable to restore a hugetlb page, the hugetlb * page is made a surplus page and removed from the list. * If are able to restore vmemmap and free one hugetlb page, we * quit processing the list to retry the bulk operation. */ list_for_each_entry_safe(folio, t_folio, folio_list, lru) if (hugetlb_vmemmap_restore_folio(h, folio)) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); } else { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); break; } } } static void update_and_free_pages_bulk(struct hstate *h, struct list_head *folio_list) { long ret; struct folio *folio, *t_folio; LIST_HEAD(non_hvo_folios); /* * First allocate required vmemmmap (if necessary) for all folios. * Carefully handle errors and free up any available hugetlb pages * in an effort to make forward progress. */ retry: ret = hugetlb_vmemmap_restore_folios(h, folio_list, &non_hvo_folios); if (ret < 0) { bulk_vmemmap_restore_error(h, folio_list, &non_hvo_folios); goto retry; } /* * At this point, list should be empty, ret should be >= 0 and there * should only be pages on the non_hvo_folios list. * Do note that the non_hvo_folios list could be empty. * Without HVO enabled, ret will be 0 and there is no need to call * __folio_clear_hugetlb as this was done previously. */ VM_WARN_ON(!list_empty(folio_list)); VM_WARN_ON(ret < 0); if (!list_empty(&non_hvo_folios) && ret) { spin_lock_irq(&hugetlb_lock); list_for_each_entry(folio, &non_hvo_folios, lru) __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } list_for_each_entry_safe(folio, t_folio, &non_hvo_folios, lru) { update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } struct hstate *size_to_hstate(unsigned long size) { struct hstate *h; for_each_hstate(h) { if (huge_page_size(h) == size) return h; } return NULL; } void free_huge_folio(struct folio *folio) { /* * Can't pass hstate in here because it is called from the * generic mm code. */ struct hstate *h = folio_hstate(folio); int nid = folio_nid(folio); struct hugepage_subpool *spool = hugetlb_folio_subpool(folio); bool restore_reserve; unsigned long flags; VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); VM_BUG_ON_FOLIO(folio_mapcount(folio), folio); hugetlb_set_folio_subpool(folio, NULL); if (folio_test_anon(folio)) __ClearPageAnonExclusive(&folio->page); folio->mapping = NULL; restore_reserve = folio_test_hugetlb_restore_reserve(folio); folio_clear_hugetlb_restore_reserve(folio); /* * If HPageRestoreReserve was set on page, page allocation consumed a * reservation. If the page was associated with a subpool, there * would have been a page reserved in the subpool before allocation * via hugepage_subpool_get_pages(). Since we are 'restoring' the * reservation, do not call hugepage_subpool_put_pages() as this will * remove the reserved page from the subpool. */ if (!restore_reserve) { /* * A return code of zero implies that the subpool will be * under its minimum size if the reservation is not restored * after page is free. Therefore, force restore_reserve * operation. */ if (hugepage_subpool_put_pages(spool, 1) == 0) restore_reserve = true; } spin_lock_irqsave(&hugetlb_lock, flags); folio_clear_hugetlb_migratable(folio); hugetlb_cgroup_uncharge_folio(hstate_index(h), pages_per_huge_page(h), folio); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); lruvec_stat_mod_folio(folio, NR_HUGETLB, -pages_per_huge_page(h)); mem_cgroup_uncharge(folio); if (restore_reserve) h->resv_huge_pages++; if (folio_test_hugetlb_temporary(folio)) { remove_hugetlb_folio(h, folio, false); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ remove_hugetlb_folio(h, folio, true); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else { arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } /* * Must be called with the hugetlb lock held */ static void account_new_hugetlb_folio(struct hstate *h, struct folio *folio) { lockdep_assert_held(&hugetlb_lock); h->nr_huge_pages++; h->nr_huge_pages_node[folio_nid(folio)]++; } static void init_new_hugetlb_folio(struct folio *folio) { __folio_set_hugetlb(folio); INIT_LIST_HEAD(&folio->lru); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); set_hugetlb_cgroup_rsvd(folio, NULL); } /* * Find and lock address space (mapping) in write mode. * * Upon entry, the folio is locked which means that folio_mapping() is * stable. Due to locking order, we can only trylock_write. If we can * not get the lock, simply return NULL to caller. */ struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (!mapping) return mapping; if (i_mmap_trylock_write(mapping)) return mapping; return NULL; } static struct folio *alloc_buddy_hugetlb_folio(int order, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; bool alloc_try_hard = true; /* * By default we always try hard to allocate the folio with * __GFP_RETRY_MAYFAIL flag. However, if we are allocating folios in * a loop (to adjust global huge page counts) and previous allocation * failed, do not continue to try hard on the same node. Use the * node_alloc_noretry bitmap to manage this state information. */ if (node_alloc_noretry && node_isset(nid, *node_alloc_noretry)) alloc_try_hard = false; if (alloc_try_hard) gfp_mask |= __GFP_RETRY_MAYFAIL; folio = (struct folio *)__alloc_frozen_pages(gfp_mask, order, nid, nmask); /* * If we did not specify __GFP_RETRY_MAYFAIL, but still got a * folio this indicates an overall state change. Clear bit so * that we resume normal 'try hard' allocations. */ if (node_alloc_noretry && folio && !alloc_try_hard) node_clear(nid, *node_alloc_noretry); /* * If we tried hard to get a folio but failed, set bit so that * subsequent attempts will not try as hard until there is an * overall state change. */ if (node_alloc_noretry && !folio && alloc_try_hard) node_set(nid, *node_alloc_noretry); if (!folio) { __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); return NULL; } __count_vm_event(HTLB_BUDDY_PGALLOC); return folio; } static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; int order = huge_page_order(h); if (nid == NUMA_NO_NODE) nid = numa_mem_id(); if (order_is_gigantic(order)) folio = alloc_gigantic_folio(order, gfp_mask, nid, nmask); else folio = alloc_buddy_hugetlb_folio(order, gfp_mask, nid, nmask, node_alloc_noretry); if (folio) init_new_hugetlb_folio(folio); return folio; } /* * Common helper to allocate a fresh hugetlb folio. All specific allocators * should use this function to get new hugetlb folio * * Note that returned folio is 'frozen': ref count of head page and all tail * pages is zero, and the accounting must be done in the caller. */ static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); if (folio) hugetlb_vmemmap_optimize_folio(h, folio); return folio; } static void prep_and_add_allocated_folios(struct hstate *h, struct list_head *folio_list) { unsigned long flags; struct folio *folio, *tmp_f; /* Send list for bulk vmemmap optimization processing */ hugetlb_vmemmap_optimize_folios(h, folio_list); /* Add all new pool pages to free lists in one lock cycle */ spin_lock_irqsave(&hugetlb_lock, flags); list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { account_new_hugetlb_folio(h, folio); enqueue_hugetlb_folio(h, folio); } spin_unlock_irqrestore(&hugetlb_lock, flags); } /* * Allocates a fresh hugetlb page in a node interleaved manner. The page * will later be added to the appropriate hugetlb pool. */ static struct folio *alloc_pool_huge_folio(struct hstate *h, nodemask_t *nodes_allowed, nodemask_t *node_alloc_noretry, int *next_node) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; int nr_nodes, node; for_each_node_mask_to_alloc(next_node, nr_nodes, node, nodes_allowed) { struct folio *folio; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, node, nodes_allowed, node_alloc_noretry); if (folio) return folio; } return NULL; } /* * Remove huge page from pool from next node to free. Attempt to keep * persistent huge pages more or less balanced over allowed nodes. * This routine only 'removes' the hugetlb page. The caller must make * an additional call to free the page to low level allocators. * Called with hugetlb_lock locked. */ static struct folio *remove_pool_hugetlb_folio(struct hstate *h, nodemask_t *nodes_allowed, bool acct_surplus) { int nr_nodes, node; struct folio *folio = NULL; lockdep_assert_held(&hugetlb_lock); for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * If we're returning unused surplus pages, only examine * nodes with surplus pages. */ if ((!acct_surplus || h->surplus_huge_pages_node[node]) && !list_empty(&h->hugepage_freelists[node])) { folio = list_entry(h->hugepage_freelists[node].next, struct folio, lru); remove_hugetlb_folio(h, folio, acct_surplus); break; } } return folio; } /* * Dissolve a given free hugetlb folio into free buddy pages. This function * does nothing for in-use hugetlb folios and non-hugetlb folios. * This function returns values like below: * * -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages * when the system is under memory pressure and the feature of * freeing unused vmemmap pages associated with each hugetlb page * is enabled. * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use * (allocated or reserved.) * 0: successfully dissolved free hugepages or the page is not a * hugepage (considered as already dissolved) */ int dissolve_free_hugetlb_folio(struct folio *folio) { int rc = -EBUSY; retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (!folio_test_hugetlb(folio)) return 0; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio)) { rc = 0; goto out; } if (!folio_ref_count(folio)) { struct hstate *h = folio_hstate(folio); bool adjust_surplus = false; if (!available_huge_pages(h)) goto out; /* * We should make sure that the page is already on the free list * when it is dissolved. */ if (unlikely(!folio_test_hugetlb_freed(folio))) { spin_unlock_irq(&hugetlb_lock); cond_resched(); /* * Theoretically, we should return -EBUSY when we * encounter this race. In fact, we have a chance * to successfully dissolve the page if we do a * retry. Because the race window is quite small. * If we seize this opportunity, it is an optimization * for increasing the success rate of dissolving page. */ goto retry; } if (h->surplus_huge_pages_node[folio_nid(folio)]) adjust_surplus = true; remove_hugetlb_folio(h, folio, adjust_surplus); h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); /* * Normally update_and_free_hugtlb_folio will allocate required vmemmmap * before freeing the page. update_and_free_hugtlb_folio will fail to * free the page if it can not allocate required vmemmap. We * need to adjust max_huge_pages if the page is not freed. * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. * * The folio_test_hugetlb check here is because * remove_hugetlb_folio will clear hugetlb folio flag for * non-vmemmap optimized hugetlb folios. */ if (folio_test_hugetlb(folio)) { rc = hugetlb_vmemmap_restore_folio(h, folio); if (rc) { spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, adjust_surplus); h->max_huge_pages++; goto out; } } else rc = 0; update_and_free_hugetlb_folio(h, folio, false); return rc; } out: spin_unlock_irq(&hugetlb_lock); return rc; } /* * Dissolve free hugepages in a given pfn range. Used by memory hotplug to * make specified memory blocks removable from the system. * Note that this will dissolve a free gigantic hugepage completely, if any * part of it lies within the given range. * Also note that if dissolve_free_hugetlb_folio() returns with an error, all * free hugetlb folios that were dissolved before that error are lost. */ int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct folio *folio; int rc = 0; unsigned int order; struct hstate *h; if (!hugepages_supported()) return rc; order = huge_page_order(&default_hstate); for_each_hstate(h) order = min(order, huge_page_order(h)); for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) { folio = pfn_folio(pfn); rc = dissolve_free_hugetlb_folio(folio); if (rc) break; } return rc; } /* * Allocates a fresh surplus page from the page allocator. */ static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio = NULL; if (hstate_is_gigantic(h)) return NULL; spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) goto out_unlock; spin_unlock_irq(&hugetlb_lock); folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask); if (!folio) return NULL; spin_lock_irq(&hugetlb_lock); /* * nr_huge_pages needs to be adjusted within the same lock cycle * as surplus_pages, otherwise it might confuse * persistent_huge_pages() momentarily. */ account_new_hugetlb_folio(h, folio); /* * We could have raced with the pool size change. * Double check that and simply deallocate the new page * if we would end up overcommiting the surpluses. Abuse * temporary page to workaround the nasty free_huge_folio * codeflow */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { folio_set_hugetlb_temporary(folio); spin_unlock_irq(&hugetlb_lock); free_huge_folio(folio); return NULL; } h->surplus_huge_pages++; h->surplus_huge_pages_node[folio_nid(folio)]++; out_unlock: spin_unlock_irq(&hugetlb_lock); return folio; } static struct folio *alloc_migrate_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio; if (hstate_is_gigantic(h)) return NULL; folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask); if (!folio) return NULL; spin_lock_irq(&hugetlb_lock); account_new_hugetlb_folio(h, folio); spin_unlock_irq(&hugetlb_lock); /* fresh huge pages are frozen */ folio_ref_unfreeze(folio, 1); /* * We do not account these pages as surplus because they are only * temporary and will be released properly on the last reference */ folio_set_hugetlb_temporary(folio); return folio; } /* * Use the VMA's mpolicy to allocate a huge page from the buddy. */ static struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = NULL; struct mempolicy *mpol; gfp_t gfp_mask = htlb_alloc_mask(h); int nid; nodemask_t *nodemask; nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { gfp_t gfp = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); folio = alloc_surplus_hugetlb_folio(h, gfp, nid, nodemask); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) folio = alloc_surplus_hugetlb_folio(h, gfp_mask, nid, nodemask); mpol_cond_put(mpol); return folio; } struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { struct folio *folio; spin_lock_irq(&hugetlb_lock); if (!h->resv_huge_pages) { spin_unlock_irq(&hugetlb_lock); return NULL; } folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, nmask); if (folio) h->resv_huge_pages--; spin_unlock_irq(&hugetlb_lock); return folio; } /* folio migration callback function */ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { spin_lock_irq(&hugetlb_lock); if (available_huge_pages(h)) { struct folio *folio; folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, nmask); if (folio) { spin_unlock_irq(&hugetlb_lock); return folio; } } spin_unlock_irq(&hugetlb_lock); /* We cannot fallback to other nodes, as we could break the per-node pool. */ if (!allow_alloc_fallback) gfp_mask |= __GFP_THISNODE; return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask); } static nodemask_t *policy_mbind_nodemask(gfp_t gfp) { #ifdef CONFIG_NUMA struct mempolicy *mpol = get_task_policy(current); /* * Only enforce MPOL_BIND policy which overlaps with cpuset policy * (from policy_nodemask) specifically for hugetlb case */ if (mpol->mode == MPOL_BIND && (apply_policy_zone(mpol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&mpol->nodes))) return &mpol->nodes; #endif return NULL; } /* * Increase the hugetlb pool such that it can accommodate a reservation * of size 'delta'. */ static int gather_surplus_pages(struct hstate *h, long delta) __must_hold(&hugetlb_lock) { LIST_HEAD(surplus_list); struct folio *folio, *tmp; int ret; long i; long needed, allocated; bool alloc_ok = true; nodemask_t *mbind_nodemask, alloc_nodemask; mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h)); if (mbind_nodemask) nodes_and(alloc_nodemask, *mbind_nodemask, cpuset_current_mems_allowed); else alloc_nodemask = cpuset_current_mems_allowed; lockdep_assert_held(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { h->resv_huge_pages += delta; return 0; } allocated = 0; ret = -ENOMEM; retry: spin_unlock_irq(&hugetlb_lock); for (i = 0; i < needed; i++) { folio = NULL; /* * It is okay to use NUMA_NO_NODE because we use numa_mem_id() * down the road to pick the current node if that is the case. */ folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h), NUMA_NO_NODE, &alloc_nodemask); if (!folio) { alloc_ok = false; break; } list_add(&folio->lru, &surplus_list); cond_resched(); } allocated += i; /* * After retaking hugetlb_lock, we need to recalculate 'needed' * because either resv_huge_pages or free_huge_pages may have changed. */ spin_lock_irq(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - (h->free_huge_pages + allocated); if (needed > 0) { if (alloc_ok) goto retry; /* * We were not able to allocate enough pages to * satisfy the entire reservation so we free what * we've allocated so far. */ goto free; } /* * The surplus_list now contains _at_least_ the number of extra pages * needed to accommodate the reservation. Add the appropriate number * of pages to the hugetlb pool and free the extras back to the buddy * allocator. Commit the entire reservation here to prevent another * process from stealing the pages as they are added to the pool but * before they are reserved. */ needed += allocated; h->resv_huge_pages += delta; ret = 0; /* Free the needed pages to the hugetlb pool */ list_for_each_entry_safe(folio, tmp, &surplus_list, lru) { if ((--needed) < 0) break; /* Add the page to the hugetlb allocator */ enqueue_hugetlb_folio(h, folio); } free: spin_unlock_irq(&hugetlb_lock); /* * Free unnecessary surplus pages to the buddy allocator. * Pages have no ref count, call free_huge_folio directly. */ list_for_each_entry_safe(folio, tmp, &surplus_list, lru) free_huge_folio(folio); spin_lock_irq(&hugetlb_lock); return ret; } /* * This routine has two main purposes: * 1) Decrement the reservation count (resv_huge_pages) by the value passed * in unused_resv_pages. This corresponds to the prior adjustments made * to the associated reservation map. * 2) Free any unused surplus pages that may have been allocated to satisfy * the reservation. As many as unused_resv_pages may be freed. */ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); /* Uncommit the reservation */ h->resv_huge_pages -= unused_resv_pages; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) goto out; /* * Part (or even all) of the reservation could have been backed * by pre-allocated pages. Only free surplus pages. */ nr_pages = min(unused_resv_pages, h->surplus_huge_pages); /* * We want to release as many surplus pages as possible, spread * evenly across all nodes with memory. Iterate across these nodes * until we can no longer free unreserved surplus pages. This occurs * when the nodes with surplus pages have no free pages. * remove_pool_hugetlb_folio() will balance the freed pages across the * on-line nodes with memory and will handle the hstate accounting. */ while (nr_pages--) { struct folio *folio; folio = remove_pool_hugetlb_folio(h, &node_states[N_MEMORY], 1); if (!folio) goto out; list_add(&folio->lru, &page_list); } out: spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); spin_lock_irq(&hugetlb_lock); } /* * vma_needs_reservation, vma_commit_reservation and vma_end_reservation * are used by the huge page allocation routines to manage reservations. * * vma_needs_reservation is called to determine if the huge page at addr * within the vma has an associated reservation. If a reservation is * needed, the value 1 is returned. The caller is then responsible for * managing the global reservation and subpool usage counts. After * the huge page has been allocated, vma_commit_reservation is called * to add the page to the reservation map. If the page allocation fails, * the reservation must be ended instead of committed. vma_end_reservation * is called in such cases. * * In the normal case, vma_commit_reservation returns the same value * as the preceding vma_needs_reservation call. The only time this * is not the case is if a reserve map was changed between calls. It * is the responsibility of the caller to notice the difference and * take appropriate action. * * vma_add_reservation is used in error paths where a reservation must * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. * * vma_del_reservation is used in error paths where an entry in the reserve * map was created during huge page allocation and must be removed. It is to * be called after calling vma_needs_reservation to determine if a reservation * exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, VMA_DEL_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, enum vma_resv_mode mode) { struct resv_map *resv; pgoff_t idx; long ret; long dummy_out_regions_needed; resv = vma_resv_map(vma); if (!resv) return 1; idx = vma_hugecache_offset(h, vma, addr); switch (mode) { case VMA_NEEDS_RESV: ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed); /* We assume that vma_reservation_* routines always operate on * 1 page, and that adding to resv map a 1 page entry can only * ever require 1 region. */ VM_BUG_ON(dummy_out_regions_needed != 1); break; case VMA_COMMIT_RESV: ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); break; case VMA_END_RESV: region_abort(resv, idx, idx + 1, 1); ret = 0; break; case VMA_ADD_RESV: if (vma->vm_flags & VM_MAYSHARE) { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } else { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } break; case VMA_DEL_RESV: if (vma->vm_flags & VM_MAYSHARE) { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } else { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } break; default: BUG(); } if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV) return ret; /* * We know private mapping must have HPAGE_RESV_OWNER set. * * In most cases, reserves always exist for private mappings. * However, a file associated with mapping could have been * hole punched or truncated after reserves were consumed. * As subsequent fault on such a range will not use reserves. * Subtle - The reserve map for private mappings has the * opposite meaning than that of shared mappings. If NO * entry is in the reserve map, it means a reservation exists. * If an entry exists in the reserve map, it means the * reservation has already been consumed. As a result, the * return value of this routine is the opposite of the * value returned from reserve map manipulation routines above. */ if (ret > 0) return 0; if (ret == 0) return 1; return ret; } static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV); } static long vma_commit_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV); } static void vma_end_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { (void)__vma_reservation_common(h, vma, addr, VMA_END_RESV); } static long vma_add_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } static long vma_del_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV); } /* * This routine is called to restore reservation information on error paths. * It should ONLY be called for folios allocated via alloc_hugetlb_folio(), * and the hugetlb mutex should remain held when calling this routine. * * It handles two specific cases: * 1) A reservation was in place and the folio consumed the reservation. * hugetlb_restore_reserve is set in the folio. * 2) No reservation was in place for the page, so hugetlb_restore_reserve is * not set. However, alloc_hugetlb_folio always updates the reserve map. * * In case 1, free_huge_folio later in the error path will increment the * global reserve count. But, free_huge_folio does not have enough context * to adjust the reservation map. This case deals primarily with private * mappings. Adjust the reserve map here to be consistent with global * reserve count adjustments to be made by free_huge_folio. Make sure the * reserve map indicates there is a reservation present. * * In case 2, simply undo reserve map modifications done by alloc_hugetlb_folio. */ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio) { long rc = vma_needs_reservation(h, vma, address); if (folio_test_hugetlb_restore_reserve(folio)) { if (unlikely(rc < 0)) /* * Rare out of memory condition in reserve map * manipulation. Clear hugetlb_restore_reserve so * that global reserve count will not be incremented * by free_huge_folio. This will make it appear * as though the reservation for this folio was * consumed. This may prevent the task from * faulting in the folio at a later time. This * is better than inconsistent global huge page * accounting of reserve counts. */ folio_clear_hugetlb_restore_reserve(folio); else if (rc) (void)vma_add_reservation(h, vma, address); else vma_end_reservation(h, vma, address); } else { if (!rc) { /* * This indicates there is an entry in the reserve map * not added by alloc_hugetlb_folio. We know it was added * before the alloc_hugetlb_folio call, otherwise * hugetlb_restore_reserve would be set on the folio. * Remove the entry so that a subsequent allocation * does not consume a reservation. */ rc = vma_del_reservation(h, vma, address); if (rc < 0) /* * VERY rare out of memory condition. Since * we can not delete the entry, set * hugetlb_restore_reserve so that the reserve * count will be incremented when the folio * is freed. This reserve will be consumed * on a subsequent allocation. */ folio_set_hugetlb_restore_reserve(folio); } else if (rc < 0) { /* * Rare out of memory condition from * vma_needs_reservation call. Memory allocation is * only attempted if a new entry is needed. Therefore, * this implies there is not an entry in the * reserve map. * * For shared mappings, no entry in the map indicates * no reservation. We are done. */ if (!(vma->vm_flags & VM_MAYSHARE)) /* * For private mappings, no entry indicates * a reservation is present. Since we can * not add an entry, set hugetlb_restore_reserve * on the folio so reserve count will be * incremented when freed. This reserve will * be consumed on a subsequent allocation. */ folio_set_hugetlb_restore_reserve(folio); } else /* * No reservation present, do nothing */ vma_end_reservation(h, vma, address); } } /* * alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve * the old one * @old_folio: Old folio to dissolve * @list: List to isolate the page in case we need to * Returns 0 on success, otherwise negated error. */ static int alloc_and_dissolve_hugetlb_folio(struct folio *old_folio, struct list_head *list) { gfp_t gfp_mask; struct hstate *h; int nid = folio_nid(old_folio); struct folio *new_folio = NULL; int ret = 0; retry: /* * The old_folio might have been dissolved from under our feet, so make sure * to carefully check the state under the lock. */ spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(old_folio)) { /* * Freed from under us. Drop new_folio too. */ goto free_new; } else if (folio_ref_count(old_folio)) { bool isolated; /* * Someone has grabbed the folio, try to isolate it here. * Fail with -EBUSY if not possible. */ spin_unlock_irq(&hugetlb_lock); isolated = folio_isolate_hugetlb(old_folio, list); ret = isolated ? 0 : -EBUSY; spin_lock_irq(&hugetlb_lock); goto free_new; } else if (!folio_test_hugetlb_freed(old_folio)) { /* * Folio's refcount is 0 but it has not been enqueued in the * freelist yet. Race window is small, so we can succeed here if * we retry. */ spin_unlock_irq(&hugetlb_lock); cond_resched(); goto retry; } else { h = folio_hstate(old_folio); if (!new_folio) { spin_unlock_irq(&hugetlb_lock); gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; new_folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, NULL); if (!new_folio) return -ENOMEM; goto retry; } /* * Ok, old_folio is still a genuine free hugepage. Remove it from * the freelist and decrease the counters. These will be * incremented again when calling account_new_hugetlb_folio() * and enqueue_hugetlb_folio() for new_folio. The counters will * remain stable since this happens under the lock. */ remove_hugetlb_folio(h, old_folio, false); /* * Ref count on new_folio is already zero as it was dropped * earlier. It can be directly added to the pool free list. */ account_new_hugetlb_folio(h, new_folio); enqueue_hugetlb_folio(h, new_folio); /* * Folio has been replaced, we can safely free the old one. */ spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, old_folio, false); } return ret; free_new: spin_unlock_irq(&hugetlb_lock); if (new_folio) update_and_free_hugetlb_folio(h, new_folio, false); return ret; } int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list) { int ret = -EBUSY; /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (!folio_test_hugetlb(folio)) return 0; /* * Fence off gigantic pages as there is a cyclic dependency between * alloc_contig_range and them. Return -ENOMEM as this has the effect * of bailing out right away without further retrying. */ if (order_is_gigantic(folio_order(folio))) return -ENOMEM; if (folio_ref_count(folio) && folio_isolate_hugetlb(folio, list)) ret = 0; else if (!folio_ref_count(folio)) ret = alloc_and_dissolve_hugetlb_folio(folio, list); return ret; } /* * replace_free_hugepage_folios - Replace free hugepage folios in a given pfn * range with new folios. * @start_pfn: start pfn of the given pfn range * @end_pfn: end pfn of the given pfn range * Returns 0 on success, otherwise negated error. */ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) { struct folio *folio; int ret = 0; LIST_HEAD(isolate_list); while (start_pfn < end_pfn) { folio = pfn_folio(start_pfn); /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (folio_test_hugetlb(folio) && !folio_ref_count(folio)) { ret = alloc_and_dissolve_hugetlb_folio(folio, &isolate_list); if (ret) break; putback_movable_pages(&isolate_list); } start_pfn++; } return ret; } void wait_for_freed_hugetlb_folios(void) { if (llist_empty(&hpage_freelist)) return; flush_work(&free_hpage_work); } typedef enum { /* * For either 0/1: we checked the per-vma resv map, and one resv * count either can be reused (0), or an extra needed (1). */ MAP_CHG_REUSE = 0, MAP_CHG_NEEDED = 1, /* * Cannot use per-vma resv count can be used, hence a new resv * count is enforced. * * NOTE: This is mostly identical to MAP_CHG_NEEDED, except * that currently vma_needs_reservation() has an unwanted side * effect to either use end() or commit() to complete the * transaction. Hence it needs to differenciate from NEEDED. */ MAP_CHG_ENFORCED = 2, } map_chg_state; /* * NOTE! "cow_from_owner" represents a very hacky usage only used in CoW * faults of hugetlb private mappings on top of a non-page-cache folio (in * which case even if there's a private vma resv map it won't cover such * allocation). New call sites should (probably) never set it to true!! * When it's set, the allocation will bypass all vma level reservations. */ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner) { struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; long retval, gbl_chg, gbl_reserve; map_chg_state map_chg; int ret, idx; struct hugetlb_cgroup *h_cg = NULL; gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL; idx = hstate_index(h); /* Whether we need a separate per-vma reservation? */ if (cow_from_owner) { /* * Special case! Since it's a CoW on top of a reserved * page, the private resv map doesn't count. So it cannot * consume the per-vma resv map even if it's reserved. */ map_chg = MAP_CHG_ENFORCED; } else { /* * Examine the region/reserve map to determine if the process * has a reservation for the page to be allocated. A return * code of zero indicates a reservation exists (no change). */ retval = vma_needs_reservation(h, vma, addr); if (retval < 0) return ERR_PTR(-ENOMEM); map_chg = retval ? MAP_CHG_NEEDED : MAP_CHG_REUSE; } /* * Whether we need a separate global reservation? * * Processes that did not create the mapping will have no * reserves as indicated by the region/reserve map. Check * that the allocation will not exceed the subpool limit. * Or if it can get one from the pool reservation directly. */ if (map_chg) { gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) goto out_end_reservation; } else { /* * If we have the vma reservation ready, no need for extra * global reservation. */ gbl_chg = 0; } /* * If this allocation is not consuming a per-vma reservation, * charge the hugetlb cgroup now. */ if (map_chg) { ret = hugetlb_cgroup_charge_cgroup_rsvd( idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_subpool_put; } ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_uncharge_cgroup_reservation; spin_lock_irq(&hugetlb_lock); /* * glb_chg is passed to indicate whether or not a page must be taken * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ folio = dequeue_hugetlb_folio_vma(h, vma, addr, gbl_chg); if (!folio) { spin_unlock_irq(&hugetlb_lock); folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr); if (!folio) goto out_uncharge_cgroup; spin_lock_irq(&hugetlb_lock); list_add(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); /* Fall through */ } /* * Either dequeued or buddy-allocated folio needs to add special * mark to the folio when it consumes a global reservation. */ if (!gbl_chg) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, folio); /* If allocation is not consuming a reservation, also store the * hugetlb_cgroup pointer on the page. */ if (map_chg) { hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h), h_cg, folio); } spin_unlock_irq(&hugetlb_lock); hugetlb_set_folio_subpool(folio, spool); if (map_chg != MAP_CHG_ENFORCED) { /* commit() is only needed if the map_chg is not enforced */ retval = vma_commit_reservation(h, vma, addr); /* * Check for possible race conditions. When it happens.. * The page was added to the reservation map between * vma_needs_reservation and vma_commit_reservation. * This indicates a race with hugetlb_reserve_pages. * Adjust for the subpool count incremented above AND * in hugetlb_reserve_pages for the same page. Also, * the reservation count added in hugetlb_reserve_pages * no longer applies. */ if (unlikely(map_chg == MAP_CHG_NEEDED && retval == 0)) { long rsv_adjust; rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); if (map_chg) { spin_lock_irq(&hugetlb_lock); hugetlb_cgroup_uncharge_folio_rsvd( hstate_index(h), pages_per_huge_page(h), folio); spin_unlock_irq(&hugetlb_lock); } } } ret = mem_cgroup_charge_hugetlb(folio, gfp); /* * Unconditionally increment NR_HUGETLB here. If it turns out that * mem_cgroup_charge_hugetlb failed, then immediately free the page and * decrement NR_HUGETLB. */ lruvec_stat_mod_folio(folio, NR_HUGETLB, pages_per_huge_page(h)); if (ret == -ENOMEM) { free_huge_folio(folio); return ERR_PTR(-ENOMEM); } return folio; out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); out_uncharge_cgroup_reservation: if (map_chg) hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: /* * put page to subpool iff the quota of subpool's rsv_hpages is used * during hugepage_subpool_get_pages. */ if (map_chg && !gbl_chg) { gbl_reserve = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -gbl_reserve); } out_end_reservation: if (map_chg != MAP_CHG_ENFORCED) vma_end_reservation(h, vma, addr); return ERR_PTR(-ENOSPC); } static __init void *alloc_bootmem(struct hstate *h, int nid, bool node_exact) { struct huge_bootmem_page *m; int listnode = nid; if (hugetlb_early_cma(h)) m = hugetlb_cma_alloc_bootmem(h, &listnode, node_exact); else { if (node_exact) m = memblock_alloc_exact_nid_raw(huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); else { m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); /* * For pre-HVO to work correctly, pages need to be on * the list for the node they were actually allocated * from. That node may be different in the case of * fallback by memblock_alloc_try_nid_raw. So, * extract the actual node first. */ if (m) listnode = early_pfn_to_nid(PHYS_PFN(virt_to_phys(m))); } if (m) { m->flags = 0; m->cma = NULL; } } if (m) { /* * Use the beginning of the huge page to store the * huge_bootmem_page struct (until gather_bootmem * puts them into the mem_map). * * Put them into a private list first because mem_map * is not up yet. */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages[listnode]); m->hstate = h; } return m; } int alloc_bootmem_huge_page(struct hstate *h, int nid) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); int __alloc_bootmem_huge_page(struct hstate *h, int nid) { struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node = nid; /* do node specific alloc */ if (nid != NUMA_NO_NODE) { m = alloc_bootmem(h, node, true); if (!m) return 0; goto found; } /* allocate from next node when distributing huge pages */ for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, &hugetlb_bootmem_nodes) { m = alloc_bootmem(h, node, false); if (!m) return 0; goto found; } found: /* * Only initialize the head struct page in memmap_init_reserved_pages, * rest of the struct pages will be initialized by the HugeTLB * subsystem itself. * The head struct page is used to get folio information by the HugeTLB * subsystem like zone id and node id. */ memblock_reserved_mark_noinit(virt_to_phys((void *)m + PAGE_SIZE), huge_page_size(h) - PAGE_SIZE); return 1; } /* Initialize [start_page:end_page_number] tail struct pages of a hugepage */ static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio, unsigned long start_page_number, unsigned long end_page_number) { enum zone_type zone = zone_idx(folio_zone(folio)); int nid = folio_nid(folio); struct page *page = folio_page(folio, start_page_number); unsigned long head_pfn = folio_pfn(folio); unsigned long pfn, end_pfn = head_pfn + end_page_number; /* * As we marked all tail pages with memblock_reserved_mark_noinit(), * we must initialize them ourselves here. */ for (pfn = head_pfn + start_page_number; pfn < end_pfn; page++, pfn++) { __init_single_page(page, pfn, zone, nid); prep_compound_tail((struct page *)folio, pfn - head_pfn); set_page_count(page, 0); } } static void __init hugetlb_folio_init_vmemmap(struct folio *folio, struct hstate *h, unsigned long nr_pages) { int ret; /* * This is an open-coded prep_compound_page() whereby we avoid * walking pages twice by initializing/preparing+freezing them in the * same go. */ __folio_clear_reserved(folio); __folio_set_head(folio); ret = folio_ref_freeze(folio, 1); VM_BUG_ON(!ret); hugetlb_folio_init_tail_vmemmap(folio, 1, nr_pages); prep_compound_head((struct page *)folio, huge_page_order(h)); } static bool __init hugetlb_bootmem_page_prehvo(struct huge_bootmem_page *m) { return m->flags & HUGE_BOOTMEM_HVO; } static bool __init hugetlb_bootmem_page_earlycma(struct huge_bootmem_page *m) { return m->flags & HUGE_BOOTMEM_CMA; } /* * memblock-allocated pageblocks might not have the migrate type set * if marked with the 'noinit' flag. Set it to the default (MIGRATE_MOVABLE) * here, or MIGRATE_CMA if this was a page allocated through an early CMA * reservation. * * In case of vmemmap optimized folios, the tail vmemmap pages are mapped * read-only, but that's ok - for sparse vmemmap this does not write to * the page structure. */ static void __init hugetlb_bootmem_init_migratetype(struct folio *folio, struct hstate *h) { unsigned long nr_pages = pages_per_huge_page(h), i; WARN_ON_ONCE(!pageblock_aligned(folio_pfn(folio))); for (i = 0; i < nr_pages; i += pageblock_nr_pages) { if (folio_test_hugetlb_cma(folio)) init_cma_pageblock(folio_page(folio, i)); else init_pageblock_migratetype(folio_page(folio, i), MIGRATE_MOVABLE, false); } } static void __init prep_and_add_bootmem_folios(struct hstate *h, struct list_head *folio_list) { unsigned long flags; struct folio *folio, *tmp_f; /* Send list for bulk vmemmap optimization processing */ hugetlb_vmemmap_optimize_bootmem_folios(h, folio_list); list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { if (!folio_test_hugetlb_vmemmap_optimized(folio)) { /* * If HVO fails, initialize all tail struct pages * We do not worry about potential long lock hold * time as this is early in boot and there should * be no contention. */ hugetlb_folio_init_tail_vmemmap(folio, HUGETLB_VMEMMAP_RESERVE_PAGES, pages_per_huge_page(h)); } hugetlb_bootmem_init_migratetype(folio, h); /* Subdivide locks to achieve better parallel performance */ spin_lock_irqsave(&hugetlb_lock, flags); account_new_hugetlb_folio(h, folio); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } bool __init hugetlb_bootmem_page_zones_valid(int nid, struct huge_bootmem_page *m) { unsigned long start_pfn; bool valid; if (m->flags & HUGE_BOOTMEM_ZONES_VALID) { /* * Already validated, skip check. */ return true; } if (hugetlb_bootmem_page_earlycma(m)) { valid = cma_validate_zones(m->cma); goto out; } start_pfn = virt_to_phys(m) >> PAGE_SHIFT; valid = !pfn_range_intersects_zones(nid, start_pfn, pages_per_huge_page(m->hstate)); out: if (!valid) hstate_boot_nrinvalid[hstate_index(m->hstate)]++; return valid; } /* * Free a bootmem page that was found to be invalid (intersecting with * multiple zones). * * Since it intersects with multiple zones, we can't just do a free * operation on all pages at once, but instead have to walk all * pages, freeing them one by one. */ static void __init hugetlb_bootmem_free_invalid_page(int nid, struct page *page, struct hstate *h) { unsigned long npages = pages_per_huge_page(h); unsigned long pfn; while (npages--) { pfn = page_to_pfn(page); __init_page_from_nid(pfn, nid); free_reserved_page(page); page++; } } /* * Put bootmem huge pages into the standard lists after mem_map is up. * Note: This only applies to gigantic (order > MAX_PAGE_ORDER) pages. */ static void __init gather_bootmem_prealloc_node(unsigned long nid) { LIST_HEAD(folio_list); struct huge_bootmem_page *m, *tm; struct hstate *h = NULL, *prev_h = NULL; list_for_each_entry_safe(m, tm, &huge_boot_pages[nid], list) { struct page *page = virt_to_page(m); struct folio *folio = (void *)page; h = m->hstate; if (!hugetlb_bootmem_page_zones_valid(nid, m)) { /* * Can't use this page. Initialize the * page structures if that hasn't already * been done, and give them to the page * allocator. */ hugetlb_bootmem_free_invalid_page(nid, page, h); continue; } /* * It is possible to have multiple huge page sizes (hstates) * in this list. If so, process each size separately. */ if (h != prev_h && prev_h != NULL) prep_and_add_bootmem_folios(prev_h, &folio_list); prev_h = h; VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(folio_ref_count(folio) != 1); hugetlb_folio_init_vmemmap(folio, h, HUGETLB_VMEMMAP_RESERVE_PAGES); init_new_hugetlb_folio(folio); if (hugetlb_bootmem_page_prehvo(m)) /* * If pre-HVO was done, just set the * flag, the HVO code will then skip * this folio. */ folio_set_hugetlb_vmemmap_optimized(folio); if (hugetlb_bootmem_page_earlycma(m)) folio_set_hugetlb_cma(folio); list_add(&folio->lru, &folio_list); /* * We need to restore the 'stolen' pages to totalram_pages * in order to fix confusing memory reports from free(1) and * other side-effects, like CommitLimit going negative. * * For CMA pages, this is done in init_cma_pageblock * (via hugetlb_bootmem_init_migratetype), so skip it here. */ if (!folio_test_hugetlb_cma(folio)) adjust_managed_page_count(page, pages_per_huge_page(h)); cond_resched(); } prep_and_add_bootmem_folios(h, &folio_list); } static void __init gather_bootmem_prealloc_parallel(unsigned long start, unsigned long end, void *arg) { int nid; for (nid = start; nid < end; nid++) gather_bootmem_prealloc_node(nid); } static void __init gather_bootmem_prealloc(void) { struct padata_mt_job job = { .thread_fn = gather_bootmem_prealloc_parallel, .fn_arg = NULL, .start = 0, .size = nr_node_ids, .align = 1, .min_chunk = 1, .max_threads = num_node_state(N_MEMORY), .numa_aware = true, }; padata_do_multithreaded(&job); } static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) { unsigned long i; char buf[32]; LIST_HEAD(folio_list); for (i = 0; i < h->max_huge_pages_node[nid]; ++i) { if (hstate_is_gigantic(h)) { if (!alloc_bootmem_huge_page(h, nid)) break; } else { struct folio *folio; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid, &node_states[N_MEMORY], NULL); if (!folio) break; list_add(&folio->lru, &folio_list); } cond_resched(); } if (!list_empty(&folio_list)) prep_and_add_allocated_folios(h, &folio_list); if (i == h->max_huge_pages_node[nid]) return; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n", h->max_huge_pages_node[nid], buf, nid, i); h->max_huge_pages -= (h->max_huge_pages_node[nid] - i); h->max_huge_pages_node[nid] = i; } static bool __init hugetlb_hstate_alloc_pages_specific_nodes(struct hstate *h) { int i; bool node_specific_alloc = false; for_each_online_node(i) { if (h->max_huge_pages_node[i] > 0) { hugetlb_hstate_alloc_pages_onenode(h, i); node_specific_alloc = true; } } return node_specific_alloc; } static void __init hugetlb_hstate_alloc_pages_errcheck(unsigned long allocated, struct hstate *h) { if (allocated < h->max_huge_pages) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %lu of page size %s failed. Only allocated %lu hugepages.\n", h->max_huge_pages, buf, allocated); h->max_huge_pages = allocated; } } static void __init hugetlb_pages_alloc_boot_node(unsigned long start, unsigned long end, void *arg) { struct hstate *h = (struct hstate *)arg; int i, num = end - start; nodemask_t node_alloc_noretry; LIST_HEAD(folio_list); int next_node = first_online_node; /* Bit mask controlling how hard we retry per-node allocations.*/ nodes_clear(node_alloc_noretry); for (i = 0; i < num; ++i) { struct folio *folio; if (hugetlb_vmemmap_optimizable_size(h) && (si_mem_available() == 0) && !list_empty(&folio_list)) { prep_and_add_allocated_folios(h, &folio_list); INIT_LIST_HEAD(&folio_list); } folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY], &node_alloc_noretry, &next_node); if (!folio) break; list_move(&folio->lru, &folio_list); cond_resched(); } prep_and_add_allocated_folios(h, &folio_list); } static unsigned long __init hugetlb_gigantic_pages_alloc_boot(struct hstate *h) { unsigned long i; for (i = 0; i < h->max_huge_pages; ++i) { if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; cond_resched(); } return i; } static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h) { struct padata_mt_job job = { .fn_arg = h, .align = 1, .numa_aware = true }; unsigned long jiffies_start; unsigned long jiffies_end; unsigned long remaining; job.thread_fn = hugetlb_pages_alloc_boot_node; /* * job.max_threads is 25% of the available cpu threads by default. * * On large servers with terabytes of memory, huge page allocation * can consume a considerably amount of time. * * Tests below show how long it takes to allocate 1 TiB of memory with 2MiB huge pages. * 2MiB huge pages. Using more threads can significantly improve allocation time. * * +-----------------------+-------+-------+-------+-------+-------+ * | threads | 8 | 16 | 32 | 64 | 128 | * +-----------------------+-------+-------+-------+-------+-------+ * | skylake 144 cpus | 44s | 22s | 16s | 19s | 20s | * | cascade lake 192 cpus | 39s | 20s | 11s | 10s | 9s | * +-----------------------+-------+-------+-------+-------+-------+ */ if (hugepage_allocation_threads == 0) { hugepage_allocation_threads = num_online_cpus() / 4; hugepage_allocation_threads = max(hugepage_allocation_threads, 1); } job.max_threads = hugepage_allocation_threads; jiffies_start = jiffies; do { remaining = h->max_huge_pages - h->nr_huge_pages; job.start = h->nr_huge_pages; job.size = remaining; job.min_chunk = remaining / hugepage_allocation_threads; padata_do_multithreaded(&job); if (h->nr_huge_pages == h->max_huge_pages) break; /* * Retry only if the vmemmap optimization might have been able to free * some memory back to the system. */ if (!hugetlb_vmemmap_optimizable(h)) break; /* Continue if progress was made in last iteration */ } while (remaining != (h->max_huge_pages - h->nr_huge_pages)); jiffies_end = jiffies; pr_info("HugeTLB: allocation took %dms with hugepage_allocation_threads=%ld\n", jiffies_to_msecs(jiffies_end - jiffies_start), hugepage_allocation_threads); return h->nr_huge_pages; } /* * NOTE: this routine is called in different contexts for gigantic and * non-gigantic pages. * - For gigantic pages, this is called early in the boot process and * pages are allocated from memblock allocated or something similar. * Gigantic pages are actually added to pools later with the routine * gather_bootmem_prealloc. * - For non-gigantic pages, this is called later in the boot process after * all of mm is up and functional. Pages are allocated from buddy and * then added to hugetlb pools. */ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long allocated; /* * Skip gigantic hugepages allocation if early CMA * reservations are not available. */ if (hstate_is_gigantic(h) && hugetlb_cma_total_size() && !hugetlb_early_cma(h)) { pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); return; } if (!h->max_huge_pages) return; /* do node specific alloc */ if (hugetlb_hstate_alloc_pages_specific_nodes(h)) return; /* below will do all node balanced alloc */ if (hstate_is_gigantic(h)) allocated = hugetlb_gigantic_pages_alloc_boot(h); else allocated = hugetlb_pages_alloc_boot(h); hugetlb_hstate_alloc_pages_errcheck(allocated, h); } static void __init hugetlb_init_hstates(void) { struct hstate *h, *h2; for_each_hstate(h) { /* * Always reset to first_memory_node here, even if * next_nid_to_alloc was set before - we can't * reference hugetlb_bootmem_nodes after init, and * first_memory_node is right for all further allocations. */ h->next_nid_to_alloc = first_memory_node; h->next_nid_to_free = first_memory_node; /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); /* * Set demote order for each hstate. Note that * h->demote_order is initially 0. * - We can not demote gigantic pages if runtime freeing * is not supported, so skip this. * - If CMA allocation is possible, we can not demote * HUGETLB_PAGE_ORDER or smaller size pages. */ if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) continue; if (hugetlb_cma_total_size() && h->order <= HUGETLB_PAGE_ORDER) continue; for_each_hstate(h2) { if (h2 == h) continue; if (h2->order < h->order && h2->order > h->demote_order) h->demote_order = h2->order; } } } static void __init report_hugepages(void) { struct hstate *h; unsigned long nrinvalid; for_each_hstate(h) { char buf[32]; nrinvalid = hstate_boot_nrinvalid[hstate_index(h)]; h->max_huge_pages -= nrinvalid; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_info("HugeTLB: registered %s page size, pre-allocated %ld pages\n", buf, h->nr_huge_pages); if (nrinvalid) pr_info("HugeTLB: %s page size: %lu invalid page%s discarded\n", buf, nrinvalid, str_plural(nrinvalid)); pr_info("HugeTLB: %d KiB vmemmap can be freed for a %s page\n", hugetlb_vmemmap_optimizable_size(h) / SZ_1K, buf); } } #ifdef CONFIG_HIGHMEM static void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { int i; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h)) return; /* * Collect pages to be freed on a list, and free after dropping lock */ for_each_node_mask(i, *nodes_allowed) { struct folio *folio, *next; struct list_head *freel = &h->hugepage_freelists[i]; list_for_each_entry_safe(folio, next, freel, lru) { if (count >= h->nr_huge_pages) goto out; if (folio_test_highmem(folio)) continue; remove_hugetlb_folio(h, folio, false); list_add(&folio->lru, &page_list); } } out: spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); spin_lock_irq(&hugetlb_lock); } #else static inline void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { } #endif /* * Increment or decrement surplus_huge_pages. Keep node-specific counters * balanced by operating on them in a round-robin fashion. * Returns 1 if an adjustment was made. */ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, int delta) { int nr_nodes, node; lockdep_assert_held(&hugetlb_lock); VM_BUG_ON(delta != -1 && delta != 1); if (delta < 0) { for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node]) goto found; } } else { for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node] < h->nr_huge_pages_node[node]) goto found; } } return 0; found: h->surplus_huge_pages += delta; h->surplus_huge_pages_node[node] += delta; return 1; } #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { unsigned long persistent_free_count; unsigned long min_count; unsigned long allocated; struct folio *folio; LIST_HEAD(page_list); NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); /* * Bit mask controlling how hard we retry per-node allocations. * If we can not allocate the bit mask, do not attempt to allocate * the requested huge pages. */ if (node_alloc_noretry) nodes_clear(*node_alloc_noretry); else return -ENOMEM; /* * resize_lock mutex prevents concurrent adjustments to number of * pages in hstate via the proc/sysfs interfaces. */ mutex_lock(&h->resize_lock); flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); /* * Check for a node specific request. * Changing node specific huge page count may require a corresponding * change to the global count. In any case, the passed node mask * (nodes_allowed) will restrict alloc/free to the specified node. */ if (nid != NUMA_NO_NODE) { unsigned long old_count = count; count += persistent_huge_pages(h) - (h->nr_huge_pages_node[nid] - h->surplus_huge_pages_node[nid]); /* * User may have specified a large count value which caused the * above calculation to overflow. In this case, they wanted * to allocate as many huge pages as possible. Set count to * largest possible value to align with their intention. */ if (count < old_count) count = ULONG_MAX; } /* * Gigantic pages runtime allocation depend on the capability for large * page range allocation. * If the system does not provide this feature, return an error when * the user tries to allocate gigantic pages but let the user free the * boottime allocated gigantic pages. */ if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { if (count > persistent_huge_pages(h)) { spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return -EINVAL; } /* Fall through to decrease pool */ } /* * Increase the pool size * First take pages out of surplus state. Then make up the * remaining difference by allocating fresh huge pages. * * We might race with alloc_surplus_hugetlb_folio() here and be unable * to convert a surplus huge page to a normal huge page. That is * not critical, though, it just means the overall size of the * pool might be one hugepage larger than it needs to be, but * within all the constraints specified by the sysctls. */ while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, -1)) break; } allocated = 0; while (count > (persistent_huge_pages(h) + allocated)) { /* * If this allocation races such that we no longer need the * page, free_huge_folio will handle it by freeing the page * and reducing the surplus. */ spin_unlock_irq(&hugetlb_lock); /* yield cpu to avoid soft lockup */ cond_resched(); folio = alloc_pool_huge_folio(h, nodes_allowed, node_alloc_noretry, &h->next_nid_to_alloc); if (!folio) { prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); goto out; } list_add(&folio->lru, &page_list); allocated++; /* Bail for signals. Probably ctrl-c from user */ if (signal_pending(current)) { prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); goto out; } spin_lock_irq(&hugetlb_lock); } /* Add allocated pages to the pool */ if (!list_empty(&page_list)) { spin_unlock_irq(&hugetlb_lock); prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); } /* * Decrease the pool size * First return free pages to the buddy allocator (being careful * to keep enough around to satisfy reservations). Then place * pages into surplus state as needed so the pool will shrink * to the desired size as pages become free. * * By placing pages into the surplus state independent of the * overcommit value, we are allowing the surplus pool size to * exceed overcommit. There are few sane options here. Since * alloc_surplus_hugetlb_folio() is checking the global counter, * though, we'll note that we're not allowed to exceed surplus * and won't grow the pool anywhere else. Not until one of the * sysctls are changed, or the surplus pages go out of use. * * min_count is the expected number of persistent pages, we * shouldn't calculate min_count by using * resv_huge_pages + persistent_huge_pages() - free_huge_pages, * because there may exist free surplus huge pages, and this will * lead to subtracting twice. Free surplus huge pages come from HVO * failing to restore vmemmap, see comments in the callers of * hugetlb_vmemmap_restore_folio(). Thus, we should calculate * persistent free count first. */ persistent_free_count = h->free_huge_pages; if (h->free_huge_pages > persistent_huge_pages(h)) { if (h->free_huge_pages > h->surplus_huge_pages) persistent_free_count -= h->surplus_huge_pages; else persistent_free_count = 0; } min_count = h->resv_huge_pages + persistent_huge_pages(h) - persistent_free_count; min_count = max(count, min_count); try_to_free_low(h, min_count, nodes_allowed); /* * Collect pages to be removed on list without dropping lock */ while (min_count < persistent_huge_pages(h)) { folio = remove_pool_hugetlb_folio(h, nodes_allowed, 0); if (!folio) break; list_add(&folio->lru, &page_list); } /* free the pages after dropping lock */ spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) break; } out: h->max_huge_pages = persistent_huge_pages(h); spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return 0; } static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, struct list_head *src_list) { long rc; struct folio *folio, *next; LIST_HEAD(dst_list); LIST_HEAD(ret_list); rc = hugetlb_vmemmap_restore_folios(src, src_list, &ret_list); list_splice_init(&ret_list, src_list); /* * Taking target hstate mutex synchronizes with set_max_huge_pages. * Without the mutex, pages added to target hstate could be marked * as surplus. * * Note that we already hold src->resize_lock. To prevent deadlock, * use the convention of always taking larger size hstate mutex first. */ mutex_lock(&dst->resize_lock); list_for_each_entry_safe(folio, next, src_list, lru) { int i; bool cma; if (folio_test_hugetlb_vmemmap_optimized(folio)) continue; cma = folio_test_hugetlb_cma(folio); list_del(&folio->lru); split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst)); pgalloc_tag_split(folio, huge_page_order(src), huge_page_order(dst)); for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) { struct page *page = folio_page(folio, i); /* Careful: see __split_huge_page_tail() */ struct folio *new_folio = (struct folio *)page; clear_compound_head(page); prep_compound_page(page, dst->order); new_folio->mapping = NULL; init_new_hugetlb_folio(new_folio); /* Copy the CMA flag so that it is freed correctly */ if (cma) folio_set_hugetlb_cma(new_folio); list_add(&new_folio->lru, &dst_list); } } prep_and_add_allocated_folios(dst, &dst_list); mutex_unlock(&dst->resize_lock); return rc; } static long demote_pool_huge_page(struct hstate *src, nodemask_t *nodes_allowed, unsigned long nr_to_demote) __must_hold(&hugetlb_lock) { int nr_nodes, node; struct hstate *dst; long rc = 0; long nr_demoted = 0; lockdep_assert_held(&hugetlb_lock); /* We should never get here if no demote order */ if (!src->demote_order) { pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n"); return -EINVAL; /* internal error */ } dst = size_to_hstate(PAGE_SIZE << src->demote_order); for_each_node_mask_to_free(src, nr_nodes, node, nodes_allowed) { LIST_HEAD(list); struct folio *folio, *next; list_for_each_entry_safe(folio, next, &src->hugepage_freelists[node], lru) { if (folio_test_hwpoison(folio)) continue; remove_hugetlb_folio(src, folio, false); list_add(&folio->lru, &list); if (++nr_demoted == nr_to_demote) break; } spin_unlock_irq(&hugetlb_lock); rc = demote_free_hugetlb_folios(src, dst, &list); spin_lock_irq(&hugetlb_lock); list_for_each_entry_safe(folio, next, &list, lru) { list_del(&folio->lru); add_hugetlb_folio(src, folio, false); nr_demoted--; } if (rc < 0 || nr_demoted == nr_to_demote) break; } /* * Not absolutely necessary, but for consistency update max_huge_pages * based on pool changes for the demoted page. */ src->max_huge_pages -= nr_demoted; dst->max_huge_pages += nr_demoted << (huge_page_order(src) - huge_page_order(dst)); if (rc < 0) return rc; if (nr_demoted) return nr_demoted; /* * Only way to get here is if all pages on free lists are poisoned. * Return -EBUSY so that caller will not retry. */ return -EBUSY; } #define HSTATE_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) #define HSTATE_ATTR_WO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_WO(_name) #define HSTATE_ATTR(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RW(_name) static struct kobject *hugepages_kobj; static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp); static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp) { int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (hstate_kobjs[i] == kobj) { if (nidp) *nidp = NUMA_NO_NODE; return &hstates[i]; } return kobj_to_node_hstate(kobj, nidp); } static ssize_t nr_hugepages_show_common(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long nr_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) nr_huge_pages = h->nr_huge_pages; else nr_huge_pages = h->nr_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", nr_huge_pages); } static ssize_t __nr_hugepages_store_common(bool obey_mempolicy, struct hstate *h, int nid, unsigned long count, size_t len) { int err; nodemask_t nodes_allowed, *n_mask; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return -EINVAL; if (nid == NUMA_NO_NODE) { /* * global hstate attribute */ if (!(obey_mempolicy && init_nodemask_of_mempolicy(&nodes_allowed))) n_mask = &node_states[N_MEMORY]; else n_mask = &nodes_allowed; } else { /* * Node specific request. count adjustment happens in * set_max_huge_pages() after acquiring hugetlb_lock. */ init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } err = set_max_huge_pages(h, count, nid, n_mask); return err ? err : len; } static ssize_t nr_hugepages_store_common(bool obey_mempolicy, struct kobject *kobj, const char *buf, size_t len) { struct hstate *h; unsigned long count; int nid; int err; err = kstrtoul(buf, 10, &count); if (err) return err; h = kobj_to_hstate(kobj, &nid); return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len); } static ssize_t nr_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(false, kobj, buf, len); } HSTATE_ATTR(nr_hugepages); #ifdef CONFIG_NUMA /* * hstate attribute for optionally mempolicy-based constraint on persistent * huge page alloc/free. */ static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return nr_hugepages_show_common(kobj, attr, buf); } static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { return nr_hugepages_store_common(true, kobj, buf, len); } HSTATE_ATTR(nr_hugepages_mempolicy); #endif static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sysfs_emit(buf, "%lu\n", h->nr_overcommit_huge_pages); } static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long input; struct hstate *h = kobj_to_hstate(kobj, NULL); if (hstate_is_gigantic(h)) return -EINVAL; err = kstrtoul(buf, 10, &input); if (err) return err; spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = input; spin_unlock_irq(&hugetlb_lock); return count; } HSTATE_ATTR(nr_overcommit_hugepages); static ssize_t free_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long free_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) free_huge_pages = h->free_huge_pages; else free_huge_pages = h->free_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", free_huge_pages); } HSTATE_ATTR_RO(free_hugepages); static ssize_t resv_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); return sysfs_emit(buf, "%lu\n", h->resv_huge_pages); } HSTATE_ATTR_RO(resv_hugepages); static ssize_t surplus_hugepages_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h; unsigned long surplus_huge_pages; int nid; h = kobj_to_hstate(kobj, &nid); if (nid == NUMA_NO_NODE) surplus_huge_pages = h->surplus_huge_pages; else surplus_huge_pages = h->surplus_huge_pages_node[nid]; return sysfs_emit(buf, "%lu\n", surplus_huge_pages); } HSTATE_ATTR_RO(surplus_hugepages); static ssize_t demote_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t len) { unsigned long nr_demote; unsigned long nr_available; nodemask_t nodes_allowed, *n_mask; struct hstate *h; int err; int nid; err = kstrtoul(buf, 10, &nr_demote); if (err) return err; h = kobj_to_hstate(kobj, &nid); if (nid != NUMA_NO_NODE) { init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } else { n_mask = &node_states[N_MEMORY]; } /* Synchronize with other sysfs operations modifying huge pages */ mutex_lock(&h->resize_lock); spin_lock_irq(&hugetlb_lock); while (nr_demote) { long rc; /* * Check for available pages to demote each time thorough the * loop as demote_pool_huge_page will drop hugetlb_lock. */ if (nid != NUMA_NO_NODE) nr_available = h->free_huge_pages_node[nid]; else nr_available = h->free_huge_pages; nr_available -= h->resv_huge_pages; if (!nr_available) break; rc = demote_pool_huge_page(h, n_mask, nr_demote); if (rc < 0) { err = rc; break; } nr_demote -= rc; } spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); if (err) return err; return len; } HSTATE_ATTR_WO(demote); static ssize_t demote_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct hstate *h = kobj_to_hstate(kobj, NULL); unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K; return sysfs_emit(buf, "%lukB\n", demote_size); } static ssize_t demote_size_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct hstate *h, *demote_hstate; unsigned long demote_size; unsigned int demote_order; demote_size = (unsigned long)memparse(buf, NULL); demote_hstate = size_to_hstate(demote_size); if (!demote_hstate) return -EINVAL; demote_order = demote_hstate->order; if (demote_order < HUGETLB_PAGE_ORDER) return -EINVAL; /* demote order must be smaller than hstate order */ h = kobj_to_hstate(kobj, NULL); if (demote_order >= h->order) return -EINVAL; /* resize_lock synchronizes access to demote size and writes */ mutex_lock(&h->resize_lock); h->demote_order = demote_order; mutex_unlock(&h->resize_lock); return count; } HSTATE_ATTR(demote_size); static struct attribute *hstate_attrs[] = { &nr_hugepages_attr.attr, &nr_overcommit_hugepages_attr.attr, &free_hugepages_attr.attr, &resv_hugepages_attr.attr, &surplus_hugepages_attr.attr, #ifdef CONFIG_NUMA &nr_hugepages_mempolicy_attr.attr, #endif NULL, }; static const struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; static struct attribute *hstate_demote_attrs[] = { &demote_size_attr.attr, &demote_attr.attr, NULL, }; static const struct attribute_group hstate_demote_attr_group = { .attrs = hstate_demote_attrs, }; static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct kobject **hstate_kobjs, const struct attribute_group *hstate_attr_group) { int retval; int hi = hstate_index(h); hstate_kobjs[hi] = kobject_create_and_add(h->name, parent); if (!hstate_kobjs[hi]) return -ENOMEM; retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); if (retval) { kobject_put(hstate_kobjs[hi]); hstate_kobjs[hi] = NULL; return retval; } if (h->demote_order) { retval = sysfs_create_group(hstate_kobjs[hi], &hstate_demote_attr_group); if (retval) { pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name); sysfs_remove_group(hstate_kobjs[hi], hstate_attr_group); kobject_put(hstate_kobjs[hi]); hstate_kobjs[hi] = NULL; return retval; } } return 0; } #ifdef CONFIG_NUMA static bool hugetlb_sysfs_initialized __ro_after_init; /* * node_hstate/s - associate per node hstate attributes, via their kobjects, * with node devices in node_devices[] using a parallel array. The array * index of a node device or _hstate == node id. * This is here to avoid any static dependency of the node device driver, in * the base kernel, on the hugetlb module. */ struct node_hstate { struct kobject *hugepages_kobj; struct kobject *hstate_kobjs[HUGE_MAX_HSTATE]; }; static struct node_hstate node_hstates[MAX_NUMNODES]; /* * A subset of global hstate attributes for node devices */ static struct attribute *per_node_hstate_attrs[] = { &nr_hugepages_attr.attr, &free_hugepages_attr.attr, &surplus_hugepages_attr.attr, NULL, }; static const struct attribute_group per_node_hstate_attr_group = { .attrs = per_node_hstate_attrs, }; /* * kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj. * Returns node id via non-NULL nidp. */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { int nid; for (nid = 0; nid < nr_node_ids; nid++) { struct node_hstate *nhs = &node_hstates[nid]; int i; for (i = 0; i < HUGE_MAX_HSTATE; i++) if (nhs->hstate_kobjs[i] == kobj) { if (nidp) *nidp = nid; return &hstates[i]; } } BUG(); return NULL; } /* * Unregister hstate attributes from a single node device. * No-op if no hstate attributes attached. */ void hugetlb_unregister_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; if (!nhs->hugepages_kobj) return; /* no hstate attributes */ for_each_hstate(h) { int idx = hstate_index(h); struct kobject *hstate_kobj = nhs->hstate_kobjs[idx]; if (!hstate_kobj) continue; if (h->demote_order) sysfs_remove_group(hstate_kobj, &hstate_demote_attr_group); sysfs_remove_group(hstate_kobj, &per_node_hstate_attr_group); kobject_put(hstate_kobj); nhs->hstate_kobjs[idx] = NULL; } kobject_put(nhs->hugepages_kobj); nhs->hugepages_kobj = NULL; } /* * Register hstate attributes for a single node device. * No-op if attributes already registered. */ void hugetlb_register_node(struct node *node) { struct hstate *h; struct node_hstate *nhs = &node_hstates[node->dev.id]; int err; if (!hugetlb_sysfs_initialized) return; if (nhs->hugepages_kobj) return; /* already allocated */ nhs->hugepages_kobj = kobject_create_and_add("hugepages", &node->dev.kobj); if (!nhs->hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj, nhs->hstate_kobjs, &per_node_hstate_attr_group); if (err) { pr_err("HugeTLB: Unable to add hstate %s for node %d\n", h->name, node->dev.id); hugetlb_unregister_node(node); break; } } } /* * hugetlb init time: register hstate attributes for all registered node * devices of nodes that have memory. All on-line nodes should have * registered their associated device by this time. */ static void __init hugetlb_register_all_nodes(void) { int nid; for_each_online_node(nid) hugetlb_register_node(node_devices[nid]); } #else /* !CONFIG_NUMA */ static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp) { BUG(); if (nidp) *nidp = -1; return NULL; } static void hugetlb_register_all_nodes(void) { } #endif static void __init hugetlb_sysfs_init(void) { struct hstate *h; int err; hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj); if (!hugepages_kobj) return; for_each_hstate(h) { err = hugetlb_sysfs_add_hstate(h, hugepages_kobj, hstate_kobjs, &hstate_attr_group); if (err) pr_err("HugeTLB: Unable to add hstate %s\n", h->name); } #ifdef CONFIG_NUMA hugetlb_sysfs_initialized = true; #endif hugetlb_register_all_nodes(); } #ifdef CONFIG_SYSCTL static void hugetlb_sysctl_init(void); #else static inline void hugetlb_sysctl_init(void) { } #endif static int __init hugetlb_init(void) { int i; BUILD_BUG_ON(sizeof_field(struct page, private) * BITS_PER_BYTE < __NR_HPAGEFLAGS); BUILD_BUG_ON_INVALID(HUGETLB_PAGE_ORDER > MAX_FOLIO_ORDER); if (!hugepages_supported()) { if (hugetlb_max_hstate || default_hstate_max_huge_pages) pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n"); return 0; } /* * Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists. Some * architectures depend on setup being done here. */ hugetlb_add_hstate(HUGETLB_PAGE_ORDER); if (!parsed_default_hugepagesz) { /* * If we did not parse a default huge page size, set * default_hstate_idx to HPAGE_SIZE hstate. And, if the * number of huge pages for this default size was implicitly * specified, set that here as well. * Note that the implicit setting will overwrite an explicit * setting. A warning will be printed in this case. */ default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE)); if (default_hstate_max_huge_pages) { if (default_hstate.max_huge_pages) { char buf[32]; string_get_size(huge_page_size(&default_hstate), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n", default_hstate.max_huge_pages, buf); pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n", default_hstate_max_huge_pages); } default_hstate.max_huge_pages = default_hstate_max_huge_pages; for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; } } hugetlb_cma_check(); hugetlb_init_hstates(); gather_bootmem_prealloc(); report_hugepages(); hugetlb_sysfs_init(); hugetlb_cgroup_file_init(); hugetlb_sysctl_init(); #ifdef CONFIG_SMP num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); #else num_fault_mutexes = 1; #endif hugetlb_fault_mutex_table = kmalloc_array(num_fault_mutexes, sizeof(struct mutex), GFP_KERNEL); BUG_ON(!hugetlb_fault_mutex_table); for (i = 0; i < num_fault_mutexes; i++) mutex_init(&hugetlb_fault_mutex_table[i]); return 0; } subsys_initcall(hugetlb_init); /* Overwritten by architectures with more huge page sizes */ bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size) { return size == HPAGE_SIZE; } void __init hugetlb_add_hstate(unsigned int order) { struct hstate *h; unsigned long i; if (size_to_hstate(PAGE_SIZE << order)) { return; } BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order < order_base_2(__NR_USED_SUBPAGE)); WARN_ON(order > MAX_FOLIO_ORDER); h = &hstates[hugetlb_max_hstate++]; __mutex_init(&h->resize_lock, "resize mutex", &h->resize_key); h->order = order; h->mask = ~(huge_page_size(h) - 1); for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); INIT_LIST_HEAD(&h->hugepage_activelist); snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/SZ_1K); parsed_hstate = h; } bool __init __weak hugetlb_node_alloc_supported(void) { return true; } static void __init hugepages_clear_pages_in_node(void) { if (!hugetlb_max_hstate) { default_hstate_max_huge_pages = 0; memset(default_hugepages_in_node, 0, sizeof(default_hugepages_in_node)); } else { parsed_hstate->max_huge_pages = 0; memset(parsed_hstate->max_huge_pages_node, 0, sizeof(parsed_hstate->max_huge_pages_node)); } } static __init int hugetlb_add_param(char *s, int (*setup)(char *)) { size_t len; char *p; if (hugetlb_param_index >= HUGE_MAX_CMDLINE_ARGS) return -EINVAL; len = strlen(s) + 1; if (len + hstate_cmdline_index > sizeof(hstate_cmdline_buf)) return -EINVAL; p = &hstate_cmdline_buf[hstate_cmdline_index]; memcpy(p, s, len); hstate_cmdline_index += len; hugetlb_params[hugetlb_param_index].val = p; hugetlb_params[hugetlb_param_index].setup = setup; hugetlb_param_index++; return 0; } static __init void hugetlb_parse_params(void) { int i; struct hugetlb_cmdline *hcp; for (i = 0; i < hugetlb_param_index; i++) { hcp = &hugetlb_params[i]; hcp->setup(hcp->val); } hugetlb_cma_validate_params(); } /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz * specification. If not, ignore the hugepages value. hugepages can also * be the first huge page command line option in which case it implicitly * specifies the number of huge pages for the default size. */ static int __init hugepages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; int node = NUMA_NO_NODE; int count; unsigned long tmp; char *p = s; if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; return -EINVAL; } /* * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter * yet, so this hugepages= parameter goes to the "default hstate". * Otherwise, it goes with the previously parsed hugepagesz or * default_hugepagesz. */ else if (!hugetlb_max_hstate) mhp = &default_hstate_max_huge_pages; else mhp = &parsed_hstate->max_huge_pages; if (mhp == last_mhp) { pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s); return 1; } while (*p) { count = 0; if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; /* Parameter is node format */ if (p[count] == ':') { if (!hugetlb_node_alloc_supported()) { pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); return 1; } if (tmp >= MAX_NUMNODES || !node_online(tmp)) goto invalid; node = array_index_nospec(tmp, MAX_NUMNODES); p += count + 1; /* Parse hugepages */ if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; if (!hugetlb_max_hstate) default_hugepages_in_node[node] = tmp; else parsed_hstate->max_huge_pages_node[node] = tmp; *mhp += tmp; /* Go to parse next node*/ if (p[count] == ',') p += count + 1; else break; } else { if (p != s) goto invalid; *mhp = tmp; break; } } last_mhp = mhp; return 0; invalid: pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); hugepages_clear_pages_in_node(); return -EINVAL; } hugetlb_early_param("hugepages", hugepages_setup); /* * hugepagesz command line processing * A specific huge page size can only be specified once with hugepagesz. * hugepagesz is followed by hugepages on the command line. The global * variable 'parsed_valid_hugepagesz' is used to determine if prior * hugepagesz argument was valid. */ static int __init hugepagesz_setup(char *s) { unsigned long size; struct hstate *h; parsed_valid_hugepagesz = false; size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported hugepagesz=%s\n", s); return -EINVAL; } h = size_to_hstate(size); if (h) { /* * hstate for this size already exists. This is normally * an error, but is allowed if the existing hstate is the * default hstate. More specifically, it is only allowed if * the number of huge pages for the default hstate was not * previously specified. */ if (!parsed_default_hugepagesz || h != &default_hstate || default_hstate.max_huge_pages) { pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s); return -EINVAL; } /* * No need to call hugetlb_add_hstate() as hstate already * exists. But, do set parsed_hstate so that a following * hugepages= parameter will be applied to this hstate. */ parsed_hstate = h; parsed_valid_hugepagesz = true; return 0; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; return 0; } hugetlb_early_param("hugepagesz", hugepagesz_setup); /* * default_hugepagesz command line input * Only one instance of default_hugepagesz allowed on command line. */ static int __init default_hugepagesz_setup(char *s) { unsigned long size; int i; parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); return -EINVAL; } size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s); return -EINVAL; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; parsed_default_hugepagesz = true; default_hstate_idx = hstate_index(size_to_hstate(size)); /* * The number of default huge pages (for this size) could have been * specified as the first hugetlb parameter: hugepages=X. If so, * then default_hstate_max_huge_pages is set. If the default huge * page size is gigantic (> MAX_PAGE_ORDER), then the pages must be * allocated here from bootmem allocator. */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; /* * Since this is an early parameter, we can't check * NUMA node state yet, so loop through MAX_NUMNODES. */ for (i = 0; i < MAX_NUMNODES; i++) { if (default_hugepages_in_node[i] != 0) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; } default_hstate_max_huge_pages = 0; } return 0; } hugetlb_early_param("default_hugepagesz", default_hugepagesz_setup); void __init hugetlb_bootmem_set_nodes(void) { int i, nid; unsigned long start_pfn, end_pfn; if (!nodes_empty(hugetlb_bootmem_nodes)) return; for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { if (end_pfn > start_pfn) node_set(nid, hugetlb_bootmem_nodes); } } static bool __hugetlb_bootmem_allocated __initdata; bool __init hugetlb_bootmem_allocated(void) { return __hugetlb_bootmem_allocated; } void __init hugetlb_bootmem_alloc(void) { struct hstate *h; int i; if (__hugetlb_bootmem_allocated) return; hugetlb_bootmem_set_nodes(); for (i = 0; i < MAX_NUMNODES; i++) INIT_LIST_HEAD(&huge_boot_pages[i]); hugetlb_parse_params(); for_each_hstate(h) { h->next_nid_to_alloc = first_online_node; if (hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); } __hugetlb_bootmem_allocated = true; } /* * hugepage_alloc_threads command line parsing. * * When set, use this specific number of threads for the boot * allocation of hugepages. */ static int __init hugepage_alloc_threads_setup(char *s) { unsigned long allocation_threads; if (kstrtoul(s, 0, &allocation_threads) != 0) return 1; if (allocation_threads == 0) return 1; hugepage_allocation_threads = allocation_threads; return 1; } __setup("hugepage_alloc_threads=", hugepage_alloc_threads_setup); static unsigned int allowed_mems_nr(struct hstate *h) { int node; unsigned int nr = 0; nodemask_t *mbind_nodemask; unsigned int *array = h->free_huge_pages_node; gfp_t gfp_mask = htlb_alloc_mask(h); mbind_nodemask = policy_mbind_nodemask(gfp_mask); for_each_node_mask(node, cpuset_current_mems_allowed) { if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) nr += array[node]; } return nr; } #ifdef CONFIG_SYSCTL static int proc_hugetlb_doulongvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos, unsigned long *out) { struct ctl_table dup_table; /* * In order to avoid races with __do_proc_doulongvec_minmax(), we * can duplicate the @table and alter the duplicate of it. */ dup_table = *table; dup_table.data = out; return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos); } static int hugetlb_sysctl_handler_common(bool obey_mempolicy, const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp = h->max_huge_pages; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) ret = __nr_hugepages_store_common(obey_mempolicy, h, NUMA_NO_NODE, tmp, *length); out: return ret; } static int hugetlb_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(false, table, write, buffer, length, ppos); } #ifdef CONFIG_NUMA static int hugetlb_mempolicy_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { return hugetlb_sysctl_handler_common(true, table, write, buffer, length, ppos); } #endif /* CONFIG_NUMA */ static int hugetlb_overcommit_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { struct hstate *h = &default_hstate; unsigned long tmp; int ret; if (!hugepages_supported()) return -EOPNOTSUPP; tmp = h->nr_overcommit_huge_pages; if (write && hstate_is_gigantic(h)) return -EINVAL; ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, &tmp); if (ret) goto out; if (write) { spin_lock_irq(&hugetlb_lock); h->nr_overcommit_huge_pages = tmp; spin_unlock_irq(&hugetlb_lock); } out: return ret; } static const struct ctl_table hugetlb_table[] = { { .procname = "nr_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = hugetlb_sysctl_handler, }, #ifdef CONFIG_NUMA { .procname = "nr_hugepages_mempolicy", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = &hugetlb_mempolicy_sysctl_handler, }, #endif { .procname = "hugetlb_shm_group", .data = &sysctl_hugetlb_shm_group, .maxlen = sizeof(gid_t), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "nr_overcommit_hugepages", .data = NULL, .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = hugetlb_overcommit_handler, }, }; static void __init hugetlb_sysctl_init(void) { register_sysctl_init("vm", hugetlb_table); } #endif /* CONFIG_SYSCTL */ void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h; unsigned long total = 0; if (!hugepages_supported()) return; for_each_hstate(h) { unsigned long count = h->nr_huge_pages; total += huge_page_size(h) * count; if (h == &default_hstate) seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" "HugePages_Rsvd: %5lu\n" "HugePages_Surp: %5lu\n" "Hugepagesize: %8lu kB\n", count, h->free_huge_pages, h->resv_huge_pages, h->surplus_huge_pages, huge_page_size(h) / SZ_1K); } seq_printf(m, "Hugetlb: %8lu kB\n", total / SZ_1K); } int hugetlb_report_node_meminfo(char *buf, int len, int nid) { struct hstate *h = &default_hstate; if (!hugepages_supported()) return 0; return sysfs_emit_at(buf, len, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" "Node %d HugePages_Surp: %5u\n", nid, h->nr_huge_pages_node[nid], nid, h->free_huge_pages_node[nid], nid, h->surplus_huge_pages_node[nid]); } void hugetlb_show_meminfo_node(int nid) { struct hstate *h; if (!hugepages_supported()) return; for_each_hstate(h) printk("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", nid, h->nr_huge_pages_node[nid], h->free_huge_pages_node[nid], h->surplus_huge_pages_node[nid], huge_page_size(h) / SZ_1K); } void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm) { seq_printf(m, "HugetlbPages:\t%8lu kB\n", K(atomic_long_read(&mm->hugetlb_usage))); } /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { struct hstate *h; unsigned long nr_total_pages = 0; for_each_hstate(h) nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h); return nr_total_pages; } static int hugetlb_acct_memory(struct hstate *h, long delta) { int ret = -ENOMEM; if (!delta) return 0; spin_lock_irq(&hugetlb_lock); /* * When cpuset is configured, it breaks the strict hugetlb page * reservation as the accounting is done on a global variable. Such * reservation is completely rubbish in the presence of cpuset because * the reservation is not checked against page availability for the * current cpuset. Application can still potentially OOM'ed by kernel * with lack of free htlb page in cpuset that the task is in. * Attempt to enforce strict accounting with cpuset is almost * impossible (or too ugly) because cpuset is too fluid that * task or memory node can be dynamically moved between cpusets. * * The change of semantics for shared hugetlb mapping with cpuset is * undesirable. However, in order to preserve some of the semantics, * we fall back to check against current free page availability as * a best attempt and hopefully to minimize the impact of changing * semantics that cpuset has. * * Apart from cpuset, we also have memory policy mechanism that * also determines from which node the kernel will allocate memory * in a NUMA system. So similar to cpuset, we also should consider * the memory policy of the current task. Similar to the description * above. */ if (delta > 0) { if (gather_surplus_pages(h, delta) < 0) goto out; if (delta > allowed_mems_nr(h)) { return_unused_surplus_pages(h, delta); goto out; } } ret = 0; if (delta < 0) return_unused_surplus_pages(h, (unsigned long) -delta); out: spin_unlock_irq(&hugetlb_lock); return ret; } static void hugetlb_vm_op_open(struct vm_area_struct *vma) { struct resv_map *resv = vma_resv_map(vma); /* * HPAGE_RESV_OWNER indicates a private mapping. * This new VMA should share its siblings reservation map if present. * The VMA will only ever have a valid reservation map pointer where * it is being copied for another still existing VMA. As that VMA * has a reference to the reservation map it cannot disappear until * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_dup_hugetlb_cgroup_uncharge_info(resv); kref_get(&resv->refs); } /* * vma_lock structure for sharable mappings is vma specific. * Clear old pointer (if copied via vm_area_dup) and allocate * new structure. Before clearing, make sure vma_lock is not * for this vma. */ if (vma->vm_flags & VM_MAYSHARE) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; if (vma_lock) { if (vma_lock->vma != vma) { vma->vm_private_data = NULL; hugetlb_vma_lock_alloc(vma); } else pr_warn("HugeTLB: vma_lock already exists in %s.\n", __func__); } else hugetlb_vma_lock_alloc(vma); } } static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); struct resv_map *resv; struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve, start, end; long gbl_reserve; hugetlb_vma_lock_free(vma); resv = vma_resv_map(vma); if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return; start = vma_hugecache_offset(h, vma, vma->vm_start); end = vma_hugecache_offset(h, vma, vma->vm_end); reserve = (end - start) - region_count(resv, start, end); hugetlb_cgroup_uncharge_counter(resv, start, end); if (reserve) { /* * Decrement reserve counts. The global reserve count may be * adjusted if the subpool has a minimum size. */ gbl_reserve = hugepage_subpool_put_pages(spool, reserve); hugetlb_acct_memory(h, -gbl_reserve); } kref_put(&resv->refs, resv_map_release); } static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; return 0; } void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) { /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. * This function is called in the middle of a VMA split operation, with * MM, VMA and rmap all write-locked to prevent concurrent page table * walks (except hardware and gup_fast()). */ vma_assert_write_locked(vma); i_mmap_assert_write_locked(vma->vm_file->f_mapping); if (addr & ~PUD_MASK) { unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; if (floor >= vma->vm_start && ceil <= vma->vm_end) { /* * Locking: * Use take_locks=false here. * The file rmap lock is already held. * The hugetlb VMA lock can't be taken when we already * hold the file rmap lock, and we don't need it because * its purpose is to synchronize against concurrent page * table walks, which are not possible thanks to the * locks held by our caller. */ hugetlb_unshare_pmds(vma, floor, ceil, /* take_locks = */ false); } } } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) { return huge_page_size(hstate_vma(vma)); } /* * We cannot handle pagefaults against hugetlb pages at all. They cause * handle_mm_fault() to try to instantiate regular-sized pages in the * hugepage VMA. do_page_fault() is supposed to trap this, so BUG is we get * this far. */ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) { BUG(); return 0; } /* * When a new function is introduced to vm_operations_struct and added * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops. * This is because under System V memory model, mappings created via * shmget/shmat with "huge page" specified are backed by hugetlbfs files, * their original vm_ops are overwritten with shm_vm_ops. */ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, .may_split = hugetlb_vm_op_split, .pagesize = hugetlb_vm_op_pagesize, }; static pte_t make_huge_pte(struct vm_area_struct *vma, struct folio *folio, bool try_mkwrite) { pte_t entry = folio_mk_pte(folio, vma->vm_page_prot); unsigned int shift = huge_page_shift(hstate_vma(vma)); if (try_mkwrite && (vma->vm_flags & VM_WRITE)) { entry = pte_mkwrite_novma(pte_mkdirty(entry)); } else { entry = pte_wrprotect(entry); } entry = pte_mkyoung(entry); entry = arch_make_huge_pte(entry, shift, vma->vm_flags); return entry; } static void set_huge_ptep_writable(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t entry; entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(vma->vm_mm, address, ptep))); if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) update_mmu_cache(vma, address, ptep); } static void set_huge_ptep_maybe_writable(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { if (vma->vm_flags & VM_WRITE) set_huge_ptep_writable(vma, address, ptep); } bool is_hugetlb_entry_migration(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_migration_entry(swp)) return true; else return false; } bool is_hugetlb_entry_hwpoisoned(pte_t pte) { swp_entry_t swp; if (huge_pte_none(pte) || pte_present(pte)) return false; swp = pte_to_swp_entry(pte); if (is_hwpoison_entry(swp)) return true; else return false; } static void hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr, struct folio *new_folio, pte_t old, unsigned long sz) { pte_t newpte = make_huge_pte(vma, new_folio, true); __folio_mark_uptodate(new_folio); hugetlb_add_new_anon_rmap(new_folio, vma, addr); if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz); hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); folio_set_hugetlb_migratable(new_folio); } int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pte_t *src_pte, *dst_pte, entry; struct folio *pte_folio; unsigned long addr; bool cow = is_cow_mapping(src_vma->vm_flags); struct hstate *h = hstate_vma(src_vma); unsigned long sz = huge_page_size(h); unsigned long npages = pages_per_huge_page(h); struct mmu_notifier_range range; unsigned long last_addr_mask; int ret = 0; if (cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src, src_vma->vm_start, src_vma->vm_end); mmu_notifier_invalidate_range_start(&range); vma_assert_write_locked(src_vma); raw_write_seqcount_begin(&src->write_protect_seq); } else { /* * For shared mappings the vma lock must be held before * calling hugetlb_walk() in the src vma. Otherwise, the * returned ptep could go away if part of a shared pmd and * another thread calls huge_pmd_unshare. */ hugetlb_vma_lock_read(src_vma); } last_addr_mask = hugetlb_mask_last_page(h); for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = hugetlb_walk(src_vma, addr, sz); if (!src_pte) { addr |= last_addr_mask; continue; } dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz); if (!dst_pte) { ret = -ENOMEM; break; } #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING /* If the pagetables are shared, there is nothing to do */ if (ptdesc_pmd_is_shared(virt_to_ptdesc(dst_pte))) { addr |= last_addr_mask; continue; } #endif dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte); again: if (huge_pte_none(entry)) { /* * Skip if src entry none. */ ; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) { if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_hugetlb_entry_migration(entry))) { swp_entry_t swp_entry = pte_to_swp_entry(entry); bool uffd_wp = pte_swp_uffd_wp(entry); if (!is_readable_migration_entry(swp_entry) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. */ swp_entry = make_readable_migration_entry( swp_offset(swp_entry)); entry = swp_entry_to_pte(swp_entry); if (userfaultfd_wp(src_vma) && uffd_wp) entry = pte_swp_mkuffd_wp(entry); set_huge_pte_at(src, addr, src_pte, entry, sz); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(is_pte_marker(entry))) { pte_marker marker = copy_pte_marker( pte_to_swp_entry(entry), dst_vma); if (marker) set_huge_pte_at(dst, addr, dst_pte, make_pte_marker(marker), sz); } else { entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte); pte_folio = page_folio(pte_page(entry)); folio_get(pte_folio); /* * Failing to duplicate the anon rmap is a rare case * where we see pinned hugetlb pages while they're * prone to COW. We need to do the COW earlier during * fork. * * When pre-allocating the page or copying data, we * need to be without the pgtable locks since we could * sleep during the process. */ if (!folio_test_anon(pte_folio)) { hugetlb_add_file_rmap(pte_folio); } else if (hugetlb_try_dup_anon_rmap(pte_folio, src_vma)) { pte_t src_pte_old = entry; struct folio *new_folio; spin_unlock(src_ptl); spin_unlock(dst_ptl); /* Do not use reserve as it's private owned */ new_folio = alloc_hugetlb_folio(dst_vma, addr, false); if (IS_ERR(new_folio)) { folio_put(pte_folio); ret = PTR_ERR(new_folio); break; } ret = copy_user_large_folio(new_folio, pte_folio, addr, dst_vma); folio_put(pte_folio); if (ret) { folio_put(new_folio); break; } /* Install the new hugetlb folio if src pte stable */ dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte); if (!pte_same(src_pte_old, entry)) { restore_reserve_on_error(h, dst_vma, addr, new_folio); folio_put(new_folio); /* huge_ptep of dst_pte won't change as in child */ goto again; } hugetlb_install_folio(dst_vma, dst_pte, addr, new_folio, src_pte_old, sz); spin_unlock(src_ptl); spin_unlock(dst_ptl); continue; } if (cow) { /* * No need to notify as we are downgrading page * table protection not changing it to point * to a new page. * * See Documentation/mm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); entry = huge_pte_wrprotect(entry); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); hugetlb_count_add(npages, dst); } spin_unlock(src_ptl); spin_unlock(dst_ptl); } if (cow) { raw_write_seqcount_end(&src->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } else { hugetlb_vma_unlock_read(src_vma); } return ret; } static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte, unsigned long sz) { bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma); struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; spinlock_t *src_ptl, *dst_ptl; pte_t pte; dst_ptl = huge_pte_lock(h, mm, dst_pte); src_ptl = huge_pte_lockptr(h, mm, src_pte); /* * We don't have to worry about the ordering of src and dst ptlocks * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock. */ if (src_ptl != dst_ptl) spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); pte = huge_ptep_get_and_clear(mm, old_addr, src_pte, sz); if (need_clear_uffd_wp && pte_marker_uffd_wp(pte)) huge_pte_clear(mm, new_addr, dst_pte, sz); else { if (need_clear_uffd_wp) { if (pte_present(pte)) pte = huge_pte_clear_uffd_wp(pte); else if (is_swap_pte(pte)) pte = pte_swp_clear_uffd_wp(pte); } set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); } if (src_ptl != dst_ptl) spin_unlock(src_ptl); spin_unlock(dst_ptl); } int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { struct hstate *h = hstate_vma(vma); struct address_space *mapping = vma->vm_file->f_mapping; unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; unsigned long old_end = old_addr + len; unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; bool shared_pmd = false; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* * In case of shared PMDs, we should cover the maximum possible * range. */ flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); last_addr_mask = hugetlb_mask_last_page(h); /* Prevent race with file truncation */ hugetlb_vma_lock_write(vma); i_mmap_lock_write(mapping); for (; old_addr < old_end; old_addr += sz, new_addr += sz) { src_pte = hugetlb_walk(vma, old_addr, sz); if (!src_pte) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } if (huge_pte_none(huge_ptep_get(mm, old_addr, src_pte))) continue; if (huge_pmd_unshare(mm, vma, old_addr, src_pte)) { shared_pmd = true; old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); if (!dst_pte) break; move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); } if (shared_pmd) flush_hugetlb_tlb_range(vma, range.start, range.end); else flush_hugetlb_tlb_range(vma, old_end - len, old_end); mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); hugetlb_vma_unlock_write(vma); return len + old_addr - old_end; } void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct folio *folio, zap_flags_t zap_flags) { struct mm_struct *mm = vma->vm_mm; const bool folio_provided = !!folio; unsigned long address; pte_t *ptep; pte_t pte; spinlock_t *ptl; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); bool adjust_reservation; unsigned long last_addr_mask; bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); /* * This is a hugetlb vma, all the pte entries should point * to huge page. */ tlb_change_page_size(tlb, sz); tlb_start_vma(tlb, vma); last_addr_mask = hugetlb_mask_last_page(h); address = start; for (; address < end; address += sz) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) { address |= last_addr_mask; continue; } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { spin_unlock(ptl); tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); force_flush = true; address |= last_addr_mask; continue; } pte = huge_ptep_get(mm, address, ptep); if (huge_pte_none(pte)) { spin_unlock(ptl); continue; } /* * Migrating hugepage or HWPoisoned hugepage is already * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { /* * If the pte was wr-protected by uffd-wp in any of the * swap forms, meanwhile the caller does not want to * drop the uffd-wp bit in this zap, then replace the * pte with a marker. */ if (pte_swp_uffd_wp_any(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), sz); else huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; } /* * If a folio is supplied, it is because a specific * folio is being unmapped, not a range. Ensure the folio we * are about to unmap is the actual folio of interest. */ if (folio_provided) { if (folio != page_folio(pte_page(pte))) { spin_unlock(ptl); continue; } /* * Mark the VMA as having unmapped its page so that * future faults in this VMA will fail rather than * looking like data was lost */ set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED); } else { folio = page_folio(pte_page(pte)); } pte = huge_ptep_get_and_clear(mm, address, ptep, sz); tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) folio_mark_dirty(folio); /* Leave a uffd-wp pte marker if needed */ if (huge_pte_uffd_wp(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), sz); hugetlb_count_sub(pages_per_huge_page(h), mm); hugetlb_remove_rmap(folio); spin_unlock(ptl); /* * Restore the reservation for anonymous page, otherwise the * backing page could be stolen by someone. * If there we are freeing a surplus, do not set the restore * reservation bit. */ adjust_reservation = false; spin_lock_irq(&hugetlb_lock); if (!h->surplus_huge_pages && __vma_private_lock(vma) && folio_test_anon(folio)) { folio_set_hugetlb_restore_reserve(folio); /* Reservation to be adjusted after the spin lock */ adjust_reservation = true; } spin_unlock_irq(&hugetlb_lock); /* * Adjust the reservation for the region that will have the * reserve restored. Keep in mind that vma_needs_reservation() changes * resv->adds_in_progress if it succeeds. If this is not done, * do_exit() will not see it, and will keep the reservation * forever. */ if (adjust_reservation) { int rc = vma_needs_reservation(h, vma, address); if (rc < 0) /* Pressumably allocate_file_region_entries failed * to allocate a file_region struct. Clear * hugetlb_restore_reserve so that global reserve * count will not be incremented by free_huge_folio. * Act as if we consumed the reservation. */ folio_clear_hugetlb_restore_reserve(folio); else if (rc) vma_add_reservation(h, vma, address); } tlb_remove_page_size(tlb, folio_page(folio, 0), folio_size(folio)); /* * If we were instructed to unmap a specific folio, we're done. */ if (folio_provided) break; } tlb_end_vma(tlb, vma); /* * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We * could defer the flush until now, since by holding i_mmap_rwsem we * guaranteed that the last refernece would not be dropped. But we must * do the flushing before we return, as otherwise i_mmap_rwsem will be * dropped and the last reference to the shared PMDs page might be * dropped as well. * * In theory we could defer the freeing of the PMD pages as well, but * huge_pmd_unshare() relies on the exact page_count for the PMD page to * detect sharing, so we cannot defer the release of the page either. * Instead, do flush now. */ if (force_flush) tlb_flush_mmu_tlbonly(tlb); } void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (!vma->vm_file) /* hugetlbfs_file_mmap error */ return; adjust_range_if_pmd_sharing_possible(vma, start, end); hugetlb_vma_lock_write(vma); if (vma->vm_file) i_mmap_lock_write(vma->vm_file->f_mapping); } void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { zap_flags_t zap_flags = details ? details->zap_flags : 0; if (!vma->vm_file) /* hugetlbfs_file_mmap error */ return; if (zap_flags & ZAP_FLAG_UNMAP) { /* final unmap */ /* * Unlock and free the vma lock before releasing i_mmap_rwsem. * When the vma_lock is freed, this makes the vma ineligible * for pmd sharing. And, i_mmap_rwsem is required to set up * pmd sharing. This is important as page tables for this * unmapped range will be asynchrously deleted. If the page * tables are shared, there will be issues when accessed by * someone else. */ __hugetlb_vma_unlock_write_free(vma); } else { hugetlb_vma_unlock_write(vma); } if (vma->vm_file) i_mmap_unlock_write(vma->vm_file->f_mapping); } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct folio *folio, zap_flags_t zap_flags) { struct mmu_notifier_range range; struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); mmu_notifier_invalidate_range_start(&range); tlb_gather_mmu(&tlb, vma->vm_mm); __unmap_hugepage_range(&tlb, vma, start, end, folio, zap_flags); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } /* * This is called when the original mapper is failing to COW a MAP_PRIVATE * mapping it owns the reserve page for. The intention is to unmap the page * from other VMAs and let the children be SIGKILLed if they are faulting the * same region. */ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, struct folio *folio, unsigned long address) { struct hstate *h = hstate_vma(vma); struct vm_area_struct *iter_vma; struct address_space *mapping; pgoff_t pgoff; /* * vm_pgoff is in PAGE_SIZE units, hence the different calculation * from page cache lookup which is in HPAGE_SIZE units. */ address = address & huge_page_mask(h); pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; mapping = vma->vm_file->f_mapping; /* * Take the mapping lock for the duration of the table walk. As * this mapping should be shared between all the VMAs, * __unmap_hugepage_range() is called as the lock is already held */ i_mmap_lock_write(mapping); vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) continue; /* * Shared VMAs have their own reserves and do not affect * MAP_PRIVATE accounting but it is possible that a shared * VMA is using the same page so check and skip such VMAs. */ if (iter_vma->vm_flags & VM_MAYSHARE) continue; /* * Unmap the page from other VMAs without their own reserves. * They get marked to be SIGKILLed if they fault in these * areas. This is because a future no-page fault on this VMA * could insert a zeroed page instead of the data existing * from the time of fork. This would look like data corruption */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) unmap_hugepage_range(iter_vma, address, address + huge_page_size(h), folio, 0); } i_mmap_unlock_write(mapping); } /* * hugetlb_wp() should be called with page lock of the original hugepage held. * Called with hugetlb_fault_mutex_table held and pte_page locked so we * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ static vm_fault_t hugetlb_wp(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; pte_t pte = huge_ptep_get(mm, vmf->address, vmf->pte); struct hstate *h = hstate_vma(vma); struct folio *old_folio; struct folio *new_folio; bool cow_from_owner = 0; vm_fault_t ret = 0; struct mmu_notifier_range range; /* * Never handle CoW for uffd-wp protected pages. It should be only * handled when the uffd-wp protection is removed. * * Note that only the CoW optimization path (in hugetlb_no_page()) * can trigger this, because hugetlb_fault() will always resolve * uffd-wp bit first. */ if (!unshare && huge_pte_uffd_wp(pte)) return 0; /* Let's take out MAP_SHARED mappings first. */ if (vma->vm_flags & VM_MAYSHARE) { set_huge_ptep_writable(vma, vmf->address, vmf->pte); return 0; } old_folio = page_folio(pte_page(pte)); delayacct_wpcopy_start(); retry_avoidcopy: /* * If no-one else is actually using this page, we're the exclusive * owner and can reuse this page. * * Note that we don't rely on the (safer) folio refcount here, because * copying the hugetlb folio when there are unexpected (temporary) * folio references could harm simple fork()+exit() users when * we run out of free hugetlb folios: we would have to kill processes * in scenarios that used to work. As a side effect, there can still * be leaks between processes, for example, with FOLL_GET users. */ if (folio_mapcount(old_folio) == 1 && folio_test_anon(old_folio)) { if (!PageAnonExclusive(&old_folio->page)) { folio_move_anon_rmap(old_folio, vma); SetPageAnonExclusive(&old_folio->page); } if (likely(!unshare)) set_huge_ptep_maybe_writable(vma, vmf->address, vmf->pte); delayacct_wpcopy_end(); return 0; } VM_BUG_ON_PAGE(folio_test_anon(old_folio) && PageAnonExclusive(&old_folio->page), &old_folio->page); /* * If the process that created a MAP_PRIVATE mapping is about to perform * a COW due to a shared page count, attempt to satisfy the allocation * without using the existing reserves. * In order to determine where this is a COW on a MAP_PRIVATE mapping it * is enough to check whether the old_folio is anonymous. This means that * the reserve for this address was consumed. If reserves were used, a * partial faulted mapping at the fime of fork() could consume its reserves * on COW instead of the full address range. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && folio_test_anon(old_folio)) cow_from_owner = true; folio_get(old_folio); /* * Drop page table lock as buddy allocator may be called. It will * be acquired again before returning to the caller, as expected. */ spin_unlock(vmf->ptl); new_folio = alloc_hugetlb_folio(vma, vmf->address, cow_from_owner); if (IS_ERR(new_folio)) { /* * If a process owning a MAP_PRIVATE mapping fails to COW, * it is due to references held by a child and an insufficient * huge page pool. To guarantee the original mappers * reliability, unmap the page from child processes. The child * may get SIGKILLed if it later faults. */ if (cow_from_owner) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx; u32 hash; folio_put(old_folio); /* * Drop hugetlb_fault_mutex and vma_lock before * unmapping. unmapping needs to hold vma_lock * in write mode. Dropping vma_lock in read mode * here is OK as COW mappings do not interact with * PMD sharing. * * Reacquire both after unmap operation. */ idx = vma_hugecache_offset(h, vma, vmf->address); hash = hugetlb_fault_mutex_hash(mapping, idx); hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); unmap_ref_private(mm, vma, old_folio, vmf->address); mutex_lock(&hugetlb_fault_mutex_table[hash]); hugetlb_vma_lock_read(vma); spin_lock(vmf->ptl); vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); if (likely(vmf->pte && pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), pte))) goto retry_avoidcopy; /* * race occurs while re-acquiring page table * lock, and our job is done. */ delayacct_wpcopy_end(); return 0; } ret = vmf_error(PTR_ERR(new_folio)); goto out_release_old; } /* * When the original hugepage is shared one, it does not have * anon_vma prepared. */ ret = __vmf_anon_prepare(vmf); if (unlikely(ret)) goto out_release_all; if (copy_user_large_folio(new_folio, old_folio, vmf->real_address, vma)) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_release_all; } __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address, vmf->address + huge_page_size(h)); mmu_notifier_invalidate_range_start(&range); /* * Retake the page table lock to check for racing updates * before the page tables are altered */ spin_lock(vmf->ptl); vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); if (likely(vmf->pte && pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), pte))) { pte_t newpte = make_huge_pte(vma, new_folio, !unshare); /* Break COW or unshare */ huge_ptep_clear_flush(vma, vmf->address, vmf->pte); hugetlb_remove_rmap(old_folio); hugetlb_add_new_anon_rmap(new_folio, vma, vmf->address); if (huge_pte_uffd_wp(pte)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(mm, vmf->address, vmf->pte, newpte, huge_page_size(h)); folio_set_hugetlb_migratable(new_folio); /* Make the old page be freed below */ new_folio = old_folio; } spin_unlock(vmf->ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: /* * No restore in case of successful pagetable update (Break COW or * unshare) */ if (new_folio != old_folio) restore_reserve_on_error(h, vma, vmf->address, new_folio); folio_put(new_folio); out_release_old: folio_put(old_folio); spin_lock(vmf->ptl); /* Caller expects lock to be held */ delayacct_wpcopy_end(); return ret; } /* * Return whether there is a pagecache page to back given address within VMA. */ bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = linear_page_index(vma, address); struct folio *folio; folio = filemap_get_folio(mapping, idx); if (IS_ERR(folio)) return false; folio_put(folio); return true; } int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx) { struct inode *inode = mapping->host; struct hstate *h = hstate_inode(inode); int err; idx <<= huge_page_order(h); __folio_set_locked(folio); err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL); if (unlikely(err)) { __folio_clear_locked(folio); return err; } folio_clear_hugetlb_restore_reserve(folio); /* * mark folio dirty so that it will not be removed from cache/file * by non-hugetlbfs specific code paths. */ folio_mark_dirty(folio); spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); return 0; } static inline vm_fault_t hugetlb_handle_userfault(struct vm_fault *vmf, struct address_space *mapping, unsigned long reason) { u32 hash; /* * vma_lock and hugetlb_fault_mutex must be dropped before handling * userfault. Also mmap_lock could be dropped due to handling * userfault, any vma operation should be careful from here. */ hugetlb_vma_unlock_read(vmf->vma); hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return handle_userfault(vmf, reason); } /* * Recheck pte with pgtable lock. Returns true if pte didn't change, or * false if pte changed or is changing. */ static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t old_pte) { spinlock_t *ptl; bool same; ptl = huge_pte_lock(h, mm, ptep); same = pte_same(huge_ptep_get(mm, addr, ptep), old_pte); spin_unlock(ptl); return same; } static vm_fault_t hugetlb_no_page(struct address_space *mapping, struct vm_fault *vmf) { u32 hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); bool new_folio, new_anon_folio = false; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; bool folio_locked = true; struct folio *folio; unsigned long size; pte_t new_pte; /* * Currently, we are forced to kill the process in the event the * original mapper has unmapped pages from the child due to a failed * COW/unsharing. Warn that such a situation has occurred as it may not * be obvious. */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", current->pid); goto out; } /* * Use page lock to guard against racing truncation * before we get page_table_lock. */ new_folio = false; folio = filemap_lock_hugetlb_folio(h, mapping, vmf->pgoff); if (IS_ERR(folio)) { size = i_size_read(mapping->host) >> huge_page_shift(h); if (vmf->pgoff >= size) goto out; /* Check for page in userfault range */ if (userfaultfd_missing(vma)) { /* * Since hugetlb_no_page() was examining pte * without pgtable lock, we need to re-test under * lock because the pte may not be stable and could * have changed from under us. Try to detect * either changed or during-changing ptes and retry * properly when needed. * * Note that userfaultfd is actually fine with * false positives (e.g. caused by pte changed), * but not wrong logical events (e.g. caused by * reading a pte during changing). The latter can * confuse the userspace, so the strictness is very * much preferred. E.g., MISSING event should * never happen on the page after UFFDIO_COPY has * correctly installed the page and returned. */ if (!hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } return hugetlb_handle_userfault(vmf, mapping, VM_UFFD_MISSING); } if (!(vma->vm_flags & VM_MAYSHARE)) { ret = __vmf_anon_prepare(vmf); if (unlikely(ret)) goto out; } folio = alloc_hugetlb_folio(vma, vmf->address, false); if (IS_ERR(folio)) { /* * Returning error will result in faulting task being * sent SIGBUS. The hugetlb fault mutex prevents two * tasks from racing to fault in the same page which * could result in false unable to allocate errors. * Page migration does not take the fault mutex, but * does a clear then write of pte's under page table * lock. Page fault code could race with migration, * notice the clear pte and try to allocate a page * here. Before returning error, get ptl and make * sure there really is no pte entry. */ if (hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) ret = vmf_error(PTR_ERR(folio)); else ret = 0; goto out; } folio_zero_user(folio, vmf->real_address); __folio_mark_uptodate(folio); new_folio = true; if (vma->vm_flags & VM_MAYSHARE) { int err = hugetlb_add_to_page_cache(folio, mapping, vmf->pgoff); if (err) { /* * err can't be -EEXIST which implies someone * else consumed the reservation since hugetlb * fault mutex is held when add a hugetlb page * to the page cache. So it's safe to call * restore_reserve_on_error() here. */ restore_reserve_on_error(h, vma, vmf->address, folio); folio_put(folio); ret = VM_FAULT_SIGBUS; goto out; } } else { new_anon_folio = true; folio_lock(folio); } } else { /* * If memory error occurs between mmap() and fault, some process * don't have hwpoisoned swap entry for errored virtual address. * So we need to block hugepage fault by PG_hwpoison bit check. */ if (unlikely(folio_test_hwpoison(folio))) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } /* Check for page in userfault range. */ if (userfaultfd_minor(vma)) { folio_unlock(folio); folio_put(folio); /* See comment in userfaultfd_missing() block above */ if (!hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } return hugetlb_handle_userfault(vmf, mapping, VM_UFFD_MINOR); } } /* * If we are going to COW a private mapping later, we examine the * pending reservations for this page now. This will ensure that * any allocations necessary to record that reservation occur outside * the spinlock. */ if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { if (vma_needs_reservation(h, vma, vmf->address) < 0) { ret = VM_FAULT_OOM; goto backout_unlocked; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, vmf->address); } vmf->ptl = huge_pte_lock(h, mm, vmf->pte); ret = 0; /* If pte changed from under us, retry */ if (!pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), vmf->orig_pte)) goto backout; if (new_anon_folio) hugetlb_add_new_anon_rmap(folio, vma, vmf->address); else hugetlb_add_file_rmap(folio); new_pte = make_huge_pte(vma, folio, vma->vm_flags & VM_SHARED); /* * If this pte was previously wr-protected, keep it wr-protected even * if populated. */ if (unlikely(pte_marker_uffd_wp(vmf->orig_pte))) new_pte = huge_pte_mkuffd_wp(new_pte); set_huge_pte_at(mm, vmf->address, vmf->pte, new_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), mm); if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* * No need to keep file folios locked. See comment in * hugetlb_fault(). */ if (!new_anon_folio) { folio_locked = false; folio_unlock(folio); } /* Optimization, do the COW without a second fault */ ret = hugetlb_wp(vmf); } spin_unlock(vmf->ptl); /* * Only set hugetlb_migratable in newly allocated pages. Existing pages * found in the pagecache may not have hugetlb_migratable if they have * been isolated for migration. */ if (new_folio) folio_set_hugetlb_migratable(folio); if (folio_locked) folio_unlock(folio); out: hugetlb_vma_unlock_read(vma); /* * We must check to release the per-VMA lock. __vmf_anon_prepare() is * the only way ret can be set to VM_FAULT_RETRY. */ if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return ret; backout: spin_unlock(vmf->ptl); backout_unlocked: /* We only need to restore reservations for private mappings */ if (new_anon_folio) restore_reserve_on_error(h, vma, vmf->address, folio); folio_unlock(folio); folio_put(folio); goto out; } #ifdef CONFIG_SMP u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { unsigned long key[2]; u32 hash; key[0] = (unsigned long) mapping; key[1] = idx; hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0); return hash & (num_fault_mutexes - 1); } #else /* * For uniprocessor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { return 0; } #endif vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { vm_fault_t ret; u32 hash; struct folio *folio = NULL; struct hstate *h = hstate_vma(vma); struct address_space *mapping; bool need_wait_lock = false; struct vm_fault vmf = { .vma = vma, .address = address & huge_page_mask(h), .real_address = address, .flags = flags, .pgoff = vma_hugecache_offset(h, vma, address & huge_page_mask(h)), /* TODO: Track hugetlb faults using vm_fault */ /* * Some fields may not be initialized, be careful as it may * be hard to debug if called functions make assumptions */ }; /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ mapping = vma->vm_file->f_mapping; hash = hugetlb_fault_mutex_hash(mapping, vmf.pgoff); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* * Acquire vma lock before calling huge_pte_alloc and hold * until finished with vmf.pte. This prevents huge_pmd_unshare from * being called elsewhere and making the vmf.pte no longer valid. */ hugetlb_vma_lock_read(vma); vmf.pte = huge_pte_alloc(mm, vma, vmf.address, huge_page_size(h)); if (!vmf.pte) { hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return VM_FAULT_OOM; } vmf.orig_pte = huge_ptep_get(mm, vmf.address, vmf.pte); if (huge_pte_none_mostly(vmf.orig_pte)) { if (is_pte_marker(vmf.orig_pte)) { pte_marker marker = pte_marker_get(pte_to_swp_entry(vmf.orig_pte)); if (marker & PTE_MARKER_POISONED) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; } else if (WARN_ON_ONCE(marker & PTE_MARKER_GUARD)) { /* This isn't supported in hugetlb. */ ret = VM_FAULT_SIGSEGV; goto out_mutex; } } /* * Other PTE markers should be handled the same way as none PTE. * * hugetlb_no_page will drop vma lock and hugetlb fault * mutex internally, which make us return immediately. */ return hugetlb_no_page(mapping, &vmf); } ret = 0; /* Not present, either a migration or a hwpoisoned entry */ if (!pte_present(vmf.orig_pte)) { if (is_hugetlb_entry_migration(vmf.orig_pte)) { /* * Release the hugetlb fault lock now, but retain * the vma lock, because it is needed to guard the * huge_pte_lockptr() later in * migration_entry_wait_huge(). The vma lock will * be released there. */ mutex_unlock(&hugetlb_fault_mutex_table[hash]); migration_entry_wait_huge(vma, vmf.address, vmf.pte); return 0; } else if (is_hugetlb_entry_hwpoisoned(vmf.orig_pte)) ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; } /* * If we are going to COW/unshare the mapping later, we examine the * pending reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the * spinlock. */ if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(vmf.orig_pte)) { if (vma_needs_reservation(h, vma, vmf.address) < 0) { ret = VM_FAULT_OOM; goto out_mutex; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, vmf.address); } vmf.ptl = huge_pte_lock(h, mm, vmf.pte); /* Check for a racing update before calling hugetlb_wp() */ if (unlikely(!pte_same(vmf.orig_pte, huge_ptep_get(mm, vmf.address, vmf.pte)))) goto out_ptl; /* Handle userfault-wp first, before trying to lock more pages */ if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(mm, vmf.address, vmf.pte)) && (flags & FAULT_FLAG_WRITE) && !huge_pte_write(vmf.orig_pte)) { if (!userfaultfd_wp_async(vma)) { spin_unlock(vmf.ptl); hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return handle_userfault(&vmf, VM_UFFD_WP); } vmf.orig_pte = huge_pte_clear_uffd_wp(vmf.orig_pte); set_huge_pte_at(mm, vmf.address, vmf.pte, vmf.orig_pte, huge_page_size(hstate_vma(vma))); /* Fallthrough to CoW */ } if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!huge_pte_write(vmf.orig_pte)) { /* * Anonymous folios need to be lock since hugetlb_wp() * checks whether we can re-use the folio exclusively * for us in case we are the only user of it. */ folio = page_folio(pte_page(vmf.orig_pte)); if (folio_test_anon(folio) && !folio_trylock(folio)) { need_wait_lock = true; goto out_ptl; } folio_get(folio); ret = hugetlb_wp(&vmf); if (folio_test_anon(folio)) folio_unlock(folio); folio_put(folio); goto out_ptl; } else if (likely(flags & FAULT_FLAG_WRITE)) { vmf.orig_pte = huge_pte_mkdirty(vmf.orig_pte); } } vmf.orig_pte = pte_mkyoung(vmf.orig_pte); if (huge_ptep_set_access_flags(vma, vmf.address, vmf.pte, vmf.orig_pte, flags & FAULT_FLAG_WRITE)) update_mmu_cache(vma, vmf.address, vmf.pte); out_ptl: spin_unlock(vmf.ptl); out_mutex: hugetlb_vma_unlock_read(vma); /* * We must check to release the per-VMA lock. __vmf_anon_prepare() in * hugetlb_wp() is the only way ret can be set to VM_FAULT_RETRY. */ if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); /* * hugetlb_wp drops all the locks, but the folio lock, before trying to * unmap the folio from other processes. During that window, if another * process mapping that folio faults in, it will take the mutex and then * it will wait on folio_lock, causing an ABBA deadlock. * Use trylock instead and bail out if we fail. * * Ideally, we should hold a refcount on the folio we wait for, but we do * not want to use the folio after it becomes unlocked, but rather just * wait for it to become unlocked, so hopefully next fault successes on * the trylock. */ if (need_wait_lock) folio_wait_locked(folio); return ret; } #ifdef CONFIG_USERFAULTFD /* * Can probably be eliminated, but still used by hugetlb_mfill_atomic_pte(). */ static struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct mempolicy *mpol; nodemask_t *nodemask; struct folio *folio; gfp_t gfp_mask; int node; gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); /* * This is used to allocate a temporary hugetlb to hold the copied * content, which will then be copied again to the final hugetlb * consuming a reservation. Set the alloc_fallback to false to indicate * that breaking the per-node hugetlb pool is not allowed in this case. */ folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask, false); mpol_cond_put(mpol); return folio; } /* * Used by userfaultfd UFFDIO_* ioctls. Based on userfaultfd's mfill_atomic_pte * with modifications for hugetlb pages. */ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { struct mm_struct *dst_mm = dst_vma->vm_mm; bool is_continue = uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE); bool wp_enabled = (flags & MFILL_ATOMIC_WP); struct hstate *h = hstate_vma(dst_vma); struct address_space *mapping = dst_vma->vm_file->f_mapping; pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr); unsigned long size = huge_page_size(h); int vm_shared = dst_vma->vm_flags & VM_SHARED; pte_t _dst_pte; spinlock_t *ptl; int ret = -ENOMEM; struct folio *folio; bool folio_in_pagecache = false; if (uffd_flags_mode_is(flags, MFILL_ATOMIC_POISON)) { ptl = huge_pte_lock(h, dst_mm, dst_pte); /* Don't overwrite any existing PTEs (even markers) */ if (!huge_pte_none(huge_ptep_get(dst_mm, dst_addr, dst_pte))) { spin_unlock(ptl); return -EEXIST; } _dst_pte = make_pte_marker(PTE_MARKER_POISONED); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, size); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); return 0; } if (is_continue) { ret = -EFAULT; folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) goto out; folio_in_pagecache = true; } else if (!*foliop) { /* If a folio already exists, then it's UFFDIO_COPY for * a non-missing case. Return -EEXIST. */ if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { ret = -EEXIST; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, false); if (IS_ERR(folio)) { pte_t *actual_pte = hugetlb_walk(dst_vma, dst_addr, PMD_SIZE); if (actual_pte) { ret = -EEXIST; goto out; } ret = -ENOMEM; goto out; } ret = copy_folio_from_user(folio, (const void __user *) src_addr, false); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; /* Free the allocated folio which may have * consumed a reservation. */ restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); /* Allocate a temporary folio to hold the copied * contents. */ folio = alloc_hugetlb_folio_vma(h, dst_vma, dst_addr); if (!folio) { ret = -ENOMEM; goto out; } *foliop = folio; /* Set the outparam foliop and return to the caller to * copy the contents outside the lock. Don't free the * folio. */ goto out; } } else { if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { folio_put(*foliop); ret = -EEXIST; *foliop = NULL; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, false); if (IS_ERR(folio)) { folio_put(*foliop); ret = -ENOMEM; *foliop = NULL; goto out; } ret = copy_user_large_folio(folio, *foliop, dst_addr, dst_vma); folio_put(*foliop); *foliop = NULL; if (ret) { folio_put(folio); goto out; } } /* * If we just allocated a new page, we need a memory barrier to ensure * that preceding stores to the page become visible before the * set_pte_at() write. The memory barrier inside __folio_mark_uptodate * is what we need. * * In the case where we have not allocated a new page (is_continue), * the page must already be uptodate. UFFDIO_CONTINUE already includes * an earlier smp_wmb() to ensure that prior stores will be visible * before the set_pte_at() write. */ if (!is_continue) __folio_mark_uptodate(folio); else WARN_ON_ONCE(!folio_test_uptodate(folio)); /* Add shared, newly allocated pages to the page cache. */ if (vm_shared && !is_continue) { ret = -EFAULT; if (idx >= (i_size_read(mapping->host) >> huge_page_shift(h))) goto out_release_nounlock; /* * Serialization between remove_inode_hugepages() and * hugetlb_add_to_page_cache() below happens through the * hugetlb_fault_mutex_table that here must be hold by * the caller. */ ret = hugetlb_add_to_page_cache(folio, mapping, idx); if (ret) goto out_release_nounlock; folio_in_pagecache = true; } ptl = huge_pte_lock(h, dst_mm, dst_pte); ret = -EIO; if (folio_test_hwpoison(folio)) goto out_release_unlock; /* * We allow to overwrite a pte marker: consider when both MISSING|WP * registered, we firstly wr-protect a none pte which has no page cache * page backing it, then access the page. */ ret = -EEXIST; if (!huge_pte_none_mostly(huge_ptep_get(dst_mm, dst_addr, dst_pte))) goto out_release_unlock; if (folio_in_pagecache) hugetlb_add_file_rmap(folio); else hugetlb_add_new_anon_rmap(folio, dst_vma, dst_addr); /* * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY * with wp flag set, don't set pte write bit. */ _dst_pte = make_huge_pte(dst_vma, folio, !wp_enabled && !(is_continue && !vm_shared)); /* * Always mark UFFDIO_COPY page dirty; note that this may not be * extremely important for hugetlbfs for now since swapping is not * supported, but we should still be clear in that this page cannot be * thrown away at will, even if write bit not set. */ _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); if (wp_enabled) _dst_pte = huge_pte_mkuffd_wp(_dst_pte); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, size); hugetlb_count_add(pages_per_huge_page(h), dst_mm); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); if (!is_continue) folio_set_hugetlb_migratable(folio); if (vm_shared || is_continue) folio_unlock(folio); ret = 0; out: return ret; out_release_unlock: spin_unlock(ptl); if (vm_shared || is_continue) folio_unlock(folio); out_release_nounlock: if (!folio_in_pagecache) restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); goto out; } #endif /* CONFIG_USERFAULTFD */ long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long start = address; pte_t *ptep; pte_t pte; struct hstate *h = hstate_vma(vma); long pages = 0, psize = huge_page_size(h); bool shared_pmd = false; struct mmu_notifier_range range; unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; /* * In the case of shared PMDs, the area to flush could be beyond * start/end. Set range.start/range.end to cover the maximum possible * range if PMD sharing is possible. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); last_addr_mask = hugetlb_mask_last_page(h); for (; address < end; address += psize) { spinlock_t *ptl; ptep = hugetlb_walk(vma, address, psize); if (!ptep) { if (!uffd_wp) { address |= last_addr_mask; continue; } /* * Userfaultfd wr-protect requires pgtable * pre-allocations to install pte markers. */ ptep = huge_pte_alloc(mm, vma, address, psize); if (!ptep) { pages = -ENOMEM; break; } } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it * happened due to some reason. */ WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); shared_pmd = true; address |= last_addr_mask; continue; } pte = huge_ptep_get(mm, address, ptep); if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { /* Nothing to do. */ } else if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); struct folio *folio = pfn_swap_entry_folio(entry); pte_t newpte = pte; if (is_writable_migration_entry(entry)) { if (folio_test_anon(folio)) entry = make_readable_exclusive_migration_entry( swp_offset(entry)); else entry = make_readable_migration_entry( swp_offset(entry)); newpte = swp_entry_to_pte(entry); pages++; } if (uffd_wp) newpte = pte_swp_mkuffd_wp(newpte); else if (uffd_wp_resolve) newpte = pte_swp_clear_uffd_wp(newpte); if (!pte_same(pte, newpte)) set_huge_pte_at(mm, address, ptep, newpte, psize); } else if (unlikely(is_pte_marker(pte))) { /* * Do nothing on a poison marker; page is * corrupted, permissons do not apply. Here * pte_marker_uffd_wp()==true implies !poison * because they're mutual exclusive. */ if (pte_marker_uffd_wp(pte) && uffd_wp_resolve) /* Safe to modify directly (non-present->none). */ huge_pte_clear(mm, address, ptep, psize); } else if (!huge_pte_none(pte)) { pte_t old_pte; unsigned int shift = huge_page_shift(hstate_vma(vma)); old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = huge_pte_modify(old_pte, newprot); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (uffd_wp) pte = huge_pte_mkuffd_wp(pte); else if (uffd_wp_resolve) pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; } else { /* None pte */ if (unlikely(uffd_wp)) /* Safe to modify directly (none->non-present). */ set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), psize); } spin_unlock(ptl); cond_resched(); } /* * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: * once we release i_mmap_rwsem, another task can do the final put_page * and that page table be reused and filled with junk. If we actually * did unshare a page of pmds, flush the range corresponding to the pud. */ if (shared_pmd) flush_hugetlb_tlb_range(vma, range.start, range.end); else flush_hugetlb_tlb_range(vma, start, end); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are * downgrading page table protection not changing it to point to a new * page. * * See Documentation/mm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); return pages > 0 ? (pages << h->order) : pages; } /* * Update the reservation map for the range [from, to]. * * Returns the number of entries that would be added to the reservation map * associated with the range [from, to]. This number is greater or equal to * zero. -EINVAL or -ENOMEM is returned in case of any errors. */ long hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags) { long chg = -1, add = -1, spool_resv, gbl_resv; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; struct hugetlb_cgroup *h_cg = NULL; long gbl_reserve, regions_needed = 0; /* This should never happen */ if (from > to) { VM_WARN(1, "%s called with a negative range\n", __func__); return -EINVAL; } /* * vma specific semaphore used for pmd sharing and fault/truncation * synchronization */ hugetlb_vma_lock_alloc(vma); /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page * without using reserves */ if (vm_flags & VM_NORESERVE) return 0; /* * Shared mappings base their reservation on the number of pages that * are already allocated on behalf of the file. Private mappings need * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !vma is a shm mapping */ if (!vma || vma->vm_flags & VM_MAYSHARE) { /* * resv_map can not be NULL as hugetlb_reserve_pages is only * called for inodes for which resv_maps were created (see * hugetlbfs_get_inode). */ resv_map = inode_resv_map(inode); chg = region_chg(resv_map, from, to, ®ions_needed); } else { /* Private mapping. */ resv_map = resv_map_alloc(); if (!resv_map) goto out_err; chg = to - from; set_vma_resv_map(vma, resv_map); set_vma_resv_flags(vma, HPAGE_RESV_OWNER); } if (chg < 0) goto out_err; if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), &h_cg) < 0) goto out_err; if (vma && !(vma->vm_flags & VM_MAYSHARE) && h_cg) { /* For private mappings, the hugetlb_cgroup uncharge info hangs * of the resv_map. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h); } /* * There must be enough pages in the subpool for the mapping. If * the subpool has a minimum size, there may be some global * reservations already in place (gbl_reserve). */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); if (gbl_reserve < 0) goto out_uncharge_cgroup; /* * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ if (hugetlb_acct_memory(h, gbl_reserve) < 0) goto out_put_pages; /* * Account for the reservations made. Shared mappings record regions * that have reservations as they are shared by multiple VMAs. * When the last VMA disappears, the region map says how much * the reservation was and the page cache tells how much of * the reservation was consumed. Private mappings are per-VMA and * only the consumed reservations are tracked. When the VMA * disappears, the original reservation is the VMA size and the * consumed reservations are stored in the map. Hence, nothing * else has to be done for private mappings here */ if (!vma || vma->vm_flags & VM_MAYSHARE) { add = region_add(resv_map, from, to, regions_needed, h, h_cg); if (unlikely(add < 0)) { hugetlb_acct_memory(h, -gbl_reserve); goto out_put_pages; } else if (unlikely(chg > add)) { /* * pages in this range were added to the reserve * map between region_chg and region_add. This * indicates a race with alloc_hugetlb_folio. Adjust * the subpool and reserve counts modified above * based on the difference. */ long rsv_adjust; /* * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the * reference to h_cg->css. See comment below for detail. */ hugetlb_cgroup_uncharge_cgroup_rsvd( hstate_index(h), (chg - add) * pages_per_huge_page(h), h_cg); rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); } else if (h_cg) { /* * The file_regions will hold their own reference to * h_cg->css. So we should release the reference held * via hugetlb_cgroup_charge_cgroup_rsvd() when we are * done. */ hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } return chg; out_put_pages: spool_resv = chg - gbl_reserve; if (spool_resv) { /* put sub pool's reservation back, chg - gbl_reserve */ gbl_resv = hugepage_subpool_put_pages(spool, spool_resv); /* * subpool's reserved pages can not be put back due to race, * return to hstate. */ hugetlb_acct_memory(h, -gbl_resv); } out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg); out_err: hugetlb_vma_lock_free(vma); if (!vma || vma->vm_flags & VM_MAYSHARE) /* Only call region_abort if the region_chg succeeded but the * region_add failed or didn't run. */ if (chg >= 0 && add < 0) region_abort(resv_map, from, to, regions_needed); if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { kref_put(&resv_map->refs, resv_map_release); set_vma_resv_map(vma, NULL); } return chg < 0 ? chg : add < 0 ? add : -EINVAL; } long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed) { struct hstate *h = hstate_inode(inode); struct resv_map *resv_map = inode_resv_map(inode); long chg = 0; struct hugepage_subpool *spool = subpool_inode(inode); long gbl_reserve; /* * Since this routine can be called in the evict inode path for all * hugetlbfs inodes, resv_map could be NULL. */ if (resv_map) { chg = region_del(resv_map, start, end); /* * region_del() can fail in the rare case where a region * must be split and another region descriptor can not be * allocated. If end == LONG_MAX, it will not fail. */ if (chg < 0) return chg; } spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); /* * If the subpool has a minimum size, the number of global * reservations to be released may be adjusted. * * Note that !resv_map implies freed == 0. So (chg - freed) * won't go negative. */ gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); hugetlb_acct_memory(h, -gbl_reserve); return 0; } #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static unsigned long page_table_shareable(struct vm_area_struct *svma, struct vm_area_struct *vma, unsigned long addr, pgoff_t idx) { unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + svma->vm_start; unsigned long sbase = saddr & PUD_MASK; unsigned long s_end = sbase + PUD_SIZE; /* Allow segments to share if only one is marked locked */ vm_flags_t vm_flags = vma->vm_flags & ~VM_LOCKED_MASK; vm_flags_t svm_flags = svma->vm_flags & ~VM_LOCKED_MASK; /* * match the virtual addresses, permission and the alignment of the * page table page. * * Also, vma_lock (vm_private_data) is required for sharing. */ if (pmd_index(addr) != pmd_index(saddr) || vm_flags != svm_flags || !range_in_vma(svma, sbase, s_end) || !svma->vm_private_data) return 0; return saddr; } bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { unsigned long start = addr & PUD_MASK; unsigned long end = start + PUD_SIZE; #ifdef CONFIG_USERFAULTFD if (uffd_disable_huge_pmd_share(vma)) return false; #endif /* * check on proper vm_flags and page table alignment */ if (!(vma->vm_flags & VM_MAYSHARE)) return false; if (!vma->vm_private_data) /* vma lock required for sharing */ return false; if (!range_in_vma(vma, start, end)) return false; return true; } /* * Determine if start,end range within vma could be mapped by shared pmd. * If yes, adjust start and end to cover range associated with possible * shared pmd mappings. */ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE), v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); /* * vma needs to span at least one aligned PUD size, and the range * must be at least partially within in. */ if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || (*end <= v_start) || (*start >= v_end)) return; /* Extend the range to be PUD aligned for a worst case scenario */ if (*start > v_start) *start = ALIGN_DOWN(*start, PUD_SIZE); if (*end < v_end) *end = ALIGN(*end, PUD_SIZE); } /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the * code much cleaner. pmd allocation is essential for the shared case because * pud has to be populated inside the same i_mmap_rwsem section - otherwise * racing tasks could either miss the sharing (see huge_pte_offset) or select a * bad pmd for sharing. */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; struct vm_area_struct *svma; unsigned long saddr; pte_t *spte = NULL; pte_t *pte; i_mmap_lock_read(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; saddr = page_table_shareable(svma, vma, addr, idx); if (saddr) { spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { ptdesc_pmd_pts_inc(virt_to_ptdesc(spte)); break; } } } if (!spte) goto out; spin_lock(&mm->page_table_lock); if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { ptdesc_pmd_pts_dec(virt_to_ptdesc(spte)); } spin_unlock(&mm->page_table_lock); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); i_mmap_unlock_read(mapping); return pte; } /* * unmap huge page backed by shared pte. * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user */ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); if (sz != PMD_SIZE) return 0; if (!ptdesc_pmd_is_shared(virt_to_ptdesc(ptep))) return 0; i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); pud_clear(pud); /* * Once our caller drops the rmap lock, some other process might be * using this page table as a normal, non-hugetlb page table. * Wait for pending gup_fast() in other threads to finish before letting * that happen. */ tlb_remove_table_sync_one(); ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; } #else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { return NULL; } int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { return false; } #endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { pte = (pte_t *)pud; } else { BUG_ON(sz != PMD_SIZE); if (want_pmd_share(vma, addr) && pud_none(*pud)) pte = huge_pmd_share(mm, vma, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); } } if (pte) { pte_t pteval = ptep_get_lockless(pte); BUG_ON(pte_present(pteval) && !pte_huge(pteval)); } return pte; } /* * huge_pte_offset() - Walk the page table to resolve the hugepage * entry at address @addr * * Return: Pointer to page table entry (PUD or PMD) for * address @addr, or NULL if a !p*d_present() entry is encountered and the * size @sz doesn't match the hugepage size at this level of the page * table. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) return NULL; p4d = p4d_offset(pgd, addr); if (!p4d_present(*p4d)) return NULL; pud = pud_offset(p4d, addr); if (sz == PUD_SIZE) /* must be pud huge, non-present or none */ return (pte_t *)pud; if (!pud_present(*pud)) return NULL; /* must have a valid entry and size to go further */ pmd = pmd_offset(pud, addr); /* must be pmd huge, non-present or none */ return (pte_t *)pmd; } /* * Return a mask that can be used to update an address to the last huge * page in a page table page mapping size. Used to skip non-present * page table entries when linearly scanning address ranges. Architectures * with unique huge page to page table relationships can define their own * version of this routine. */ unsigned long hugetlb_mask_last_page(struct hstate *h) { unsigned long hp_size = huge_page_size(h); if (hp_size == PUD_SIZE) return P4D_SIZE - PUD_SIZE; else if (hp_size == PMD_SIZE) return PUD_SIZE - PMD_SIZE; else return 0UL; } #else /* See description above. Architectures can provide their own version. */ __weak unsigned long hugetlb_mask_last_page(struct hstate *h) { #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING if (huge_page_size(h) == PMD_SIZE) return PUD_SIZE - PMD_SIZE; #endif return 0UL; } #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ /** * folio_isolate_hugetlb - try to isolate an allocated hugetlb folio * @folio: the folio to isolate * @list: the list to add the folio to on success * * Isolate an allocated (refcount > 0) hugetlb folio, marking it as * isolated/non-migratable, and moving it from the active list to the * given list. * * Isolation will fail if @folio is not an allocated hugetlb folio, or if * it is already isolated/non-migratable. * * On success, an additional folio reference is taken that must be dropped * using folio_putback_hugetlb() to undo the isolation. * * Return: True if isolation worked, otherwise False. */ bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list) { bool ret = true; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio) || !folio_test_hugetlb_migratable(folio) || !folio_try_get(folio)) { ret = false; goto unlock; } folio_clear_hugetlb_migratable(folio); list_move_tail(&folio->lru, list); unlock: spin_unlock_irq(&hugetlb_lock); return ret; } int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { int ret = 0; *hugetlb = false; spin_lock_irq(&hugetlb_lock); if (folio_test_hugetlb(folio)) { *hugetlb = true; if (folio_test_hugetlb_freed(folio)) ret = 0; else if (folio_test_hugetlb_migratable(folio) || unpoison) ret = folio_try_get(folio); else ret = -EBUSY; } spin_unlock_irq(&hugetlb_lock); return ret; } int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { int ret; spin_lock_irq(&hugetlb_lock); ret = __get_huge_page_for_hwpoison(pfn, flags, migratable_cleared); spin_unlock_irq(&hugetlb_lock); return ret; } /** * folio_putback_hugetlb - unisolate a hugetlb folio * @folio: the isolated hugetlb folio * * Putback/un-isolate the hugetlb folio that was previous isolated using * folio_isolate_hugetlb(): marking it non-isolated/migratable and putting it * back onto the active list. * * Will drop the additional folio reference obtained through * folio_isolate_hugetlb(). */ void folio_putback_hugetlb(struct folio *folio) { spin_lock_irq(&hugetlb_lock); folio_set_hugetlb_migratable(folio); list_move_tail(&folio->lru, &(folio_hstate(folio))->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); folio_put(folio); } void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { struct hstate *h = folio_hstate(old_folio); hugetlb_cgroup_migrate(old_folio, new_folio); folio_set_owner_migrate_reason(new_folio, reason); /* * transfer temporary state of the new hugetlb folio. This is * reverse to other transitions because the newpage is going to * be final while the old one will be freed so it takes over * the temporary status. * * Also note that we have to transfer the per-node surplus state * here as well otherwise the global surplus count will not match * the per-node's. */ if (folio_test_hugetlb_temporary(new_folio)) { int old_nid = folio_nid(old_folio); int new_nid = folio_nid(new_folio); folio_set_hugetlb_temporary(old_folio); folio_clear_hugetlb_temporary(new_folio); /* * There is no need to transfer the per-node surplus state * when we do not cross the node. */ if (new_nid == old_nid) return; spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages_node[old_nid]) { h->surplus_huge_pages_node[old_nid]--; h->surplus_huge_pages_node[new_nid]++; } spin_unlock_irq(&hugetlb_lock); } /* * Our old folio is isolated and has "migratable" cleared until it * is putback. As migration succeeded, set the new folio "migratable" * and add it to the active list. */ spin_lock_irq(&hugetlb_lock); folio_set_hugetlb_migratable(new_folio); list_move_tail(&new_folio->lru, &(folio_hstate(new_folio))->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); } /* * If @take_locks is false, the caller must ensure that no concurrent page table * access can happen (except for gup_fast() and hardware page walks). * If @take_locks is true, we take the hugetlb VMA lock (to lock out things like * concurrent page fault handling) and the file rmap lock. */ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool take_locks) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; unsigned long address; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & VM_MAYSHARE)) return; if (start >= end) return; flush_cache_range(vma, start, end); /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, start, end); mmu_notifier_invalidate_range_start(&range); if (take_locks) { hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); } else { i_mmap_assert_write_locked(vma->vm_file->f_mapping); } for (address = start; address < end; address += PUD_SIZE) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); huge_pmd_unshare(mm, vma, address, ptep); spin_unlock(ptl); } flush_hugetlb_tlb_range(vma, start, end); if (take_locks) { i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); } /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); } /* * This function will unconditionally remove all the shared pmd pgtable entries * within the specific vma for a hugetlbfs memory range. */ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE), /* take_locks = */ true); } /* * For hugetlb, mremap() is an odd edge case - while the VMA copying is * performed, we permit both the old and new VMAs to reference the same * reservation. * * We fix this up after the operation succeeds, or if a newly allocated VMA * is closed as a result of a failure to allocate memory. */ void fixup_hugetlb_reservations(struct vm_area_struct *vma) { if (is_vm_hugetlb_page(vma)) clear_vma_resv_huge_pages(vma); } |
| 4 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 |
| 44 8 34 44 36 35 15 19 44 1 1 44 43 8 36 10 30 40 48 13 8 39 20 23 43 47 10 10 10 1 2 8 10 10 10 10 3 1 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/read_write.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/slab.h> #include <linux/stat.h> #include <linux/sched/xacct.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> #include "internal.h" #include <linux/uaccess.h> #include <asm/unistd.h> const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, .mmap_prepare = generic_file_readonly_mmap_prepare, .splice_read = filemap_splice_read, }; EXPORT_SYMBOL(generic_ro_fops); static inline bool unsigned_offsets(struct file *file) { return file->f_op->fop_flags & FOP_UNSIGNED_OFFSET; } /** * vfs_setpos_cookie - update the file offset for lseek and reset cookie * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * @cookie: cookie to reset * * Update the file offset to the value specified by @offset if the given * offset is valid and it is not equal to the current file offset and * reset the specified cookie to indicate that a seek happened. * * Return the specified offset on success and -EINVAL on invalid offset. */ static loff_t vfs_setpos_cookie(struct file *file, loff_t offset, loff_t maxsize, u64 *cookie) { if (offset < 0 && !unsigned_offsets(file)) return -EINVAL; if (offset > maxsize) return -EINVAL; if (offset != file->f_pos) { file->f_pos = offset; if (cookie) *cookie = 0; } return offset; } /** * vfs_setpos - update the file offset for lseek * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * * This is a low-level filesystem helper for updating the file offset to * the value specified by @offset if the given offset is valid and it is * not equal to the current file offset. * * Return the specified offset on success and -EINVAL on invalid offset. */ loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) { return vfs_setpos_cookie(file, offset, maxsize, NULL); } EXPORT_SYMBOL(vfs_setpos); /** * must_set_pos - check whether f_pos has to be updated * @file: file to seek on * @offset: offset to use * @whence: type of seek operation * @eof: end of file * * Check whether f_pos needs to be updated and update @offset according * to @whence. * * Return: 0 if f_pos doesn't need to be updated, 1 if f_pos has to be * updated, and negative error code on failure. */ static int must_set_pos(struct file *file, loff_t *offset, int whence, loff_t eof) { switch (whence) { case SEEK_END: *offset += eof; break; case SEEK_CUR: /* * Here we special-case the lseek(fd, 0, SEEK_CUR) * position-querying operation. Avoid rewriting the "same" * f_pos value back to the file because a concurrent read(), * write() or lseek() might have altered it */ if (*offset == 0) { *offset = file->f_pos; return 0; } break; case SEEK_DATA: /* * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ if ((unsigned long long)*offset >= eof) return -ENXIO; break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ if ((unsigned long long)*offset >= eof) return -ENXIO; *offset = eof; break; } return 1; } /** * generic_file_llseek_size - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @maxsize: max size of this file in file system * @eof: offset used for SEEK_END position * * This is a variant of generic_file_llseek that allows passing in a custom * maximum file size and a custom EOF position, for e.g. hashed directories * * Synchronization: * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes. * read/writes behave like SEEK_SET against seeks. */ loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof) { int ret; ret = must_set_pos(file, &offset, whence, eof); if (ret < 0) return ret; if (ret == 0) return offset; if (whence == SEEK_CUR) { /* * If the file requires locking via f_pos_lock we know * that mutual exclusion for SEEK_CUR on the same file * is guaranteed. If the file isn't locked, we take * f_lock to protect against f_pos races with other * SEEK_CURs. */ if (file_seek_cur_needs_f_lock(file)) { guard(spinlock)(&file->f_lock); return vfs_setpos(file, file->f_pos + offset, maxsize); } return vfs_setpos(file, file->f_pos + offset, maxsize); } return vfs_setpos(file, offset, maxsize); } EXPORT_SYMBOL(generic_file_llseek_size); /** * generic_llseek_cookie - versioned llseek implementation * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @cookie: cookie to update * * See generic_file_llseek for a general description and locking assumptions. * * In contrast to generic_file_llseek, this function also resets a * specified cookie to indicate a seek took place. */ loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, u64 *cookie) { struct inode *inode = file->f_mapping->host; loff_t maxsize = inode->i_sb->s_maxbytes; loff_t eof = i_size_read(inode); int ret; if (WARN_ON_ONCE(!cookie)) return -EINVAL; /* * Require that this is only used for directories that guarantee * synchronization between readdir and seek so that an update to * @cookie is correctly synchronized with concurrent readdir. */ if (WARN_ON_ONCE(!(file->f_mode & FMODE_ATOMIC_POS))) return -EINVAL; ret = must_set_pos(file, &offset, whence, eof); if (ret < 0) return ret; if (ret == 0) return offset; /* No need to hold f_lock because we know that f_pos_lock is held. */ if (whence == SEEK_CUR) return vfs_setpos_cookie(file, file->f_pos + offset, maxsize, cookie); return vfs_setpos_cookie(file, offset, maxsize, cookie); } EXPORT_SYMBOL(generic_llseek_cookie); /** * generic_file_llseek - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is a generic implementation of ->llseek useable for all normal local * filesystems. It just updates the file offset to the value specified by * @offset and @whence. */ loff_t generic_file_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; return generic_file_llseek_size(file, offset, whence, inode->i_sb->s_maxbytes, i_size_read(inode)); } EXPORT_SYMBOL(generic_file_llseek); /** * fixed_size_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: size of the file * */ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: case SEEK_END: return generic_file_llseek_size(file, offset, whence, size, size); default: return -EINVAL; } } EXPORT_SYMBOL(fixed_size_llseek); /** * no_seek_end_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * */ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, OFFSET_MAX, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek); /** * no_seek_end_llseek_size - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: maximal offset allowed * */ loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, size, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek_size); /** * noop_llseek - No Operation Performed llseek implementation * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is an implementation of ->llseek useable for the rare special case when * userspace expects the seek to succeed but the (device) file is actually not * able to perform the seek. In this case you use noop_llseek() instead of * falling back to the default implementation of ->llseek. */ loff_t noop_llseek(struct file *file, loff_t offset, int whence) { return file->f_pos; } EXPORT_SYMBOL(noop_llseek); loff_t default_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file_inode(file); loff_t retval; retval = inode_lock_killable(inode); if (retval) return retval; switch (whence) { case SEEK_END: offset += i_size_read(inode); break; case SEEK_CUR: if (offset == 0) { retval = file->f_pos; goto out; } offset += file->f_pos; break; case SEEK_DATA: /* * In the generic case the entire file is data, so as * long as offset isn't at the end of the file then the * offset is data. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so * as long as offset isn't i_size or larger, return * i_size. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } offset = inode->i_size; break; } retval = -EINVAL; if (offset >= 0 || unsigned_offsets(file)) { if (offset != file->f_pos) file->f_pos = offset; retval = offset; } out: inode_unlock(inode); return retval; } EXPORT_SYMBOL(default_llseek); loff_t vfs_llseek(struct file *file, loff_t offset, int whence) { if (!(file->f_mode & FMODE_LSEEK)) return -ESPIPE; return file->f_op->llseek(file, offset, whence); } EXPORT_SYMBOL(vfs_llseek); static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; CLASS(fd_pos, f)(fd); if (fd_empty(f)) return -EBADF; retval = -EINVAL; if (whence <= SEEK_MAX) { loff_t res = vfs_llseek(fd_file(f), offset, whence); retval = res; if (res != (loff_t)retval) retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */ } return retval; } SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #endif #if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) || \ defined(__ARCH_WANT_SYS_LLSEEK) SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, unsigned long, offset_low, loff_t __user *, result, unsigned int, whence) { int retval; CLASS(fd_pos, f)(fd); loff_t offset; if (fd_empty(f)) return -EBADF; if (whence > SEEK_MAX) return -EINVAL; offset = vfs_llseek(fd_file(f), ((loff_t) offset_high << 32) | offset_low, whence); retval = (int)offset; if (offset >= 0) { retval = -EFAULT; if (!copy_to_user(result, &offset, sizeof(offset))) retval = 0; } return retval; } #endif int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { int mask = read_write == READ ? MAY_READ : MAY_WRITE; int ret; if (unlikely((ssize_t) count < 0)) return -EINVAL; if (ppos) { loff_t pos = *ppos; if (unlikely(pos < 0)) { if (!unsigned_offsets(file)) return -EINVAL; if (count >= -pos) /* both values are in 0..LLONG_MAX */ return -EOVERFLOW; } else if (unlikely((loff_t) (pos + count) < 0)) { if (!unsigned_offsets(file)) return -EINVAL; } } ret = security_file_permission(file, mask); if (ret) return ret; return fsnotify_file_area_perm(file, mask, ppos, count); } EXPORT_SYMBOL(rw_verify_area); static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_DEST, buf, len); ret = filp->f_op->read_iter(&kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } static int warn_unsupported(struct file *file, const char *op) { pr_warn_ratelimited( "kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n", op, file, current->pid, current->comm); return -EINVAL; } ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ))) return -EINVAL; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; /* * Also fail if ->read_iter and ->read are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->read_iter || file->f_op->read)) return warn_unsupported(file, "read"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; iov_iter_kvec(&iter, ITER_DEST, &iov, 1, iov.iov_len); ret = file->f_op->read_iter(&kiocb, &iter); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; return __kernel_read(file, buf, count, pos); } EXPORT_SYMBOL(kernel_read); ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; if (file->f_op->read) ret = file->f_op->read(file, buf, count, pos); else if (file->f_op->read_iter) ret = new_sync_read(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_SOURCE, (void __user *)buf, len); ret = filp->f_op->write_iter(&kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ret > 0 && ppos) *ppos = kiocb.ki_pos; return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos) { struct kiocb kiocb; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; /* * Also fail if ->write_iter and ->write are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->write_iter || file->f_op->write)) return warn_unsupported(file, "write"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; ret = file->f_op->write_iter(&kiocb, from); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = (void *)buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct iov_iter iter; iov_iter_kvec(&iter, ITER_SOURCE, &iov, 1, iov.iov_len); return __kernel_write_iter(file, &iter, pos); } /* * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()", * but autofs is one of the few internal kernel users that actually * wants this _and_ can be built as a module. So we need to export * this symbol for autofs, even though it really isn't appropriate * for any other kernel modules. */ EXPORT_SYMBOL_GPL(__kernel_write); ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; file_start_write(file); ret = __kernel_write(file, buf, count, pos); file_end_write(file); return ret; } EXPORT_SYMBOL(kernel_write); ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; file_start_write(file); if (file->f_op->write) ret = file->f_op->write(file, buf, count, pos); else if (file->f_op->write_iter) ret = new_sync_write(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); file_end_write(file); return ret; } /* file_ppos returns &file->f_pos or NULL if file is stream */ static inline loff_t *file_ppos(struct file *file) { return file->f_mode & FMODE_STREAM ? NULL : &file->f_pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_read(fd_file(f), buf, count, ppos); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } return ret; } SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) { return ksys_read(fd, buf, count); } ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_write(fd_file(f), buf, count, ppos); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } return ret; } SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, size_t, count) { return ksys_write(fd, buf, count); } ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos) { if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_mode & FMODE_PREAD) return vfs_read(fd_file(f), buf, count, &pos); return -ESPIPE; } SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, size_t, count, loff_t, pos) { return ksys_pread64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PREAD64) COMPAT_SYSCALL_DEFINE5(pread64, unsigned int, fd, char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pread64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos) { if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_mode & FMODE_PWRITE) return vfs_write(fd_file(f), buf, count, &pos); return -ESPIPE; } SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, loff_t, pos) { return ksys_pwrite64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PWRITE64) COMPAT_SYSCALL_DEFINE5(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pwrite64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); ret = kiocb_set_rw_flags(&kiocb, flags, type); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); if (type == READ) ret = filp->f_op->read_iter(&kiocb, iter); else ret = filp->f_op->write_iter(&kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { ssize_t ret = 0; if (flags & ~RWF_HIPRI) return -EOPNOTSUPP; while (iov_iter_count(iter)) { ssize_t nr; if (type == READ) { nr = filp->f_op->read(filp, iter_iov_addr(iter), iter_iov_len(iter), ppos); } else { nr = filp->f_op->write(filp, iter_iov_addr(iter), iter_iov_len(iter), ppos); } if (nr < 0) { if (!ret) ret = nr; break; } ret += nr; if (nr != iter_iov_len(iter)) break; iov_iter_advance(iter, nr); } return ret; } ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; ret = file->f_op->read_iter(iocb, iter); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_read); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, ppos, tot_len); if (ret < 0) return ret; ret = do_iter_readv_writev(file, iter, ppos, READ, flags); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iter_read); /* * Caller is responsible for calling kiocb_end_write() on completion * if async iocb was queued. */ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->write_iter) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; kiocb_start_write(iocb); ret = file->f_op->write_iter(iocb, iter); if (ret != -EIOCBQUEUED) kiocb_end_write(iocb); if (ret > 0) fsnotify_modify(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_write); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { size_t tot_len; ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (!file->f_op->write_iter) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, ppos, tot_len); if (ret < 0) return ret; file_start_write(file); ret = do_iter_readv_writev(file, iter, ppos, WRITE, flags); if (ret > 0) fsnotify_modify(file); file_end_write(file); return ret; } EXPORT_SYMBOL(vfs_iter_write); static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) return ret; tot_len = iov_iter_count(&iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, pos, tot_len); if (ret < 0) goto out; if (file->f_op->read_iter) ret = do_iter_readv_writev(file, &iter, pos, READ, flags); else ret = do_loop_readv_writev(file, &iter, pos, READ, flags); out: if (ret >= 0) fsnotify_access(file); kfree(iov); return ret; } static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) return ret; tot_len = iov_iter_count(&iter); if (!tot_len) goto out; ret = rw_verify_area(WRITE, file, pos, tot_len); if (ret < 0) goto out; file_start_write(file); if (file->f_op->write_iter) ret = do_iter_readv_writev(file, &iter, pos, WRITE, flags); else ret = do_loop_readv_writev(file, &iter, pos, WRITE, flags); if (ret > 0) fsnotify_modify(file); file_end_write(file); out: kfree(iov); return ret; } static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_readv(fd_file(f), vec, vlen, ppos, flags); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_writev(fd_file(f), vec, vlen, ppos, flags); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) { #define HALF_LONG_BITS (BITS_PER_LONG / 2) return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; } static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (!fd_empty(f)) { ret = -ESPIPE; if (fd_file(f)->f_mode & FMODE_PREAD) ret = vfs_readv(fd_file(f), vec, vlen, &pos, flags); } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (!fd_empty(f)) { ret = -ESPIPE; if (fd_file(f)->f_mode & FMODE_PWRITE) ret = vfs_writev(fd_file(f), vec, vlen, &pos, flags); } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_readv(fd, vec, vlen, 0); } SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_writev(fd, vec, vlen, 0); } SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_preadv(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_pwritev(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } /* * Various compat syscalls. Note that they all pretend to take a native * iovec - import_iovec will properly treat those as compat_iovecs based on * in_compat_syscall(). */ #ifdef CONFIG_COMPAT #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_preadv(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_preadv(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_pwritev(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_pwritev(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif /* CONFIG_COMPAT */ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, loff_t max) { struct inode *in_inode, *out_inode; struct pipe_inode_info *opipe; loff_t pos; loff_t out_pos; ssize_t retval; int fl; /* * Get input file, and verify that it is ok.. */ CLASS(fd, in)(in_fd); if (fd_empty(in)) return -EBADF; if (!(fd_file(in)->f_mode & FMODE_READ)) return -EBADF; if (!ppos) { pos = fd_file(in)->f_pos; } else { pos = *ppos; if (!(fd_file(in)->f_mode & FMODE_PREAD)) return -ESPIPE; } retval = rw_verify_area(READ, fd_file(in), &pos, count); if (retval < 0) return retval; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; /* * Get output file, and verify that it is ok.. */ CLASS(fd, out)(out_fd); if (fd_empty(out)) return -EBADF; if (!(fd_file(out)->f_mode & FMODE_WRITE)) return -EBADF; in_inode = file_inode(fd_file(in)); out_inode = file_inode(fd_file(out)); out_pos = fd_file(out)->f_pos; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); if (unlikely(pos + count > max)) { if (pos >= max) return -EOVERFLOW; count = max - pos; } fl = 0; #if 0 /* * We need to debate whether we can enable this or not. The * man page documents EAGAIN return for the output at least, * and the application is arguably buggy if it doesn't expect * EAGAIN on a non-blocking file descriptor. */ if (fd_file(in)->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif opipe = get_pipe_info(fd_file(out), true); if (!opipe) { retval = rw_verify_area(WRITE, fd_file(out), &out_pos, count); if (retval < 0) return retval; retval = do_splice_direct(fd_file(in), &pos, fd_file(out), &out_pos, count, fl); } else { if (fd_file(out)->f_flags & O_NONBLOCK) fl |= SPLICE_F_NONBLOCK; retval = splice_file_to_pipe(fd_file(in), opipe, &pos, count, fl); } if (retval > 0) { add_rchar(current, retval); add_wchar(current, retval); fsnotify_access(fd_file(in)); fsnotify_modify(fd_file(out)); fd_file(out)->f_pos = out_pos; if (ppos) *ppos = pos; else fd_file(in)->f_pos = pos; } inc_syscr(current); inc_syscw(current); if (pos > max) retval = -EOVERFLOW; return retval; } SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, compat_off_t __user *, offset, compat_size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, compat_loff_t __user *, offset, compat_size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #endif /* * Performs necessary checks before doing a file copy * * Can adjust amount of bytes to copy via @req_count argument. * Returns appropriate error code that caller should return or * zero in case the copy should be allowed. */ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t *req_count, unsigned int flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); uint64_t count = *req_count; loff_t size_in; int ret; ret = generic_file_rw_checks(file_in, file_out); if (ret) return ret; /* * We allow some filesystems to handle cross sb copy, but passing * a file of the wrong filesystem type to filesystem driver can result * in an attempt to dereference the wrong type of ->private_data, so * avoid doing that until we really have a good reason. * * nfs and cifs define several different file_system_type structures * and several different sets of file_operations, but they all end up * using the same ->copy_file_range() function pointer. */ if (flags & COPY_FILE_SPLICE) { /* cross sb splice is allowed */ } else if (file_out->f_op->copy_file_range) { if (file_in->f_op->copy_file_range != file_out->f_op->copy_file_range) return -EXDEV; } else if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) { return -EXDEV; } /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Ensure offsets don't wrap. */ if (pos_in + count < pos_in || pos_out + count < pos_out) return -EOVERFLOW; /* Shorten the copy to EOF */ size_in = i_size_read(inode_in); if (pos_in >= size_in) count = 0; else count = min(count, size_in - (uint64_t)pos_in); ret = generic_write_check_limits(file_out, pos_out, &count); if (ret) return ret; /* Don't allow overlapped copying within the same file. */ if (inode_in == inode_out && pos_out + count > pos_in && pos_out < pos_in + count) return -EINVAL; *req_count = count; return 0; } /* * copy_file_range() differs from regular file read and write in that it * specifically allows return partial success. When it does so is up to * the copy_file_range method. */ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { ssize_t ret; bool splice = flags & COPY_FILE_SPLICE; bool samesb = file_inode(file_in)->i_sb == file_inode(file_out)->i_sb; if (flags & ~COPY_FILE_SPLICE) return -EINVAL; ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, flags); if (unlikely(ret)) return ret; ret = rw_verify_area(READ, file_in, &pos_in, len); if (unlikely(ret)) return ret; ret = rw_verify_area(WRITE, file_out, &pos_out, len); if (unlikely(ret)) return ret; if (len == 0) return 0; /* * Make sure return value doesn't overflow in 32bit compat mode. Also * limit the size for all cases except when calling ->copy_file_range(). */ if (splice || !file_out->f_op->copy_file_range || in_compat_syscall()) len = min_t(size_t, MAX_RW_COUNT, len); file_start_write(file_out); /* * Cloning is supported by more file systems, so we implement copy on * same sb using clone, but for filesystems where both clone and copy * are supported (e.g. nfs,cifs), we only call the copy method. */ if (!splice && file_out->f_op->copy_file_range) { ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); } else if (!splice && file_in->f_op->remap_file_range && samesb) { ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, len, REMAP_FILE_CAN_SHORTEN); /* fallback to splice */ if (ret <= 0) splice = true; } else if (samesb) { /* Fallback to splice for same sb copy for backward compat */ splice = true; } file_end_write(file_out); if (!splice) goto done; /* * We can get here for same sb copy of filesystems that do not implement * ->copy_file_range() in case filesystem does not support clone or in * case filesystem supports clone but rejected the clone request (e.g. * because it was not block aligned). * * In both cases, fall back to kernel copy so we are able to maintain a * consistent story about which filesystems support copy_file_range() * and which filesystems do not, that will allow userspace tools to * make consistent desicions w.r.t using copy_file_range(). * * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE * for server-side-copy between any two sb. * * In any case, we call do_splice_direct() and not splice_file_range(), * without file_start_write() held, to avoid possible deadlocks related * to splicing from input file, while file_start_write() is held on * the output file on a different sb. */ ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, len, 0); done: if (ret > 0) { fsnotify_access(file_in); add_rchar(current, ret); fsnotify_modify(file_out); add_wchar(current, ret); } inc_syscr(current); inc_syscw(current); return ret; } EXPORT_SYMBOL(vfs_copy_file_range); SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) { loff_t pos_in; loff_t pos_out; ssize_t ret = -EBADF; CLASS(fd, f_in)(fd_in); if (fd_empty(f_in)) return -EBADF; CLASS(fd, f_out)(fd_out); if (fd_empty(f_out)) return -EBADF; if (off_in) { if (copy_from_user(&pos_in, off_in, sizeof(loff_t))) return -EFAULT; } else { pos_in = fd_file(f_in)->f_pos; } if (off_out) { if (copy_from_user(&pos_out, off_out, sizeof(loff_t))) return -EFAULT; } else { pos_out = fd_file(f_out)->f_pos; } if (flags != 0) return -EINVAL; ret = vfs_copy_file_range(fd_file(f_in), pos_in, fd_file(f_out), pos_out, len, flags); if (ret > 0) { pos_in += ret; pos_out += ret; if (off_in) { if (copy_to_user(off_in, &pos_in, sizeof(loff_t))) ret = -EFAULT; } else { fd_file(f_in)->f_pos = pos_in; } if (off_out) { if (copy_to_user(off_out, &pos_out, sizeof(loff_t))) ret = -EFAULT; } else { fd_file(f_out)->f_pos = pos_out; } } return ret; } /* * Don't operate on ranges the page cache doesn't support, and don't exceed the * LFS limits. If pos is under the limit it becomes a short access. If it * exceeds the limit we return -EFBIG. */ int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count) { struct inode *inode = file->f_mapping->host; loff_t max_size = inode->i_sb->s_maxbytes; loff_t limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY) { if (pos >= limit) { send_sig(SIGXFSZ, current, 0); return -EFBIG; } *count = min(*count, limit - pos); } if (!(file->f_flags & O_LARGEFILE)) max_size = MAX_NON_LFS; if (unlikely(pos >= max_size)) return -EFBIG; *count = min(*count, max_size - pos); return 0; } EXPORT_SYMBOL_GPL(generic_write_check_limits); /* Like generic_write_checks(), but takes size of write instead of iter. */ int generic_write_checks_count(struct kiocb *iocb, loff_t *count) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; if (IS_SWAPFILE(inode)) return -ETXTBSY; if (!*count) return 0; if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); if ((iocb->ki_flags & IOCB_NOWAIT) && !((iocb->ki_flags & IOCB_DIRECT) || (file->f_op->fop_flags & FOP_BUFFER_WASYNC))) return -EINVAL; return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count); } EXPORT_SYMBOL(generic_write_checks_count); /* * Performs necessary checks before doing a write * * Can adjust writing position or amount of bytes to write. * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */ ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { loff_t count = iov_iter_count(from); int ret; ret = generic_write_checks_count(iocb, &count); if (ret) return ret; iov_iter_truncate(from, count); return iov_iter_count(from); } EXPORT_SYMBOL(generic_write_checks); /* * Performs common checks before doing a file copy/clone * from @file_in to @file_out. */ int generic_file_rw_checks(struct file *file_in, struct file *file_out) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); /* Don't copy dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || (file_out->f_flags & O_APPEND)) return -EBADF; return 0; } int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter) { size_t len = iov_iter_count(iter); if (!iter_is_ubuf(iter)) return -EINVAL; if (!is_power_of_2(len)) return -EINVAL; if (!IS_ALIGNED(iocb->ki_pos, len)) return -EINVAL; if (!(iocb->ki_flags & IOCB_DIRECT)) return -EOPNOTSUPP; return 0; } EXPORT_SYMBOL_GPL(generic_atomic_write_valid); |
| 4 4 4 | 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); |
| 4 4 3 4 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Copyright Amazon.com Inc. or its affiliates. */ #include <linux/init.h> #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/rtnetlink.h> #include <net/net_namespace.h> #include <net/netdev_lock.h> #include <net/netns/generic.h> int netdev_debug_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); enum netdev_cmd cmd = event; /* Keep enum and don't add default to trigger -Werror=switch */ switch (cmd) { case NETDEV_XDP_FEAT_CHANGE: netdev_assert_locked(dev); fallthrough; case NETDEV_CHANGE: case NETDEV_REGISTER: case NETDEV_UP: netdev_ops_assert_locked(dev); fallthrough; case NETDEV_DOWN: case NETDEV_REBOOT: case NETDEV_UNREGISTER: case NETDEV_CHANGEMTU: case NETDEV_CHANGEADDR: case NETDEV_PRE_CHANGEADDR: case NETDEV_GOING_DOWN: case NETDEV_FEAT_CHANGE: case NETDEV_BONDING_FAILOVER: case NETDEV_PRE_UP: case NETDEV_PRE_TYPE_CHANGE: case NETDEV_POST_TYPE_CHANGE: case NETDEV_POST_INIT: case NETDEV_PRE_UNINIT: case NETDEV_RELEASE: case NETDEV_NOTIFY_PEERS: case NETDEV_JOIN: case NETDEV_CHANGEUPPER: case NETDEV_RESEND_IGMP: case NETDEV_PRECHANGEMTU: case NETDEV_CHANGEINFODATA: case NETDEV_BONDING_INFO: case NETDEV_PRECHANGEUPPER: case NETDEV_CHANGELOWERSTATE: case NETDEV_UDP_TUNNEL_PUSH_INFO: case NETDEV_UDP_TUNNEL_DROP_INFO: case NETDEV_CHANGE_TX_QUEUE_LEN: case NETDEV_CVLAN_FILTER_PUSH_INFO: case NETDEV_CVLAN_FILTER_DROP_INFO: case NETDEV_SVLAN_FILTER_PUSH_INFO: case NETDEV_SVLAN_FILTER_DROP_INFO: case NETDEV_OFFLOAD_XSTATS_ENABLE: case NETDEV_OFFLOAD_XSTATS_DISABLE: case NETDEV_OFFLOAD_XSTATS_REPORT_USED: case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA: ASSERT_RTNL(); break; case NETDEV_CHANGENAME: ASSERT_RTNL_NET(net); break; } return NOTIFY_DONE; } EXPORT_SYMBOL_NS_GPL(netdev_debug_event, "NETDEV_INTERNAL"); static int rtnl_net_debug_net_id; static int __net_init rtnl_net_debug_net_init(struct net *net) { struct notifier_block *nb; nb = net_generic(net, rtnl_net_debug_net_id); nb->notifier_call = netdev_debug_event; return register_netdevice_notifier_net(net, nb); } static void __net_exit rtnl_net_debug_net_exit(struct net *net) { struct notifier_block *nb; nb = net_generic(net, rtnl_net_debug_net_id); unregister_netdevice_notifier_net(net, nb); } static struct pernet_operations rtnl_net_debug_net_ops __net_initdata = { .init = rtnl_net_debug_net_init, .exit = rtnl_net_debug_net_exit, .id = &rtnl_net_debug_net_id, .size = sizeof(struct notifier_block), }; static struct notifier_block rtnl_net_debug_block = { .notifier_call = netdev_debug_event, }; static int __init rtnl_net_debug_init(void) { int ret; ret = register_pernet_subsys(&rtnl_net_debug_net_ops); if (ret) return ret; ret = register_netdevice_notifier(&rtnl_net_debug_block); if (ret) unregister_pernet_subsys(&rtnl_net_debug_net_ops); return ret; } subsys_initcall(rtnl_net_debug_init); |
| 5 3 148 148 148 2 2 1 1 1 1 1 1 1 1 56 56 1 14 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * KVM dirty ring implementation * * Copyright 2019 Red Hat, Inc. */ #include <linux/kvm_host.h> #include <linux/kvm.h> #include <linux/vmalloc.h> #include <linux/kvm_dirty_ring.h> #include <trace/events/kvm.h> #include "kvm_mm.h" int __weak kvm_cpu_dirty_log_size(struct kvm *kvm) { return 0; } u32 kvm_dirty_ring_get_rsvd_entries(struct kvm *kvm) { return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size(kvm); } bool kvm_use_dirty_bitmap(struct kvm *kvm) { lockdep_assert_held(&kvm->slots_lock); return !kvm->dirty_ring_size || kvm->dirty_ring_with_bitmap; } #ifndef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) { return false; } #endif static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring) { return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index); } static bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) { return kvm_dirty_ring_used(ring) >= ring->soft_limit; } static bool kvm_dirty_ring_full(struct kvm_dirty_ring *ring) { return kvm_dirty_ring_used(ring) >= ring->size; } static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask) { struct kvm_memory_slot *memslot; int as_id, id; as_id = slot >> 16; id = (u16)slot; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return; memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id); if (!memslot || (offset + __fls(mask)) >= memslot->npages) return; KVM_MMU_LOCK(kvm); kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); KVM_MMU_UNLOCK(kvm); } int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring, int index, u32 size) { ring->dirty_gfns = vzalloc(size); if (!ring->dirty_gfns) return -ENOMEM; ring->size = size / sizeof(struct kvm_dirty_gfn); ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries(kvm); ring->dirty_index = 0; ring->reset_index = 0; ring->index = index; return 0; } static inline void kvm_dirty_gfn_set_invalid(struct kvm_dirty_gfn *gfn) { smp_store_release(&gfn->flags, 0); } static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn) { gfn->flags = KVM_DIRTY_GFN_F_DIRTY; } static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn) { return smp_load_acquire(&gfn->flags) & KVM_DIRTY_GFN_F_RESET; } int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring, int *nr_entries_reset) { /* * To minimize mmu_lock contention, batch resets for harvested entries * whose gfns are in the same slot, and are within N frame numbers of * each other, where N is the number of bits in an unsigned long. For * simplicity, process the current set of entries when the next entry * can't be included in the batch. * * Track the current batch slot, the gfn offset into the slot for the * batch, and the bitmask of gfns that need to be reset (relative to * offset). Note, the offset may be adjusted backwards, e.g. so that * a sequence of gfns X, X-1, ... X-N-1 can be batched. */ u32 cur_slot, next_slot; u64 cur_offset, next_offset; unsigned long mask = 0; struct kvm_dirty_gfn *entry; /* * Ensure concurrent calls to KVM_RESET_DIRTY_RINGS are serialized, * e.g. so that KVM fully resets all entries processed by a given call * before returning to userspace. Holding slots_lock also protects * the various memslot accesses. */ lockdep_assert_held(&kvm->slots_lock); while (likely((*nr_entries_reset) < INT_MAX)) { if (signal_pending(current)) return -EINTR; entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)]; if (!kvm_dirty_gfn_harvested(entry)) break; next_slot = READ_ONCE(entry->slot); next_offset = READ_ONCE(entry->offset); /* Update the flags to reflect that this GFN is reset */ kvm_dirty_gfn_set_invalid(entry); ring->reset_index++; (*nr_entries_reset)++; if (mask) { /* * While the size of each ring is fixed, it's possible * for the ring to be constantly re-dirtied/harvested * while the reset is in-progress (the hard limit exists * only to guard against the count becoming negative). */ cond_resched(); /* * Try to coalesce the reset operations when the guest * is scanning pages in the same slot. */ if (next_slot == cur_slot) { s64 delta = next_offset - cur_offset; if (delta >= 0 && delta < BITS_PER_LONG) { mask |= 1ull << delta; continue; } /* Backwards visit, careful about overflows! */ if (delta > -BITS_PER_LONG && delta < 0 && (mask << -delta >> -delta) == mask) { cur_offset = next_offset; mask = (mask << -delta) | 1; continue; } } /* * Reset the slot for all the harvested entries that * have been gathered, but not yet fully processed. */ kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); } /* * The current slot was reset or this is the first harvested * entry, (re)initialize the metadata. */ cur_slot = next_slot; cur_offset = next_offset; mask = 1; } /* * Perform a final reset if there are harvested entries that haven't * been processed, which is guaranteed if at least one harvested was * found. The loop only performs a reset when the "next" entry can't * be batched with the "current" entry(s), and that reset processes the * _current_ entry(s); i.e. the last harvested entry, a.k.a. next, will * always be left pending. */ if (mask) kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask); /* * The request KVM_REQ_DIRTY_RING_SOFT_FULL will be cleared * by the VCPU thread next time when it enters the guest. */ trace_kvm_dirty_ring_reset(ring); return 0; } void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset) { struct kvm_dirty_ring *ring = &vcpu->dirty_ring; struct kvm_dirty_gfn *entry; /* It should never get full */ WARN_ON_ONCE(kvm_dirty_ring_full(ring)); entry = &ring->dirty_gfns[ring->dirty_index & (ring->size - 1)]; entry->slot = slot; entry->offset = offset; /* * Make sure the data is filled in before we publish this to * the userspace program. There's no paired kernel-side reader. */ smp_wmb(); kvm_dirty_gfn_set_dirtied(entry); ring->dirty_index++; trace_kvm_dirty_ring_push(ring, slot, offset); if (kvm_dirty_ring_soft_full(ring)) kvm_make_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu); } bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu) { /* * The VCPU isn't runnable when the dirty ring becomes soft full. * The KVM_REQ_DIRTY_RING_SOFT_FULL event is always set to prevent * the VCPU from running until the dirty pages are harvested and * the dirty ring is reset by userspace. */ if (kvm_check_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu) && kvm_dirty_ring_soft_full(&vcpu->dirty_ring)) { kvm_make_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu); vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL; trace_kvm_dirty_ring_exit(vcpu); return true; } return false; } struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset) { return vmalloc_to_page((void *)ring->dirty_gfns + offset * PAGE_SIZE); } void kvm_dirty_ring_free(struct kvm_dirty_ring *ring) { vfree(ring->dirty_gfns); ring->dirty_gfns = NULL; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMEKEEPING_H #define _LINUX_TIMEKEEPING_H #include <linux/errno.h> #include <linux/clocksource_ids.h> #include <linux/ktime.h> /* Included from linux/ktime.h */ void timekeeping_init(void); extern int timekeeping_suspended; /* Architecture timer tick functions: */ extern void legacy_timer_tick(unsigned long ticks); /* * Get and set timeofday */ extern int do_settimeofday64(const struct timespec64 *ts); extern int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz); /* * ktime_get() family - read the current time in a multitude of ways. * * The default time reference is CLOCK_MONOTONIC, starting at * boot time but not counting the time spent in suspend. * For other references, use the functions with "real", "clocktai", * "boottime" and "raw" suffixes. * * To get the time in a different format, use the ones with * "ns", "ts64" and "seconds" suffix. * * See Documentation/core-api/timekeeping.rst for more details. */ /* * timespec64 based interfaces */ extern void ktime_get_raw_ts64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); extern void ktime_get_clock_ts64(clockid_t id, struct timespec64 *ts); /* Multigrain timestamp interfaces */ extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); extern void ktime_get_real_ts64_mg(struct timespec64 *ts); extern unsigned long timekeeping_get_mg_floor_swaps(void); void getboottime64(struct timespec64 *ts); /* * time64_t base interfaces */ extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); /* * ktime_t based interfaces */ enum tk_offsets { TK_OFFS_REAL, TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; extern ktime_t ktime_get(void); extern ktime_t ktime_get_with_offset(enum tk_offsets offs); extern ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs); extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); /** * ktime_get_real - get the real (wall-) time in ktime_t format * * Returns: real (wall) time in ktime_t format */ static inline ktime_t ktime_get_real(void) { return ktime_get_with_offset(TK_OFFS_REAL); } static inline ktime_t ktime_get_coarse_real(void) { return ktime_get_coarse_with_offset(TK_OFFS_REAL); } /** * ktime_get_boottime - Get monotonic time since boot in ktime_t format * * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the * time spent in suspend. * * Returns: monotonic time since boot in ktime_t format */ static inline ktime_t ktime_get_boottime(void) { return ktime_get_with_offset(TK_OFFS_BOOT); } static inline ktime_t ktime_get_coarse_boottime(void) { return ktime_get_coarse_with_offset(TK_OFFS_BOOT); } /** * ktime_get_clocktai - Get the TAI time of day in ktime_t format * * Returns: the TAI time of day in ktime_t format */ static inline ktime_t ktime_get_clocktai(void) { return ktime_get_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse_clocktai(void) { return ktime_get_coarse_with_offset(TK_OFFS_TAI); } static inline ktime_t ktime_get_coarse(void) { struct timespec64 ts; ktime_get_coarse_ts64(&ts); return timespec64_to_ktime(ts); } static inline u64 ktime_get_coarse_ns(void) { return ktime_to_ns(ktime_get_coarse()); } static inline u64 ktime_get_coarse_real_ns(void) { return ktime_to_ns(ktime_get_coarse_real()); } static inline u64 ktime_get_coarse_boottime_ns(void) { return ktime_to_ns(ktime_get_coarse_boottime()); } static inline u64 ktime_get_coarse_clocktai_ns(void) { return ktime_to_ns(ktime_get_coarse_clocktai()); } /** * ktime_mono_to_real - Convert monotonic time to clock realtime * @mono: monotonic time to convert * * Returns: time converted to realtime clock */ static inline ktime_t ktime_mono_to_real(ktime_t mono) { return ktime_mono_to_any(mono, TK_OFFS_REAL); } /** * ktime_get_ns - Get the current time in nanoseconds * * Returns: current time converted to nanoseconds */ static inline u64 ktime_get_ns(void) { return ktime_to_ns(ktime_get()); } /** * ktime_get_real_ns - Get the current real/wall time in nanoseconds * * Returns: current real time converted to nanoseconds */ static inline u64 ktime_get_real_ns(void) { return ktime_to_ns(ktime_get_real()); } /** * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds * * Returns: current boottime converted to nanoseconds */ static inline u64 ktime_get_boottime_ns(void) { return ktime_to_ns(ktime_get_boottime()); } /** * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds * * Returns: current TAI time converted to nanoseconds */ static inline u64 ktime_get_clocktai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); } /** * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds * * Returns: current raw monotonic time converted to nanoseconds */ static inline u64 ktime_get_raw_ns(void) { return ktime_to_ns(ktime_get_raw()); } extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64/time64_t interfaces utilizing the ktime based ones * for API completeness, these could be implemented more efficiently * if needed. */ static inline void ktime_get_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_boottime()); } static inline void ktime_get_coarse_boottime_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_boottime()); } static inline time64_t ktime_get_boottime_seconds(void) { return ktime_divns(ktime_get_coarse_boottime(), NSEC_PER_SEC); } static inline void ktime_get_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); } static inline void ktime_get_coarse_clocktai_ts64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_coarse_clocktai()); } static inline time64_t ktime_get_clocktai_seconds(void) { return ktime_divns(ktime_get_coarse_clocktai(), NSEC_PER_SEC); } /* * RTC specific */ extern bool timekeeping_rtc_skipsuspend(void); extern bool timekeeping_rtc_skipresume(void); extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta); /* * Auxiliary clock interfaces */ #ifdef CONFIG_POSIX_AUX_CLOCKS extern bool ktime_get_aux(clockid_t id, ktime_t *kt); extern bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt); #else static inline bool ktime_get_aux(clockid_t id, ktime_t *kt) { return false; } static inline bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt) { return false; } #endif /** * struct system_time_snapshot - simultaneous raw/real time capture with * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time * @boot: Boot time * @raw: Monotonic raw system time * @cs_id: Clocksource ID * @clock_was_set_seq: The sequence number of clock-was-set events * @cs_was_changed_seq: The sequence number of clocksource change events */ struct system_time_snapshot { u64 cycles; ktime_t real; ktime_t boot; ktime_t raw; enum clocksource_ids cs_id; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; }; /** * struct system_device_crosststamp - system/device cross-timestamp * (synchronized capture) * @device: Device time * @sys_realtime: Realtime simultaneous with device time * @sys_monoraw: Monotonic raw simultaneous with device time */ struct system_device_crosststamp { ktime_t device; ktime_t sys_realtime; ktime_t sys_monoraw; }; /** * struct system_counterval_t - system counter value with the ID of the * corresponding clocksource * @cycles: System counter value * @cs_id: Clocksource ID corresponding to system counter value. Used by * timekeeping code to verify comparability of two cycle values. * The default ID, CSID_GENERIC, does not identify a specific * clocksource. * @use_nsecs: @cycles is in nanoseconds. */ struct system_counterval_t { u64 cycles; enum clocksource_ids cs_id; bool use_nsecs; }; extern bool ktime_real_to_base_clock(ktime_t treal, enum clocksource_ids base_id, u64 *cycles); extern bool timekeeping_clocksource_has_base(enum clocksource_ids id); /* * Get cross timestamp between system clock and device clock */ extern int get_device_system_crosststamp( int (*get_time_fn)(ktime_t *device_time, struct system_counterval_t *system_counterval, void *ctx), void *ctx, struct system_time_snapshot *history, struct system_device_crosststamp *xtstamp); /* * Simultaneously snapshot realtime and monotonic raw clocks */ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); /* * Persistent clock related interfaces */ extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, struct timespec64 *boot_offset); #ifdef CONFIG_GENERIC_CMOS_UPDATE extern int update_persistent_clock64(struct timespec64 now); #endif #endif |
| 2 2 3 114 114 114 114 114 114 138 138 163 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Derived from arch/arm/kvm/coproc.h * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Authors: Christoffer Dall <c.dall@virtualopensystems.com> */ #ifndef __ARM64_KVM_SYS_REGS_LOCAL_H__ #define __ARM64_KVM_SYS_REGS_LOCAL_H__ #include <linux/bsearch.h> #define reg_to_encoding(x) \ sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \ (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2) struct sys_reg_params { u8 Op0; u8 Op1; u8 CRn; u8 CRm; u8 Op2; u64 regval; bool is_write; }; #define encoding_to_params(reg) \ ((struct sys_reg_params){ .Op0 = sys_reg_Op0(reg), \ .Op1 = sys_reg_Op1(reg), \ .CRn = sys_reg_CRn(reg), \ .CRm = sys_reg_CRm(reg), \ .Op2 = sys_reg_Op2(reg) }) #define esr_sys64_to_params(esr) \ ((struct sys_reg_params){ .Op0 = ((esr) >> 20) & 3, \ .Op1 = ((esr) >> 14) & 0x7, \ .CRn = ((esr) >> 10) & 0xf, \ .CRm = ((esr) >> 1) & 0xf, \ .Op2 = ((esr) >> 17) & 0x7, \ .is_write = !((esr) & 1) }) #define esr_cp1x_32_to_params(esr) \ ((struct sys_reg_params){ .Op1 = ((esr) >> 14) & 0x7, \ .CRn = ((esr) >> 10) & 0xf, \ .CRm = ((esr) >> 1) & 0xf, \ .Op2 = ((esr) >> 17) & 0x7, \ .is_write = !((esr) & 1) }) struct sys_reg_desc { /* Sysreg string for debug */ const char *name; enum { AA32_DIRECT, AA32_LO, AA32_HI, } aarch32_map; /* MRS/MSR instruction which accesses it. */ u8 Op0; u8 Op1; u8 CRn; u8 CRm; u8 Op2; /* Trapped access from guest, if non-NULL. */ bool (*access)(struct kvm_vcpu *, struct sys_reg_params *, const struct sys_reg_desc *); /* * Initialization for vcpu. Return initialized value, or KVM * sanitized value for ID registers. */ u64 (*reset)(struct kvm_vcpu *, const struct sys_reg_desc *); /* Index into sys_reg[], or 0 if we don't need to save it. */ int reg; /* Value (usually reset value), or write mask for idregs */ u64 val; /* Custom get/set_user functions, fallback to generic if NULL */ int (*get_user)(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 *val); int (*set_user)(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val); /* Return mask of REG_* runtime visibility overrides */ unsigned int (*visibility)(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd); }; #define REG_HIDDEN (1 << 0) /* hidden from userspace and guest */ #define REG_RAZ (1 << 1) /* RAZ from userspace and guest */ #define REG_USER_WI (1 << 2) /* WI from userspace only */ static __printf(2, 3) inline void print_sys_reg_msg(const struct sys_reg_params *p, char *fmt, ...) { va_list va; va_start(va, fmt); /* Look, we even formatted it for you to paste into the table! */ kvm_pr_unimpl("%pV { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n", &(struct va_format){ fmt, &va }, p->Op0, p->Op1, p->CRn, p->CRm, p->Op2, str_write_read(p->is_write)); va_end(va); } static inline void print_sys_reg_instr(const struct sys_reg_params *p) { /* GCC warns on an empty format string */ print_sys_reg_msg(p, "%s", ""); } static inline bool ignore_write(struct kvm_vcpu *vcpu, const struct sys_reg_params *p) { return true; } static inline bool read_zero(struct kvm_vcpu *vcpu, struct sys_reg_params *p) { p->regval = 0; return true; } /* Reset functions */ static inline u64 reset_unknown(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { BUG_ON(!r->reg); BUG_ON(r->reg >= NR_SYS_REGS); __vcpu_assign_sys_reg(vcpu, r->reg, 0x1de7ec7edbadc0deULL); return __vcpu_sys_reg(vcpu, r->reg); } static inline u64 reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { BUG_ON(!r->reg); BUG_ON(r->reg >= NR_SYS_REGS); __vcpu_assign_sys_reg(vcpu, r->reg, r->val); return __vcpu_sys_reg(vcpu, r->reg); } static inline unsigned int sysreg_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { if (likely(!r->visibility)) return 0; return r->visibility(vcpu, r); } static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return sysreg_visibility(vcpu, r) & REG_HIDDEN; } static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return sysreg_visibility(vcpu, r) & REG_RAZ; } static inline bool sysreg_user_write_ignore(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return sysreg_visibility(vcpu, r) & REG_USER_WI; } static inline int cmp_sys_reg(const struct sys_reg_desc *i1, const struct sys_reg_desc *i2) { BUG_ON(i1 == i2); if (!i1) return 1; else if (!i2) return -1; if (i1->Op0 != i2->Op0) return i1->Op0 - i2->Op0; if (i1->Op1 != i2->Op1) return i1->Op1 - i2->Op1; if (i1->CRn != i2->CRn) return i1->CRn - i2->CRn; if (i1->CRm != i2->CRm) return i1->CRm - i2->CRm; return i1->Op2 - i2->Op2; } static inline int match_sys_reg(const void *key, const void *elt) { const unsigned long pval = (unsigned long)key; const struct sys_reg_desc *r = elt; return pval - reg_to_encoding(r); } static inline const struct sys_reg_desc * find_reg(const struct sys_reg_params *params, const struct sys_reg_desc table[], unsigned int num) { unsigned long pval = reg_to_encoding(params); return __inline_bsearch((void *)pval, table, num, sizeof(table[0]), match_sys_reg); } const struct sys_reg_desc *get_reg_by_id(u64 id, const struct sys_reg_desc table[], unsigned int num); int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); int kvm_sys_reg_get_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, const struct sys_reg_desc table[], unsigned int num); int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, const struct sys_reg_desc table[], unsigned int num); bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index); int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu); #define AA32(_x) .aarch32_map = AA32_##_x #define Op0(_x) .Op0 = _x #define Op1(_x) .Op1 = _x #define CRn(_x) .CRn = _x #define CRm(_x) .CRm = _x #define Op2(_x) .Op2 = _x #define SYS_DESC(reg) \ .name = #reg, \ Op0(sys_reg_Op0(reg)), Op1(sys_reg_Op1(reg)), \ CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)), \ Op2(sys_reg_Op2(reg)) #define CP15_SYS_DESC(reg) \ .name = #reg, \ .aarch32_map = AA32_DIRECT, \ Op0(0), Op1(sys_reg_Op1(reg)), \ CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)), \ Op2(sys_reg_Op2(reg)) #define ID_REG_LIMIT_FIELD_ENUM(val, reg, field, limit) \ ({ \ u64 __f_val = FIELD_GET(reg##_##field##_MASK, val); \ (val) &= ~reg##_##field##_MASK; \ (val) |= FIELD_PREP(reg##_##field##_MASK, \ min(__f_val, \ (u64)SYS_FIELD_VALUE(reg, field, limit))); \ (val); \ }) #define TO_ARM64_SYS_REG(r) ARM64_SYS_REG(sys_reg_Op0(SYS_ ## r), \ sys_reg_Op1(SYS_ ## r), \ sys_reg_CRn(SYS_ ## r), \ sys_reg_CRm(SYS_ ## r), \ sys_reg_Op2(SYS_ ## r)) #endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */ |
| 268 268 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/of.h> #include <linux/of_device.h> #include <linux/of_address.h> #include <linux/of_iommu.h> #include <linux/of_reserved_mem.h> #include <linux/dma-direct.h> /* for bus_dma_region */ #include <linux/dma-map-ops.h> #include <linux/init.h> #include <linux/mod_devicetable.h> #include <linux/slab.h> #include <linux/platform_device.h> #include <asm/errno.h> #include "of_private.h" /** * of_match_device - Tell if a struct device matches an of_device_id list * @matches: array of of_device_id match structures to search in * @dev: the OF device structure to match against * * Used by a driver to check whether an platform_device present in the * system is in its list of supported devices. */ const struct of_device_id *of_match_device(const struct of_device_id *matches, const struct device *dev) { if (!matches || !dev->of_node || dev->of_node_reused) return NULL; return of_match_node(matches, dev->of_node); } EXPORT_SYMBOL(of_match_device); static void of_dma_set_restricted_buffer(struct device *dev, struct device_node *np) { struct device_node *of_node = dev->of_node; struct of_phandle_iterator it; int rc, i = 0; if (!IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL)) return; /* * If dev->of_node doesn't exist or doesn't contain memory-region, try * the OF node having DMA configuration. */ if (!of_property_present(of_node, "memory-region")) of_node = np; of_for_each_phandle(&it, rc, of_node, "memory-region", NULL, 0) { /* * There might be multiple memory regions, but only one * restricted-dma-pool region is allowed. */ if (of_device_is_compatible(it.node, "restricted-dma-pool") && of_device_is_available(it.node)) { if (of_reserved_mem_device_init_by_idx(dev, of_node, i)) dev_warn(dev, "failed to initialise \"restricted-dma-pool\" memory node\n"); of_node_put(it.node); break; } i++; } } /** * of_dma_configure_id - Setup DMA configuration * @dev: Device to apply DMA configuration * @np: Pointer to OF node having DMA configuration * @force_dma: Whether device is to be set up by of_dma_configure() even if * DMA capability is not explicitly described by firmware. * @id: Optional const pointer value input id * * Try to get devices's DMA configuration from DT and update it * accordingly. * * If platform code needs to use its own special DMA configuration, it * can use a platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE events * to fix up DMA configuration. */ int of_dma_configure_id(struct device *dev, struct device_node *np, bool force_dma, const u32 *id) { const struct bus_dma_region *map = NULL; struct device_node *bus_np; u64 mask, end = 0; bool coherent, set_map = false; int ret; if (dev->dma_range_map) { dev_dbg(dev, "dma_range_map already set\n"); goto skip_map; } if (np == dev->of_node) bus_np = __of_get_dma_parent(np); else bus_np = of_node_get(np); ret = of_dma_get_range(bus_np, &map); of_node_put(bus_np); if (ret < 0) { /* * For legacy reasons, we have to assume some devices need * DMA configuration regardless of whether "dma-ranges" is * correctly specified or not. */ if (!force_dma) return ret == -ENODEV ? 0 : ret; } else { /* Determine the overall bounds of all DMA regions */ end = dma_range_map_max(map); set_map = true; } skip_map: /* * If @dev is expected to be DMA-capable then the bus code that created * it should have initialised its dma_mask pointer by this point. For * now, we'll continue the legacy behaviour of coercing it to the * coherent mask if not, but we'll no longer do so quietly. */ if (!dev->dma_mask) { dev_warn(dev, "DMA mask not set\n"); dev->dma_mask = &dev->coherent_dma_mask; } if (!end && dev->coherent_dma_mask) end = dev->coherent_dma_mask; else if (!end) end = (1ULL << 32) - 1; /* * Limit coherent and dma mask based on size and default mask * set by the driver. */ mask = DMA_BIT_MASK(ilog2(end) + 1); dev->coherent_dma_mask &= mask; *dev->dma_mask &= mask; /* ...but only set bus limit and range map if we found valid dma-ranges earlier */ if (set_map) { dev->bus_dma_limit = end; dev->dma_range_map = map; } coherent = of_dma_is_coherent(np); dev_dbg(dev, "device is%sdma coherent\n", coherent ? " " : " not "); ret = of_iommu_configure(dev, np, id); if (ret == -EPROBE_DEFER) { /* Don't touch range map if it wasn't set from a valid dma-ranges */ if (set_map) dev->dma_range_map = NULL; kfree(map); return -EPROBE_DEFER; } /* Take all other IOMMU errors to mean we'll just carry on without it */ dev_dbg(dev, "device is%sbehind an iommu\n", !ret ? " " : " not "); arch_setup_dma_ops(dev, coherent); if (ret) of_dma_set_restricted_buffer(dev, np); return 0; } EXPORT_SYMBOL_GPL(of_dma_configure_id); const void *of_device_get_match_data(const struct device *dev) { const struct of_device_id *match; match = of_match_device(dev->driver->of_match_table, dev); if (!match) return NULL; return match->data; } EXPORT_SYMBOL(of_device_get_match_data); /** * of_device_modalias - Fill buffer with newline terminated modalias string * @dev: Calling device * @str: Modalias string * @len: Size of @str */ ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len) { ssize_t sl; if (!dev || !dev->of_node || dev->of_node_reused) return -ENODEV; sl = of_modalias(dev->of_node, str, len - 2); if (sl < 0) return sl; if (sl > len - 2) return -ENOMEM; str[sl++] = '\n'; str[sl] = 0; return sl; } EXPORT_SYMBOL_GPL(of_device_modalias); /** * of_device_uevent - Display OF related uevent information * @dev: Device to display the uevent information for * @env: Kernel object's userspace event reference to fill up */ void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { const char *compat, *type; struct alias_prop *app; struct property *p; int seen = 0; if ((!dev) || (!dev->of_node)) return; add_uevent_var(env, "OF_NAME=%pOFn", dev->of_node); add_uevent_var(env, "OF_FULLNAME=%pOF", dev->of_node); type = of_node_get_device_type(dev->of_node); if (type) add_uevent_var(env, "OF_TYPE=%s", type); /* Since the compatible field can contain pretty much anything * it's not really legal to split it out with commas. We split it * up using a number of environment variables instead. */ of_property_for_each_string(dev->of_node, "compatible", p, compat) { add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat); seen++; } add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen); seen = 0; mutex_lock(&of_mutex); list_for_each_entry(app, &aliases_lookup, link) { if (dev->of_node == app->np) { add_uevent_var(env, "OF_ALIAS_%d=%s", seen, app->alias); seen++; } } mutex_unlock(&of_mutex); } EXPORT_SYMBOL_GPL(of_device_uevent); int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { int sl; if ((!dev) || (!dev->of_node) || dev->of_node_reused) return -ENODEV; /* Devicetree modalias is tricky, we add it in 2 steps */ if (add_uevent_var(env, "MODALIAS=")) return -ENOMEM; sl = of_modalias(dev->of_node, &env->buf[env->buflen-1], sizeof(env->buf) - env->buflen); if (sl < 0) return sl; if (sl >= (sizeof(env->buf) - env->buflen)) return -ENOMEM; env->buflen += sl; return 0; } EXPORT_SYMBOL_GPL(of_device_uevent_modalias); /** * of_device_make_bus_id - Use the device node data to assign a unique name * @dev: pointer to device structure that is linked to a device tree node * * This routine will first try using the translated bus address to * derive a unique name. If it cannot, then it will prepend names from * parent nodes until a unique name can be derived. */ void of_device_make_bus_id(struct device *dev) { struct device_node *node = dev->of_node; const __be32 *reg; u64 addr; u32 mask; /* Construct the name, using parent nodes if necessary to ensure uniqueness */ while (node->parent) { /* * If the address can be translated, then that is as much * uniqueness as we need. Make it the first component and return */ reg = of_get_property(node, "reg", NULL); if (reg && (addr = of_translate_address(node, reg)) != OF_BAD_ADDR) { if (!of_property_read_u32(node, "mask", &mask)) dev_set_name(dev, dev_name(dev) ? "%llx.%x.%pOFn:%s" : "%llx.%x.%pOFn", addr, ffs(mask) - 1, node, dev_name(dev)); else dev_set_name(dev, dev_name(dev) ? "%llx.%pOFn:%s" : "%llx.%pOFn", addr, node, dev_name(dev)); return; } /* format arguments only used if dev_name() resolves to NULL */ dev_set_name(dev, dev_name(dev) ? "%s:%s" : "%s", kbasename(node->full_name), dev_name(dev)); node = node->parent; } } EXPORT_SYMBOL_GPL(of_device_make_bus_id); |
| 301 144 157 157 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2022 Christian Brauner <brauner@kernel.org> */ #include <linux/cred.h> #include <linux/fs.h> #include <linux/mnt_idmapping.h> #include <linux/slab.h> #include <linux/user_namespace.h> #include <linux/seq_file.h> #include "internal.h" /* * Outside of this file vfs{g,u}id_t are always created from k{g,u}id_t, * never from raw values. These are just internal helpers. */ #define VFSUIDT_INIT_RAW(val) (vfsuid_t){ val } #define VFSGIDT_INIT_RAW(val) (vfsgid_t){ val } struct mnt_idmap { struct uid_gid_map uid_map; struct uid_gid_map gid_map; refcount_t count; }; /* * Carries the initial idmapping of 0:0:4294967295 which is an identity * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. */ struct mnt_idmap nop_mnt_idmap = { .count = REFCOUNT_INIT(1), }; EXPORT_SYMBOL_GPL(nop_mnt_idmap); /* * Carries the invalid idmapping of a full 0-4294967295 {g,u}id range. * This means that all {g,u}ids are mapped to INVALID_VFS{G,U}ID. */ struct mnt_idmap invalid_mnt_idmap = { .count = REFCOUNT_INIT(1), }; EXPORT_SYMBOL_GPL(invalid_mnt_idmap); /** * initial_idmapping - check whether this is the initial mapping * @ns: idmapping to check * * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1, * [...], 1000 to 1000 [...]. * * Return: true if this is the initial mapping, false if not. */ static inline bool initial_idmapping(const struct user_namespace *ns) { return ns == &init_user_ns; } /** * make_vfsuid - map a filesystem kuid according to an idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kuid : kuid to be mapped * * Take a @kuid and remap it from @fs_userns into @idmap. Use this * function when preparing a @kuid to be reported to userspace. * * If initial_idmapping() determines that this is not an idmapped mount * we can simply return @kuid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kuid won't change when calling * from_kuid() so we can simply retrieve the value via __kuid_val() * directly. * * Return: @kuid mapped according to @idmap. * If @kuid has no mapping in either @idmap or @fs_userns INVALID_UID is * returned. */ vfsuid_t make_vfsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, kuid_t kuid) { uid_t uid; if (idmap == &nop_mnt_idmap) return VFSUIDT_INIT(kuid); if (idmap == &invalid_mnt_idmap) return INVALID_VFSUID; if (initial_idmapping(fs_userns)) uid = __kuid_val(kuid); else uid = from_kuid(fs_userns, kuid); if (uid == (uid_t)-1) return INVALID_VFSUID; return VFSUIDT_INIT_RAW(map_id_down(&idmap->uid_map, uid)); } EXPORT_SYMBOL_GPL(make_vfsuid); /** * make_vfsgid - map a filesystem kgid according to an idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kgid : kgid to be mapped * * Take a @kgid and remap it from @fs_userns into @idmap. Use this * function when preparing a @kgid to be reported to userspace. * * If initial_idmapping() determines that this is not an idmapped mount * we can simply return @kgid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kgid won't change when calling * from_kgid() so we can simply retrieve the value via __kgid_val() * directly. * * Return: @kgid mapped according to @idmap. * If @kgid has no mapping in either @idmap or @fs_userns INVALID_GID is * returned. */ vfsgid_t make_vfsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, kgid_t kgid) { gid_t gid; if (idmap == &nop_mnt_idmap) return VFSGIDT_INIT(kgid); if (idmap == &invalid_mnt_idmap) return INVALID_VFSGID; if (initial_idmapping(fs_userns)) gid = __kgid_val(kgid); else gid = from_kgid(fs_userns, kgid); if (gid == (gid_t)-1) return INVALID_VFSGID; return VFSGIDT_INIT_RAW(map_id_down(&idmap->gid_map, gid)); } EXPORT_SYMBOL_GPL(make_vfsgid); /** * from_vfsuid - map a vfsuid into the filesystem idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsuid : vfsuid to be mapped * * Map @vfsuid into the filesystem idmapping. This function has to be used in * order to e.g. write @vfsuid to inode->i_uid. * * Return: @vfsuid mapped into the filesystem idmapping */ kuid_t from_vfsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsuid_t vfsuid) { uid_t uid; if (idmap == &nop_mnt_idmap) return AS_KUIDT(vfsuid); if (idmap == &invalid_mnt_idmap) return INVALID_UID; uid = map_id_up(&idmap->uid_map, __vfsuid_val(vfsuid)); if (uid == (uid_t)-1) return INVALID_UID; if (initial_idmapping(fs_userns)) return KUIDT_INIT(uid); return make_kuid(fs_userns, uid); } EXPORT_SYMBOL_GPL(from_vfsuid); /** * from_vfsgid - map a vfsgid into the filesystem idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsgid : vfsgid to be mapped * * Map @vfsgid into the filesystem idmapping. This function has to be used in * order to e.g. write @vfsgid to inode->i_gid. * * Return: @vfsgid mapped into the filesystem idmapping */ kgid_t from_vfsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsgid_t vfsgid) { gid_t gid; if (idmap == &nop_mnt_idmap) return AS_KGIDT(vfsgid); if (idmap == &invalid_mnt_idmap) return INVALID_GID; gid = map_id_up(&idmap->gid_map, __vfsgid_val(vfsgid)); if (gid == (gid_t)-1) return INVALID_GID; if (initial_idmapping(fs_userns)) return KGIDT_INIT(gid); return make_kgid(fs_userns, gid); } EXPORT_SYMBOL_GPL(from_vfsgid); #ifdef CONFIG_MULTIUSER /** * vfsgid_in_group_p() - check whether a vfsuid matches the caller's groups * @vfsgid: the mnt gid to match * * This function can be used to determine whether @vfsuid matches any of the * caller's groups. * * Return: 1 if vfsuid matches caller's groups, 0 if not. */ int vfsgid_in_group_p(vfsgid_t vfsgid) { return in_group_p(AS_KGIDT(vfsgid)); } #else int vfsgid_in_group_p(vfsgid_t vfsgid) { return 1; } #endif EXPORT_SYMBOL_GPL(vfsgid_in_group_p); static int copy_mnt_idmap(struct uid_gid_map *map_from, struct uid_gid_map *map_to) { struct uid_gid_extent *forward, *reverse; u32 nr_extents = READ_ONCE(map_from->nr_extents); /* Pairs with smp_wmb() when writing the idmapping. */ smp_rmb(); /* * Don't blindly copy @map_to into @map_from if nr_extents is * smaller or equal to UID_GID_MAP_MAX_BASE_EXTENTS. Since we * read @nr_extents someone could have written an idmapping and * then we might end up with inconsistent data. So just don't do * anything at all. */ if (nr_extents == 0) return -EINVAL; /* * Here we know that nr_extents is greater than zero which means * a map has been written. Since idmappings can't be changed * once they have been written we know that we can safely copy * from @map_to into @map_from. */ if (nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { *map_to = *map_from; return 0; } forward = kmemdup_array(map_from->forward, nr_extents, sizeof(struct uid_gid_extent), GFP_KERNEL_ACCOUNT); if (!forward) return -ENOMEM; reverse = kmemdup_array(map_from->reverse, nr_extents, sizeof(struct uid_gid_extent), GFP_KERNEL_ACCOUNT); if (!reverse) { kfree(forward); return -ENOMEM; } /* * The idmapping isn't exposed anywhere so we don't need to care * about ordering between extent pointers and @nr_extents * initialization. */ map_to->forward = forward; map_to->reverse = reverse; map_to->nr_extents = nr_extents; return 0; } static void free_mnt_idmap(struct mnt_idmap *idmap) { if (idmap->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(idmap->uid_map.forward); kfree(idmap->uid_map.reverse); } if (idmap->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(idmap->gid_map.forward); kfree(idmap->gid_map.reverse); } kfree(idmap); } struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns) { struct mnt_idmap *idmap; int ret; idmap = kzalloc(sizeof(struct mnt_idmap), GFP_KERNEL_ACCOUNT); if (!idmap) return ERR_PTR(-ENOMEM); refcount_set(&idmap->count, 1); ret = copy_mnt_idmap(&mnt_userns->uid_map, &idmap->uid_map); if (!ret) ret = copy_mnt_idmap(&mnt_userns->gid_map, &idmap->gid_map); if (ret) { free_mnt_idmap(idmap); idmap = ERR_PTR(ret); } return idmap; } /** * mnt_idmap_get - get a reference to an idmapping * @idmap: the idmap to bump the reference on * * If @idmap is not the @nop_mnt_idmap bump the reference count. * * Return: @idmap with reference count bumped if @not_mnt_idmap isn't passed. */ struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap) { if (idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap) refcount_inc(&idmap->count); return idmap; } EXPORT_SYMBOL_GPL(mnt_idmap_get); /** * mnt_idmap_put - put a reference to an idmapping * @idmap: the idmap to put the reference on * * If this is a non-initial idmapping, put the reference count when a mount is * released and free it if we're the last user. */ void mnt_idmap_put(struct mnt_idmap *idmap) { if (idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap && refcount_dec_and_test(&idmap->count)) free_mnt_idmap(idmap); } EXPORT_SYMBOL_GPL(mnt_idmap_put); int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_map) { struct uid_gid_map *map, *map_up; u32 idx, nr_mappings; if (!is_valid_mnt_idmap(idmap)) return 0; /* * Idmappings are shown relative to the caller's idmapping. * This is both the most intuitive and most useful solution. */ if (uid_map) { map = &idmap->uid_map; map_up = ¤t_user_ns()->uid_map; } else { map = &idmap->gid_map; map_up = ¤t_user_ns()->gid_map; } for (idx = 0, nr_mappings = 0; idx < map->nr_extents; idx++) { uid_t lower; struct uid_gid_extent *extent; if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = &map->extent[idx]; else extent = &map->forward[idx]; /* * Verify that the whole range of the mapping can be * resolved in the caller's idmapping. If it cannot be * resolved skip the mapping. */ lower = map_id_range_up(map_up, extent->lower_first, extent->count); if (lower == (uid_t) -1) continue; seq_printf(seq, "%u %u %u", extent->first, lower, extent->count); seq->count++; /* mappings are separated by \0 */ if (seq_has_overflowed(seq)) return -EAGAIN; nr_mappings++; } return nr_mappings; } |
| 5 3 4 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/spinlock.h> #include <linux/atomic.h> /* * This is an implementation of the notion of "decrement a * reference count, and return locked if it decremented to zero". * * NOTE NOTE NOTE! This is _not_ equivalent to * * if (atomic_dec_and_test(&atomic)) { * spin_lock(&lock); * return 1; * } * return 0; * * because the spin-lock and the decrement must be * "atomic". */ int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock(lock); if (atomic_dec_and_test(atomic)) return 1; spin_unlock(lock); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock); int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ spin_lock_irqsave(lock, *flags); if (atomic_dec_and_test(atomic)) return 1; spin_unlock_irqrestore(lock, *flags); return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave); int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ raw_spin_lock(lock); if (atomic_dec_and_test(atomic)) return 1; raw_spin_unlock(lock); return 0; } EXPORT_SYMBOL(_atomic_dec_and_raw_lock); int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock, unsigned long *flags) { /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ if (atomic_add_unless(atomic, -1, 1)) return 0; /* Otherwise do it the slow way */ raw_spin_lock_irqsave(lock, *flags); if (atomic_dec_and_test(atomic)) return 1; raw_spin_unlock_irqrestore(lock, *flags); return 0; } EXPORT_SYMBOL(_atomic_dec_and_raw_lock_irqsave); |
| 548 549 552 551 550 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LOCAL_LOCK_H # error "Do not include directly, include linux/local_lock.h" #endif #include <linux/percpu-defs.h> #include <linux/lockdep.h> #ifndef CONFIG_PREEMPT_RT typedef struct { #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; struct task_struct *owner; #endif } local_lock_t; /* local_trylock() and local_trylock_irqsave() only work with local_trylock_t */ typedef struct { #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; struct task_struct *owner; #endif u8 acquired; } local_trylock_t; #ifdef CONFIG_DEBUG_LOCK_ALLOC # define LOCAL_LOCK_DEBUG_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ .lock_type = LD_LOCK_PERCPU, \ }, \ .owner = NULL, # define LOCAL_TRYLOCK_DEBUG_INIT(lockname) \ LOCAL_LOCK_DEBUG_INIT(lockname) static inline void local_lock_acquire(local_lock_t *l) { lock_map_acquire(&l->dep_map); DEBUG_LOCKS_WARN_ON(l->owner); l->owner = current; } static inline void local_trylock_acquire(local_lock_t *l) { lock_map_acquire_try(&l->dep_map); DEBUG_LOCKS_WARN_ON(l->owner); l->owner = current; } static inline void local_lock_release(local_lock_t *l) { DEBUG_LOCKS_WARN_ON(l->owner != current); l->owner = NULL; lock_map_release(&l->dep_map); } static inline void local_lock_debug_init(local_lock_t *l) { l->owner = NULL; } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) # define LOCAL_TRYLOCK_DEBUG_INIT(lockname) static inline void local_lock_acquire(local_lock_t *l) { } static inline void local_trylock_acquire(local_lock_t *l) { } static inline void local_lock_release(local_lock_t *l) { } static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } #define INIT_LOCAL_TRYLOCK(lockname) { LOCAL_TRYLOCK_DEBUG_INIT(lockname) } #define __local_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ LD_LOCK_PERCPU); \ local_lock_debug_init(lock); \ } while (0) #define __local_trylock_init(lock) __local_lock_init((local_lock_t *)lock) #define __spinlock_nested_bh_init(lock) \ do { \ static struct lock_class_key __key; \ \ debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ LD_LOCK_NORMAL); \ local_lock_debug_init(lock); \ } while (0) #define __local_lock_acquire(lock) \ do { \ local_trylock_t *tl; \ local_lock_t *l; \ \ l = (local_lock_t *)(lock); \ tl = (local_trylock_t *)l; \ _Generic((lock), \ local_trylock_t *: ({ \ lockdep_assert(tl->acquired == 0); \ WRITE_ONCE(tl->acquired, 1); \ }), \ local_lock_t *: (void)0); \ local_lock_acquire(l); \ } while (0) #define __local_lock(lock) \ do { \ preempt_disable(); \ __local_lock_acquire(lock); \ } while (0) #define __local_lock_irq(lock) \ do { \ local_irq_disable(); \ __local_lock_acquire(lock); \ } while (0) #define __local_lock_irqsave(lock, flags) \ do { \ local_irq_save(flags); \ __local_lock_acquire(lock); \ } while (0) #define __local_trylock(lock) \ ({ \ local_trylock_t *tl; \ \ preempt_disable(); \ tl = (lock); \ if (READ_ONCE(tl->acquired)) { \ preempt_enable(); \ tl = NULL; \ } else { \ WRITE_ONCE(tl->acquired, 1); \ local_trylock_acquire( \ (local_lock_t *)tl); \ } \ !!tl; \ }) #define __local_trylock_irqsave(lock, flags) \ ({ \ local_trylock_t *tl; \ \ local_irq_save(flags); \ tl = (lock); \ if (READ_ONCE(tl->acquired)) { \ local_irq_restore(flags); \ tl = NULL; \ } else { \ WRITE_ONCE(tl->acquired, 1); \ local_trylock_acquire( \ (local_lock_t *)tl); \ } \ !!tl; \ }) /* preemption or migration must be disabled before calling __local_lock_is_locked */ #define __local_lock_is_locked(lock) READ_ONCE(this_cpu_ptr(lock)->acquired) #define __local_lock_release(lock) \ do { \ local_trylock_t *tl; \ local_lock_t *l; \ \ l = (local_lock_t *)(lock); \ tl = (local_trylock_t *)l; \ local_lock_release(l); \ _Generic((lock), \ local_trylock_t *: ({ \ lockdep_assert(tl->acquired == 1); \ WRITE_ONCE(tl->acquired, 0); \ }), \ local_lock_t *: (void)0); \ } while (0) #define __local_unlock(lock) \ do { \ __local_lock_release(lock); \ preempt_enable(); \ } while (0) #define __local_unlock_irq(lock) \ do { \ __local_lock_release(lock); \ local_irq_enable(); \ } while (0) #define __local_unlock_irqrestore(lock, flags) \ do { \ __local_lock_release(lock); \ local_irq_restore(flags); \ } while (0) #define __local_lock_nested_bh(lock) \ do { \ lockdep_assert_in_softirq(); \ local_lock_acquire((lock)); \ } while (0) #define __local_unlock_nested_bh(lock) \ local_lock_release((lock)) #else /* !CONFIG_PREEMPT_RT */ /* * On PREEMPT_RT local_lock maps to a per CPU spinlock, which protects the * critical section while staying preemptible. */ typedef spinlock_t local_lock_t; typedef spinlock_t local_trylock_t; #define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname)) #define INIT_LOCAL_TRYLOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname)) #define __local_lock_init(l) \ do { \ local_spin_lock_init((l)); \ } while (0) #define __local_trylock_init(l) __local_lock_init(l) #define __local_lock(__lock) \ do { \ migrate_disable(); \ spin_lock((__lock)); \ } while (0) #define __local_lock_irq(lock) __local_lock(lock) #define __local_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ flags = 0; \ __local_lock(lock); \ } while (0) #define __local_unlock(__lock) \ do { \ spin_unlock((__lock)); \ migrate_enable(); \ } while (0) #define __local_unlock_irq(lock) __local_unlock(lock) #define __local_unlock_irqrestore(lock, flags) __local_unlock(lock) #define __local_lock_nested_bh(lock) \ do { \ lockdep_assert_in_softirq_func(); \ spin_lock((lock)); \ } while (0) #define __local_unlock_nested_bh(lock) \ do { \ spin_unlock((lock)); \ } while (0) #define __local_trylock(lock) \ ({ \ int __locked; \ \ if (in_nmi() | in_hardirq()) { \ __locked = 0; \ } else { \ migrate_disable(); \ __locked = spin_trylock((lock)); \ if (!__locked) \ migrate_enable(); \ } \ __locked; \ }) #define __local_trylock_irqsave(lock, flags) \ ({ \ typecheck(unsigned long, flags); \ flags = 0; \ __local_trylock(lock); \ }) /* migration must be disabled before calling __local_lock_is_locked */ #define __local_lock_is_locked(__lock) \ (rt_mutex_owner(&this_cpu_ptr(__lock)->lock) == current) #endif /* CONFIG_PREEMPT_RT */ |
| 1 1 7 102 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* fs/ internal definitions * * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ struct super_block; struct file_system_type; struct iomap; struct iomap_ops; struct linux_binprm; struct path; struct mount; struct shrink_control; struct fs_context; struct pipe_inode_info; struct iov_iter; struct mnt_idmap; struct ns_common; /* * block/bdev.c */ #ifdef CONFIG_BLOCK extern void __init bdev_cache_init(void); #else static inline void bdev_cache_init(void) { } #endif /* CONFIG_BLOCK */ /* * buffer.c */ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block, const struct iomap *iomap); /* * char_dev.c */ extern void __init chrdev_init(void); /* * fs_context.c */ extern const struct fs_context_operations legacy_fs_context_ops; extern int parse_monolithic_mount_data(struct fs_context *, void *); extern void vfs_clean_context(struct fs_context *fc); extern int finish_clean_context(struct fs_context *fc); /* * namei.c */ extern int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, const struct path *root); int do_rmdir(int dfd, struct filename *name); int do_unlinkat(int dfd, struct filename *name); int may_linkat(struct mnt_idmap *idmap, const struct path *link); int do_renameat2(int olddfd, struct filename *oldname, int newdfd, struct filename *newname, unsigned int flags); int do_mkdirat(int dfd, struct filename *name, umode_t mode); int do_symlinkat(struct filename *from, int newdfd, struct filename *to); int do_linkat(int olddfd, struct filename *old, int newdfd, struct filename *new, int flags); int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, struct file *file, umode_t mode); struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); /* * namespace.c */ extern struct vfsmount *lookup_mnt(const struct path *); extern int finish_automount(struct vfsmount *, const struct path *); extern int sb_prepare_remount_readonly(struct super_block *); extern void __init mnt_init(void); int mnt_get_write_access_file(struct file *file); void mnt_put_write_access_file(struct file *file); extern void dissolve_on_fput(struct vfsmount *); extern bool may_mount(void); int path_mount(const char *dev_name, const struct path *path, const char *type_page, unsigned long flags, void *data_page); int path_umount(const struct path *path, int flags); int show_path(struct seq_file *m, struct dentry *root); /* * fs_struct.c */ extern void chroot_fs_refs(const struct path *, const struct path *); /* * file_table.c */ struct file *alloc_empty_file(int flags, const struct cred *cred); struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred); struct file *alloc_empty_backing_file(int flags, const struct cred *cred); void backing_file_set_user_path(struct file *f, const struct path *path); static inline void file_put_write_access(struct file *file) { put_write_access(file->f_inode); mnt_put_write_access(file->f_path.mnt); if (unlikely(file->f_mode & FMODE_BACKING)) mnt_put_write_access(backing_file_user_path(file)->mnt); } static inline void put_file_access(struct file *file) { if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) { i_readcount_dec(file->f_inode); } else if (file->f_mode & FMODE_WRITER) { file_put_write_access(file); } } void fput_close_sync(struct file *); void fput_close(struct file *); /* * super.c */ extern int reconfigure_super(struct fs_context *); extern bool super_trylock_shared(struct super_block *sb); struct super_block *user_get_super(dev_t, bool excl); void put_super(struct super_block *sb); extern bool mount_capable(struct fs_context *); int sb_init_dio_done_wq(struct super_block *sb); /* * Prepare superblock for changing its read-only state (i.e., either remount * read-write superblock read-only or vice versa). After this function returns * mnt_is_readonly() will return true for any mount of the superblock if its * caller is able to observe any changes done by the remount. This holds until * sb_end_ro_state_change() is called. */ static inline void sb_start_ro_state_change(struct super_block *sb) { WRITE_ONCE(sb->s_readonly_remount, 1); /* * For RO->RW transition, the barrier pairs with the barrier in * mnt_is_readonly() making sure if mnt_is_readonly() sees SB_RDONLY * cleared, it will see s_readonly_remount set. * For RW->RO transition, the barrier pairs with the barrier in * mnt_get_write_access() before the mnt_is_readonly() check. * The barrier makes sure if mnt_get_write_access() sees MNT_WRITE_HOLD * already cleared, it will see s_readonly_remount set. */ smp_wmb(); } /* * Ends section changing read-only state of the superblock. After this function * returns if mnt_is_readonly() returns false, the caller will be able to * observe all the changes remount did to the superblock. */ static inline void sb_end_ro_state_change(struct super_block *sb) { /* * This barrier provides release semantics that pairs with * the smp_rmb() acquire semantics in mnt_is_readonly(). * This barrier pair ensure that when mnt_is_readonly() sees * 0 for sb->s_readonly_remount, it will also see all the * preceding flag changes that were made during the RO state * change. */ smp_wmb(); WRITE_ONCE(sb->s_readonly_remount, 0); } /* * open.c */ struct open_flags { int open_flag; umode_t mode; int acc_mode; int intent; int lookup_flags; }; extern struct file *do_filp_open(int dfd, struct filename *pathname, const struct open_flags *op); extern struct file *do_file_open_root(const struct path *, const char *, const struct open_flags *); extern struct open_how build_open_how(int flags, umode_t mode); extern int build_open_flags(const struct open_how *how, struct open_flags *op); struct file *file_close_fd_locked(struct files_struct *files, unsigned fd); int do_ftruncate(struct file *file, loff_t length, int small); int do_sys_ftruncate(unsigned int fd, loff_t length, int small); int chmod_common(const struct path *path, umode_t mode); int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag); int chown_common(const struct path *path, uid_t user, gid_t group); extern int vfs_open(const struct path *, struct file *); /* * inode.c */ extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc); int dentry_needs_remove_privs(struct mnt_idmap *, struct dentry *dentry); bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); /* * fs-writeback.c */ extern long get_nr_dirty_inodes(void); /* * dcache.c */ extern int d_set_mounted(struct dentry *dentry); extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc); extern struct dentry *d_alloc_cursor(struct dentry *); extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); extern char *simple_dname(struct dentry *, char *, int); extern void dput_to_list(struct dentry *, struct list_head *); extern void shrink_dentry_list(struct list_head *); extern void shrink_dcache_for_umount(struct super_block *); extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seq); extern void d_genocide(struct dentry *); /* * pipe.c */ extern const struct file_operations pipefifo_fops; /* * fs_pin.c */ extern void group_pin_kill(struct hlist_head *p); extern void mnt_pin_kill(struct mount *m); /* * fs/nsfs.c */ extern const struct dentry_operations ns_dentry_operations; int open_namespace(struct ns_common *ns); /* * fs/stat.c: */ int do_statx(int dfd, struct filename *filename, unsigned int flags, unsigned int mask, struct statx __user *buffer); int do_statx_fd(int fd, unsigned int flags, unsigned int mask, struct statx __user *buffer); /* * fs/splice.c: */ ssize_t splice_file_to_pipe(struct file *in, struct pipe_inode_info *opipe, loff_t *offset, size_t len, unsigned int flags); /* * fs/xattr.c: */ struct xattr_name { char name[XATTR_NAME_MAX + 1]; }; struct kernel_xattr_ctx { /* Value of attribute */ union { const void __user *cvalue; void __user *value; }; void *kvalue; size_t size; /* Attribute name */ struct xattr_name *kname; unsigned int flags; }; ssize_t file_getxattr(struct file *file, struct kernel_xattr_ctx *ctx); ssize_t filename_getxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx); int file_setxattr(struct file *file, struct kernel_xattr_ctx *ctx); int filename_setxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx); int setxattr_copy(const char __user *name, struct kernel_xattr_ctx *ctx); int import_xattr_name(struct xattr_name *kname, const char __user *name); int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode); #ifdef CONFIG_FS_POSIX_ACL int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size); ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size); #else static inline int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size) { return -EOPNOTSUPP; } static inline ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size) { return -EOPNOTSUPP; } #endif ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos); /* * fs/attr.c */ struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns); struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap); void mnt_idmap_put(struct mnt_idmap *idmap); struct stashed_operations { struct dentry *(*stash_dentry)(struct dentry **stashed, struct dentry *dentry); void (*put_data)(void *data); int (*init_inode)(struct inode *inode, void *data); }; int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data, struct path *path); void stashed_dentry_prune(struct dentry *dentry); struct dentry *stash_dentry(struct dentry **stashed, struct dentry *dentry); struct dentry *stashed_dentry_get(struct dentry **stashed); /** * path_mounted - check whether path is mounted * @path: path to check * * Determine whether @path refers to the root of a mount. * * Return: true if @path is the root of a mount, false if not. */ static inline bool path_mounted(const struct path *path) { return path->mnt->mnt_root == path->dentry; } void file_f_owner_release(struct file *file); bool file_seek_cur_needs_f_lock(struct file *file); int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_map); struct dentry *find_next_child(struct dentry *parent, struct dentry *prev); int anon_inode_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags); int anon_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); void pidfs_get_root(struct path *path); void nsfs_get_root(struct path *path); |
| 31 33 10 10 33 23 23 23 25 8 8 20 20 20 10 10 10 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/bvec.h> #include <linux/fault-inject-usercopy.h> #include <linux/uio.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/scatterlist.h> #include <linux/instrumented.h> #include <linux/iov_iter.h> static __always_inline size_t copy_to_user_iter(void __user *iter_to, size_t progress, size_t len, void *from, void *priv2) { if (should_fail_usercopy()) return len; if (access_ok(iter_to, len)) { from += progress; instrument_copy_to_user(iter_to, from, len); len = raw_copy_to_user(iter_to, from, len); } return len; } static __always_inline size_t copy_to_user_iter_nofault(void __user *iter_to, size_t progress, size_t len, void *from, void *priv2) { ssize_t res; if (should_fail_usercopy()) return len; from += progress; res = copy_to_user_nofault(iter_to, from, len); return res < 0 ? len : res; } static __always_inline size_t copy_from_user_iter(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { size_t res = len; if (should_fail_usercopy()) return len; if (access_ok(iter_from, len)) { to += progress; instrument_copy_from_user_before(to, iter_from, len); res = raw_copy_from_user(to, iter_from, len); instrument_copy_from_user_after(to, iter_from, len, res); } return res; } static __always_inline size_t memcpy_to_iter(void *iter_to, size_t progress, size_t len, void *from, void *priv2) { memcpy(iter_to, from + progress, len); return 0; } static __always_inline size_t memcpy_from_iter(void *iter_from, size_t progress, size_t len, void *to, void *priv2) { memcpy(to + progress, iter_from, len); return 0; } /* * fault_in_iov_iter_readable - fault in iov iterator for reading * @i: iterator * @size: maximum length * * Fault in one or more iovecs of the given iov_iter, to a maximum length of * @size. For each iovec, fault in each page that constitutes the iovec. * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). * * Always returns 0 for non-userspace iterators. */ size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t size) { if (iter_is_ubuf(i)) { size_t n = min(size, iov_iter_count(i)); n -= fault_in_readable(i->ubuf + i->iov_offset, n); return size - n; } else if (iter_is_iovec(i)) { size_t count = min(size, iov_iter_count(i)); const struct iovec *p; size_t skip; size -= count; for (p = iter_iov(i), skip = i->iov_offset; count; p++, skip = 0) { size_t len = min(count, p->iov_len - skip); size_t ret; if (unlikely(!len)) continue; ret = fault_in_readable(p->iov_base + skip, len); count -= len - ret; if (ret) break; } return count + size; } return 0; } EXPORT_SYMBOL(fault_in_iov_iter_readable); /* * fault_in_iov_iter_writeable - fault in iov iterator for writing * @i: iterator * @size: maximum length * * Faults in the iterator using get_user_pages(), i.e., without triggering * hardware page faults. This is primarily useful when we already know that * some or all of the pages in @i aren't in memory. * * Returns the number of bytes not faulted in, like copy_to_user() and * copy_from_user(). * * Always returns 0 for non-user-space iterators. */ size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t size) { if (iter_is_ubuf(i)) { size_t n = min(size, iov_iter_count(i)); n -= fault_in_safe_writeable(i->ubuf + i->iov_offset, n); return size - n; } else if (iter_is_iovec(i)) { size_t count = min(size, iov_iter_count(i)); const struct iovec *p; size_t skip; size -= count; for (p = iter_iov(i), skip = i->iov_offset; count; p++, skip = 0) { size_t len = min(count, p->iov_len - skip); size_t ret; if (unlikely(!len)) continue; ret = fault_in_safe_writeable(p->iov_base + skip, len); count -= len - ret; if (ret) break; } return count + size; } return 0; } EXPORT_SYMBOL(fault_in_iov_iter_writeable); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_IOVEC, .nofault = false, .data_source = direction, .__iov = iov, .nr_segs = nr_segs, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_init); size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(i->data_source)) return 0; if (user_backed_iter(i)) might_fault(); return iterate_and_advance(i, bytes, (void *)addr, copy_to_user_iter, memcpy_to_iter); } EXPORT_SYMBOL(_copy_to_iter); #ifdef CONFIG_ARCH_HAS_COPY_MC static __always_inline size_t copy_to_user_iter_mc(void __user *iter_to, size_t progress, size_t len, void *from, void *priv2) { if (access_ok(iter_to, len)) { from += progress; instrument_copy_to_user(iter_to, from, len); len = copy_mc_to_user(iter_to, from, len); } return len; } static __always_inline size_t memcpy_to_iter_mc(void *iter_to, size_t progress, size_t len, void *from, void *priv2) { return copy_mc_to_kernel(iter_to, from + progress, len); } /** * _copy_mc_to_iter - copy to iter with source memory error exception handling * @addr: source kernel address * @bytes: total transfer length * @i: destination iterator * * The pmem driver deploys this for the dax operation * (dax_copy_to_iter()) for dax reads (bypass page-cache and the * block-layer). Upon #MC read(2) aborts and returns EIO or the bytes * successfully copied. * * The main differences between this and typical _copy_to_iter(). * * * Typical tail/residue handling after a fault retries the copy * byte-by-byte until the fault happens again. Re-triggering machine * checks is potentially fatal so the implementation uses source * alignment and poison alignment assumptions to avoid re-triggering * hardware exceptions. * * * ITER_KVEC and ITER_BVEC can return short copies. Compare to * copy_to_iter() where only ITER_IOVEC attempts might return a short copy. * * Return: number of bytes copied (may be %0) */ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(i->data_source)) return 0; if (user_backed_iter(i)) might_fault(); return iterate_and_advance(i, bytes, (void *)addr, copy_to_user_iter_mc, memcpy_to_iter_mc); } EXPORT_SYMBOL_GPL(_copy_mc_to_iter); #endif /* CONFIG_ARCH_HAS_COPY_MC */ static __always_inline size_t __copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { return iterate_and_advance(i, bytes, addr, copy_from_user_iter, memcpy_from_iter); } size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(!i->data_source)) return 0; if (user_backed_iter(i)) might_fault(); return __copy_from_iter(addr, bytes, i); } EXPORT_SYMBOL(_copy_from_iter); static __always_inline size_t copy_from_user_iter_nocache(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { return __copy_from_user_inatomic_nocache(to + progress, iter_from, len); } size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(!i->data_source)) return 0; return iterate_and_advance(i, bytes, addr, copy_from_user_iter_nocache, memcpy_from_iter); } EXPORT_SYMBOL(_copy_from_iter_nocache); #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE static __always_inline size_t copy_from_user_iter_flushcache(void __user *iter_from, size_t progress, size_t len, void *to, void *priv2) { return __copy_from_user_flushcache(to + progress, iter_from, len); } static __always_inline size_t memcpy_from_iter_flushcache(void *iter_from, size_t progress, size_t len, void *to, void *priv2) { memcpy_flushcache(to + progress, iter_from, len); return 0; } /** * _copy_from_iter_flushcache - write destination through cpu cache * @addr: destination kernel address * @bytes: total transfer length * @i: source iterator * * The pmem driver arranges for filesystem-dax to use this facility via * dax_copy_from_iter() for ensuring that writes to persistent memory * are flushed through the CPU cache. It is differentiated from * _copy_from_iter_nocache() in that guarantees all data is flushed for * all iterator types. The _copy_from_iter_nocache() only attempts to * bypass the cache for the ITER_IOVEC case, and on some archs may use * instructions that strand dirty-data in the cache. * * Return: number of bytes copied (may be %0) */ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { if (WARN_ON_ONCE(!i->data_source)) return 0; return iterate_and_advance(i, bytes, addr, copy_from_user_iter_flushcache, memcpy_from_iter_flushcache); } EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache); #endif static inline bool page_copy_sane(struct page *page, size_t offset, size_t n) { struct page *head; size_t v = n + offset; /* * The general case needs to access the page order in order * to compute the page size. * However, we mostly deal with order-0 pages and thus can * avoid a possible cache line miss for requests that fit all * page orders. */ if (n <= v && v <= PAGE_SIZE) return true; head = compound_head(page); v += (page - head) << PAGE_SHIFT; if (WARN_ON(n > v || v > page_size(head))) return false; return true; } size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t res = 0; if (!page_copy_sane(page, offset, bytes)) return 0; if (WARN_ON_ONCE(i->data_source)) return 0; page += offset / PAGE_SIZE; // first subpage offset %= PAGE_SIZE; while (1) { void *kaddr = kmap_local_page(page); size_t n = min(bytes, (size_t)PAGE_SIZE - offset); n = _copy_to_iter(kaddr + offset, n, i); kunmap_local(kaddr); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page++; offset = 0; } } return res; } EXPORT_SYMBOL(copy_page_to_iter); size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i) { size_t res = 0; if (!page_copy_sane(page, offset, bytes)) return 0; if (WARN_ON_ONCE(i->data_source)) return 0; page += offset / PAGE_SIZE; // first subpage offset %= PAGE_SIZE; while (1) { void *kaddr = kmap_local_page(page); size_t n = min(bytes, (size_t)PAGE_SIZE - offset); n = iterate_and_advance(i, n, kaddr + offset, copy_to_user_iter_nofault, memcpy_to_iter); kunmap_local(kaddr); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page++; offset = 0; } } return res; } EXPORT_SYMBOL(copy_page_to_iter_nofault); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { size_t res = 0; if (!page_copy_sane(page, offset, bytes)) return 0; page += offset / PAGE_SIZE; // first subpage offset %= PAGE_SIZE; while (1) { void *kaddr = kmap_local_page(page); size_t n = min(bytes, (size_t)PAGE_SIZE - offset); n = _copy_from_iter(kaddr + offset, n, i); kunmap_local(kaddr); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page++; offset = 0; } } return res; } EXPORT_SYMBOL(copy_page_from_iter); static __always_inline size_t zero_to_user_iter(void __user *iter_to, size_t progress, size_t len, void *priv, void *priv2) { return clear_user(iter_to, len); } static __always_inline size_t zero_to_iter(void *iter_to, size_t progress, size_t len, void *priv, void *priv2) { memset(iter_to, 0, len); return 0; } size_t iov_iter_zero(size_t bytes, struct iov_iter *i) { return iterate_and_advance(i, bytes, NULL, zero_to_user_iter, zero_to_iter); } EXPORT_SYMBOL(iov_iter_zero); size_t copy_folio_from_iter_atomic(struct folio *folio, size_t offset, size_t bytes, struct iov_iter *i) { size_t n, copied = 0; if (!page_copy_sane(&folio->page, offset, bytes)) return 0; if (WARN_ON_ONCE(!i->data_source)) return 0; do { char *to = kmap_local_folio(folio, offset); n = bytes - copied; if (folio_test_partial_kmap(folio) && n > PAGE_SIZE - offset_in_page(offset)) n = PAGE_SIZE - offset_in_page(offset); pagefault_disable(); n = __copy_from_iter(to, n, i); pagefault_enable(); kunmap_local(to); copied += n; offset += n; } while (copied != bytes && n > 0); return copied; } EXPORT_SYMBOL(copy_folio_from_iter_atomic); static void iov_iter_bvec_advance(struct iov_iter *i, size_t size) { const struct bio_vec *bvec, *end; if (!i->count) return; i->count -= size; size += i->iov_offset; for (bvec = i->bvec, end = bvec + i->nr_segs; bvec < end; bvec++) { if (likely(size < bvec->bv_len)) break; size -= bvec->bv_len; } i->iov_offset = size; i->nr_segs -= bvec - i->bvec; i->bvec = bvec; } static void iov_iter_iovec_advance(struct iov_iter *i, size_t size) { const struct iovec *iov, *end; if (!i->count) return; i->count -= size; size += i->iov_offset; // from beginning of current segment for (iov = iter_iov(i), end = iov + i->nr_segs; iov < end; iov++) { if (likely(size < iov->iov_len)) break; size -= iov->iov_len; } i->iov_offset = size; i->nr_segs -= iov - iter_iov(i); i->__iov = iov; } static void iov_iter_folioq_advance(struct iov_iter *i, size_t size) { const struct folio_queue *folioq = i->folioq; unsigned int slot = i->folioq_slot; if (!i->count) return; i->count -= size; if (slot >= folioq_nr_slots(folioq)) { folioq = folioq->next; slot = 0; } size += i->iov_offset; /* From beginning of current segment. */ do { size_t fsize = folioq_folio_size(folioq, slot); if (likely(size < fsize)) break; size -= fsize; slot++; if (slot >= folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } while (size); i->iov_offset = size; i->folioq_slot = slot; i->folioq = folioq; } void iov_iter_advance(struct iov_iter *i, size_t size) { if (unlikely(i->count < size)) size = i->count; if (likely(iter_is_ubuf(i)) || unlikely(iov_iter_is_xarray(i))) { i->iov_offset += size; i->count -= size; } else if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) { /* iovec and kvec have identical layouts */ iov_iter_iovec_advance(i, size); } else if (iov_iter_is_bvec(i)) { iov_iter_bvec_advance(i, size); } else if (iov_iter_is_folioq(i)) { iov_iter_folioq_advance(i, size); } else if (iov_iter_is_discard(i)) { i->count -= size; } } EXPORT_SYMBOL(iov_iter_advance); static void iov_iter_folioq_revert(struct iov_iter *i, size_t unroll) { const struct folio_queue *folioq = i->folioq; unsigned int slot = i->folioq_slot; for (;;) { size_t fsize; if (slot == 0) { folioq = folioq->prev; slot = folioq_nr_slots(folioq); } slot--; fsize = folioq_folio_size(folioq, slot); if (unroll <= fsize) { i->iov_offset = fsize - unroll; break; } unroll -= fsize; } i->folioq_slot = slot; i->folioq = folioq; } void iov_iter_revert(struct iov_iter *i, size_t unroll) { if (!unroll) return; if (WARN_ON(unroll > MAX_RW_COUNT)) return; i->count += unroll; if (unlikely(iov_iter_is_discard(i))) return; if (unroll <= i->iov_offset) { i->iov_offset -= unroll; return; } unroll -= i->iov_offset; if (iov_iter_is_xarray(i) || iter_is_ubuf(i)) { BUG(); /* We should never go beyond the start of the specified * range since we might then be straying into pages that * aren't pinned. */ } else if (iov_iter_is_bvec(i)) { const struct bio_vec *bvec = i->bvec; while (1) { size_t n = (--bvec)->bv_len; i->nr_segs++; if (unroll <= n) { i->bvec = bvec; i->iov_offset = n - unroll; return; } unroll -= n; } } else if (iov_iter_is_folioq(i)) { i->iov_offset = 0; iov_iter_folioq_revert(i, unroll); } else { /* same logics for iovec and kvec */ const struct iovec *iov = iter_iov(i); while (1) { size_t n = (--iov)->iov_len; i->nr_segs++; if (unroll <= n) { i->__iov = iov; i->iov_offset = n - unroll; return; } unroll -= n; } } } EXPORT_SYMBOL(iov_iter_revert); /* * Return the count of just the current iov_iter segment. */ size_t iov_iter_single_seg_count(const struct iov_iter *i) { if (i->nr_segs > 1) { if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return min(i->count, iter_iov(i)->iov_len - i->iov_offset); if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); } if (unlikely(iov_iter_is_folioq(i))) return !i->count ? 0 : umin(folioq_folio_size(i->folioq, i->folioq_slot), i->count); return i->count; } EXPORT_SYMBOL(iov_iter_single_seg_count); void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_KVEC, .data_source = direction, .kvec = kvec, .nr_segs = nr_segs, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_kvec); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count) { WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_BVEC, .data_source = direction, .bvec = bvec, .nr_segs = nr_segs, .iov_offset = 0, .count = count }; } EXPORT_SYMBOL(iov_iter_bvec); /** * iov_iter_folio_queue - Initialise an I/O iterator to use the folios in a folio queue * @i: The iterator to initialise. * @direction: The direction of the transfer. * @folioq: The starting point in the folio queue. * @first_slot: The first slot in the folio queue to use * @offset: The offset into the folio in the first slot to start at * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator to either draw data out of the pages attached to an * inode or to inject data into those pages. The pages *must* be prevented * from evaporation, either by taking a ref on them or locking them by the * caller. */ void iov_iter_folio_queue(struct iov_iter *i, unsigned int direction, const struct folio_queue *folioq, unsigned int first_slot, unsigned int offset, size_t count) { BUG_ON(direction & ~1); *i = (struct iov_iter) { .iter_type = ITER_FOLIOQ, .data_source = direction, .folioq = folioq, .folioq_slot = first_slot, .count = count, .iov_offset = offset, }; } EXPORT_SYMBOL(iov_iter_folio_queue); /** * iov_iter_xarray - Initialise an I/O iterator to use the pages in an xarray * @i: The iterator to initialise. * @direction: The direction of the transfer. * @xarray: The xarray to access. * @start: The start file position. * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator to either draw data out of the pages attached to an * inode or to inject data into those pages. The pages *must* be prevented * from evaporation, either by taking a ref on them or locking them by the * caller. */ void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count) { BUG_ON(direction & ~1); *i = (struct iov_iter) { .iter_type = ITER_XARRAY, .data_source = direction, .xarray = xarray, .xarray_start = start, .count = count, .iov_offset = 0 }; } EXPORT_SYMBOL(iov_iter_xarray); /** * iov_iter_discard - Initialise an I/O iterator that discards data * @i: The iterator to initialise. * @direction: The direction of the transfer. * @count: The size of the I/O buffer in bytes. * * Set up an I/O iterator that just discards everything that's written to it. * It's only available as a READ iterator. */ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) { BUG_ON(direction != READ); *i = (struct iov_iter){ .iter_type = ITER_DISCARD, .data_source = false, .count = count, .iov_offset = 0 }; } EXPORT_SYMBOL(iov_iter_discard); static unsigned long iov_iter_alignment_iovec(const struct iov_iter *i) { const struct iovec *iov = iter_iov(i); unsigned long res = 0; size_t size = i->count; size_t skip = i->iov_offset; do { size_t len = iov->iov_len - skip; if (len) { res |= (unsigned long)iov->iov_base + skip; if (len > size) len = size; res |= len; size -= len; } iov++; skip = 0; } while (size); return res; } static unsigned long iov_iter_alignment_bvec(const struct iov_iter *i) { const struct bio_vec *bvec = i->bvec; unsigned res = 0; size_t size = i->count; unsigned skip = i->iov_offset; do { size_t len = bvec->bv_len - skip; res |= (unsigned long)bvec->bv_offset + skip; if (len > size) len = size; res |= len; bvec++; size -= len; skip = 0; } while (size); return res; } unsigned long iov_iter_alignment(const struct iov_iter *i) { if (likely(iter_is_ubuf(i))) { size_t size = i->count; if (size) return ((unsigned long)i->ubuf + i->iov_offset) | size; return 0; } /* iovec and kvec have identical layouts */ if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return iov_iter_alignment_iovec(i); if (iov_iter_is_bvec(i)) return iov_iter_alignment_bvec(i); /* With both xarray and folioq types, we're dealing with whole folios. */ if (iov_iter_is_folioq(i)) return i->iov_offset | i->count; if (iov_iter_is_xarray(i)) return (i->xarray_start + i->iov_offset) | i->count; return 0; } EXPORT_SYMBOL(iov_iter_alignment); unsigned long iov_iter_gap_alignment(const struct iov_iter *i) { unsigned long res = 0; unsigned long v = 0; size_t size = i->count; unsigned k; if (iter_is_ubuf(i)) return 0; if (WARN_ON(!iter_is_iovec(i))) return ~0U; for (k = 0; k < i->nr_segs; k++) { const struct iovec *iov = iter_iov(i) + k; if (iov->iov_len) { unsigned long base = (unsigned long)iov->iov_base; if (v) // if not the first one res |= base | v; // this start | previous end v = base + iov->iov_len; if (size <= iov->iov_len) break; size -= iov->iov_len; } } return res; } EXPORT_SYMBOL(iov_iter_gap_alignment); static int want_pages_array(struct page ***res, size_t size, size_t start, unsigned int maxpages) { unsigned int count = DIV_ROUND_UP(size + start, PAGE_SIZE); if (count > maxpages) count = maxpages; WARN_ON(!count); // caller should've prevented that if (!*res) { *res = kvmalloc_array(count, sizeof(struct page *), GFP_KERNEL); if (!*res) return 0; } return count; } static ssize_t iter_folioq_get_pages(struct iov_iter *iter, struct page ***ppages, size_t maxsize, unsigned maxpages, size_t *_start_offset) { const struct folio_queue *folioq = iter->folioq; struct page **pages; unsigned int slot = iter->folioq_slot; size_t extracted = 0, count = iter->count, iov_offset = iter->iov_offset; if (slot >= folioq_nr_slots(folioq)) { folioq = folioq->next; slot = 0; if (WARN_ON(iov_offset != 0)) return -EIO; } maxpages = want_pages_array(ppages, maxsize, iov_offset & ~PAGE_MASK, maxpages); if (!maxpages) return -ENOMEM; *_start_offset = iov_offset & ~PAGE_MASK; pages = *ppages; for (;;) { struct folio *folio = folioq_folio(folioq, slot); size_t offset = iov_offset, fsize = folioq_folio_size(folioq, slot); size_t part = PAGE_SIZE - offset % PAGE_SIZE; if (offset < fsize) { part = umin(part, umin(maxsize - extracted, fsize - offset)); count -= part; iov_offset += part; extracted += part; *pages = folio_page(folio, offset / PAGE_SIZE); get_page(*pages); pages++; maxpages--; } if (maxpages == 0 || extracted >= maxsize) break; if (iov_offset >= fsize) { iov_offset = 0; slot++; if (slot == folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } } iter->count = count; iter->iov_offset = iov_offset; iter->folioq = folioq; iter->folioq_slot = slot; return extracted; } static ssize_t iter_xarray_populate_pages(struct page **pages, struct xarray *xa, pgoff_t index, unsigned int nr_pages) { XA_STATE(xas, xa, index); struct folio *folio; unsigned int ret = 0; rcu_read_lock(); for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; /* Has the folio moved or been split? */ if (unlikely(folio != xas_reload(&xas))) { xas_reset(&xas); continue; } pages[ret] = folio_file_page(folio, xas.xa_index); folio_get(folio); if (++ret == nr_pages) break; } rcu_read_unlock(); return ret; } static ssize_t iter_xarray_get_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned maxpages, size_t *_start_offset) { unsigned nr, offset, count; pgoff_t index; loff_t pos; pos = i->xarray_start + i->iov_offset; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; *_start_offset = offset; count = want_pages_array(pages, maxsize, offset, maxpages); if (!count) return -ENOMEM; nr = iter_xarray_populate_pages(*pages, i->xarray, index, count); if (nr == 0) return 0; maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize); i->iov_offset += maxsize; i->count -= maxsize; return maxsize; } /* must be done on non-empty ITER_UBUF or ITER_IOVEC one */ static unsigned long first_iovec_segment(const struct iov_iter *i, size_t *size) { size_t skip; long k; if (iter_is_ubuf(i)) return (unsigned long)i->ubuf + i->iov_offset; for (k = 0, skip = i->iov_offset; k < i->nr_segs; k++, skip = 0) { const struct iovec *iov = iter_iov(i) + k; size_t len = iov->iov_len - skip; if (unlikely(!len)) continue; if (*size > len) *size = len; return (unsigned long)iov->iov_base + skip; } BUG(); // if it had been empty, we wouldn't get called } /* must be done on non-empty ITER_BVEC one */ static struct page *first_bvec_segment(const struct iov_iter *i, size_t *size, size_t *start) { struct page *page; size_t skip = i->iov_offset, len; len = i->bvec->bv_len - skip; if (*size > len) *size = len; skip += i->bvec->bv_offset; page = i->bvec->bv_page + skip / PAGE_SIZE; *start = skip % PAGE_SIZE; return page; } static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, size_t *start) { unsigned int n, gup_flags = 0; if (maxsize > i->count) maxsize = i->count; if (!maxsize) return 0; if (maxsize > MAX_RW_COUNT) maxsize = MAX_RW_COUNT; if (likely(user_backed_iter(i))) { unsigned long addr; int res; if (iov_iter_rw(i) != WRITE) gup_flags |= FOLL_WRITE; if (i->nofault) gup_flags |= FOLL_NOFAULT; addr = first_iovec_segment(i, &maxsize); *start = addr % PAGE_SIZE; addr &= PAGE_MASK; n = want_pages_array(pages, maxsize, *start, maxpages); if (!n) return -ENOMEM; res = get_user_pages_fast(addr, n, gup_flags, *pages); if (unlikely(res <= 0)) return res; maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - *start); iov_iter_advance(i, maxsize); return maxsize; } if (iov_iter_is_bvec(i)) { struct page **p; struct page *page; page = first_bvec_segment(i, &maxsize, start); n = want_pages_array(pages, maxsize, *start, maxpages); if (!n) return -ENOMEM; p = *pages; for (int k = 0; k < n; k++) { struct folio *folio = page_folio(page + k); p[k] = page + k; if (!folio_test_slab(folio)) folio_get(folio); } maxsize = min_t(size_t, maxsize, n * PAGE_SIZE - *start); i->count -= maxsize; i->iov_offset += maxsize; if (i->iov_offset == i->bvec->bv_len) { i->iov_offset = 0; i->bvec++; i->nr_segs--; } return maxsize; } if (iov_iter_is_folioq(i)) return iter_folioq_get_pages(i, pages, maxsize, maxpages, start); if (iov_iter_is_xarray(i)) return iter_xarray_get_pages(i, pages, maxsize, maxpages, start); return -EFAULT; } ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { if (!maxpages) return 0; BUG_ON(!pages); return __iov_iter_get_pages_alloc(i, &pages, maxsize, maxpages, start); } EXPORT_SYMBOL(iov_iter_get_pages2); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start) { ssize_t len; *pages = NULL; len = __iov_iter_get_pages_alloc(i, pages, maxsize, ~0U, start); if (len <= 0) { kvfree(*pages); *pages = NULL; } return len; } EXPORT_SYMBOL(iov_iter_get_pages_alloc2); static int iov_npages(const struct iov_iter *i, int maxpages) { size_t skip = i->iov_offset, size = i->count; const struct iovec *p; int npages = 0; for (p = iter_iov(i); size; skip = 0, p++) { unsigned offs = offset_in_page(p->iov_base + skip); size_t len = min(p->iov_len - skip, size); if (len) { size -= len; npages += DIV_ROUND_UP(offs + len, PAGE_SIZE); if (unlikely(npages > maxpages)) return maxpages; } } return npages; } static int bvec_npages(const struct iov_iter *i, int maxpages) { size_t skip = i->iov_offset, size = i->count; const struct bio_vec *p; int npages = 0; for (p = i->bvec; size; skip = 0, p++) { unsigned offs = (p->bv_offset + skip) % PAGE_SIZE; size_t len = min(p->bv_len - skip, size); size -= len; npages += DIV_ROUND_UP(offs + len, PAGE_SIZE); if (unlikely(npages > maxpages)) return maxpages; } return npages; } int iov_iter_npages(const struct iov_iter *i, int maxpages) { if (unlikely(!i->count)) return 0; if (likely(iter_is_ubuf(i))) { unsigned offs = offset_in_page(i->ubuf + i->iov_offset); int npages = DIV_ROUND_UP(offs + i->count, PAGE_SIZE); return min(npages, maxpages); } /* iovec and kvec have identical layouts */ if (likely(iter_is_iovec(i) || iov_iter_is_kvec(i))) return iov_npages(i, maxpages); if (iov_iter_is_bvec(i)) return bvec_npages(i, maxpages); if (iov_iter_is_folioq(i)) { unsigned offset = i->iov_offset % PAGE_SIZE; int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); return min(npages, maxpages); } if (iov_iter_is_xarray(i)) { unsigned offset = (i->xarray_start + i->iov_offset) % PAGE_SIZE; int npages = DIV_ROUND_UP(offset + i->count, PAGE_SIZE); return min(npages, maxpages); } return 0; } EXPORT_SYMBOL(iov_iter_npages); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) { *new = *old; if (iov_iter_is_bvec(new)) return new->bvec = kmemdup(new->bvec, new->nr_segs * sizeof(struct bio_vec), flags); else if (iov_iter_is_kvec(new) || iter_is_iovec(new)) /* iovec and kvec have identical layout */ return new->__iov = kmemdup(new->__iov, new->nr_segs * sizeof(struct iovec), flags); return NULL; } EXPORT_SYMBOL(dup_iter); static __noclone int copy_compat_iovec_from_user(struct iovec *iov, const struct iovec __user *uvec, u32 nr_segs) { const struct compat_iovec __user *uiov = (const struct compat_iovec __user *)uvec; int ret = -EFAULT; u32 i; if (!user_access_begin(uiov, nr_segs * sizeof(*uiov))) return -EFAULT; for (i = 0; i < nr_segs; i++) { compat_uptr_t buf; compat_ssize_t len; unsafe_get_user(len, &uiov[i].iov_len, uaccess_end); unsafe_get_user(buf, &uiov[i].iov_base, uaccess_end); /* check for compat_size_t not fitting in compat_ssize_t .. */ if (len < 0) { ret = -EINVAL; goto uaccess_end; } iov[i].iov_base = compat_ptr(buf); iov[i].iov_len = len; } ret = 0; uaccess_end: user_access_end(); return ret; } static __noclone int copy_iovec_from_user(struct iovec *iov, const struct iovec __user *uiov, unsigned long nr_segs) { int ret = -EFAULT; if (!user_access_begin(uiov, nr_segs * sizeof(*uiov))) return -EFAULT; do { void __user *buf; ssize_t len; unsafe_get_user(len, &uiov->iov_len, uaccess_end); unsafe_get_user(buf, &uiov->iov_base, uaccess_end); /* check for size_t not fitting in ssize_t .. */ if (unlikely(len < 0)) { ret = -EINVAL; goto uaccess_end; } iov->iov_base = buf; iov->iov_len = len; uiov++; iov++; } while (--nr_segs); ret = 0; uaccess_end: user_access_end(); return ret; } struct iovec *iovec_from_user(const struct iovec __user *uvec, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_iov, bool compat) { struct iovec *iov = fast_iov; int ret; /* * SuS says "The readv() function *may* fail if the iovcnt argument was * less than or equal to 0, or greater than {IOV_MAX}. Linux has * traditionally returned zero for zero segments, so... */ if (nr_segs == 0) return iov; if (nr_segs > UIO_MAXIOV) return ERR_PTR(-EINVAL); if (nr_segs > fast_segs) { iov = kmalloc_array(nr_segs, sizeof(struct iovec), GFP_KERNEL); if (!iov) return ERR_PTR(-ENOMEM); } if (unlikely(compat)) ret = copy_compat_iovec_from_user(iov, uvec, nr_segs); else ret = copy_iovec_from_user(iov, uvec, nr_segs); if (ret) { if (iov != fast_iov) kfree(iov); return ERR_PTR(ret); } return iov; } /* * Single segment iovec supplied by the user, import it as ITER_UBUF. */ static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec, struct iovec **iovp, struct iov_iter *i, bool compat) { struct iovec *iov = *iovp; ssize_t ret; *iovp = NULL; if (compat) ret = copy_compat_iovec_from_user(iov, uvec, 1); else ret = copy_iovec_from_user(iov, uvec, 1); if (unlikely(ret)) return ret; ret = import_ubuf(type, iov->iov_base, iov->iov_len, i); if (unlikely(ret)) return ret; return i->count; } ssize_t __import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i, bool compat) { ssize_t total_len = 0; unsigned long seg; struct iovec *iov; if (nr_segs == 1) return __import_iovec_ubuf(type, uvec, iovp, i, compat); iov = iovec_from_user(uvec, nr_segs, fast_segs, *iovp, compat); if (IS_ERR(iov)) { *iovp = NULL; return PTR_ERR(iov); } /* * According to the Single Unix Specification we should return EINVAL if * an element length is < 0 when cast to ssize_t or if the total length * would overflow the ssize_t return value of the system call. * * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the * overflow case. */ for (seg = 0; seg < nr_segs; seg++) { ssize_t len = (ssize_t)iov[seg].iov_len; if (!access_ok(iov[seg].iov_base, len)) { if (iov != *iovp) kfree(iov); *iovp = NULL; return -EFAULT; } if (len > MAX_RW_COUNT - total_len) { len = MAX_RW_COUNT - total_len; iov[seg].iov_len = len; } total_len += len; } iov_iter_init(i, type, iov, nr_segs, total_len); if (iov == *iovp) *iovp = NULL; else *iovp = iov; return total_len; } /** * import_iovec() - Copy an array of &struct iovec from userspace * into the kernel, check that it is valid, and initialize a new * &struct iov_iter iterator to access it. * * @type: One of %READ or %WRITE. * @uvec: Pointer to the userspace array. * @nr_segs: Number of elements in userspace array. * @fast_segs: Number of elements in @iov. * @iovp: (input and output parameter) Pointer to pointer to (usually small * on-stack) kernel array. * @i: Pointer to iterator that will be initialized on success. * * If the array pointed to by *@iov is large enough to hold all @nr_segs, * then this function places %NULL in *@iov on return. Otherwise, a new * array will be allocated and the result placed in *@iov. This means that * the caller may call kfree() on *@iov regardless of whether the small * on-stack array was used or not (and regardless of whether this function * returns an error or not). * * Return: Negative error code on error, bytes imported on success */ ssize_t import_iovec(int type, const struct iovec __user *uvec, unsigned nr_segs, unsigned fast_segs, struct iovec **iovp, struct iov_iter *i) { return __import_iovec(type, uvec, nr_segs, fast_segs, iovp, i, in_compat_syscall()); } EXPORT_SYMBOL(import_iovec); int import_ubuf(int rw, void __user *buf, size_t len, struct iov_iter *i) { if (len > MAX_RW_COUNT) len = MAX_RW_COUNT; if (unlikely(!access_ok(buf, len))) return -EFAULT; iov_iter_ubuf(i, rw, buf, len); return 0; } EXPORT_SYMBOL_GPL(import_ubuf); /** * iov_iter_restore() - Restore a &struct iov_iter to the same state as when * iov_iter_save_state() was called. * * @i: &struct iov_iter to restore * @state: state to restore from * * Used after iov_iter_save_state() to bring restore @i, if operations may * have advanced it. * * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC */ void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) { if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i) && !iter_is_ubuf(i)) && !iov_iter_is_kvec(i)) return; i->iov_offset = state->iov_offset; i->count = state->count; if (iter_is_ubuf(i)) return; /* * For the *vec iters, nr_segs + iov is constant - if we increment * the vec, then we also decrement the nr_segs count. Hence we don't * need to track both of these, just one is enough and we can deduct * the other from that. ITER_KVEC and ITER_IOVEC are the same struct * size, so we can just increment the iov pointer as they are unionzed. * ITER_BVEC _may_ be the same size on some archs, but on others it is * not. Be safe and handle it separately. */ BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec)); if (iov_iter_is_bvec(i)) i->bvec -= state->nr_segs - i->nr_segs; else i->__iov -= state->nr_segs - i->nr_segs; i->nr_segs = state->nr_segs; } /* * Extract a list of contiguous pages from an ITER_FOLIOQ iterator. This does * not get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_folioq_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { const struct folio_queue *folioq = i->folioq; struct page **p; unsigned int nr = 0; size_t extracted = 0, offset, slot = i->folioq_slot; if (slot >= folioq_nr_slots(folioq)) { folioq = folioq->next; slot = 0; if (WARN_ON(i->iov_offset != 0)) return -EIO; } offset = i->iov_offset & ~PAGE_MASK; *offset0 = offset; maxpages = want_pages_array(pages, maxsize, offset, maxpages); if (!maxpages) return -ENOMEM; p = *pages; for (;;) { struct folio *folio = folioq_folio(folioq, slot); size_t offset = i->iov_offset, fsize = folioq_folio_size(folioq, slot); size_t part = PAGE_SIZE - offset % PAGE_SIZE; if (offset < fsize) { part = umin(part, umin(maxsize - extracted, fsize - offset)); i->count -= part; i->iov_offset += part; extracted += part; p[nr++] = folio_page(folio, offset / PAGE_SIZE); } if (nr >= maxpages || extracted >= maxsize) break; if (i->iov_offset >= fsize) { i->iov_offset = 0; slot++; if (slot == folioq_nr_slots(folioq) && folioq->next) { folioq = folioq->next; slot = 0; } } } i->folioq = folioq; i->folioq_slot = slot; return extracted; } /* * Extract a list of contiguous pages from an ITER_XARRAY iterator. This does not * get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_xarray_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { struct page **p; struct folio *folio; unsigned int nr = 0, offset; loff_t pos = i->xarray_start + i->iov_offset; XA_STATE(xas, i->xarray, pos >> PAGE_SHIFT); offset = pos & ~PAGE_MASK; *offset0 = offset; maxpages = want_pages_array(pages, maxsize, offset, maxpages); if (!maxpages) return -ENOMEM; p = *pages; rcu_read_lock(); for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; /* Has the folio moved or been split? */ if (unlikely(folio != xas_reload(&xas))) { xas_reset(&xas); continue; } p[nr++] = folio_file_page(folio, xas.xa_index); if (nr == maxpages) break; } rcu_read_unlock(); maxsize = min_t(size_t, nr * PAGE_SIZE - offset, maxsize); iov_iter_advance(i, maxsize); return maxsize; } /* * Extract a list of virtually contiguous pages from an ITER_BVEC iterator. * This does not get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_bvec_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { size_t skip = i->iov_offset, size = 0; struct bvec_iter bi; int k = 0; if (i->nr_segs == 0) return 0; if (i->iov_offset == i->bvec->bv_len) { i->iov_offset = 0; i->nr_segs--; i->bvec++; skip = 0; } bi.bi_idx = 0; bi.bi_size = maxsize; bi.bi_bvec_done = skip; maxpages = want_pages_array(pages, maxsize, skip, maxpages); while (bi.bi_size && bi.bi_idx < i->nr_segs) { struct bio_vec bv = bvec_iter_bvec(i->bvec, bi); /* * The iov_iter_extract_pages interface only allows an offset * into the first page. Break out of the loop if we see an * offset into subsequent pages, the caller will have to call * iov_iter_extract_pages again for the reminder. */ if (k) { if (bv.bv_offset) break; } else { *offset0 = bv.bv_offset; } (*pages)[k++] = bv.bv_page; size += bv.bv_len; if (k >= maxpages) break; /* * We are done when the end of the bvec doesn't align to a page * boundary as that would create a hole in the returned space. * The caller will handle this with another call to * iov_iter_extract_pages. */ if (bv.bv_offset + bv.bv_len != PAGE_SIZE) break; bvec_iter_advance_single(i->bvec, &bi, bv.bv_len); } iov_iter_advance(i, size); return size; } /* * Extract a list of virtually contiguous pages from an ITER_KVEC iterator. * This does not get references on the pages, nor does it get a pin on them. */ static ssize_t iov_iter_extract_kvec_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { struct page **p, *page; const void *kaddr; size_t skip = i->iov_offset, offset, len, size; int k; for (;;) { if (i->nr_segs == 0) return 0; size = min(maxsize, i->kvec->iov_len - skip); if (size) break; i->iov_offset = 0; i->nr_segs--; i->kvec++; skip = 0; } kaddr = i->kvec->iov_base + skip; offset = (unsigned long)kaddr & ~PAGE_MASK; *offset0 = offset; maxpages = want_pages_array(pages, size, offset, maxpages); if (!maxpages) return -ENOMEM; p = *pages; kaddr -= offset; len = offset + size; for (k = 0; k < maxpages; k++) { size_t seg = min_t(size_t, len, PAGE_SIZE); if (is_vmalloc_or_module_addr(kaddr)) page = vmalloc_to_page(kaddr); else page = virt_to_page(kaddr); p[k] = page; len -= seg; kaddr += PAGE_SIZE; } size = min_t(size_t, size, maxpages * PAGE_SIZE - offset); iov_iter_advance(i, size); return size; } /* * Extract a list of contiguous pages from a user iterator and get a pin on * each of them. This should only be used if the iterator is user-backed * (IOBUF/UBUF). * * It does not get refs on the pages, but the pages must be unpinned by the * caller once the transfer is complete. * * This is safe to be used where background IO/DMA *is* going to be modifying * the buffer; using a pin rather than a ref makes forces fork() to give the * child a copy of the page. */ static ssize_t iov_iter_extract_user_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { unsigned long addr; unsigned int gup_flags = 0; size_t offset; int res; if (i->data_source == ITER_DEST) gup_flags |= FOLL_WRITE; if (extraction_flags & ITER_ALLOW_P2PDMA) gup_flags |= FOLL_PCI_P2PDMA; if (i->nofault) gup_flags |= FOLL_NOFAULT; addr = first_iovec_segment(i, &maxsize); *offset0 = offset = addr % PAGE_SIZE; addr &= PAGE_MASK; maxpages = want_pages_array(pages, maxsize, offset, maxpages); if (!maxpages) return -ENOMEM; res = pin_user_pages_fast(addr, maxpages, gup_flags, *pages); if (unlikely(res <= 0)) return res; maxsize = min_t(size_t, maxsize, res * PAGE_SIZE - offset); iov_iter_advance(i, maxsize); return maxsize; } /** * iov_iter_extract_pages - Extract a list of contiguous pages from an iterator * @i: The iterator to extract from * @pages: Where to return the list of pages * @maxsize: The maximum amount of iterator to extract * @maxpages: The maximum size of the list of pages * @extraction_flags: Flags to qualify request * @offset0: Where to return the starting offset into (*@pages)[0] * * Extract a list of contiguous pages from the current point of the iterator, * advancing the iterator. The maximum number of pages and the maximum amount * of page contents can be set. * * If *@pages is NULL, a page list will be allocated to the required size and * *@pages will be set to its base. If *@pages is not NULL, it will be assumed * that the caller allocated a page list at least @maxpages in size and this * will be filled in. * * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA * be allowed on the pages extracted. * * The iov_iter_extract_will_pin() function can be used to query how cleanup * should be performed. * * Extra refs or pins on the pages may be obtained as follows: * * (*) If the iterator is user-backed (ITER_IOVEC/ITER_UBUF), pins will be * added to the pages, but refs will not be taken. * iov_iter_extract_will_pin() will return true. * * (*) If the iterator is ITER_KVEC, ITER_BVEC, ITER_FOLIOQ or ITER_XARRAY, the * pages are merely listed; no extra refs or pins are obtained. * iov_iter_extract_will_pin() will return 0. * * Note also: * * (*) Use with ITER_DISCARD is not supported as that has no content. * * On success, the function sets *@pages to the new pagelist, if allocated, and * sets *offset0 to the offset into the first page. * * It may also return -ENOMEM and -EFAULT. */ ssize_t iov_iter_extract_pages(struct iov_iter *i, struct page ***pages, size_t maxsize, unsigned int maxpages, iov_iter_extraction_t extraction_flags, size_t *offset0) { maxsize = min_t(size_t, min_t(size_t, maxsize, i->count), MAX_RW_COUNT); if (!maxsize) return 0; if (likely(user_backed_iter(i))) return iov_iter_extract_user_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); if (iov_iter_is_kvec(i)) return iov_iter_extract_kvec_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); if (iov_iter_is_bvec(i)) return iov_iter_extract_bvec_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); if (iov_iter_is_folioq(i)) return iov_iter_extract_folioq_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); if (iov_iter_is_xarray(i)) return iov_iter_extract_xarray_pages(i, pages, maxsize, maxpages, extraction_flags, offset0); return -EFAULT; } EXPORT_SYMBOL_GPL(iov_iter_extract_pages); |
| 14 14 14 14 14 14 14 19 19 19 14 14 19 19 83 38 37 1 38 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 | // 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_rwsem 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 && dfd >= 0) { 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 && dfd >= 0) { 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); } static bool xattr_is_maclabel(const char *name) { const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; return !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) && security_ismaclabel(suffix); } /** * 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; err = security_inode_listsecurity(inode, buffer, remaining_size); if (err < 0) return err; if (buffer) { if (remaining_size < err) return -ERANGE; buffer += err; } remaining_size -= err; err = 0; 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; /* skip MAC labels; these are provided by LSM above */ if (xattr_is_maclabel(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; } } |
| 459 538 348 349 206 206 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/lockref.h> #if USE_CMPXCHG_LOCKREF /* * Note that the "cmpxchg()" reloads the "old" value for the * failure case. */ #define CMPXCHG_LOOP(CODE, SUCCESS) do { \ int retry = 100; \ struct lockref old; \ BUILD_BUG_ON(sizeof(old) != 8); \ old.lock_count = READ_ONCE(lockref->lock_count); \ while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ struct lockref new = old; \ CODE \ if (likely(try_cmpxchg64_relaxed(&lockref->lock_count, \ &old.lock_count, \ new.lock_count))) { \ SUCCESS; \ } \ if (!--retry) \ break; \ } \ } while (0) #else #define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0) #endif /** * lockref_get - Increments reference count unconditionally * @lockref: pointer to lockref structure * * This operation is only valid if you already hold a reference * to the object, so you know the count cannot be zero. */ void lockref_get(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; , return; ); spin_lock(&lockref->lock); lockref->count++; spin_unlock(&lockref->lock); } EXPORT_SYMBOL(lockref_get); /** * lockref_get_not_zero - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero */ bool lockref_get_not_zero(struct lockref *lockref) { bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count <= 0) return false; , return true; ); spin_lock(&lockref->lock); if (lockref->count > 0) { lockref->count++; retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_zero); /** * lockref_put_return - Decrement reference count if possible * @lockref: pointer to lockref structure * * Decrement the reference count and return the new value. * If the lockref was dead or locked, return -1. */ int lockref_put_return(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 0) return -1; , return new.count; ); return -1; } EXPORT_SYMBOL(lockref_put_return); /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken */ bool lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , return true; ); spin_lock(&lockref->lock); if (lockref->count <= 1) return false; lockref->count--; spin_unlock(&lockref->lock); return true; } EXPORT_SYMBOL(lockref_put_or_lock); /** * lockref_mark_dead - mark lockref dead * @lockref: pointer to lockref structure */ void lockref_mark_dead(struct lockref *lockref) { assert_spin_locked(&lockref->lock); lockref->count = -128; } EXPORT_SYMBOL(lockref_mark_dead); /** * lockref_get_not_dead - Increments count unless the ref is dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if lockref was dead */ bool lockref_get_not_dead(struct lockref *lockref) { bool retval = false; CMPXCHG_LOOP( new.count++; if (old.count < 0) return false; , return true; ); spin_lock(&lockref->lock); if (lockref->count >= 0) { lockref->count++; retval = true; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_dead); |
| 1430 15 1418 1459 28 28 1450 1459 1449 201 201 1 202 1451 1454 201 1427 1451 1451 1450 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/util.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include <linux/slab.h> #include <linux/rculist.h> #include "common.h" /* Lock for protecting policy. */ DEFINE_MUTEX(tomoyo_policy_lock); /* Has /sbin/init started? */ bool tomoyo_policy_loaded; /* * Mapping table from "enum tomoyo_mac_index" to * "enum tomoyo_mac_category_index". */ const u8 tomoyo_index2category[TOMOYO_MAX_MAC_INDEX] = { /* CONFIG::file group */ [TOMOYO_MAC_FILE_EXECUTE] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_OPEN] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CREATE] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_UNLINK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_GETATTR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKDIR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_RMDIR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKFIFO] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKSOCK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_TRUNCATE] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_SYMLINK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKBLOCK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MKCHAR] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_LINK] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_RENAME] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHMOD] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHOWN] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHGRP] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_IOCTL] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_CHROOT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_MOUNT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_UMOUNT] = TOMOYO_MAC_CATEGORY_FILE, [TOMOYO_MAC_FILE_PIVOT_ROOT] = TOMOYO_MAC_CATEGORY_FILE, /* CONFIG::network group */ [TOMOYO_MAC_NETWORK_INET_STREAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_STREAM_LISTEN] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_STREAM_CONNECT] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_DGRAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_DGRAM_SEND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_RAW_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_INET_RAW_SEND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_STREAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_STREAM_LISTEN] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_STREAM_CONNECT] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_DGRAM_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_DGRAM_SEND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_BIND] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_LISTEN] = TOMOYO_MAC_CATEGORY_NETWORK, [TOMOYO_MAC_NETWORK_UNIX_SEQPACKET_CONNECT] = TOMOYO_MAC_CATEGORY_NETWORK, /* CONFIG::misc group */ [TOMOYO_MAC_ENVIRON] = TOMOYO_MAC_CATEGORY_MISC, }; /** * tomoyo_convert_time - Convert time_t to YYYY/MM/DD hh/mm/ss. * * @time64: Seconds since 1970/01/01 00:00:00. * @stamp: Pointer to "struct tomoyo_time". * * Returns nothing. */ void tomoyo_convert_time(time64_t time64, struct tomoyo_time *stamp) { struct tm tm; time64_to_tm(time64, 0, &tm); stamp->sec = tm.tm_sec; stamp->min = tm.tm_min; stamp->hour = tm.tm_hour; stamp->day = tm.tm_mday; stamp->month = tm.tm_mon + 1; stamp->year = tm.tm_year + 1900; } /** * tomoyo_permstr - Find permission keywords. * * @string: String representation for permissions in foo/bar/buz format. * @keyword: Keyword to find from @string/ * * Returns true if @keyword was found in @string, false otherwise. * * This function assumes that strncmp(w1, w2, strlen(w1)) != 0 if w1 != w2. */ bool tomoyo_permstr(const char *string, const char *keyword) { const char *cp = strstr(string, keyword); if (cp) return cp == string || *(cp - 1) == '/'; return false; } /** * tomoyo_read_token - Read a word from a line. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns a word on success, "" otherwise. * * To allow the caller to skip NULL check, this function returns "" rather than * NULL if there is no more words to read. */ char *tomoyo_read_token(struct tomoyo_acl_param *param) { char *pos = param->data; char *del = strchr(pos, ' '); if (del) *del++ = '\0'; else del = pos + strlen(pos); param->data = del; return pos; } static bool tomoyo_correct_path2(const char *filename, const size_t len); /** * tomoyo_get_domainname - Read a domainname from a line. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns a domainname on success, NULL otherwise. */ const struct tomoyo_path_info *tomoyo_get_domainname (struct tomoyo_acl_param *param) { char *start = param->data; char *pos = start; while (*pos) { if (*pos++ != ' ' || tomoyo_correct_path2(pos, strchrnul(pos, ' ') - pos)) continue; *(pos - 1) = '\0'; break; } param->data = pos; if (tomoyo_correct_domain(start)) return tomoyo_get_name(start); return NULL; } /** * tomoyo_parse_ulong - Parse an "unsigned long" value. * * @result: Pointer to "unsigned long". * @str: Pointer to string to parse. * * Returns one of values in "enum tomoyo_value_type". * * The @src is updated to point the first character after the value * on success. */ u8 tomoyo_parse_ulong(unsigned long *result, char **str) { const char *cp = *str; char *ep; int base = 10; if (*cp == '0') { char c = *(cp + 1); if (c == 'x' || c == 'X') { base = 16; cp += 2; } else if (c >= '0' && c <= '7') { base = 8; cp++; } } *result = simple_strtoul(cp, &ep, base); if (cp == ep) return TOMOYO_VALUE_TYPE_INVALID; *str = ep; switch (base) { case 16: return TOMOYO_VALUE_TYPE_HEXADECIMAL; case 8: return TOMOYO_VALUE_TYPE_OCTAL; default: return TOMOYO_VALUE_TYPE_DECIMAL; } } /** * tomoyo_print_ulong - Print an "unsigned long" value. * * @buffer: Pointer to buffer. * @buffer_len: Size of @buffer. * @value: An "unsigned long" value. * @type: Type of @value. * * Returns nothing. */ void tomoyo_print_ulong(char *buffer, const int buffer_len, const unsigned long value, const u8 type) { if (type == TOMOYO_VALUE_TYPE_DECIMAL) snprintf(buffer, buffer_len, "%lu", value); else if (type == TOMOYO_VALUE_TYPE_OCTAL) snprintf(buffer, buffer_len, "0%lo", value); else if (type == TOMOYO_VALUE_TYPE_HEXADECIMAL) snprintf(buffer, buffer_len, "0x%lX", value); else snprintf(buffer, buffer_len, "type(%u)", type); } /** * tomoyo_parse_name_union - Parse a tomoyo_name_union. * * @param: Pointer to "struct tomoyo_acl_param". * @ptr: Pointer to "struct tomoyo_name_union". * * Returns true on success, false otherwise. */ bool tomoyo_parse_name_union(struct tomoyo_acl_param *param, struct tomoyo_name_union *ptr) { char *filename; if (param->data[0] == '@') { param->data++; ptr->group = tomoyo_get_group(param, TOMOYO_PATH_GROUP); return ptr->group != NULL; } filename = tomoyo_read_token(param); if (!tomoyo_correct_word(filename)) return false; ptr->filename = tomoyo_get_name(filename); return ptr->filename != NULL; } /** * tomoyo_parse_number_union - Parse a tomoyo_number_union. * * @param: Pointer to "struct tomoyo_acl_param". * @ptr: Pointer to "struct tomoyo_number_union". * * Returns true on success, false otherwise. */ bool tomoyo_parse_number_union(struct tomoyo_acl_param *param, struct tomoyo_number_union *ptr) { char *data; u8 type; unsigned long v; memset(ptr, 0, sizeof(*ptr)); if (param->data[0] == '@') { param->data++; ptr->group = tomoyo_get_group(param, TOMOYO_NUMBER_GROUP); return ptr->group != NULL; } data = tomoyo_read_token(param); type = tomoyo_parse_ulong(&v, &data); if (type == TOMOYO_VALUE_TYPE_INVALID) return false; ptr->values[0] = v; ptr->value_type[0] = type; if (!*data) { ptr->values[1] = v; ptr->value_type[1] = type; return true; } if (*data++ != '-') return false; type = tomoyo_parse_ulong(&v, &data); if (type == TOMOYO_VALUE_TYPE_INVALID || *data || ptr->values[0] > v) return false; ptr->values[1] = v; ptr->value_type[1] = type; return true; } /** * tomoyo_byte_range - Check whether the string is a \ooo style octal value. * * @str: Pointer to the string. * * Returns true if @str is a \ooo style octal value, false otherwise. * * TOMOYO uses \ooo style representation for 0x01 - 0x20 and 0x7F - 0xFF. * This function verifies that \ooo is in valid range. */ static inline bool tomoyo_byte_range(const char *str) { return *str >= '0' && *str++ <= '3' && *str >= '0' && *str++ <= '7' && *str >= '0' && *str <= '7'; } /** * tomoyo_alphabet_char - Check whether the character is an alphabet. * * @c: The character to check. * * Returns true if @c is an alphabet character, false otherwise. */ static inline bool tomoyo_alphabet_char(const char c) { return (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z'); } /** * tomoyo_make_byte - Make byte value from three octal characters. * * @c1: The first character. * @c2: The second character. * @c3: The third character. * * Returns byte value. */ static inline u8 tomoyo_make_byte(const u8 c1, const u8 c2, const u8 c3) { return ((c1 - '0') << 6) + ((c2 - '0') << 3) + (c3 - '0'); } /** * tomoyo_valid - Check whether the character is a valid char. * * @c: The character to check. * * Returns true if @c is a valid character, false otherwise. */ static inline bool tomoyo_valid(const unsigned char c) { return c > ' ' && c < 127; } /** * tomoyo_invalid - Check whether the character is an invalid char. * * @c: The character to check. * * Returns true if @c is an invalid character, false otherwise. */ static inline bool tomoyo_invalid(const unsigned char c) { return c && (c <= ' ' || c >= 127); } /** * tomoyo_str_starts - Check whether the given string starts with the given keyword. * * @src: Pointer to pointer to the string. * @find: Pointer to the keyword. * * Returns true if @src starts with @find, false otherwise. * * The @src is updated to point the first character after the @find * if @src starts with @find. */ bool tomoyo_str_starts(char **src, const char *find) { const int len = strlen(find); char *tmp = *src; if (strncmp(tmp, find, len)) return false; tmp += len; *src = tmp; return true; } /** * tomoyo_normalize_line - Format string. * * @buffer: The line to normalize. * * Leading and trailing whitespaces are removed. * Multiple whitespaces are packed into single space. * * Returns nothing. */ void tomoyo_normalize_line(unsigned char *buffer) { unsigned char *sp = buffer; unsigned char *dp = buffer; bool first = true; while (tomoyo_invalid(*sp)) sp++; while (*sp) { if (!first) *dp++ = ' '; first = false; while (tomoyo_valid(*sp)) *dp++ = *sp++; while (tomoyo_invalid(*sp)) sp++; } *dp = '\0'; } /** * tomoyo_correct_word2 - Validate a string. * * @string: The string to check. Maybe non-'\0'-terminated. * @len: Length of @string. * * Check whether the given string follows the naming rules. * Returns true if @string follows the naming rules, false otherwise. */ static bool tomoyo_correct_word2(const char *string, size_t len) { u8 recursion = 20; const char *const start = string; bool in_repetition = false; if (!len) goto out; while (len--) { unsigned char c = *string++; if (c == '\\') { if (!len--) goto out; c = *string++; if (c >= '0' && c <= '3') { unsigned char d; unsigned char e; if (!len-- || !len--) goto out; d = *string++; e = *string++; if (d < '0' || d > '7' || e < '0' || e > '7') goto out; c = tomoyo_make_byte(c, d, e); if (c <= ' ' || c >= 127) continue; goto out; } switch (c) { case '\\': /* "\\" */ case '+': /* "\+" */ case '?': /* "\?" */ case 'x': /* "\x" */ case 'a': /* "\a" */ case '-': /* "\-" */ continue; } if (!recursion--) goto out; switch (c) { case '*': /* "\*" */ case '@': /* "\@" */ case '$': /* "\$" */ case 'X': /* "\X" */ case 'A': /* "\A" */ continue; case '{': /* "/\{" */ if (string - 3 < start || *(string - 3) != '/') goto out; in_repetition = true; continue; case '}': /* "\}/" */ if (*string != '/') goto out; if (!in_repetition) goto out; in_repetition = false; continue; } goto out; } else if (in_repetition && c == '/') { goto out; } else if (c <= ' ' || c >= 127) { goto out; } } if (in_repetition) goto out; return true; out: return false; } /** * tomoyo_correct_word - Validate a string. * * @string: The string to check. * * Check whether the given string follows the naming rules. * Returns true if @string follows the naming rules, false otherwise. */ bool tomoyo_correct_word(const char *string) { return tomoyo_correct_word2(string, strlen(string)); } /** * tomoyo_correct_path2 - Check whether the given pathname follows the naming rules. * * @filename: The pathname to check. * @len: Length of @filename. * * Returns true if @filename follows the naming rules, false otherwise. */ static bool tomoyo_correct_path2(const char *filename, const size_t len) { const char *cp1 = memchr(filename, '/', len); const char *cp2 = memchr(filename, '.', len); return cp1 && (!cp2 || (cp1 < cp2)) && tomoyo_correct_word2(filename, len); } /** * tomoyo_correct_path - Validate a pathname. * * @filename: The pathname to check. * * Check whether the given pathname follows the naming rules. * Returns true if @filename follows the naming rules, false otherwise. */ bool tomoyo_correct_path(const char *filename) { return tomoyo_correct_path2(filename, strlen(filename)); } /** * tomoyo_correct_domain - Check whether the given domainname follows the naming rules. * * @domainname: The domainname to check. * * Returns true if @domainname follows the naming rules, false otherwise. */ bool tomoyo_correct_domain(const unsigned char *domainname) { if (!domainname || !tomoyo_domain_def(domainname)) return false; domainname = strchr(domainname, ' '); if (!domainname++) return true; while (1) { const unsigned char *cp = strchr(domainname, ' '); if (!cp) break; if (!tomoyo_correct_path2(domainname, cp - domainname)) return false; domainname = cp + 1; } return tomoyo_correct_path(domainname); } /** * tomoyo_domain_def - Check whether the given token can be a domainname. * * @buffer: The token to check. * * Returns true if @buffer possibly be a domainname, false otherwise. */ bool tomoyo_domain_def(const unsigned char *buffer) { const unsigned char *cp; int len; if (*buffer != '<') return false; cp = strchr(buffer, ' '); if (!cp) len = strlen(buffer); else len = cp - buffer; if (buffer[len - 1] != '>' || !tomoyo_correct_word2(buffer + 1, len - 2)) return false; return true; } /** * tomoyo_find_domain - Find a domain by the given name. * * @domainname: The domainname to find. * * Returns pointer to "struct tomoyo_domain_info" if found, NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_domain_info *tomoyo_find_domain(const char *domainname) { struct tomoyo_domain_info *domain; struct tomoyo_path_info name; name.name = domainname; tomoyo_fill_path_info(&name); list_for_each_entry_rcu(domain, &tomoyo_domain_list, list, srcu_read_lock_held(&tomoyo_ss)) { if (!domain->is_deleted && !tomoyo_pathcmp(&name, domain->domainname)) return domain; } return NULL; } /** * tomoyo_const_part_length - Evaluate the initial length without a pattern in a token. * * @filename: The string to evaluate. * * Returns the initial length without a pattern in @filename. */ static int tomoyo_const_part_length(const char *filename) { char c; int len = 0; if (!filename) return 0; while ((c = *filename++) != '\0') { if (c != '\\') { len++; continue; } c = *filename++; switch (c) { case '\\': /* "\\" */ len += 2; continue; case '0': /* "\ooo" */ case '1': case '2': case '3': c = *filename++; if (c < '0' || c > '7') break; c = *filename++; if (c < '0' || c > '7') break; len += 4; continue; } break; } return len; } /** * tomoyo_fill_path_info - Fill in "struct tomoyo_path_info" members. * * @ptr: Pointer to "struct tomoyo_path_info" to fill in. * * The caller sets "struct tomoyo_path_info"->name. */ void tomoyo_fill_path_info(struct tomoyo_path_info *ptr) { const char *name = ptr->name; const int len = strlen(name); ptr->const_len = tomoyo_const_part_length(name); ptr->is_dir = len && (name[len - 1] == '/'); ptr->is_patterned = (ptr->const_len < len); ptr->hash = full_name_hash(NULL, name, len); } /** * tomoyo_file_matches_pattern2 - Pattern matching without '/' character and "\-" pattern. * * @filename: The start of string to check. * @filename_end: The end of string to check. * @pattern: The start of pattern to compare. * @pattern_end: The end of pattern to compare. * * Returns true if @filename matches @pattern, false otherwise. */ static bool tomoyo_file_matches_pattern2(const char *filename, const char *filename_end, const char *pattern, const char *pattern_end) { while (filename < filename_end && pattern < pattern_end) { char c; int i; int j; if (*pattern != '\\') { if (*filename++ != *pattern++) return false; continue; } c = *filename; pattern++; switch (*pattern) { case '?': if (c == '/') { return false; } else if (c == '\\') { if (filename[1] == '\\') filename++; else if (tomoyo_byte_range(filename + 1)) filename += 3; else return false; } break; case '\\': if (c != '\\') return false; if (*++filename != '\\') return false; break; case '+': if (!isdigit(c)) return false; break; case 'x': if (!isxdigit(c)) return false; break; case 'a': if (!tomoyo_alphabet_char(c)) return false; break; case '0': case '1': case '2': case '3': if (c == '\\' && tomoyo_byte_range(filename + 1) && strncmp(filename + 1, pattern, 3) == 0) { filename += 3; pattern += 2; break; } return false; /* Not matched. */ case '*': case '@': for (i = 0; i <= filename_end - filename; i++) { if (tomoyo_file_matches_pattern2( filename + i, filename_end, pattern + 1, pattern_end)) return true; c = filename[i]; if (c == '.' && *pattern == '@') break; if (c != '\\') continue; if (filename[i + 1] == '\\') i++; else if (tomoyo_byte_range(filename + i + 1)) i += 3; else break; /* Bad pattern. */ } return false; /* Not matched. */ default: j = 0; c = *pattern; if (c == '$') { while (isdigit(filename[j])) j++; } else if (c == 'X') { while (isxdigit(filename[j])) j++; } else if (c == 'A') { while (tomoyo_alphabet_char(filename[j])) j++; } for (i = 1; i <= j; i++) { if (tomoyo_file_matches_pattern2( filename + i, filename_end, pattern + 1, pattern_end)) return true; } return false; /* Not matched or bad pattern. */ } filename++; pattern++; } while (*pattern == '\\' && (*(pattern + 1) == '*' || *(pattern + 1) == '@')) pattern += 2; return filename == filename_end && pattern == pattern_end; } /** * tomoyo_file_matches_pattern - Pattern matching without '/' character. * * @filename: The start of string to check. * @filename_end: The end of string to check. * @pattern: The start of pattern to compare. * @pattern_end: The end of pattern to compare. * * Returns true if @filename matches @pattern, false otherwise. */ static bool tomoyo_file_matches_pattern(const char *filename, const char *filename_end, const char *pattern, const char *pattern_end) { const char *pattern_start = pattern; bool first = true; bool result; while (pattern < pattern_end - 1) { /* Split at "\-" pattern. */ if (*pattern++ != '\\' || *pattern++ != '-') continue; result = tomoyo_file_matches_pattern2(filename, filename_end, pattern_start, pattern - 2); if (first) result = !result; if (result) return false; first = false; pattern_start = pattern; } result = tomoyo_file_matches_pattern2(filename, filename_end, pattern_start, pattern_end); return first ? result : !result; } /** * tomoyo_path_matches_pattern2 - Do pathname pattern matching. * * @f: The start of string to check. * @p: The start of pattern to compare. * * Returns true if @f matches @p, false otherwise. */ static bool tomoyo_path_matches_pattern2(const char *f, const char *p) { const char *f_delimiter; const char *p_delimiter; while (*f && *p) { f_delimiter = strchr(f, '/'); if (!f_delimiter) f_delimiter = f + strlen(f); p_delimiter = strchr(p, '/'); if (!p_delimiter) p_delimiter = p + strlen(p); if (*p == '\\' && *(p + 1) == '{') goto recursive; if (!tomoyo_file_matches_pattern(f, f_delimiter, p, p_delimiter)) return false; f = f_delimiter; if (*f) f++; p = p_delimiter; if (*p) p++; } /* Ignore trailing "\*" and "\@" in @pattern. */ while (*p == '\\' && (*(p + 1) == '*' || *(p + 1) == '@')) p += 2; return !*f && !*p; recursive: /* * The "\{" pattern is permitted only after '/' character. * This guarantees that below "*(p - 1)" is safe. * Also, the "\}" pattern is permitted only before '/' character * so that "\{" + "\}" pair will not break the "\-" operator. */ if (*(p - 1) != '/' || p_delimiter <= p + 3 || *p_delimiter != '/' || *(p_delimiter - 1) != '}' || *(p_delimiter - 2) != '\\') return false; /* Bad pattern. */ do { /* Compare current component with pattern. */ if (!tomoyo_file_matches_pattern(f, f_delimiter, p + 2, p_delimiter - 2)) break; /* Proceed to next component. */ f = f_delimiter; if (!*f) break; f++; /* Continue comparison. */ if (tomoyo_path_matches_pattern2(f, p_delimiter + 1)) return true; f_delimiter = strchr(f, '/'); } while (f_delimiter); return false; /* Not matched. */ } /** * tomoyo_path_matches_pattern - Check whether the given filename matches the given pattern. * * @filename: The filename to check. * @pattern: The pattern to compare. * * Returns true if matches, false otherwise. * * The following patterns are available. * \\ \ itself. * \ooo Octal representation of a byte. * \* Zero or more repetitions of characters other than '/'. * \@ Zero or more repetitions of characters other than '/' or '.'. * \? 1 byte character other than '/'. * \$ One or more repetitions of decimal digits. * \+ 1 decimal digit. * \X One or more repetitions of hexadecimal digits. * \x 1 hexadecimal digit. * \A One or more repetitions of alphabet characters. * \a 1 alphabet character. * * \- Subtraction operator. * * /\{dir\}/ '/' + 'One or more repetitions of dir/' (e.g. /dir/ /dir/dir/ * /dir/dir/dir/ ). */ bool tomoyo_path_matches_pattern(const struct tomoyo_path_info *filename, const struct tomoyo_path_info *pattern) { const char *f = filename->name; const char *p = pattern->name; const int len = pattern->const_len; /* If @pattern doesn't contain pattern, I can use strcmp(). */ if (!pattern->is_patterned) return !tomoyo_pathcmp(filename, pattern); /* Don't compare directory and non-directory. */ if (filename->is_dir != pattern->is_dir) return false; /* Compare the initial length without patterns. */ if (strncmp(f, p, len)) return false; f += len; p += len; return tomoyo_path_matches_pattern2(f, p); } /** * tomoyo_get_exe - Get tomoyo_realpath() of current process. * * Returns the tomoyo_realpath() of current process on success, NULL otherwise. * * This function uses kzalloc(), so the caller must call kfree() * if this function didn't return NULL. */ const char *tomoyo_get_exe(void) { struct file *exe_file; const char *cp; struct mm_struct *mm = current->mm; if (!mm) return NULL; exe_file = get_mm_exe_file(mm); if (!exe_file) return NULL; cp = tomoyo_realpath_from_path(&exe_file->f_path); fput(exe_file); return cp; } /** * tomoyo_get_mode - Get MAC mode. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number. * @index: Index number of functionality. * * Returns mode. */ int tomoyo_get_mode(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index) { u8 mode; struct tomoyo_profile *p; if (!tomoyo_policy_loaded) return TOMOYO_CONFIG_DISABLED; p = tomoyo_profile(ns, profile); mode = p->config[index]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->config[tomoyo_index2category[index] + TOMOYO_MAX_MAC_INDEX]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->default_config; return mode & 3; } /** * tomoyo_init_request_info - Initialize "struct tomoyo_request_info" members. * * @r: Pointer to "struct tomoyo_request_info" to initialize. * @domain: Pointer to "struct tomoyo_domain_info". NULL for tomoyo_domain(). * @index: Index number of functionality. * * Returns mode. */ int tomoyo_init_request_info(struct tomoyo_request_info *r, struct tomoyo_domain_info *domain, const u8 index) { u8 profile; memset(r, 0, sizeof(*r)); if (!domain) domain = tomoyo_domain(); r->domain = domain; profile = domain->profile; r->profile = profile; r->type = index; r->mode = tomoyo_get_mode(domain->ns, profile, index); return r->mode; } /** * tomoyo_domain_quota_is_ok - Check for domain's quota. * * @r: Pointer to "struct tomoyo_request_info". * * Returns true if the domain is not exceeded quota, false otherwise. * * Caller holds tomoyo_read_lock(). */ bool tomoyo_domain_quota_is_ok(struct tomoyo_request_info *r) { unsigned int count = 0; struct tomoyo_domain_info *domain = r->domain; struct tomoyo_acl_info *ptr; if (r->mode != TOMOYO_CONFIG_LEARNING) return false; if (!domain) return true; if (READ_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED])) return false; list_for_each_entry_rcu(ptr, &domain->acl_info_list, list, srcu_read_lock_held(&tomoyo_ss)) { u16 perm; if (ptr->is_deleted) continue; /* * Reading perm bitmap might race with tomoyo_merge_*() because * caller does not hold tomoyo_policy_lock mutex. But exceeding * max_learning_entry parameter by a few entries does not harm. */ switch (ptr->type) { case TOMOYO_TYPE_PATH_ACL: perm = data_race(container_of(ptr, struct tomoyo_path_acl, head)->perm); break; case TOMOYO_TYPE_PATH2_ACL: perm = data_race(container_of(ptr, struct tomoyo_path2_acl, head)->perm); break; case TOMOYO_TYPE_PATH_NUMBER_ACL: perm = data_race(container_of(ptr, struct tomoyo_path_number_acl, head) ->perm); break; case TOMOYO_TYPE_MKDEV_ACL: perm = data_race(container_of(ptr, struct tomoyo_mkdev_acl, head)->perm); break; case TOMOYO_TYPE_INET_ACL: perm = data_race(container_of(ptr, struct tomoyo_inet_acl, head)->perm); break; case TOMOYO_TYPE_UNIX_ACL: perm = data_race(container_of(ptr, struct tomoyo_unix_acl, head)->perm); break; case TOMOYO_TYPE_MANUAL_TASK_ACL: perm = 0; break; default: perm = 1; } count += hweight16(perm); } if (count < tomoyo_profile(domain->ns, domain->profile)-> pref[TOMOYO_PREF_MAX_LEARNING_ENTRY]) return true; WRITE_ONCE(domain->flags[TOMOYO_DIF_QUOTA_WARNED], true); /* r->granted = false; */ tomoyo_write_log(r, "%s", tomoyo_dif[TOMOYO_DIF_QUOTA_WARNED]); #ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING pr_warn("WARNING: Domain '%s' has too many ACLs to hold. Stopped learning mode.\n", domain->domainname->name); #endif return false; } |
| 1 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * VGIC system registers handling functions for AArch64 mode */ #include <linux/irqchip/arm-gic-v3.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include "vgic/vgic.h" #include "sys_regs.h" static int set_gic_ctlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { u32 host_pri_bits, host_id_bits, host_seis, host_a3v, seis, a3v; struct vgic_cpu *vgic_v3_cpu = &vcpu->arch.vgic_cpu; struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); /* * Disallow restoring VM state if not supported by this * hardware. */ host_pri_bits = FIELD_GET(ICC_CTLR_EL1_PRI_BITS_MASK, val) + 1; if (host_pri_bits > vgic_v3_cpu->num_pri_bits) return -EINVAL; vgic_v3_cpu->num_pri_bits = host_pri_bits; host_id_bits = FIELD_GET(ICC_CTLR_EL1_ID_BITS_MASK, val); if (host_id_bits > vgic_v3_cpu->num_id_bits) return -EINVAL; vgic_v3_cpu->num_id_bits = host_id_bits; host_seis = FIELD_GET(ICH_VTR_EL2_SEIS, kvm_vgic_global_state.ich_vtr_el2); seis = FIELD_GET(ICC_CTLR_EL1_SEIS_MASK, val); if (host_seis != seis) return -EINVAL; host_a3v = FIELD_GET(ICH_VTR_EL2_A3V, kvm_vgic_global_state.ich_vtr_el2); a3v = FIELD_GET(ICC_CTLR_EL1_A3V_MASK, val); if (host_a3v != a3v) return -EINVAL; /* * Here set VMCR.CTLR in ICC_CTLR_EL1 layout. * The vgic_set_vmcr() will convert to ICH_VMCR layout. */ vmcr.cbpr = FIELD_GET(ICC_CTLR_EL1_CBPR_MASK, val); vmcr.eoim = FIELD_GET(ICC_CTLR_EL1_EOImode_MASK, val); vgic_set_vmcr(vcpu, &vmcr); return 0; } static int get_gic_ctlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *valp) { struct vgic_cpu *vgic_v3_cpu = &vcpu->arch.vgic_cpu; struct vgic_vmcr vmcr; u64 val; vgic_get_vmcr(vcpu, &vmcr); val = 0; val |= FIELD_PREP(ICC_CTLR_EL1_PRI_BITS_MASK, vgic_v3_cpu->num_pri_bits - 1); val |= FIELD_PREP(ICC_CTLR_EL1_ID_BITS_MASK, vgic_v3_cpu->num_id_bits); val |= FIELD_PREP(ICC_CTLR_EL1_SEIS_MASK, FIELD_GET(ICH_VTR_EL2_SEIS, kvm_vgic_global_state.ich_vtr_el2)); val |= FIELD_PREP(ICC_CTLR_EL1_A3V_MASK, FIELD_GET(ICH_VTR_EL2_A3V, kvm_vgic_global_state.ich_vtr_el2)); /* * The VMCR.CTLR value is in ICC_CTLR_EL1 layout. * Extract it directly using ICC_CTLR_EL1 reg definitions. */ val |= FIELD_PREP(ICC_CTLR_EL1_CBPR_MASK, vmcr.cbpr); val |= FIELD_PREP(ICC_CTLR_EL1_EOImode_MASK, vmcr.eoim); *valp = val; return 0; } static int set_gic_pmr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); vmcr.pmr = FIELD_GET(ICC_PMR_EL1_MASK, val); vgic_set_vmcr(vcpu, &vmcr); return 0; } static int get_gic_pmr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); *val = FIELD_PREP(ICC_PMR_EL1_MASK, vmcr.pmr); return 0; } static int set_gic_bpr0(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); vmcr.bpr = FIELD_GET(ICC_BPR0_EL1_MASK, val); vgic_set_vmcr(vcpu, &vmcr); return 0; } static int get_gic_bpr0(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); *val = FIELD_PREP(ICC_BPR0_EL1_MASK, vmcr.bpr); return 0; } static int set_gic_bpr1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); if (!vmcr.cbpr) { vmcr.abpr = FIELD_GET(ICC_BPR1_EL1_MASK, val); vgic_set_vmcr(vcpu, &vmcr); } return 0; } static int get_gic_bpr1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); if (!vmcr.cbpr) *val = FIELD_PREP(ICC_BPR1_EL1_MASK, vmcr.abpr); else *val = min((vmcr.bpr + 1), 7U); return 0; } static int set_gic_grpen0(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); vmcr.grpen0 = FIELD_GET(ICC_IGRPEN0_EL1_MASK, val); vgic_set_vmcr(vcpu, &vmcr); return 0; } static int get_gic_grpen0(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); *val = FIELD_PREP(ICC_IGRPEN0_EL1_MASK, vmcr.grpen0); return 0; } static int set_gic_grpen1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); vmcr.grpen1 = FIELD_GET(ICC_IGRPEN1_EL1_MASK, val); vgic_set_vmcr(vcpu, &vmcr); return 0; } static int get_gic_grpen1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { struct vgic_vmcr vmcr; vgic_get_vmcr(vcpu, &vmcr); *val = FIELD_GET(ICC_IGRPEN1_EL1_MASK, vmcr.grpen1); return 0; } static void set_apr_reg(struct kvm_vcpu *vcpu, u64 val, u8 apr, u8 idx) { struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3; if (apr) vgicv3->vgic_ap1r[idx] = val; else vgicv3->vgic_ap0r[idx] = val; } static u64 get_apr_reg(struct kvm_vcpu *vcpu, u8 apr, u8 idx) { struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3; if (apr) return vgicv3->vgic_ap1r[idx]; else return vgicv3->vgic_ap0r[idx]; } static int set_gic_ap0r(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { u8 idx = r->Op2 & 3; if (idx > vgic_v3_max_apr_idx(vcpu)) return -EINVAL; set_apr_reg(vcpu, val, 0, idx); return 0; } static int get_gic_ap0r(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { u8 idx = r->Op2 & 3; if (idx > vgic_v3_max_apr_idx(vcpu)) return -EINVAL; *val = get_apr_reg(vcpu, 0, idx); return 0; } static int set_gic_ap1r(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { u8 idx = r->Op2 & 3; if (idx > vgic_v3_max_apr_idx(vcpu)) return -EINVAL; set_apr_reg(vcpu, val, 1, idx); return 0; } static int get_gic_ap1r(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { u8 idx = r->Op2 & 3; if (idx > vgic_v3_max_apr_idx(vcpu)) return -EINVAL; *val = get_apr_reg(vcpu, 1, idx); return 0; } static int set_gic_sre(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { /* Validate SRE bit */ if (!(val & ICC_SRE_EL1_SRE)) return -EINVAL; return 0; } static int get_gic_sre(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { struct vgic_v3_cpu_if *vgicv3 = &vcpu->arch.vgic_cpu.vgic_v3; *val = vgicv3->vgic_sre; return 0; } static int set_gic_ich_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { __vcpu_assign_sys_reg(vcpu, r->reg, val); return 0; } static int get_gic_ich_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { *val = __vcpu_sys_reg(vcpu, r->reg); return 0; } static int set_gic_ich_apr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { u8 idx = r->Op2 & 3; if (idx > vgic_v3_max_apr_idx(vcpu)) return -EINVAL; return set_gic_ich_reg(vcpu, r, val); } static int get_gic_ich_apr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { u8 idx = r->Op2 & 3; if (idx > vgic_v3_max_apr_idx(vcpu)) return -EINVAL; return get_gic_ich_reg(vcpu, r, val); } static int set_gic_icc_sre(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { if (val != KVM_ICC_SRE_EL2) return -EINVAL; return 0; } static int get_gic_icc_sre(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { *val = KVM_ICC_SRE_EL2; return 0; } static int set_gic_ich_vtr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val) { if (val != kvm_get_guest_vtr_el2()) return -EINVAL; return 0; } static int get_gic_ich_vtr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val) { *val = kvm_get_guest_vtr_el2(); return 0; } static unsigned int el2_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { return vcpu_has_nv(vcpu) ? 0 : REG_HIDDEN; } #define __EL2_REG(r, acc, i) \ { \ SYS_DESC(SYS_ ## r), \ .get_user = get_gic_ ## acc, \ .set_user = set_gic_ ## acc, \ .reg = i, \ .visibility = el2_visibility, \ } #define EL2_REG(r, acc) __EL2_REG(r, acc, r) #define EL2_REG_RO(r, acc) __EL2_REG(r, acc, 0) static const struct sys_reg_desc gic_v3_icc_reg_descs[] = { { SYS_DESC(SYS_ICC_PMR_EL1), .set_user = set_gic_pmr, .get_user = get_gic_pmr, }, { SYS_DESC(SYS_ICC_BPR0_EL1), .set_user = set_gic_bpr0, .get_user = get_gic_bpr0, }, { SYS_DESC(SYS_ICC_AP0R0_EL1), .set_user = set_gic_ap0r, .get_user = get_gic_ap0r, }, { SYS_DESC(SYS_ICC_AP0R1_EL1), .set_user = set_gic_ap0r, .get_user = get_gic_ap0r, }, { SYS_DESC(SYS_ICC_AP0R2_EL1), .set_user = set_gic_ap0r, .get_user = get_gic_ap0r, }, { SYS_DESC(SYS_ICC_AP0R3_EL1), .set_user = set_gic_ap0r, .get_user = get_gic_ap0r, }, { SYS_DESC(SYS_ICC_AP1R0_EL1), .set_user = set_gic_ap1r, .get_user = get_gic_ap1r, }, { SYS_DESC(SYS_ICC_AP1R1_EL1), .set_user = set_gic_ap1r, .get_user = get_gic_ap1r, }, { SYS_DESC(SYS_ICC_AP1R2_EL1), .set_user = set_gic_ap1r, .get_user = get_gic_ap1r, }, { SYS_DESC(SYS_ICC_AP1R3_EL1), .set_user = set_gic_ap1r, .get_user = get_gic_ap1r, }, { SYS_DESC(SYS_ICC_BPR1_EL1), .set_user = set_gic_bpr1, .get_user = get_gic_bpr1, }, { SYS_DESC(SYS_ICC_CTLR_EL1), .set_user = set_gic_ctlr, .get_user = get_gic_ctlr, }, { SYS_DESC(SYS_ICC_SRE_EL1), .set_user = set_gic_sre, .get_user = get_gic_sre, }, { SYS_DESC(SYS_ICC_IGRPEN0_EL1), .set_user = set_gic_grpen0, .get_user = get_gic_grpen0, }, { SYS_DESC(SYS_ICC_IGRPEN1_EL1), .set_user = set_gic_grpen1, .get_user = get_gic_grpen1, }, EL2_REG(ICH_AP0R0_EL2, ich_apr), EL2_REG(ICH_AP0R1_EL2, ich_apr), EL2_REG(ICH_AP0R2_EL2, ich_apr), EL2_REG(ICH_AP0R3_EL2, ich_apr), EL2_REG(ICH_AP1R0_EL2, ich_apr), EL2_REG(ICH_AP1R1_EL2, ich_apr), EL2_REG(ICH_AP1R2_EL2, ich_apr), EL2_REG(ICH_AP1R3_EL2, ich_apr), EL2_REG_RO(ICC_SRE_EL2, icc_sre), EL2_REG(ICH_HCR_EL2, ich_reg), EL2_REG_RO(ICH_VTR_EL2, ich_vtr), EL2_REG(ICH_VMCR_EL2, ich_reg), EL2_REG(ICH_LR0_EL2, ich_reg), EL2_REG(ICH_LR1_EL2, ich_reg), EL2_REG(ICH_LR2_EL2, ich_reg), EL2_REG(ICH_LR3_EL2, ich_reg), EL2_REG(ICH_LR4_EL2, ich_reg), EL2_REG(ICH_LR5_EL2, ich_reg), EL2_REG(ICH_LR6_EL2, ich_reg), EL2_REG(ICH_LR7_EL2, ich_reg), EL2_REG(ICH_LR8_EL2, ich_reg), EL2_REG(ICH_LR9_EL2, ich_reg), EL2_REG(ICH_LR10_EL2, ich_reg), EL2_REG(ICH_LR11_EL2, ich_reg), EL2_REG(ICH_LR12_EL2, ich_reg), EL2_REG(ICH_LR13_EL2, ich_reg), EL2_REG(ICH_LR14_EL2, ich_reg), EL2_REG(ICH_LR15_EL2, ich_reg), }; const struct sys_reg_desc *vgic_v3_get_sysreg_table(unsigned int *sz) { *sz = ARRAY_SIZE(gic_v3_icc_reg_descs); return gic_v3_icc_reg_descs; } static u64 attr_to_id(u64 attr) { return ARM64_SYS_REG(FIELD_GET(KVM_REG_ARM_VGIC_SYSREG_OP0_MASK, attr), FIELD_GET(KVM_REG_ARM_VGIC_SYSREG_OP1_MASK, attr), FIELD_GET(KVM_REG_ARM_VGIC_SYSREG_CRN_MASK, attr), FIELD_GET(KVM_REG_ARM_VGIC_SYSREG_CRM_MASK, attr), FIELD_GET(KVM_REG_ARM_VGIC_SYSREG_OP2_MASK, attr)); } int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { const struct sys_reg_desc *r; r = get_reg_by_id(attr_to_id(attr->attr), gic_v3_icc_reg_descs, ARRAY_SIZE(gic_v3_icc_reg_descs)); if (r && !sysreg_hidden(vcpu, r)) return 0; return -ENXIO; } int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr, bool is_write) { struct kvm_one_reg reg = { .id = attr_to_id(attr->attr), .addr = attr->addr, }; if (is_write) return kvm_sys_reg_set_user(vcpu, ®, gic_v3_icc_reg_descs, ARRAY_SIZE(gic_v3_icc_reg_descs)); else return kvm_sys_reg_get_user(vcpu, ®, gic_v3_icc_reg_descs, ARRAY_SIZE(gic_v3_icc_reg_descs)); } |
| 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 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 | // 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, *new_tb; if (id == 0) id = RT6_TABLE_MAIN; tb = fib6_get_table(net, id); if (tb) return tb; new_tb = fib6_alloc_table(net, id); if (!new_tb) return NULL; spin_lock_bh(&net->ipv6.fib_table_hash_lock); tb = fib6_get_table(net, id); if (unlikely(tb)) { spin_unlock_bh(&net->ipv6.fib_table_hash_lock); kfree(new_tb); return tb; } fib6_link_table(net, new_tb); spin_unlock_bh(&net->ipv6.fib_table_hash_lock); return new_tb; } EXPORT_SYMBOL_GPL(fib6_new_table); struct fib6_table *fib6_get_table(struct net *net, u32 id) { struct hlist_head *head; struct fib6_table *tb; if (!id) id = RT6_TABLE_MAIN; head = &net->ipv6.fib_table_hash[id & (FIB6_TABLE_HASHSZ - 1)]; /* See comment in fib6_link_table(). RCU is not required, * but rcu_dereference_raw() is used to avoid data-race. */ hlist_for_each_entry_rcu(tb, head, tb6_hlist, true) if (tb->tb6_id == id) return tb; 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; unsigned int nsiblings; int err; if (!rt || rt == arg->net->ipv6.fib6_null_entry) return 0; nsiblings = READ_ONCE(rt->fib6_nsiblings); if (nsiblings) err = call_fib6_multipath_entry_notifier(arg->nb, fib_event, rt, 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) { 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(); } static int fib6_nh_drop_pcpu_from(struct fib6_nh *nh, void *_arg) { struct fib6_info *arg = _arg; __fib6_drop_pcpu_from(nh, arg); return 0; } static void fib6_drop_pcpu_from(struct fib6_info *f6i) { /* 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) { rcu_read_lock(); nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_drop_pcpu_from, f6i); rcu_read_unlock(); } else { struct fib6_nh *fib6_nh; fib6_nh = f6i->fib6_nh; __fib6_drop_pcpu_from(fib6_nh, f6i); } } 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); if (rt->nh) { spin_lock(&rt->nh->lock); if (!list_empty(&rt->nh_list)) list_del_init(&rt->nh_list); spin_unlock(&rt->nh->lock); } 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 list_head *purge_list) { 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) WRITE_ONCE(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)) WRITE_ONCE(rt->fib6_nsiblings, rt->fib6_nsiblings + 1); } 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) { WRITE_ONCE(sibling->fib6_nsiblings, sibling->fib6_nsiblings + 1); BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); fib6_nsiblings++; } BUG_ON(fib6_nsiblings != rt->fib6_nsiblings); rcu_read_lock(); rt6_multipath_rebalance(temp_sibling); rcu_read_unlock(); } /* * 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) WRITE_ONCE(sibling->fib6_nsiblings, sibling->fib6_nsiblings - 1); WRITE_ONCE(rt->fib6_nsiblings, 0); list_del_rcu(&rt->fib6_siblings); rcu_read_lock(); rt6_multipath_rebalance(next_sibling); rcu_read_unlock(); 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; list_add(&iter->purge_link, purge_list); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; 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; list_add(&iter->purge_link, purge_list); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; 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 int fib6_add_rt2node_nh(struct fib6_node *fn, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack, struct list_head *purge_list) { int err; spin_lock(&rt->nh->lock); if (rt->nh->dead) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); err = -EINVAL; } else { err = fib6_add_rt2node(fn, rt, info, extack, purge_list); if (!err) list_add(&rt->nh_list, &rt->nh->f6i_list); } spin_unlock(&rt->nh->lock); return err; } 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; LIST_HEAD(purge_list); 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 if (rt->nh) err = fib6_add_rt2node_nh(fn, rt, info, extack, &purge_list); else err = fib6_add_rt2node(fn, rt, info, extack, &purge_list); if (!err) { struct fib6_info *iter, *next; list_for_each_entry_safe(iter, next, &purge_list, purge_link) { list_del(&iter->purge_link); fib6_purge_rt(iter, fn, info->nl_net); fib6_info_release(iter); } __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) WRITE_ONCE(sibling->fib6_nsiblings, sibling->fib6_nsiblings - 1); WRITE_ONCE(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 timer_delete(&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 = timer_container_of(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; spin_lock_init(&net->ipv6.fib_table_hash_lock); 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; timer_delete_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 */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_FLOW_DISSECTOR_H #define _NET_FLOW_DISSECTOR_H #include <linux/types.h> #include <linux/in6.h> #include <linux/siphash.h> #include <linux/string.h> #include <uapi/linux/if_ether.h> #include <uapi/linux/pkt_cls.h> struct bpf_prog; struct net; struct sk_buff; /** * struct flow_dissector_key_control: * @thoff: Transport header offset * @addr_type: Type of key. One of FLOW_DISSECTOR_KEY_* * @flags: Key flags. * Any of FLOW_DIS_(IS_FRAGMENT|FIRST_FRAG|ENCAPSULATION|F_*) */ struct flow_dissector_key_control { u16 thoff; u16 addr_type; u32 flags; }; /* The control flags are kept in sync with TCA_FLOWER_KEY_FLAGS_*, as those * flags are exposed to userspace in some error paths, ie. unsupported flags. */ enum flow_dissector_ctrl_flags { FLOW_DIS_IS_FRAGMENT = TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT, FLOW_DIS_FIRST_FRAG = TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST, FLOW_DIS_F_TUNNEL_CSUM = TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM, FLOW_DIS_F_TUNNEL_DONT_FRAGMENT = TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT, FLOW_DIS_F_TUNNEL_OAM = TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM, FLOW_DIS_F_TUNNEL_CRIT_OPT = TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT, /* These flags are internal to the kernel */ FLOW_DIS_ENCAPSULATION = (TCA_FLOWER_KEY_FLAGS_MAX << 1), }; enum flow_dissect_ret { FLOW_DISSECT_RET_OUT_GOOD, FLOW_DISSECT_RET_OUT_BAD, FLOW_DISSECT_RET_PROTO_AGAIN, FLOW_DISSECT_RET_IPPROTO_AGAIN, FLOW_DISSECT_RET_CONTINUE, }; /** * struct flow_dissector_key_basic: * @n_proto: Network header protocol (eg. IPv4/IPv6) * @ip_proto: Transport header protocol (eg. TCP/UDP) * @padding: Unused */ struct flow_dissector_key_basic { __be16 n_proto; u8 ip_proto; u8 padding; }; struct flow_dissector_key_tags { u32 flow_label; }; struct flow_dissector_key_vlan { union { struct { u16 vlan_id:12, vlan_dei:1, vlan_priority:3; }; __be16 vlan_tci; }; __be16 vlan_tpid; __be16 vlan_eth_type; u16 padding; }; struct flow_dissector_mpls_lse { u32 mpls_ttl:8, mpls_bos:1, mpls_tc:3, mpls_label:20; }; #define FLOW_DIS_MPLS_MAX 7 struct flow_dissector_key_mpls { struct flow_dissector_mpls_lse ls[FLOW_DIS_MPLS_MAX]; /* Label Stack */ u8 used_lses; /* One bit set for each Label Stack Entry in use */ }; static inline void dissector_set_mpls_lse(struct flow_dissector_key_mpls *mpls, int lse_index) { mpls->used_lses |= 1 << lse_index; } #define FLOW_DIS_TUN_OPTS_MAX 255 /** * struct flow_dissector_key_enc_opts: * @data: tunnel option data * @len: length of tunnel option data * @dst_opt_type: tunnel option type */ struct flow_dissector_key_enc_opts { u8 data[FLOW_DIS_TUN_OPTS_MAX]; /* Using IP_TUNNEL_OPTS_MAX is desired * here but seems difficult to #include */ u8 len; u32 dst_opt_type; }; struct flow_dissector_key_keyid { __be32 keyid; }; /** * struct flow_dissector_key_ipv4_addrs: * @src: source ip address * @dst: destination ip address */ struct flow_dissector_key_ipv4_addrs { /* (src,dst) must be grouped, in the same way than in IP header */ __be32 src; __be32 dst; }; /** * struct flow_dissector_key_ipv6_addrs: * @src: source ip address * @dst: destination ip address */ struct flow_dissector_key_ipv6_addrs { /* (src,dst) must be grouped, in the same way than in IP header */ struct in6_addr src; struct in6_addr dst; }; /** * struct flow_dissector_key_tipc: * @key: source node address combined with selector */ struct flow_dissector_key_tipc { __be32 key; }; /** * struct flow_dissector_key_addrs: * @v4addrs: IPv4 addresses * @v6addrs: IPv6 addresses * @tipckey: TIPC key */ struct flow_dissector_key_addrs { union { struct flow_dissector_key_ipv4_addrs v4addrs; struct flow_dissector_key_ipv6_addrs v6addrs; struct flow_dissector_key_tipc tipckey; }; }; /** * struct flow_dissector_key_arp: * @sip: Sender IP address * @tip: Target IP address * @op: Operation * @sha: Sender hardware address * @tha: Target hardware address */ struct flow_dissector_key_arp { __u32 sip; __u32 tip; __u8 op; unsigned char sha[ETH_ALEN]; unsigned char tha[ETH_ALEN]; }; /** * struct flow_dissector_key_ports: * @ports: port numbers of Transport header * @src: source port number * @dst: destination port number */ struct flow_dissector_key_ports { union { __be32 ports; struct { __be16 src; __be16 dst; }; }; }; /** * struct flow_dissector_key_ports_range * @tp: port number from packet * @tp_min: min port number in range * @tp_max: max port number in range */ struct flow_dissector_key_ports_range { union { struct flow_dissector_key_ports tp; struct { struct flow_dissector_key_ports tp_min; struct flow_dissector_key_ports tp_max; }; }; }; /** * struct flow_dissector_key_icmp: * @type: ICMP type * @code: ICMP code * @id: Session identifier */ struct flow_dissector_key_icmp { struct { u8 type; u8 code; }; u16 id; }; /** * struct flow_dissector_key_eth_addrs: * @src: source Ethernet address * @dst: destination Ethernet address */ struct flow_dissector_key_eth_addrs { /* (dst,src) must be grouped, in the same way than in ETH header */ unsigned char dst[ETH_ALEN]; unsigned char src[ETH_ALEN]; }; /** * struct flow_dissector_key_tcp: * @flags: flags */ struct flow_dissector_key_tcp { __be16 flags; }; /** * struct flow_dissector_key_ip: * @tos: tos * @ttl: ttl */ struct flow_dissector_key_ip { __u8 tos; __u8 ttl; }; /** * struct flow_dissector_key_meta: * @ingress_ifindex: ingress ifindex * @ingress_iftype: ingress interface type * @l2_miss: packet did not match an L2 entry during forwarding */ struct flow_dissector_key_meta { int ingress_ifindex; u16 ingress_iftype; u8 l2_miss; }; /** * struct flow_dissector_key_ct: * @ct_state: conntrack state after converting with map * @ct_mark: conttrack mark * @ct_zone: conntrack zone * @ct_labels: conntrack labels */ struct flow_dissector_key_ct { u16 ct_state; u16 ct_zone; u32 ct_mark; u32 ct_labels[4]; }; /** * struct flow_dissector_key_hash: * @hash: hash value */ struct flow_dissector_key_hash { u32 hash; }; /** * struct flow_dissector_key_num_of_vlans: * @num_of_vlans: num_of_vlans value */ struct flow_dissector_key_num_of_vlans { u8 num_of_vlans; }; /** * struct flow_dissector_key_pppoe: * @session_id: pppoe session id * @ppp_proto: ppp protocol * @type: pppoe eth type */ struct flow_dissector_key_pppoe { __be16 session_id; __be16 ppp_proto; __be16 type; }; /** * struct flow_dissector_key_l2tpv3: * @session_id: identifier for a l2tp session */ struct flow_dissector_key_l2tpv3 { __be32 session_id; }; /** * struct flow_dissector_key_ipsec: * @spi: identifier for a ipsec connection */ struct flow_dissector_key_ipsec { __be32 spi; }; /** * struct flow_dissector_key_cfm * @mdl_ver: maintenance domain level (mdl) and cfm protocol version * @opcode: code specifying a type of cfm protocol packet * * See 802.1ag, ITU-T G.8013/Y.1731 * 1 2 * |7 6 5 4 3 2 1 0|7 6 5 4 3 2 1 0| * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | mdl | version | opcode | * +-----+---------+-+-+-+-+-+-+-+-+ */ struct flow_dissector_key_cfm { u8 mdl_ver; u8 opcode; }; #define FLOW_DIS_CFM_MDL_MASK GENMASK(7, 5) #define FLOW_DIS_CFM_MDL_MAX 7 enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ FLOW_DISSECTOR_KEY_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ FLOW_DISSECTOR_KEY_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ FLOW_DISSECTOR_KEY_PORTS, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_PORTS_RANGE, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_ICMP, /* struct flow_dissector_key_icmp */ FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */ FLOW_DISSECTOR_KEY_TIPC, /* struct flow_dissector_key_tipc */ FLOW_DISSECTOR_KEY_ARP, /* struct flow_dissector_key_arp */ FLOW_DISSECTOR_KEY_VLAN, /* struct flow_dissector_key_vlan */ FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_tags */ FLOW_DISSECTOR_KEY_GRE_KEYID, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_MPLS_ENTROPY, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_ENC_KEYID, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, /* struct flow_dissector_key_ipv4_addrs */ FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, /* struct flow_dissector_key_ipv6_addrs */ FLOW_DISSECTOR_KEY_ENC_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_ENC_PORTS, /* struct flow_dissector_key_ports */ FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */ FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */ FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_vlan */ FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */ FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */ FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */ FLOW_DISSECTOR_KEY_HASH, /* struct flow_dissector_key_hash */ FLOW_DISSECTOR_KEY_NUM_OF_VLANS, /* struct flow_dissector_key_num_of_vlans */ FLOW_DISSECTOR_KEY_PPPOE, /* struct flow_dissector_key_pppoe */ FLOW_DISSECTOR_KEY_L2TPV3, /* struct flow_dissector_key_l2tpv3 */ FLOW_DISSECTOR_KEY_CFM, /* struct flow_dissector_key_cfm */ FLOW_DISSECTOR_KEY_IPSEC, /* struct flow_dissector_key_ipsec */ FLOW_DISSECTOR_KEY_MAX, }; #define FLOW_DISSECTOR_F_PARSE_1ST_FRAG BIT(0) #define FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL BIT(1) #define FLOW_DISSECTOR_F_STOP_AT_ENCAP BIT(2) #define FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP BIT(3) struct flow_dissector_key { enum flow_dissector_key_id key_id; size_t offset; /* offset of struct flow_dissector_key_* in target the struct */ }; struct flow_dissector { unsigned long long used_keys; /* each bit represents presence of one key id */ unsigned short int offset[FLOW_DISSECTOR_KEY_MAX]; }; struct flow_keys_basic { struct flow_dissector_key_control control; struct flow_dissector_key_basic basic; }; struct flow_keys { struct flow_dissector_key_control control; #define FLOW_KEYS_HASH_START_FIELD basic struct flow_dissector_key_basic basic __aligned(SIPHASH_ALIGNMENT); struct flow_dissector_key_tags tags; struct flow_dissector_key_vlan vlan; struct flow_dissector_key_vlan cvlan; struct flow_dissector_key_keyid keyid; struct flow_dissector_key_ports ports; struct flow_dissector_key_icmp icmp; /* 'addrs' must be the last member */ struct flow_dissector_key_addrs addrs; }; #define FLOW_KEYS_HASH_OFFSET \ offsetof(struct flow_keys, FLOW_KEYS_HASH_START_FIELD) __be32 flow_get_u32_src(const struct flow_keys *flow); __be32 flow_get_u32_dst(const struct flow_keys *flow); extern struct flow_dissector flow_keys_dissector; extern struct flow_dissector flow_keys_basic_dissector; /* struct flow_keys_digest: * * This structure is used to hold a digest of the full flow keys. This is a * larger "hash" of a flow to allow definitively matching specific flows where * the 32 bit skb->hash is not large enough. The size is limited to 16 bytes so * that it can be used in CB of skb (see sch_choke for an example). */ #define FLOW_KEYS_DIGEST_LEN 16 struct flow_keys_digest { u8 data[FLOW_KEYS_DIGEST_LEN]; }; void make_flow_keys_digest(struct flow_keys_digest *digest, const struct flow_keys *flow); static inline bool flow_keys_have_l4(const struct flow_keys *keys) { return (keys->ports.ports || keys->tags.flow_label); } u32 flow_hash_from_keys(struct flow_keys *keys); u32 flow_hash_from_keys_seed(struct flow_keys *keys, const siphash_key_t *keyval); 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); static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) { return flow_dissector->used_keys & (1ULL << key_id); } static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id, void *target_container) { return ((char *)target_container) + flow_dissector->offset[key_id]; } struct bpf_flow_dissector { struct bpf_flow_keys *flow_keys; const struct sk_buff *skb; const void *data; const void *data_end; }; static inline void flow_dissector_init_keys(struct flow_dissector_key_control *key_control, struct flow_dissector_key_basic *key_basic) { memset(key_control, 0, sizeof(*key_control)); memset(key_basic, 0, sizeof(*key_basic)); } #ifdef CONFIG_BPF_SYSCALL int flow_dissector_bpf_prog_attach_check(struct net *net, struct bpf_prog *prog); #endif /* CONFIG_BPF_SYSCALL */ #endif |
| 200 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some * particular ordering. One way to make the compiler aware of ordering is to * put the two invocations of READ_ONCE or WRITE_ONCE in different C * statements. * * These two macros will also work on aggregate data types like structs or * unions. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, * and (2) Ensuring that the compiler does not fold, spindle, or otherwise * mutilate accesses that either do not require ordering or that interact * with an explicit memory barrier or atomic instruction that provides the * required ordering. */ #ifndef __ASM_GENERIC_RWONCE_H #define __ASM_GENERIC_RWONCE_H #ifndef __ASSEMBLY__ #include <linux/compiler_types.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> /* * Yes, this permits 64-bit accesses on 32-bit architectures. These will * actually be atomic in some cases (namely Armv7 + LPAE), but for others we * rely on the access being split into 2x32-bit accesses for a 32-bit quantity * (e.g. a virtual address) and a strong prevailing wind. */ #define compiletime_assert_rwonce_type(t) \ compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ "Unsupported access size for {READ,WRITE}_ONCE().") /* * Use __READ_ONCE() instead of READ_ONCE() if you do not require any * atomicity. Note that this may result in tears! */ #ifndef __READ_ONCE #define __READ_ONCE(x) (*(const volatile __unqual_scalar_typeof(x) *)&(x)) #endif #define READ_ONCE(x) \ ({ \ compiletime_assert_rwonce_type(x); \ __READ_ONCE(x); \ }) #define __WRITE_ONCE(x, val) \ do { \ *(volatile typeof(x) *)&(x) = (val); \ } while (0) #define WRITE_ONCE(x, val) \ do { \ compiletime_assert_rwonce_type(x); \ __WRITE_ONCE(x, val); \ } while (0) static __no_sanitize_or_inline unsigned long __read_once_word_nocheck(const void *addr) { return __READ_ONCE(*(unsigned long *)addr); } /* * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a * word from memory atomically but without telling KASAN/KCSAN. This is * usually used by unwinding code when walking the stack of a running process. */ #define READ_ONCE_NOCHECK(x) \ ({ \ compiletime_assert(sizeof(x) == sizeof(unsigned long), \ "Unsupported access size for READ_ONCE_NOCHECK()."); \ (typeof(x))__read_once_word_nocheck(&(x)); \ }) static __no_sanitize_or_inline unsigned long read_word_at_a_time(const void *addr) { /* open-coded instrument_read(addr, 1) */ kasan_check_read(addr, 1); kcsan_check_read(addr, 1); /* * This load can race with concurrent stores to out-of-bounds memory, * but READ_ONCE() can't be used because it requires higher alignment * than plain loads in arm64 builds with LTO. */ return *(unsigned long *)addr; } #endif /* __ASSEMBLY__ */ #endif /* __ASM_GENERIC_RWONCE_H */ |
| 410 | 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+ */ /* * RCU-based infrastructure for lightweight reader-writer locking * * Copyright (c) 2015, Red Hat, Inc. * * Author: Oleg Nesterov <oleg@redhat.com> */ #ifndef _LINUX_RCU_SYNC_H_ #define _LINUX_RCU_SYNC_H_ #include <linux/wait.h> #include <linux/rcupdate.h> /* Structure to mediate between updaters and fastpath-using readers. */ struct rcu_sync { int gp_state; int gp_count; wait_queue_head_t gp_wait; struct rcu_head cb_head; }; /** * rcu_sync_is_idle() - Are readers permitted to use their fastpaths? * @rsp: Pointer to rcu_sync structure to use for synchronization * * Returns true if readers are permitted to use their fastpaths. Must be * invoked within some flavor of RCU read-side critical section. */ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) { RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), "suspicious rcu_sync_is_idle() usage"); return !READ_ONCE(rsp->gp_state); /* GP_IDLE */ } extern void rcu_sync_init(struct rcu_sync *); extern void rcu_sync_enter(struct rcu_sync *); extern void rcu_sync_exit(struct rcu_sync *); extern void rcu_sync_dtor(struct rcu_sync *); #define __RCU_SYNC_INITIALIZER(name) { \ .gp_state = 0, \ .gp_count = 0, \ .gp_wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.gp_wait), \ } #define DEFINE_RCU_SYNC(name) \ struct rcu_sync name = __RCU_SYNC_INITIALIZER(name) #endif /* _LINUX_RCU_SYNC_H_ */ |
| 295 1 315 80 315 315 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_BL_H #define _LINUX_LIST_BL_H #include <linux/list.h> #include <linux/bit_spinlock.h> /* * Special version of lists, where head of the list has a lock in the lowest * bit. This is useful for scalable hash tables without increasing memory * footprint overhead. * * For modification operations, the 0 bit of hlist_bl_head->first * pointer must be set. * * With some small modifications, this can easily be adapted to store several * arbitrary bits (not just a single lock bit), if the need arises to store * some fast and compact auxiliary data. */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define LIST_BL_LOCKMASK 1UL #else #define LIST_BL_LOCKMASK 0UL #endif #ifdef CONFIG_DEBUG_LIST #define LIST_BL_BUG_ON(x) BUG_ON(x) #else #define LIST_BL_BUG_ON(x) #endif struct hlist_bl_head { struct hlist_bl_node *first; }; struct hlist_bl_node { struct hlist_bl_node *next, **pprev; }; #define INIT_HLIST_BL_HEAD(ptr) \ ((ptr)->first = NULL) static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) { h->next = NULL; h->pprev = NULL; } #define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member) static inline bool hlist_bl_unhashed(const struct hlist_bl_node *h) { return !h->pprev; } static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)h->first & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_set_first(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK); } static inline bool hlist_bl_empty(const struct hlist_bl_head *h) { return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_add_head(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; hlist_bl_set_first(h, n); } static inline void hlist_bl_add_before(struct hlist_bl_node *n, struct hlist_bl_node *next) { struct hlist_bl_node **pprev = next->pprev; n->pprev = pprev; n->next = next; next->pprev = &n->next; /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((uintptr_t)n | ((uintptr_t)*pprev & LIST_BL_LOCKMASK))); } static inline void hlist_bl_add_behind(struct hlist_bl_node *n, struct hlist_bl_node *prev) { n->next = prev->next; n->pprev = &prev->next; prev->next = n; if (n->next) n->next->pprev = &n->next; } static inline void __hlist_bl_del(struct hlist_bl_node *n) { struct hlist_bl_node *next = n->next; struct hlist_bl_node **pprev = n->pprev; LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((unsigned long)next | ((unsigned long)*pprev & LIST_BL_LOCKMASK))); if (next) next->pprev = pprev; } static inline void hlist_bl_del(struct hlist_bl_node *n) { __hlist_bl_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } static inline void hlist_bl_del_init(struct hlist_bl_node *n) { if (!hlist_bl_unhashed(n)) { __hlist_bl_del(n); INIT_HLIST_BL_NODE(n); } } static inline void hlist_bl_lock(struct hlist_bl_head *b) { bit_spin_lock(0, (unsigned long *)b); } static inline void hlist_bl_unlock(struct hlist_bl_head *b) { __bit_spin_unlock(0, (unsigned long *)b); } static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) { return bit_spin_is_locked(0, (unsigned long *)b); } /** * hlist_bl_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * */ #define hlist_bl_for_each_entry(tpos, pos, head, member) \ for (pos = hlist_bl_first(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_bl_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @n: another &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_bl_for_each_entry_safe(tpos, pos, n, head, member) \ for (pos = hlist_bl_first(head); \ pos && ({ n = pos->next; 1; }) && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = n) #endif |
| 30 251 31 250 131 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk). * * (C) SGI 2006, Christoph Lameter * Cleaned up and restructured to ease the addition of alternative * implementations of SLAB allocators. * (C) Linux Foundation 2008-2013 * Unified interface for all slab allocators */ #ifndef _LINUX_SLAB_H #define _LINUX_SLAB_H #include <linux/cache.h> #include <linux/gfp.h> #include <linux/overflow.h> #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/percpu-refcount.h> #include <linux/cleanup.h> #include <linux/hash.h> enum _slab_flag_bits { _SLAB_CONSISTENCY_CHECKS, _SLAB_RED_ZONE, _SLAB_POISON, _SLAB_KMALLOC, _SLAB_HWCACHE_ALIGN, _SLAB_CACHE_DMA, _SLAB_CACHE_DMA32, _SLAB_STORE_USER, _SLAB_PANIC, _SLAB_TYPESAFE_BY_RCU, _SLAB_TRACE, #ifdef CONFIG_DEBUG_OBJECTS _SLAB_DEBUG_OBJECTS, #endif _SLAB_NOLEAKTRACE, _SLAB_NO_MERGE, #ifdef CONFIG_FAILSLAB _SLAB_FAILSLAB, #endif #ifdef CONFIG_MEMCG _SLAB_ACCOUNT, #endif #ifdef CONFIG_KASAN_GENERIC _SLAB_KASAN, #endif _SLAB_NO_USER_FLAGS, #ifdef CONFIG_KFENCE _SLAB_SKIP_KFENCE, #endif #ifndef CONFIG_SLUB_TINY _SLAB_RECLAIM_ACCOUNT, #endif _SLAB_OBJECT_POISON, _SLAB_CMPXCHG_DOUBLE, #ifdef CONFIG_SLAB_OBJ_EXT _SLAB_NO_OBJ_EXT, #endif _SLAB_FLAGS_LAST_BIT }; #define __SLAB_FLAG_BIT(nr) ((slab_flags_t __force)(1U << (nr))) #define __SLAB_FLAG_UNUSED ((slab_flags_t __force)(0U)) /* * Flags to pass to kmem_cache_create(). * The ones marked DEBUG need CONFIG_SLUB_DEBUG enabled, otherwise are no-op */ /* DEBUG: Perform (expensive) checks on alloc/free */ #define SLAB_CONSISTENCY_CHECKS __SLAB_FLAG_BIT(_SLAB_CONSISTENCY_CHECKS) /* DEBUG: Red zone objs in a cache */ #define SLAB_RED_ZONE __SLAB_FLAG_BIT(_SLAB_RED_ZONE) /* DEBUG: Poison objects */ #define SLAB_POISON __SLAB_FLAG_BIT(_SLAB_POISON) /* Indicate a kmalloc slab */ #define SLAB_KMALLOC __SLAB_FLAG_BIT(_SLAB_KMALLOC) /** * define SLAB_HWCACHE_ALIGN - Align objects on cache line boundaries. * * Sufficiently large objects are aligned on cache line boundary. For object * size smaller than a half of cache line size, the alignment is on the half of * cache line size. In general, if object size is smaller than 1/2^n of cache * line size, the alignment is adjusted to 1/2^n. * * If explicit alignment is also requested by the respective * &struct kmem_cache_args field, the greater of both is alignments is applied. */ #define SLAB_HWCACHE_ALIGN __SLAB_FLAG_BIT(_SLAB_HWCACHE_ALIGN) /* Use GFP_DMA memory */ #define SLAB_CACHE_DMA __SLAB_FLAG_BIT(_SLAB_CACHE_DMA) /* Use GFP_DMA32 memory */ #define SLAB_CACHE_DMA32 __SLAB_FLAG_BIT(_SLAB_CACHE_DMA32) /* DEBUG: Store the last owner for bug hunting */ #define SLAB_STORE_USER __SLAB_FLAG_BIT(_SLAB_STORE_USER) /* Panic if kmem_cache_create() fails */ #define SLAB_PANIC __SLAB_FLAG_BIT(_SLAB_PANIC) /** * define SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS! * * This delays freeing the SLAB page by a grace period, it does _NOT_ * delay object freeing. This means that if you do kmem_cache_free() * that memory location is free to be reused at any time. Thus it may * be possible to see another object there in the same RCU grace period. * * This feature only ensures the memory location backing the object * stays valid, the trick to using this is relying on an independent * object validation pass. Something like: * * :: * * begin: * rcu_read_lock(); * obj = lockless_lookup(key); * if (obj) { * if (!try_get_ref(obj)) // might fail for free objects * rcu_read_unlock(); * goto begin; * * if (obj->key != key) { // not the object we expected * put_ref(obj); * rcu_read_unlock(); * goto begin; * } * } * rcu_read_unlock(); * * This is useful if we need to approach a kernel structure obliquely, * from its address obtained without the usual locking. We can lock * the structure to stabilize it and check it's still at the given address, * only if we can be sure that the memory has not been meanwhile reused * for some other kind of object (which our subsystem's lock might corrupt). * * rcu_read_lock before reading the address, then rcu_read_unlock after * taking the spinlock within the structure expected at that address. * * Note that object identity check has to be done *after* acquiring a * reference, therefore user has to ensure proper ordering for loads. * Similarly, when initializing objects allocated with SLAB_TYPESAFE_BY_RCU, * the newly allocated object has to be fully initialized *before* its * refcount gets initialized and proper ordering for stores is required. * refcount_{add|inc}_not_zero_acquire() and refcount_set_release() are * designed with the proper fences required for reference counting objects * allocated with SLAB_TYPESAFE_BY_RCU. * * Note that it is not possible to acquire a lock within a structure * allocated with SLAB_TYPESAFE_BY_RCU without first acquiring a reference * as described above. The reason is that SLAB_TYPESAFE_BY_RCU pages * are not zeroed before being given to the slab, which means that any * locks must be initialized after each and every kmem_struct_alloc(). * Alternatively, make the ctor passed to kmem_cache_create() initialize * the locks at page-allocation time, as is done in __i915_request_ctor(), * sighand_ctor(), and anon_vma_ctor(). Such a ctor permits readers * to safely acquire those ctor-initialized locks under rcu_read_lock() * protection. * * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU. */ #define SLAB_TYPESAFE_BY_RCU __SLAB_FLAG_BIT(_SLAB_TYPESAFE_BY_RCU) /* Trace allocations and frees */ #define SLAB_TRACE __SLAB_FLAG_BIT(_SLAB_TRACE) /* Flag to prevent checks on free */ #ifdef CONFIG_DEBUG_OBJECTS # define SLAB_DEBUG_OBJECTS __SLAB_FLAG_BIT(_SLAB_DEBUG_OBJECTS) #else # define SLAB_DEBUG_OBJECTS __SLAB_FLAG_UNUSED #endif /* Avoid kmemleak tracing */ #define SLAB_NOLEAKTRACE __SLAB_FLAG_BIT(_SLAB_NOLEAKTRACE) /* * Prevent merging with compatible kmem caches. This flag should be used * cautiously. Valid use cases: * * - caches created for self-tests (e.g. kunit) * - general caches created and used by a subsystem, only when a * (subsystem-specific) debug option is enabled * - performance critical caches, should be very rare and consulted with slab * maintainers, and not used together with CONFIG_SLUB_TINY */ #define SLAB_NO_MERGE __SLAB_FLAG_BIT(_SLAB_NO_MERGE) /* Fault injection mark */ #ifdef CONFIG_FAILSLAB # define SLAB_FAILSLAB __SLAB_FLAG_BIT(_SLAB_FAILSLAB) #else # define SLAB_FAILSLAB __SLAB_FLAG_UNUSED #endif /** * define SLAB_ACCOUNT - Account allocations to memcg. * * All object allocations from this cache will be memcg accounted, regardless of * __GFP_ACCOUNT being or not being passed to individual allocations. */ #ifdef CONFIG_MEMCG # define SLAB_ACCOUNT __SLAB_FLAG_BIT(_SLAB_ACCOUNT) #else # define SLAB_ACCOUNT __SLAB_FLAG_UNUSED #endif #ifdef CONFIG_KASAN_GENERIC #define SLAB_KASAN __SLAB_FLAG_BIT(_SLAB_KASAN) #else #define SLAB_KASAN __SLAB_FLAG_UNUSED #endif /* * Ignore user specified debugging flags. * Intended for caches created for self-tests so they have only flags * specified in the code and other flags are ignored. */ #define SLAB_NO_USER_FLAGS __SLAB_FLAG_BIT(_SLAB_NO_USER_FLAGS) #ifdef CONFIG_KFENCE #define SLAB_SKIP_KFENCE __SLAB_FLAG_BIT(_SLAB_SKIP_KFENCE) #else #define SLAB_SKIP_KFENCE __SLAB_FLAG_UNUSED #endif /* The following flags affect the page allocator grouping pages by mobility */ /** * define SLAB_RECLAIM_ACCOUNT - Objects are reclaimable. * * Use this flag for caches that have an associated shrinker. As a result, slab * pages are allocated with __GFP_RECLAIMABLE, which affects grouping pages by * mobility, and are accounted in SReclaimable counter in /proc/meminfo */ #ifndef CONFIG_SLUB_TINY #define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_BIT(_SLAB_RECLAIM_ACCOUNT) #else #define SLAB_RECLAIM_ACCOUNT __SLAB_FLAG_UNUSED #endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ /* Slab created using create_boot_cache */ #ifdef CONFIG_SLAB_OBJ_EXT #define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT) #else #define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED #endif /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * * Dereferencing ZERO_SIZE_PTR will lead to a distinct access fault. * * ZERO_SIZE_PTR can be passed to kfree though in the same way that NULL can. * Both make kfree a no-op. */ #define ZERO_SIZE_PTR ((void *)16) #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \ (unsigned long)ZERO_SIZE_PTR) #include <linux/kasan.h> struct list_lru; struct mem_cgroup; /* * struct kmem_cache related prototypes */ bool slab_is_available(void); /** * struct kmem_cache_args - Less common arguments for kmem_cache_create() * * Any uninitialized fields of the structure are interpreted as unused. The * exception is @freeptr_offset where %0 is a valid value, so * @use_freeptr_offset must be also set to %true in order to interpret the field * as used. For @useroffset %0 is also valid, but only with non-%0 * @usersize. * * When %NULL args is passed to kmem_cache_create(), it is equivalent to all * fields unused. */ struct kmem_cache_args { /** * @align: The required alignment for the objects. * * %0 means no specific alignment is requested. */ unsigned int align; /** * @useroffset: Usercopy region offset. * * %0 is a valid offset, when @usersize is non-%0 */ unsigned int useroffset; /** * @usersize: Usercopy region size. * * %0 means no usercopy region is specified. */ unsigned int usersize; /** * @freeptr_offset: Custom offset for the free pointer * in &SLAB_TYPESAFE_BY_RCU caches * * By default &SLAB_TYPESAFE_BY_RCU caches place the free pointer * outside of the object. This might cause the object to grow in size. * Cache creators that have a reason to avoid this can specify a custom * free pointer offset in their struct where the free pointer will be * placed. * * Note that placing the free pointer inside the object requires the * caller to ensure that no fields are invalidated that are required to * guard against object recycling (See &SLAB_TYPESAFE_BY_RCU for * details). * * Using %0 as a value for @freeptr_offset is valid. If @freeptr_offset * is specified, %use_freeptr_offset must be set %true. * * Note that @ctor currently isn't supported with custom free pointers * as a @ctor requires an external free pointer. */ unsigned int freeptr_offset; /** * @use_freeptr_offset: Whether a @freeptr_offset is used. */ bool use_freeptr_offset; /** * @ctor: A constructor for the objects. * * The constructor is invoked for each object in a newly allocated slab * page. It is the cache user's responsibility to free object in the * same state as after calling the constructor, or deal appropriately * with any differences between a freshly constructed and a reallocated * object. * * %NULL means no constructor. */ void (*ctor)(void *); /** * @sheaf_capacity: Enable sheaves of given capacity for the cache. * * With a non-zero value, allocations from the cache go through caching * arrays called sheaves. Each cpu has a main sheaf that's always * present, and a spare sheaf that may be not present. When both become * empty, there's an attempt to replace an empty sheaf with a full sheaf * from the per-node barn. * * When no full sheaf is available, and gfp flags allow blocking, a * sheaf is allocated and filled from slab(s) using bulk allocation. * Otherwise the allocation falls back to the normal operation * allocating a single object from a slab. * * Analogically when freeing and both percpu sheaves are full, the barn * may replace it with an empty sheaf, unless it's over capacity. In * that case a sheaf is bulk freed to slab pages. * * The sheaves do not enforce NUMA placement of objects, so allocations * via kmem_cache_alloc_node() with a node specified other than * NUMA_NO_NODE will bypass them. * * Bulk allocation and free operations also try to use the cpu sheaves * and barn, but fallback to using slab pages directly. * * When slub_debug is enabled for the cache, the sheaf_capacity argument * is ignored. * * %0 means no sheaves will be created. */ unsigned int sheaf_capacity; }; struct kmem_cache *__kmem_cache_create_args(const char *name, unsigned int object_size, struct kmem_cache_args *args, slab_flags_t flags); static inline struct kmem_cache * __kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)) { struct kmem_cache_args kmem_args = { .align = align, .ctor = ctor, }; return __kmem_cache_create_args(name, size, &kmem_args, flags); } /** * kmem_cache_create_usercopy - Create a kmem cache with a region suitable * for copying to userspace. * @name: A string which is used in /proc/slabinfo to identify this cache. * @size: The size of objects to be created in this cache. * @align: The required alignment for the objects. * @flags: SLAB flags * @useroffset: Usercopy region offset * @usersize: Usercopy region size * @ctor: A constructor for the objects, or %NULL. * * This is a legacy wrapper, new code should use either KMEM_CACHE_USERCOPY() * if whitelisting a single field is sufficient, or kmem_cache_create() with * the necessary parameters passed via the args parameter (see * &struct kmem_cache_args) * * Return: a pointer to the cache on success, NULL on failure. */ static inline struct kmem_cache * kmem_cache_create_usercopy(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)) { struct kmem_cache_args kmem_args = { .align = align, .ctor = ctor, .useroffset = useroffset, .usersize = usersize, }; return __kmem_cache_create_args(name, size, &kmem_args, flags); } /* If NULL is passed for @args, use this variant with default arguments. */ static inline struct kmem_cache * __kmem_cache_default_args(const char *name, unsigned int size, struct kmem_cache_args *args, slab_flags_t flags) { struct kmem_cache_args kmem_default_args = {}; /* Make sure we don't get passed garbage. */ if (WARN_ON_ONCE(args)) return ERR_PTR(-EINVAL); return __kmem_cache_create_args(name, size, &kmem_default_args, flags); } /** * kmem_cache_create - Create a kmem cache. * @__name: A string which is used in /proc/slabinfo to identify this cache. * @__object_size: The size of objects to be created in this cache. * @__args: Optional arguments, see &struct kmem_cache_args. Passing %NULL * means defaults will be used for all the arguments. * * This is currently implemented as a macro using ``_Generic()`` to call * either the new variant of the function, or a legacy one. * * The new variant has 4 parameters: * ``kmem_cache_create(name, object_size, args, flags)`` * * See __kmem_cache_create_args() which implements this. * * The legacy variant has 5 parameters: * ``kmem_cache_create(name, object_size, align, flags, ctor)`` * * The align and ctor parameters map to the respective fields of * &struct kmem_cache_args * * Context: Cannot be called within a interrupt, but can be interrupted. * * Return: a pointer to the cache on success, NULL on failure. */ #define kmem_cache_create(__name, __object_size, __args, ...) \ _Generic((__args), \ struct kmem_cache_args *: __kmem_cache_create_args, \ void *: __kmem_cache_default_args, \ default: __kmem_cache_create)(__name, __object_size, __args, __VA_ARGS__) void kmem_cache_destroy(struct kmem_cache *s); int kmem_cache_shrink(struct kmem_cache *s); /* * Please use this macro to create slab caches. Simply specify the * name of the structure and maybe some flags that are listed above. * * The alignment of the struct determines object alignment. If you * f.e. add ____cacheline_aligned_in_smp to the struct declaration * then the objects will be properly aligned in SMP configurations. */ #define KMEM_CACHE(__struct, __flags) \ __kmem_cache_create_args(#__struct, sizeof(struct __struct), \ &(struct kmem_cache_args) { \ .align = __alignof__(struct __struct), \ }, (__flags)) /* * To whitelist a single field for copying to/from usercopy, use this * macro instead for KMEM_CACHE() above. */ #define KMEM_CACHE_USERCOPY(__struct, __flags, __field) \ __kmem_cache_create_args(#__struct, sizeof(struct __struct), \ &(struct kmem_cache_args) { \ .align = __alignof__(struct __struct), \ .useroffset = offsetof(struct __struct, __field), \ .usersize = sizeof_field(struct __struct, __field), \ }, (__flags)) /* * Common kmalloc functions provided by all allocators */ void * __must_check krealloc_node_align_noprof(const void *objp, size_t new_size, unsigned long align, gfp_t flags, int nid) __realloc_size(2); #define krealloc_noprof(_o, _s, _f) krealloc_node_align_noprof(_o, _s, 1, _f, NUMA_NO_NODE) #define krealloc_node_align(...) alloc_hooks(krealloc_node_align_noprof(__VA_ARGS__)) #define krealloc_node(_o, _s, _f, _n) krealloc_node_align(_o, _s, 1, _f, _n) #define krealloc(...) krealloc_node(__VA_ARGS__, NUMA_NO_NODE) void kfree(const void *objp); void kfree_nolock(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T)) /** * ksize - Report actual allocation size of associated object * * @objp: Pointer returned from a prior kmalloc()-family allocation. * * This should not be used for writing beyond the originally requested * allocation size. Either use krealloc() or round up the allocation size * with kmalloc_size_roundup() prior to allocation. If this is used to * access beyond the originally requested allocation size, UBSAN_BOUNDS * and/or FORTIFY_SOURCE may trip, since they only know about the * originally allocated size via the __alloc_size attribute. */ size_t ksize(const void *objp); #ifdef CONFIG_PRINTK bool kmem_dump_obj(void *object); #else static inline bool kmem_dump_obj(void *object) { return false; } #endif /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. * Setting ARCH_DMA_MINALIGN in arch headers allows that. */ #ifdef ARCH_HAS_DMA_MINALIGN #if ARCH_DMA_MINALIGN > 8 && !defined(ARCH_KMALLOC_MINALIGN) #define ARCH_KMALLOC_MINALIGN ARCH_DMA_MINALIGN #endif #endif #ifndef ARCH_KMALLOC_MINALIGN #define ARCH_KMALLOC_MINALIGN __alignof__(unsigned long long) #elif ARCH_KMALLOC_MINALIGN > 8 #define KMALLOC_MIN_SIZE ARCH_KMALLOC_MINALIGN #define KMALLOC_SHIFT_LOW ilog2(KMALLOC_MIN_SIZE) #endif /* * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. * Intended for arches that get misalignment faults even for 64 bit integer * aligned buffers. */ #ifndef ARCH_SLAB_MINALIGN #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif /* * Arches can define this function if they want to decide the minimum slab * alignment at runtime. The value returned by the function must be a power * of two and >= ARCH_SLAB_MINALIGN. */ #ifndef arch_slab_minalign static inline unsigned int arch_slab_minalign(void) { return ARCH_SLAB_MINALIGN; } #endif /* * kmem_cache_alloc and friends return pointers aligned to ARCH_SLAB_MINALIGN. * kmalloc and friends return pointers aligned to both ARCH_KMALLOC_MINALIGN * and ARCH_SLAB_MINALIGN, but here we only assume the former alignment. */ #define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) #define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) #define __assume_page_alignment __assume_aligned(PAGE_SIZE) /* * Kmalloc array related definitions */ /* * SLUB directly allocates requests fitting in to an order-1 page * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_PAGE_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif /* Maximum allocatable size */ #define KMALLOC_MAX_SIZE (1UL << KMALLOC_SHIFT_MAX) /* Maximum size for which we actually use a slab cache */ #define KMALLOC_MAX_CACHE_SIZE (1UL << KMALLOC_SHIFT_HIGH) /* Maximum order allocatable via the slab allocator */ #define KMALLOC_MAX_ORDER (KMALLOC_SHIFT_MAX - PAGE_SHIFT) /* * Kmalloc subsystem. */ #ifndef KMALLOC_MIN_SIZE #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW) #endif /* * This restriction comes from byte sized index implementation. * Page size is normally 2^12 bytes and, in this case, if we want to use * byte sized index which can represent 2^8 entries, the size of the object * should be equal or greater to 2^12 / 2^8 = 2^4 = 16. * If minimum size of kmalloc is less than 16, we use it as minimum object * size and give up to use byte sized index. */ #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) #ifdef CONFIG_RANDOM_KMALLOC_CACHES #define RANDOM_KMALLOC_CACHES_NR 15 // # of cache copies #else #define RANDOM_KMALLOC_CACHES_NR 0 #endif /* * Whenever changing this, take care of that kmalloc_type() and * create_kmalloc_caches() still work as intended. * * KMALLOC_NORMAL can contain only unaccounted objects whereas KMALLOC_CGROUP * is for accounted but unreclaimable and non-dma objects. All the other * kmem caches can have both accounted and unaccounted objects. */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, #ifndef CONFIG_ZONE_DMA KMALLOC_DMA = KMALLOC_NORMAL, #endif #ifndef CONFIG_MEMCG KMALLOC_CGROUP = KMALLOC_NORMAL, #endif KMALLOC_RANDOM_START = KMALLOC_NORMAL, KMALLOC_RANDOM_END = KMALLOC_RANDOM_START + RANDOM_KMALLOC_CACHES_NR, #ifdef CONFIG_SLUB_TINY KMALLOC_RECLAIM = KMALLOC_NORMAL, #else KMALLOC_RECLAIM, #endif #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif #ifdef CONFIG_MEMCG KMALLOC_CGROUP, #endif NR_KMALLOC_TYPES }; typedef struct kmem_cache * kmem_buckets[KMALLOC_SHIFT_HIGH + 1]; extern kmem_buckets kmalloc_caches[NR_KMALLOC_TYPES]; /* * Define gfp bits that should not be set for KMALLOC_NORMAL. */ #define KMALLOC_NOT_NORMAL_BITS \ (__GFP_RECLAIMABLE | \ (IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \ (IS_ENABLED(CONFIG_MEMCG) ? __GFP_ACCOUNT : 0)) extern unsigned long random_kmalloc_seed; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags, unsigned long caller) { /* * The most common case is KMALLOC_NORMAL, so test for it * with a single branch for all the relevant flags. */ if (likely((flags & KMALLOC_NOT_NORMAL_BITS) == 0)) #ifdef CONFIG_RANDOM_KMALLOC_CACHES /* RANDOM_KMALLOC_CACHES_NR (=15) copies + the KMALLOC_NORMAL */ return KMALLOC_RANDOM_START + hash_64(caller ^ random_kmalloc_seed, ilog2(RANDOM_KMALLOC_CACHES_NR + 1)); #else return KMALLOC_NORMAL; #endif /* * At least one of the flags has to be set. Their priorities in * decreasing order are: * 1) __GFP_DMA * 2) __GFP_RECLAIMABLE * 3) __GFP_ACCOUNT */ if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA)) return KMALLOC_DMA; if (!IS_ENABLED(CONFIG_MEMCG) || (flags & __GFP_RECLAIMABLE)) return KMALLOC_RECLAIM; else return KMALLOC_CGROUP; } /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. * 0 = zero alloc * 1 = 65 .. 96 bytes * 2 = 129 .. 192 bytes * n = 2^(n-1)+1 .. 2^n * * Note: __kmalloc_index() is compile-time optimized, and not runtime optimized; * typical usage is via kmalloc_index() and therefore evaluated at compile-time. * Callers where !size_is_constant should only be test modules, where runtime * overheads of __kmalloc_index() can be tolerated. Also see kmalloc_slab(). */ static __always_inline unsigned int __kmalloc_index(size_t size, bool size_is_constant) { if (!size) return 0; if (size <= KMALLOC_MIN_SIZE) return KMALLOC_SHIFT_LOW; if (KMALLOC_MIN_SIZE <= 32 && size > 64 && size <= 96) return 1; if (KMALLOC_MIN_SIZE <= 64 && size > 128 && size <= 192) return 2; if (size <= 8) return 3; if (size <= 16) return 4; if (size <= 32) return 5; if (size <= 64) return 6; if (size <= 128) return 7; if (size <= 256) return 8; if (size <= 512) return 9; if (size <= 1024) return 10; if (size <= 2 * 1024) return 11; if (size <= 4 * 1024) return 12; if (size <= 8 * 1024) return 13; if (size <= 16 * 1024) return 14; if (size <= 32 * 1024) return 15; if (size <= 64 * 1024) return 16; if (size <= 128 * 1024) return 17; if (size <= 256 * 1024) return 18; if (size <= 512 * 1024) return 19; if (size <= 1024 * 1024) return 20; if (size <= 2 * 1024 * 1024) return 21; if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()"); else BUG(); /* Will never be reached. Needed because the compiler may complain */ return -1; } static_assert(PAGE_SHIFT <= 20); #define kmalloc_index(s) __kmalloc_index(s, true) #include <linux/alloc_tag.h> /** * kmem_cache_alloc - Allocate an object * @cachep: The cache to allocate from. * @flags: See kmalloc(). * * Allocate an object from this cache. * See kmem_cache_zalloc() for a shortcut of adding __GFP_ZERO to flags. * * Return: pointer to the new object or %NULL in case of error */ void *kmem_cache_alloc_noprof(struct kmem_cache *cachep, gfp_t flags) __assume_slab_alignment __malloc; #define kmem_cache_alloc(...) alloc_hooks(kmem_cache_alloc_noprof(__VA_ARGS__)) void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru, gfp_t gfpflags) __assume_slab_alignment __malloc; #define kmem_cache_alloc_lru(...) alloc_hooks(kmem_cache_alloc_lru_noprof(__VA_ARGS__)) /** * kmem_cache_charge - memcg charge an already allocated slab memory * @objp: address of the slab object to memcg charge * @gfpflags: describe the allocation context * * kmem_cache_charge allows charging a slab object to the current memcg, * primarily in cases where charging at allocation time might not be possible * because the target memcg is not known (i.e. softirq context) * * The objp should be pointer returned by the slab allocator functions like * kmalloc (with __GFP_ACCOUNT in flags) or kmem_cache_alloc. The memcg charge * behavior can be controlled through gfpflags parameter, which affects how the * necessary internal metadata can be allocated. Including __GFP_NOFAIL denotes * that overcharging is requested instead of failure, but is not applied for the * internal metadata allocation. * * There are several cases where it will return true even if the charging was * not done: * More specifically: * * 1. For !CONFIG_MEMCG or cgroup_disable=memory systems. * 2. Already charged slab objects. * 3. For slab objects from KMALLOC_NORMAL caches - allocated by kmalloc() * without __GFP_ACCOUNT * 4. Allocating internal metadata has failed * * Return: true if charge was successful otherwise false. */ bool kmem_cache_charge(void *objp, gfp_t gfpflags); void kmem_cache_free(struct kmem_cache *s, void *objp); kmem_buckets *kmem_buckets_create(const char *name, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); /* * Bulk allocation and freeing operations. These are accelerated in an * allocator specific way to avoid taking locks repeatedly or building * metadata structures unnecessarily. * * Note that interrupts must be enabled when calling these functions. */ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size, void **p); #define kmem_cache_alloc_bulk(...) alloc_hooks(kmem_cache_alloc_bulk_noprof(__VA_ARGS__)) static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; #define kmem_cache_alloc_node(...) alloc_hooks(kmem_cache_alloc_node_noprof(__VA_ARGS__)) struct slab_sheaf * kmem_cache_prefill_sheaf(struct kmem_cache *s, gfp_t gfp, unsigned int size); int kmem_cache_refill_sheaf(struct kmem_cache *s, gfp_t gfp, struct slab_sheaf **sheafp, unsigned int size); void kmem_cache_return_sheaf(struct kmem_cache *s, gfp_t gfp, struct slab_sheaf *sheaf); void *kmem_cache_alloc_from_sheaf_noprof(struct kmem_cache *cachep, gfp_t gfp, struct slab_sheaf *sheaf) __assume_slab_alignment __malloc; #define kmem_cache_alloc_from_sheaf(...) \ alloc_hooks(kmem_cache_alloc_from_sheaf_noprof(__VA_ARGS__)) unsigned int kmem_cache_sheaf_size(struct slab_sheaf *sheaf); /* * These macros allow declaring a kmem_buckets * parameter alongside size, which * can be compiled out with CONFIG_SLAB_BUCKETS=n so that a large number of call * sites don't have to pass NULL. */ #ifdef CONFIG_SLAB_BUCKETS #define DECL_BUCKET_PARAMS(_size, _b) size_t (_size), kmem_buckets *(_b) #define PASS_BUCKET_PARAMS(_size, _b) (_size), (_b) #define PASS_BUCKET_PARAM(_b) (_b) #else #define DECL_BUCKET_PARAMS(_size, _b) size_t (_size) #define PASS_BUCKET_PARAMS(_size, _b) (_size) #define PASS_BUCKET_PARAM(_b) NULL #endif /* * The following functions are not to be used directly and are intended only * for internal use from kmalloc() and kmalloc_node() * with the exception of kunit tests */ void *__kmalloc_noprof(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); void *__kmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) __assume_kmalloc_alignment __alloc_size(1); void *__kmalloc_cache_noprof(struct kmem_cache *s, gfp_t flags, size_t size) __assume_kmalloc_alignment __alloc_size(3); void *__kmalloc_cache_node_noprof(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) __assume_kmalloc_alignment __alloc_size(4); void *__kmalloc_large_noprof(size_t size, gfp_t flags) __assume_page_alignment __alloc_size(1); void *__kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) __assume_page_alignment __alloc_size(1); /** * kmalloc - allocate kernel memory * @size: how many bytes of memory are required. * @flags: describe the allocation context * * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN * bytes. For @size of power of two bytes, the alignment is also guaranteed * to be at least to the size. For other sizes, the alignment is guaranteed to * be at least the largest power-of-two divisor of @size. * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp_types.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` * * The recommended usage of the @flags is described at * :ref:`Documentation/core-api/memory-allocation.rst <memory_allocation>` * * Below is a brief outline of the most useful GFP flags * * %GFP_KERNEL * Allocate normal kernel ram. May sleep. * * %GFP_NOWAIT * Allocation will not sleep. * * %GFP_ATOMIC * Allocation will not sleep. May use emergency pools. * * Also it is possible to set different flags by OR'ing * in one or more of the following additional @flags: * * %__GFP_ZERO * Zero the allocated memory before returning. Also see kzalloc(). * * %__GFP_HIGH * This allocation has high priority and may use emergency pools. * * %__GFP_NOFAIL * Indicate that this allocation is in no way allowed to fail * (think twice before using). * * %__GFP_NORETRY * If memory is not immediately available, * then give up at once. * * %__GFP_NOWARN * If allocation fails, don't issue any warnings. * * %__GFP_RETRY_MAYFAIL * Try really hard to succeed the allocation but fail * eventually. */ static __always_inline __alloc_size(1) void *kmalloc_noprof(size_t size, gfp_t flags) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) return __kmalloc_large_noprof(size, flags); index = kmalloc_index(size); return __kmalloc_cache_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, size); } return __kmalloc_noprof(size, flags); } #define kmalloc(...) alloc_hooks(kmalloc_noprof(__VA_ARGS__)) void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node); #define kmalloc_nolock(...) alloc_hooks(kmalloc_nolock_noprof(__VA_ARGS__)) #define kmem_buckets_alloc(_b, _size, _flags) \ alloc_hooks(__kmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) #define kmem_buckets_alloc_track_caller(_b, _size, _flags) \ alloc_hooks(__kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE, _RET_IP_)) static __always_inline __alloc_size(1) void *kmalloc_node_noprof(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) return __kmalloc_large_node_noprof(size, flags, node); index = kmalloc_index(size); return __kmalloc_cache_node_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, node, size); } return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node); } #define kmalloc_node(...) alloc_hooks(kmalloc_node_noprof(__VA_ARGS__)) /** * kmalloc_array - allocate memory for an array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ static inline __alloc_size(1, 2) void *kmalloc_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 kmalloc_noprof(bytes, flags); } #define kmalloc_array(...) alloc_hooks(kmalloc_array_noprof(__VA_ARGS__)) /** * krealloc_array - reallocate memory for an array. * @p: pointer to the memory chunk to reallocate * @new_n: new number of elements to alloc * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) * * 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. * * See krealloc_noprof() for further details. * * In any case, the contents of the object pointed to are preserved up to the * lesser of the new and old sizes. */ static inline __realloc_size(2, 3) void * __must_check krealloc_array_noprof(void *p, size_t new_n, size_t new_size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; return krealloc_noprof(p, bytes, flags); } #define krealloc_array(...) alloc_hooks(krealloc_array_noprof(__VA_ARGS__)) /** * kcalloc - allocate memory for an array. The memory is set to zero. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ #define kcalloc(n, size, flags) kmalloc_array(n, size, (flags) | __GFP_ZERO) void *__kmalloc_node_track_caller_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node, unsigned long caller) __alloc_size(1); #define kmalloc_node_track_caller_noprof(size, flags, node, caller) \ __kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node, caller) #define kmalloc_node_track_caller(...) \ alloc_hooks(kmalloc_node_track_caller_noprof(__VA_ARGS__, _RET_IP_)) /* * kmalloc_track_caller is a special version of kmalloc that records the * calling function of the routine calling it for slab leak tracking instead * of just the calling function (confusing, eh?). * It's useful when the call to kmalloc comes from a widely-used standard * allocator where we care about the real place the memory allocation * request comes from. */ #define kmalloc_track_caller(...) kmalloc_node_track_caller(__VA_ARGS__, NUMA_NO_NODE) #define kmalloc_track_caller_noprof(...) \ kmalloc_node_track_caller_noprof(__VA_ARGS__, NUMA_NO_NODE, _RET_IP_) static inline __alloc_size(1, 2) void *kmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) return kmalloc_node_noprof(bytes, flags, node); return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(bytes, NULL), flags, node); } #define kmalloc_array_node(...) alloc_hooks(kmalloc_array_node_noprof(__VA_ARGS__)) #define kcalloc_node(_n, _size, _flags, _node) \ kmalloc_array_node(_n, _size, (_flags) | __GFP_ZERO, _node) /* * Shortcuts */ #define kmem_cache_zalloc(_k, _flags) kmem_cache_alloc(_k, (_flags)|__GFP_ZERO) /** * kzalloc - allocate memory. The memory is set to zero. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ static inline __alloc_size(1) void *kzalloc_noprof(size_t size, gfp_t flags) { return kmalloc_noprof(size, flags | __GFP_ZERO); } #define kzalloc(...) alloc_hooks(kzalloc_noprof(__VA_ARGS__)) #define kzalloc_node(_size, _flags, _node) kmalloc_node(_size, (_flags)|__GFP_ZERO, _node) void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), unsigned long align, gfp_t flags, int node) __alloc_size(1); #define kvmalloc_node_align_noprof(_size, _align, _flags, _node) \ __kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, NULL), _align, _flags, _node) #define kvmalloc_node_align(...) \ alloc_hooks(kvmalloc_node_align_noprof(__VA_ARGS__)) #define kvmalloc_node(_s, _f, _n) kvmalloc_node_align(_s, 1, _f, _n) #define kvmalloc(...) kvmalloc_node(__VA_ARGS__, NUMA_NO_NODE) #define kvzalloc(_size, _flags) kvmalloc(_size, (_flags)|__GFP_ZERO) #define kvzalloc_node(_size, _flags, _node) kvmalloc_node(_size, (_flags)|__GFP_ZERO, _node) #define kmem_buckets_valloc(_b, _size, _flags) \ alloc_hooks(__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), 1, _flags, NUMA_NO_NODE)) static inline __alloc_size(1, 2) void * kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return kvmalloc_node_align_noprof(bytes, 1, flags, node); } #define kvmalloc_array_noprof(...) kvmalloc_array_node_noprof(__VA_ARGS__, NUMA_NO_NODE) #define kvcalloc_node_noprof(_n,_s,_f,_node) kvmalloc_array_node_noprof(_n,_s,(_f)|__GFP_ZERO,_node) #define kvcalloc_noprof(...) kvcalloc_node_noprof(__VA_ARGS__, NUMA_NO_NODE) #define kvmalloc_array(...) alloc_hooks(kvmalloc_array_noprof(__VA_ARGS__)) #define kvcalloc_node(...) alloc_hooks(kvcalloc_node_noprof(__VA_ARGS__)) #define kvcalloc(...) alloc_hooks(kvcalloc_noprof(__VA_ARGS__)) void *kvrealloc_node_align_noprof(const void *p, size_t size, unsigned long align, gfp_t flags, int nid) __realloc_size(2); #define kvrealloc_node_align(...) \ alloc_hooks(kvrealloc_node_align_noprof(__VA_ARGS__)) #define kvrealloc_node(_p, _s, _f, _n) kvrealloc_node_align(_p, _s, 1, _f, _n) #define kvrealloc(...) kvrealloc_node(__VA_ARGS__, NUMA_NO_NODE) extern void kvfree(const void *addr); DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) extern void kvfree_sensitive(const void *addr, size_t len); unsigned int kmem_cache_size(struct kmem_cache *s); #ifndef CONFIG_KVFREE_RCU_BATCHED static inline void kvfree_rcu_barrier(void) { rcu_barrier(); } static inline void kfree_rcu_scheduler_running(void) { } #else void kvfree_rcu_barrier(void); void kfree_rcu_scheduler_running(void); #endif /** * kmalloc_size_roundup - Report allocation bucket size for the given size * * @size: Number of bytes to round up from. * * This returns the number of bytes that would be available in a kmalloc() * allocation of @size bytes. For example, a 126 byte request would be * rounded up to the next sized kmalloc bucket, 128 bytes. (This is strictly * for the general-purpose kmalloc()-based allocations, and is not for the * pre-sized kmem_cache_alloc()-based allocations.) * * Use this to kmalloc() the full bucket size ahead of time instead of using * ksize() to query the size after an allocation. */ size_t kmalloc_size_roundup(size_t size); void __init kmem_cache_init_late(void); void __init kvfree_rcu_init(void); #endif /* _LINUX_SLAB_H */ |
| 14 14 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_IVERSION_H #define _LINUX_IVERSION_H #include <linux/fs.h> /* * The inode->i_version field: * --------------------------- * The change attribute (i_version) is mandated by NFSv4 and is mostly for * knfsd, but is also used for other purposes (e.g. IMA). The i_version must * appear larger to observers if there was an explicit change to the inode's * data or metadata since it was last queried. * * An explicit change is one that would ordinarily result in a change to the * inode status change time (aka ctime). i_version must appear to change, even * if the ctime does not (since the whole point is to avoid missing updates due * to timestamp granularity). If POSIX or other relevant spec mandates that the * ctime must change due to an operation, then the i_version counter must be * incremented as well. * * Making the i_version update completely atomic with the operation itself would * be prohibitively expensive. Traditionally the kernel has updated the times on * directories after an operation that changes its contents. For regular files, * the ctime is usually updated before the data is copied into the cache for a * write. This means that there is a window of time when an observer can * associate a new timestamp with old file contents. Since the purpose of the * i_version is to allow for better cache coherency, the i_version must always * be updated after the results of the operation are visible. Updating it before * and after a change is also permitted. (Note that no filesystems currently do * this. Fixing that is a work-in-progress). * * Observers see the i_version as a 64-bit number that never decreases. If it * remains the same since it was last checked, then nothing has changed in the * inode. If it's different then something has changed. Observers cannot infer * anything about the nature or magnitude of the changes from the value, only * that the inode has changed in some fashion. * * Not all filesystems properly implement the i_version counter. Subsystems that * want to use i_version field on an inode should first check whether the * filesystem sets the SB_I_VERSION flag (usually via the IS_I_VERSION macro). * * Those that set SB_I_VERSION will automatically have their i_version counter * incremented on writes to normal files. If the SB_I_VERSION is not set, then * the VFS will not touch it on writes, and the filesystem can use it how it * wishes. Note that the filesystem is always responsible for updating the * i_version on namespace changes in directories (mkdir, rmdir, unlink, etc.). * We consider these sorts of filesystems to have a kernel-managed i_version. * * It may be impractical for filesystems to keep i_version updates atomic with * respect to the changes that cause them. They should, however, guarantee * that i_version updates are never visible before the changes that caused * them. Also, i_version updates should never be delayed longer than it takes * the original change to reach disk. * * This implementation uses the low bit in the i_version field as a flag to * track when the value has been queried. If it has not been queried since it * was last incremented, we can skip the increment in most cases. * * In the event that we're updating the ctime, we will usually go ahead and * bump the i_version anyway. Since that has to go to stable storage in some * fashion, we might as well increment it as well. * * With this implementation, the value should always appear to observers to * increase over time if the file has changed. It's recommended to use * inode_eq_iversion() helper to compare values. * * Note that some filesystems (e.g. NFS and AFS) just use the field to store * a server-provided value (for the most part). For that reason, those * filesystems do not set SB_I_VERSION. These filesystems are considered to * have a self-managed i_version. * * Persistently storing the i_version * ---------------------------------- * Queries of the i_version field are not gated on them hitting the backing * store. It's always possible that the host could crash after allowing * a query of the value but before it has made it to disk. * * To mitigate this problem, filesystems should always use * inode_set_iversion_queried when loading an existing inode from disk. This * ensures that the next attempted inode increment will result in the value * changing. * * Storing the value to disk therefore does not count as a query, so those * filesystems should use inode_peek_iversion to grab the value to be stored. * There is no need to flag the value as having been queried in that case. */ /* * We borrow the lowest bit in the i_version to use as a flag to tell whether * it has been queried since we last incremented it. If it has, then we must * increment it on the next change. After that, we can clear the flag and * avoid incrementing it again until it has again been queried. */ #define I_VERSION_QUERIED_SHIFT (1) #define I_VERSION_QUERIED (1ULL << (I_VERSION_QUERIED_SHIFT - 1)) #define I_VERSION_INCREMENT (1ULL << I_VERSION_QUERIED_SHIFT) /** * inode_set_iversion_raw - set i_version to the specified raw value * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val. This function is for use by * filesystems that self-manage the i_version. * * For example, the NFS client stores its NFSv4 change attribute in this way, * and the AFS client stores the data_version from the server here. */ static inline void inode_set_iversion_raw(struct inode *inode, u64 val) { atomic64_set(&inode->i_version, val); } /** * inode_peek_iversion_raw - grab a "raw" iversion value * @inode: inode from which i_version should be read * * Grab a "raw" inode->i_version value and return it. The i_version is not * flagged or converted in any way. This is mostly used to access a self-managed * i_version. * * With those filesystems, we want to treat the i_version as an entirely * opaque value. */ static inline u64 inode_peek_iversion_raw(const struct inode *inode) { return atomic64_read(&inode->i_version); } /** * inode_set_max_iversion_raw - update i_version new value is larger * @inode: inode to set * @val: new i_version to set * * Some self-managed filesystems (e.g Ceph) will only update the i_version * value if the new value is larger than the one we already have. */ static inline void inode_set_max_iversion_raw(struct inode *inode, u64 val) { u64 cur = inode_peek_iversion_raw(inode); do { if (cur > val) break; } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, val)); } /** * inode_set_iversion - set i_version to a particular value * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val. This function is for filesystems with * a kernel-managed i_version, for initializing a newly-created inode from * scratch. * * In this case, we do not set the QUERIED flag since we know that this value * has never been queried. */ static inline void inode_set_iversion(struct inode *inode, u64 val) { inode_set_iversion_raw(inode, val << I_VERSION_QUERIED_SHIFT); } /** * inode_set_iversion_queried - set i_version to a particular value as quereied * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val, and flag it for increment on the next * change. * * Filesystems that persistently store the i_version on disk should use this * when loading an existing inode from disk. * * When loading in an i_version value from a backing store, we can't be certain * that it wasn't previously viewed before being stored. Thus, we must assume * that it was, to ensure that we don't end up handing out the same value for * different versions of the same inode. */ static inline void inode_set_iversion_queried(struct inode *inode, u64 val) { inode_set_iversion_raw(inode, (val << I_VERSION_QUERIED_SHIFT) | I_VERSION_QUERIED); } bool inode_maybe_inc_iversion(struct inode *inode, bool force); /** * inode_inc_iversion - forcibly increment i_version * @inode: inode that needs to be updated * * Forcbily increment the i_version field. This always results in a change to * the observable value. */ static inline void inode_inc_iversion(struct inode *inode) { inode_maybe_inc_iversion(inode, true); } /** * inode_iversion_need_inc - is the i_version in need of being incremented? * @inode: inode to check * * Returns whether the inode->i_version counter needs incrementing on the next * change. Just fetch the value and check the QUERIED flag. */ static inline bool inode_iversion_need_inc(struct inode *inode) { return inode_peek_iversion_raw(inode) & I_VERSION_QUERIED; } /** * inode_inc_iversion_raw - forcibly increment raw i_version * @inode: inode that needs to be updated * * Forcbily increment the raw i_version field. This always results in a change * to the raw value. * * NFS will use the i_version field to store the value from the server. It * mostly treats it as opaque, but in the case where it holds a write * delegation, it must increment the value itself. This function does that. */ static inline void inode_inc_iversion_raw(struct inode *inode) { atomic64_inc(&inode->i_version); } /** * inode_peek_iversion - read i_version without flagging it to be incremented * @inode: inode from which i_version should be read * * Read the inode i_version counter for an inode without registering it as a * query. * * This is typically used by local filesystems that need to store an i_version * on disk. In that situation, it's not necessary to flag it as having been * viewed, as the result won't be used to gauge changes from that point. */ static inline u64 inode_peek_iversion(const struct inode *inode) { return inode_peek_iversion_raw(inode) >> I_VERSION_QUERIED_SHIFT; } /* * For filesystems without any sort of change attribute, the best we can * do is fake one up from the ctime: */ static inline u64 time_to_chattr(const struct timespec64 *t) { u64 chattr = t->tv_sec; chattr <<= 32; chattr += t->tv_nsec; return chattr; } u64 inode_query_iversion(struct inode *inode); /** * inode_eq_iversion_raw - check whether the raw i_version counter has changed * @inode: inode to check * @old: old value to check against its i_version * * Compare the current raw i_version counter with a previous one. Returns true * if they are the same or false if they are different. */ static inline bool inode_eq_iversion_raw(const struct inode *inode, u64 old) { return inode_peek_iversion_raw(inode) == old; } /** * inode_eq_iversion - check whether the i_version counter has changed * @inode: inode to check * @old: old value to check against its i_version * * Compare an i_version counter with a previous one. Returns true if they are * the same, and false if they are different. * * Note that we don't need to set the QUERIED flag in this case, as the value * in the inode is not being recorded for later use. */ static inline bool inode_eq_iversion(const struct inode *inode, u64 old) { return inode_peek_iversion(inode) == old; } #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0+ /* * ext4_jbd2.h * * Written by Stephen C. Tweedie <sct@redhat.com>, 1999 * * Copyright 1998--1999 Red Hat corp --- All Rights Reserved * * Ext4-specific journaling extensions. */ #ifndef _EXT4_JBD2_H #define _EXT4_JBD2_H #include <linux/fs.h> #include <linux/jbd2.h> #include "ext4.h" #define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal) /* Define the number of blocks we need to account to a transaction to * modify one block of data. * * We may have to touch one inode, one bitmap buffer, up to three * indirection blocks, the group and superblock summaries, and the data * block to complete the transaction. * * For extents-enabled fs we may have to allocate and modify up to * 5 levels of tree, data block (for each of these we need bitmap + group * summaries), root which is stored in the inode, sb */ #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb) \ (ext4_has_feature_extents(sb) ? 20U : 8U) /* Extended attribute operations touch at most two data buffers, * two bitmap buffers, and two group summaries, in addition to the inode * and the superblock, which are already accounted for. */ #define EXT4_XATTR_TRANS_BLOCKS 6U /* Define the minimum size for a transaction which modifies data. This * needs to take into account the fact that we may end up modifying two * quota files too (one for the group, one for the user quota). The * superblock only gets updated once, of course, so don't bother * counting that again for the quota updates. */ #define EXT4_DATA_TRANS_BLOCKS(sb) (EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \ EXT4_XATTR_TRANS_BLOCKS - 2 + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* * Define the number of metadata blocks we need to account to modify data. * * This include super block, inode block, quota blocks and xattr blocks */ #define EXT4_META_TRANS_BLOCKS(sb) (EXT4_XATTR_TRANS_BLOCKS + \ EXT4_MAXQUOTAS_TRANS_BLOCKS(sb)) /* Define an arbitrary limit for the amount of data we will anticipate * writing to any given transaction. For unbounded transactions such as * write(2) and truncate(2) we can write more than this, but we always * start off at the maximum transaction size and grow the transaction * optimistically as we go. */ #define EXT4_MAX_TRANS_DATA 64U /* We break up a large truncate or write transaction once the handle's * buffer credits gets this low, we need either to extend the * transaction or to start a new one. Reserve enough space here for * inode, bitmap, superblock, group and indirection updates for at least * one block, plus two quota updates. Quota allocations are not * needed. */ #define EXT4_RESERVE_TRANS_BLOCKS 12U /* * Number of credits needed if we need to insert an entry into a * directory. For each new index block, we need 4 blocks (old index * block, new index block, bitmap block, bg summary). For normal * htree directories there are 2 levels; if the largedir feature * enabled it's 3 levels. */ #define EXT4_INDEX_EXTRA_TRANS_BLOCKS 12U #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was * allocated so we need to update only data block */ #define EXT4_QUOTA_TRANS_BLOCKS(sb) ((ext4_quota_capable(sb)) ? 1 : 0) /* Amount of blocks needed for quota insert/delete - we do some block writes * but inode, sb and group updates are done only once */ #define EXT4_QUOTA_INIT_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_INIT_REWRITE) : 0) #define EXT4_QUOTA_DEL_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\ (DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\ +3+DQUOT_DEL_REWRITE) : 0) #else #define EXT4_QUOTA_TRANS_BLOCKS(sb) 0 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0 #define EXT4_QUOTA_DEL_BLOCKS(sb) 0 #endif #define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb)) #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb)) #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb)) /* * Ext4 handle operation types -- for logging purposes */ #define EXT4_HT_MISC 0 #define EXT4_HT_INODE 1 #define EXT4_HT_WRITE_PAGE 2 #define EXT4_HT_MAP_BLOCKS 3 #define EXT4_HT_DIR 4 #define EXT4_HT_TRUNCATE 5 #define EXT4_HT_QUOTA 6 #define EXT4_HT_RESIZE 7 #define EXT4_HT_MIGRATE 8 #define EXT4_HT_MOVE_EXTENTS 9 #define EXT4_HT_XATTR 10 #define EXT4_HT_EXT_CONVERT 11 #define EXT4_HT_MAX 12 int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); /* * On success, We end up with an outstanding reference count against * iloc->bh. This _must_ be cleaned up later. */ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc); #define ext4_mark_inode_dirty(__h, __i) \ __ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__) int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode, const char *func, unsigned int line); int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc *iloc); /* * Wrapper functions with which ext4 calls into JBD. */ int __ext4_journal_get_write_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type); int __ext4_forget(const char *where, unsigned int line, handle_t *handle, int is_metadata, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t blocknr); int __ext4_journal_get_create_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type); int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct buffer_head *bh); #define ext4_journal_get_write_access(handle, sb, bh, trigger_type) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (sb), \ (bh), (trigger_type)) #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \ __ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \ (bh), (block_nr)) #define ext4_journal_get_create_access(handle, sb, bh, trigger_type) \ __ext4_journal_get_create_access(__func__, __LINE__, (handle), (sb), \ (bh), (trigger_type)) #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) handle_t *__ext4_journal_start_sb(struct inode *inode, struct super_block *sb, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); #define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096) /* Note: Do not use this for NULL handles. This is only to determine if * a properly allocated handle is using a journal or not. */ static inline int ext4_handle_valid(handle_t *handle) { if ((unsigned long)handle < EXT4_NOJOURNAL_MAX_REF_COUNT) return 0; return 1; } static inline void ext4_handle_sync(handle_t *handle) { if (ext4_handle_valid(handle)) handle->h_sync = 1; } static inline int ext4_handle_is_aborted(handle_t *handle) { if (ext4_handle_valid(handle)) return is_handle_aborted(handle); return 0; } static inline int ext4_free_metadata_revoke_credits(struct super_block *sb, int blocks) { /* Freeing each metadata block can result in freeing one cluster */ return blocks * EXT4_SB(sb)->s_cluster_ratio; } static inline int ext4_trans_default_revoke_credits(struct super_block *sb) { return ext4_free_metadata_revoke_credits(sb, 8); } #define ext4_journal_start_sb(sb, type, nblocks) \ __ext4_journal_start_sb(NULL, (sb), __LINE__, (type), (nblocks), 0,\ ext4_trans_default_revoke_credits(sb)) #define ext4_journal_start(inode, type, nblocks) \ __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0, \ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks)\ __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks),\ ext4_trans_default_revoke_credits((inode)->i_sb)) #define ext4_journal_start_with_revoke(inode, type, blocks, revoke_creds) \ __ext4_journal_start((inode), __LINE__, (type), (blocks), 0, \ (revoke_creds)) static inline handle_t *__ext4_journal_start(struct inode *inode, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds) { return __ext4_journal_start_sb(inode, inode->i_sb, line, type, blocks, rsv_blocks, revoke_creds); } #define ext4_journal_stop(handle) \ __ext4_journal_stop(__func__, __LINE__, (handle)) #define ext4_journal_start_reserved(handle, type) \ __ext4_journal_start_reserved((handle), __LINE__, (type)) handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, int type); static inline handle_t *ext4_journal_current_handle(void) { return journal_current_handle(); } static inline int ext4_journal_extend(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2_journal_extend(handle, nblocks, revoke); return 0; } static inline int ext4_journal_restart(handle_t *handle, int nblocks, int revoke) { if (ext4_handle_valid(handle)) return jbd2__journal_restart(handle, nblocks, revoke, GFP_NOFS); return 0; } int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, int extend_cred, int revoke_cred); /* * Ensure @handle has at least @check_creds credits available. If not, * transaction will be extended or restarted to contain at least @extend_cred * credits. Before restarting transaction @fn is executed to allow for cleanup * before the transaction is restarted. * * The return value is < 0 in case of error, 0 in case the handle has enough * credits or transaction extension succeeded, 1 in case transaction had to be * restarted. */ #define ext4_journal_ensure_credits_fn(handle, check_cred, extend_cred, \ revoke_cred, fn) \ ({ \ __label__ __ensure_end; \ int err = __ext4_journal_ensure_credits((handle), (check_cred), \ (extend_cred), (revoke_cred)); \ \ if (err <= 0) \ goto __ensure_end; \ err = (fn); \ if (err < 0) \ goto __ensure_end; \ err = ext4_journal_restart((handle), (extend_cred), (revoke_cred)); \ if (err == 0) \ err = 1; \ __ensure_end: \ err; \ }) /* * Ensure given handle has at least requested amount of credits available, * possibly restarting transaction if needed. We also make sure the transaction * has space for at least ext4_trans_default_revoke_credits(sb) revoke records * as freeing one or two blocks is very common pattern and requesting this is * very cheap. */ static inline int ext4_journal_ensure_credits(handle_t *handle, int credits, int revoke_creds) { return ext4_journal_ensure_credits_fn(handle, credits, credits, revoke_creds, 0); } static inline int ext4_journal_blocks_per_folio(struct inode *inode) { if (EXT4_JOURNAL(inode) != NULL) return jbd2_journal_blocks_per_folio(inode); return 0; } static inline int ext4_journal_force_commit(journal_t *journal) { if (journal) return jbd2_journal_force_commit(journal); return 0; } static inline int ext4_jbd2_inode_add_write(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_write(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline int ext4_jbd2_inode_add_wait(handle_t *handle, struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) return jbd2_journal_inode_ranged_wait(handle, EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline void ext4_update_inode_fsync_trans(handle_t *handle, struct inode *inode, int datasync) { struct ext4_inode_info *ei = EXT4_I(inode); if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) { ei->i_sync_tid = handle->h_transaction->t_tid; if (datasync) ei->i_datasync_tid = handle->h_transaction->t_tid; } } /* super.c */ int ext4_force_commit(struct super_block *sb); /* * Ext4 inode journal modes */ #define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */ #define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */ #define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */ int ext4_inode_journal_mode(struct inode *inode); static inline int ext4_should_journal_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE; } static inline int ext4_should_order_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE; } static inline int ext4_should_writeback_data(struct inode *inode) { return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE; } static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks) { if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) return 0; if (!ext4_should_journal_data(inode)) return 0; /* * Data blocks in one extent are contiguous, just account for partial * clusters at extent boundaries */ return blocks + 2*(EXT4_SB(inode->i_sb)->s_cluster_ratio - 1); } /* * This function controls whether or not we should try to go down the * dioread_nolock code paths, which makes it safe to avoid taking * i_rwsem for direct I/O reads. This only works for extent-based * files, and it doesn't work if data journaling is enabled, since the * dioread_nolock code uses b_private to pass information back to the * I/O completion handler, and this conflicts with the jbd's use of * b_private. */ static inline int ext4_should_dioread_nolock(struct inode *inode) { if (!test_opt(inode->i_sb, DIOREAD_NOLOCK)) return 0; if (!S_ISREG(inode->i_mode)) return 0; if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return 0; if (ext4_should_journal_data(inode)) return 0; /* temporary fix to prevent generic/422 test failures */ if (!test_opt(inode->i_sb, DELALLOC)) return 0; return 1; } /* * Pass journal explicitly as it may not be cached in the sbi->s_journal in some * cases */ static inline int ext4_journal_destroy(struct ext4_sb_info *sbi, journal_t *journal) { int err = 0; /* * At this point only two things can be operating on the journal. * JBD2 thread performing transaction commit and s_sb_upd_work * issuing sb update through the journal. Once we set * EXT4_JOURNAL_DESTROY, new ext4_handle_error() calls will not * queue s_sb_upd_work and ext4_force_commit() makes sure any * ext4_handle_error() calls from the running transaction commit are * finished. Hence no new s_sb_upd_work can be queued after we * flush it here. */ ext4_set_mount_flag(sbi->s_sb, EXT4_MF_JOURNAL_DESTROY); ext4_force_commit(sbi->s_sb); flush_work(&sbi->s_sb_upd_work); err = jbd2_journal_destroy(journal); sbi->s_journal = NULL; return err; } #endif /* _EXT4_JBD2_H */ |
| 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/super.c * * Copyright (C) 1991, 1992 Linus Torvalds * * super.c contains code to handle: - mount structures * - super-block tables * - filesystem drivers list * - mount system call * - umount system call * - ustat system call * * GK 2/5/95 - Changed to support mounting the root fs via NFS * * Added kerneld support: Jacques Gelinas and Bjorn Ekwall * Added change_root: Werner Almesberger & Hans Lermen, Feb '96 * Added options to /proc/mounts: * Torbjörn Lindh (torbjorn.lindh@gopta.se), April 14, 1996. * Added devfs support: Richard Gooch <rgooch@atnf.csiro.au>, 13-JAN-1998 * Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000 */ #include <linux/export.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/writeback.h> /* for the emergency remount stuff */ #include <linux/idr.h> #include <linux/mutex.h> #include <linux/backing-dev.h> #include <linux/rculist_bl.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/lockdep.h> #include <linux/user_namespace.h> #include <linux/fs_context.h> #include <uapi/linux/mount.h> #include "internal.h" static int thaw_super_locked(struct super_block *sb, enum freeze_holder who, const void *freeze_owner); static LIST_HEAD(super_blocks); static DEFINE_SPINLOCK(sb_lock); static char *sb_writers_name[SB_FREEZE_LEVELS] = { "sb_writers", "sb_pagefaults", "sb_internal", }; static inline void __super_lock(struct super_block *sb, bool excl) { if (excl) down_write(&sb->s_umount); else down_read(&sb->s_umount); } static inline void super_unlock(struct super_block *sb, bool excl) { if (excl) up_write(&sb->s_umount); else up_read(&sb->s_umount); } static inline void __super_lock_excl(struct super_block *sb) { __super_lock(sb, true); } static inline void super_unlock_excl(struct super_block *sb) { super_unlock(sb, true); } static inline void super_unlock_shared(struct super_block *sb) { super_unlock(sb, false); } static bool super_flags(const struct super_block *sb, unsigned int flags) { /* * Pairs with smp_store_release() in super_wake() and ensures * that we see @flags after we're woken. */ return smp_load_acquire(&sb->s_flags) & flags; } /** * super_lock - wait for superblock to become ready and lock it * @sb: superblock to wait for * @excl: whether exclusive access is required * * If the superblock has neither passed through vfs_get_tree() or * generic_shutdown_super() yet wait for it to happen. Either superblock * creation will succeed and SB_BORN is set by vfs_get_tree() or we're * woken and we'll see SB_DYING. * * The caller must have acquired a temporary reference on @sb->s_count. * * Return: The function returns true if SB_BORN was set and with * s_umount held. The function returns false if SB_DYING was * set and without s_umount held. */ static __must_check bool super_lock(struct super_block *sb, bool excl) { lockdep_assert_not_held(&sb->s_umount); /* wait until the superblock is ready or dying */ wait_var_event(&sb->s_flags, super_flags(sb, SB_BORN | SB_DYING)); /* Don't pointlessly acquire s_umount. */ if (super_flags(sb, SB_DYING)) return false; __super_lock(sb, excl); /* * Has gone through generic_shutdown_super() in the meantime. * @sb->s_root is NULL and @sb->s_active is 0. No one needs to * grab a reference to this. Tell them so. */ if (sb->s_flags & SB_DYING) { super_unlock(sb, excl); return false; } WARN_ON_ONCE(!(sb->s_flags & SB_BORN)); return true; } /* wait and try to acquire read-side of @sb->s_umount */ static inline bool super_lock_shared(struct super_block *sb) { return super_lock(sb, false); } /* wait and try to acquire write-side of @sb->s_umount */ static inline bool super_lock_excl(struct super_block *sb) { return super_lock(sb, true); } /* wake waiters */ #define SUPER_WAKE_FLAGS (SB_BORN | SB_DYING | SB_DEAD) static void super_wake(struct super_block *sb, unsigned int flag) { WARN_ON_ONCE((flag & ~SUPER_WAKE_FLAGS)); WARN_ON_ONCE(hweight32(flag & SUPER_WAKE_FLAGS) > 1); /* * Pairs with smp_load_acquire() in super_lock() to make sure * all initializations in the superblock are seen by the user * seeing SB_BORN sent. */ smp_store_release(&sb->s_flags, sb->s_flags | flag); /* * Pairs with the barrier in prepare_to_wait_event() to make sure * ___wait_var_event() either sees SB_BORN set or * waitqueue_active() check in wake_up_var() sees the waiter. */ smp_mb(); wake_up_var(&sb->s_flags); } /* * One thing we have to be careful of with a per-sb shrinker is that we don't * drop the last active reference to the superblock from within the shrinker. * If that happens we could trigger unregistering the shrinker from within the * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we * take a passive reference to the superblock to avoid this from occurring. */ static unsigned long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { struct super_block *sb; long fs_objects = 0; long total_objects; long freed = 0; long dentries; long inodes; sb = shrink->private_data; /* * Deadlock avoidance. We may hold various FS locks, and we don't want * to recurse into the FS that called us in clear_inode() and friends.. */ if (!(sc->gfp_mask & __GFP_FS)) return SHRINK_STOP; if (!super_trylock_shared(sb)) return SHRINK_STOP; if (sb->s_op->nr_cached_objects) fs_objects = sb->s_op->nr_cached_objects(sb, sc); inodes = list_lru_shrink_count(&sb->s_inode_lru, sc); dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc); total_objects = dentries + inodes + fs_objects; if (!total_objects) total_objects = 1; /* proportion the scan between the caches */ dentries = mult_frac(sc->nr_to_scan, dentries, total_objects); inodes = mult_frac(sc->nr_to_scan, inodes, total_objects); fs_objects = mult_frac(sc->nr_to_scan, fs_objects, total_objects); /* * prune the dcache first as the icache is pinned by it, then * prune the icache, followed by the filesystem specific caches * * Ensure that we always scan at least one object - memcg kmem * accounting uses this to fully empty the caches. */ sc->nr_to_scan = dentries + 1; freed = prune_dcache_sb(sb, sc); sc->nr_to_scan = inodes + 1; freed += prune_icache_sb(sb, sc); if (fs_objects) { sc->nr_to_scan = fs_objects + 1; freed += sb->s_op->free_cached_objects(sb, sc); } super_unlock_shared(sb); return freed; } static unsigned long super_cache_count(struct shrinker *shrink, struct shrink_control *sc) { struct super_block *sb; long total_objects = 0; sb = shrink->private_data; /* * We don't call super_trylock_shared() here as it is a scalability * bottleneck, so we're exposed to partial setup state. The shrinker * rwsem does not protect filesystem operations backing * list_lru_shrink_count() or s_op->nr_cached_objects(). Counts can * change between super_cache_count and super_cache_scan, so we really * don't need locks here. * * However, if we are currently mounting the superblock, the underlying * filesystem might be in a state of partial construction and hence it * is dangerous to access it. super_trylock_shared() uses a SB_BORN check * to avoid this situation, so do the same here. The memory barrier is * matched with the one in mount_fs() as we don't hold locks here. */ if (!(sb->s_flags & SB_BORN)) return 0; smp_rmb(); if (sb->s_op && sb->s_op->nr_cached_objects) total_objects = sb->s_op->nr_cached_objects(sb, sc); total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc); total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc); if (!total_objects) return SHRINK_EMPTY; total_objects = vfs_pressure_ratio(total_objects); return total_objects; } static void destroy_super_work(struct work_struct *work) { struct super_block *s = container_of(work, struct super_block, destroy_work); fsnotify_sb_free(s); security_sb_free(s); put_user_ns(s->s_user_ns); kfree(s->s_subtype); for (int i = 0; i < SB_FREEZE_LEVELS; i++) percpu_free_rwsem(&s->s_writers.rw_sem[i]); kfree(s); } static void destroy_super_rcu(struct rcu_head *head) { struct super_block *s = container_of(head, struct super_block, rcu); INIT_WORK(&s->destroy_work, destroy_super_work); schedule_work(&s->destroy_work); } /* Free a superblock that has never been seen by anyone */ static void destroy_unused_super(struct super_block *s) { if (!s) return; super_unlock_excl(s); list_lru_destroy(&s->s_dentry_lru); list_lru_destroy(&s->s_inode_lru); shrinker_free(s->s_shrink); /* no delays needed */ destroy_super_work(&s->destroy_work); } /** * alloc_super - create new superblock * @type: filesystem type superblock should belong to * @flags: the mount flags * @user_ns: User namespace for the super_block * * Allocates and initializes a new &struct super_block. alloc_super() * returns a pointer new superblock or %NULL if allocation had failed. */ static struct super_block *alloc_super(struct file_system_type *type, int flags, struct user_namespace *user_ns) { struct super_block *s = kzalloc(sizeof(struct super_block), GFP_KERNEL); static const struct super_operations default_op; int i; if (!s) return NULL; s->s_user_ns = get_user_ns(user_ns); init_rwsem(&s->s_umount); lockdep_set_class(&s->s_umount, &type->s_umount_key); /* * sget() can have s_umount recursion. * * When it cannot find a suitable sb, it allocates a new * one (this one), and tries again to find a suitable old * one. * * In case that succeeds, it will acquire the s_umount * lock of the old one. Since these are clearly distrinct * locks, and this object isn't exposed yet, there's no * risk of deadlocks. * * Annotate this by putting this lock in a different * subclass. */ down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); if (security_sb_alloc(s)) goto fail; for (i = 0; i < SB_FREEZE_LEVELS; i++) { if (__percpu_init_rwsem(&s->s_writers.rw_sem[i], sb_writers_name[i], &type->s_writers_key[i])) goto fail; } s->s_bdi = &noop_backing_dev_info; s->s_flags = flags; if (s->s_user_ns != &init_user_ns) s->s_iflags |= SB_I_NODEV; INIT_HLIST_NODE(&s->s_instances); INIT_HLIST_BL_HEAD(&s->s_roots); mutex_init(&s->s_sync_lock); INIT_LIST_HEAD(&s->s_inodes); spin_lock_init(&s->s_inode_list_lock); INIT_LIST_HEAD(&s->s_inodes_wb); spin_lock_init(&s->s_inode_wblist_lock); s->s_count = 1; atomic_set(&s->s_active, 1); mutex_init(&s->s_vfs_rename_mutex); lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key); init_rwsem(&s->s_dquot.dqio_sem); s->s_maxbytes = MAX_NON_LFS; s->s_op = &default_op; s->s_time_gran = 1000000000; s->s_time_min = TIME64_MIN; s->s_time_max = TIME64_MAX; s->s_shrink = shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, "sb-%s", type->name); if (!s->s_shrink) goto fail; s->s_shrink->scan_objects = super_cache_scan; s->s_shrink->count_objects = super_cache_count; s->s_shrink->batch = 1024; s->s_shrink->private_data = s; if (list_lru_init_memcg(&s->s_dentry_lru, s->s_shrink)) goto fail; if (list_lru_init_memcg(&s->s_inode_lru, s->s_shrink)) goto fail; return s; fail: destroy_unused_super(s); return NULL; } /* Superblock refcounting */ /* * Drop a superblock's refcount. The caller must hold sb_lock. */ static void __put_super(struct super_block *s) { if (!--s->s_count) { list_del_init(&s->s_list); WARN_ON(s->s_dentry_lru.node); WARN_ON(s->s_inode_lru.node); WARN_ON(s->s_mounts); call_rcu(&s->rcu, destroy_super_rcu); } } /** * put_super - drop a temporary reference to superblock * @sb: superblock in question * * Drops a temporary reference, frees superblock if there's no * references left. */ void put_super(struct super_block *sb) { spin_lock(&sb_lock); __put_super(sb); spin_unlock(&sb_lock); } static void kill_super_notify(struct super_block *sb) { lockdep_assert_not_held(&sb->s_umount); /* already notified earlier */ if (sb->s_flags & SB_DEAD) return; /* * Remove it from @fs_supers so it isn't found by new * sget{_fc}() walkers anymore. Any concurrent mounter still * managing to grab a temporary reference is guaranteed to * already see SB_DYING and will wait until we notify them about * SB_DEAD. */ spin_lock(&sb_lock); hlist_del_init(&sb->s_instances); spin_unlock(&sb_lock); /* * Let concurrent mounts know that this thing is really dead. * We don't need @sb->s_umount here as every concurrent caller * will see SB_DYING and either discard the superblock or wait * for SB_DEAD. */ super_wake(sb, SB_DEAD); } /** * deactivate_locked_super - drop an active reference to superblock * @s: superblock to deactivate * * Drops an active reference to superblock, converting it into a temporary * one if there is no other active references left. In that case we * tell fs driver to shut it down and drop the temporary reference we * had just acquired. * * Caller holds exclusive lock on superblock; that lock is released. */ void deactivate_locked_super(struct super_block *s) { struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { shrinker_free(s->s_shrink); fs->kill_sb(s); kill_super_notify(s); /* * Since list_lru_destroy() may sleep, we cannot call it from * put_super(), where we hold the sb_lock. Therefore we destroy * the lru lists right now. */ list_lru_destroy(&s->s_dentry_lru); list_lru_destroy(&s->s_inode_lru); put_filesystem(fs); put_super(s); } else { super_unlock_excl(s); } } EXPORT_SYMBOL(deactivate_locked_super); /** * deactivate_super - drop an active reference to superblock * @s: superblock to deactivate * * Variant of deactivate_locked_super(), except that superblock is *not* * locked by caller. If we are going to drop the final active reference, * lock will be acquired prior to that. */ void deactivate_super(struct super_block *s) { if (!atomic_add_unless(&s->s_active, -1, 1)) { __super_lock_excl(s); deactivate_locked_super(s); } } EXPORT_SYMBOL(deactivate_super); /** * grab_super - acquire an active reference to a superblock * @sb: superblock to acquire * * Acquire a temporary reference on a superblock and try to trade it for * an active reference. This is used in sget{_fc}() to wait for a * superblock to either become SB_BORN or for it to pass through * sb->kill() and be marked as SB_DEAD. * * Return: This returns true if an active reference could be acquired, * false if not. */ static bool grab_super(struct super_block *sb) { bool locked; sb->s_count++; spin_unlock(&sb_lock); locked = super_lock_excl(sb); if (locked) { if (atomic_inc_not_zero(&sb->s_active)) { put_super(sb); return true; } super_unlock_excl(sb); } wait_var_event(&sb->s_flags, super_flags(sb, SB_DEAD)); put_super(sb); return false; } /* * super_trylock_shared - try to grab ->s_umount shared * @sb: reference we are trying to grab * * Try to prevent fs shutdown. This is used in places where we * cannot take an active reference but we need to ensure that the * filesystem is not shut down while we are working on it. It returns * false if we cannot acquire s_umount or if we lose the race and * filesystem already got into shutdown, and returns true with the s_umount * lock held in read mode in case of success. On successful return, * the caller must drop the s_umount lock when done. * * Note that unlike get_super() et.al. this one does *not* bump ->s_count. * The reason why it's safe is that we are OK with doing trylock instead * of down_read(). There's a couple of places that are OK with that, but * it's very much not a general-purpose interface. */ bool super_trylock_shared(struct super_block *sb) { if (down_read_trylock(&sb->s_umount)) { if (!(sb->s_flags & SB_DYING) && sb->s_root && (sb->s_flags & SB_BORN)) return true; super_unlock_shared(sb); } return false; } /** * retire_super - prevents superblock from being reused * @sb: superblock to retire * * The function marks superblock to be ignored in superblock test, which * prevents it from being reused for any new mounts. If the superblock has * a private bdi, it also unregisters it, but doesn't reduce the refcount * of the superblock to prevent potential races. The refcount is reduced * by generic_shutdown_super(). The function can not be called * concurrently with generic_shutdown_super(). It is safe to call the * function multiple times, subsequent calls have no effect. * * The marker will affect the re-use only for block-device-based * superblocks. Other superblocks will still get marked if this function * is used, but that will not affect their reusability. */ void retire_super(struct super_block *sb) { WARN_ON(!sb->s_bdev); __super_lock_excl(sb); if (sb->s_iflags & SB_I_PERSB_BDI) { bdi_unregister(sb->s_bdi); sb->s_iflags &= ~SB_I_PERSB_BDI; } sb->s_iflags |= SB_I_RETIRED; super_unlock_excl(sb); } EXPORT_SYMBOL(retire_super); /** * generic_shutdown_super - common helper for ->kill_sb() * @sb: superblock to kill * * generic_shutdown_super() does all fs-independent work on superblock * shutdown. Typical ->kill_sb() should pick all fs-specific objects * that need destruction out of superblock, call generic_shutdown_super() * and release aforementioned objects. Note: dentries and inodes _are_ * taken care of and do not need specific handling. * * Upon calling this function, the filesystem may no longer alter or * rearrange the set of dentries belonging to this super_block, nor may it * change the attachments of dentries to inodes. */ void generic_shutdown_super(struct super_block *sb) { const struct super_operations *sop = sb->s_op; if (sb->s_root) { shrink_dcache_for_umount(sb); sync_filesystem(sb); sb->s_flags &= ~SB_ACTIVE; cgroup_writeback_umount(sb); /* Evict all inodes with zero refcount. */ evict_inodes(sb); /* * Clean up and evict any inodes that still have references due * to fsnotify or the security policy. */ fsnotify_sb_delete(sb); security_sb_delete(sb); if (sb->s_dio_done_wq) { destroy_workqueue(sb->s_dio_done_wq); sb->s_dio_done_wq = NULL; } if (sop->put_super) sop->put_super(sb); /* * Now that all potentially-encrypted inodes have been evicted, * the fscrypt keyring can be destroyed. */ fscrypt_destroy_keyring(sb); if (CHECK_DATA_CORRUPTION(!list_empty(&sb->s_inodes), NULL, "VFS: Busy inodes after unmount of %s (%s)", sb->s_id, sb->s_type->name)) { /* * Adding a proper bailout path here would be hard, but * we can at least make it more likely that a later * iput_final() or such crashes cleanly. */ struct inode *inode; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { inode->i_op = VFS_PTR_POISON; inode->i_sb = VFS_PTR_POISON; inode->i_mapping = VFS_PTR_POISON; } spin_unlock(&sb->s_inode_list_lock); } } /* * Broadcast to everyone that grabbed a temporary reference to this * superblock before we removed it from @fs_supers that the superblock * is dying. Every walker of @fs_supers outside of sget{_fc}() will now * discard this superblock and treat it as dead. * * We leave the superblock on @fs_supers so it can be found by * sget{_fc}() until we passed sb->kill_sb(). */ super_wake(sb, SB_DYING); super_unlock_excl(sb); if (sb->s_bdi != &noop_backing_dev_info) { if (sb->s_iflags & SB_I_PERSB_BDI) bdi_unregister(sb->s_bdi); bdi_put(sb->s_bdi); sb->s_bdi = &noop_backing_dev_info; } } EXPORT_SYMBOL(generic_shutdown_super); bool mount_capable(struct fs_context *fc) { if (!(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) return capable(CAP_SYS_ADMIN); else return ns_capable(fc->user_ns, CAP_SYS_ADMIN); } /** * sget_fc - Find or create a superblock * @fc: Filesystem context. * @test: Comparison callback * @set: Setup callback * * Create a new superblock or find an existing one. * * The @test callback is used to find a matching existing superblock. * Whether or not the requested parameters in @fc are taken into account * is specific to the @test callback that is used. They may even be * completely ignored. * * If an extant superblock is matched, it will be returned unless: * * (1) the namespace the filesystem context @fc and the extant * superblock's namespace differ * * (2) the filesystem context @fc has requested that reusing an extant * superblock is not allowed * * In both cases EBUSY will be returned. * * If no match is made, a new superblock will be allocated and basic * initialisation will be performed (s_type, s_fs_info and s_id will be * set and the @set callback will be invoked), the superblock will be * published and it will be returned in a partially constructed state * with SB_BORN and SB_ACTIVE as yet unset. * * Return: On success, an extant or newly created superblock is * returned. On failure an error pointer is returned. */ 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 *s = NULL; struct super_block *old; struct user_namespace *user_ns = fc->global ? &init_user_ns : fc->user_ns; int err; /* * Never allow s_user_ns != &init_user_ns when FS_USERNS_MOUNT is * not set, as the filesystem is likely unprepared to handle it. * This can happen when fsconfig() is called from init_user_ns with * an fs_fd opened in another user namespace. */ if (user_ns != &init_user_ns && !(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) { errorfc(fc, "VFS: Mounting from non-initial user namespace is not allowed"); return ERR_PTR(-EPERM); } retry: spin_lock(&sb_lock); if (test) { hlist_for_each_entry(old, &fc->fs_type->fs_supers, s_instances) { if (test(old, fc)) goto share_extant_sb; } } if (!s) { spin_unlock(&sb_lock); s = alloc_super(fc->fs_type, fc->sb_flags, user_ns); if (!s) return ERR_PTR(-ENOMEM); goto retry; } s->s_fs_info = fc->s_fs_info; err = set(s, fc); if (err) { s->s_fs_info = NULL; spin_unlock(&sb_lock); destroy_unused_super(s); return ERR_PTR(err); } fc->s_fs_info = NULL; s->s_type = fc->fs_type; s->s_iflags |= fc->s_iflags; strscpy(s->s_id, s->s_type->name, sizeof(s->s_id)); /* * Make the superblock visible on @super_blocks and @fs_supers. * It's in a nascent state and users should wait on SB_BORN or * SB_DYING to be set. */ list_add_tail(&s->s_list, &super_blocks); hlist_add_head(&s->s_instances, &s->s_type->fs_supers); spin_unlock(&sb_lock); get_filesystem(s->s_type); shrinker_register(s->s_shrink); return s; share_extant_sb: if (user_ns != old->s_user_ns || fc->exclusive) { spin_unlock(&sb_lock); destroy_unused_super(s); if (fc->exclusive) warnfc(fc, "reusing existing filesystem not allowed"); else warnfc(fc, "reusing existing filesystem in another namespace not allowed"); return ERR_PTR(-EBUSY); } if (!grab_super(old)) goto retry; destroy_unused_super(s); return old; } EXPORT_SYMBOL(sget_fc); /** * sget - find or create a superblock * @type: filesystem type superblock should belong to * @test: comparison callback * @set: setup callback * @flags: mount flags * @data: argument to each of them */ 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 user_namespace *user_ns = current_user_ns(); struct super_block *s = NULL; struct super_block *old; int err; retry: spin_lock(&sb_lock); if (test) { hlist_for_each_entry(old, &type->fs_supers, s_instances) { if (!test(old, data)) continue; if (user_ns != old->s_user_ns) { spin_unlock(&sb_lock); destroy_unused_super(s); return ERR_PTR(-EBUSY); } if (!grab_super(old)) goto retry; destroy_unused_super(s); return old; } } if (!s) { spin_unlock(&sb_lock); s = alloc_super(type, flags, user_ns); if (!s) return ERR_PTR(-ENOMEM); goto retry; } err = set(s, data); if (err) { spin_unlock(&sb_lock); destroy_unused_super(s); return ERR_PTR(err); } s->s_type = type; strscpy(s->s_id, type->name, sizeof(s->s_id)); list_add_tail(&s->s_list, &super_blocks); hlist_add_head(&s->s_instances, &type->fs_supers); spin_unlock(&sb_lock); get_filesystem(type); shrinker_register(s->s_shrink); return s; } EXPORT_SYMBOL(sget); void drop_super(struct super_block *sb) { super_unlock_shared(sb); put_super(sb); } EXPORT_SYMBOL(drop_super); void drop_super_exclusive(struct super_block *sb) { super_unlock_excl(sb); put_super(sb); } EXPORT_SYMBOL(drop_super_exclusive); enum super_iter_flags_t { SUPER_ITER_EXCL = (1U << 0), SUPER_ITER_UNLOCKED = (1U << 1), SUPER_ITER_REVERSE = (1U << 2), }; static inline struct super_block *first_super(enum super_iter_flags_t flags) { if (flags & SUPER_ITER_REVERSE) return list_last_entry(&super_blocks, struct super_block, s_list); return list_first_entry(&super_blocks, struct super_block, s_list); } static inline struct super_block *next_super(struct super_block *sb, enum super_iter_flags_t flags) { if (flags & SUPER_ITER_REVERSE) return list_prev_entry(sb, s_list); return list_next_entry(sb, s_list); } static void __iterate_supers(void (*f)(struct super_block *, void *), void *arg, enum super_iter_flags_t flags) { struct super_block *sb, *p = NULL; bool excl = flags & SUPER_ITER_EXCL; guard(spinlock)(&sb_lock); for (sb = first_super(flags); !list_entry_is_head(sb, &super_blocks, s_list); sb = next_super(sb, flags)) { if (super_flags(sb, SB_DYING)) continue; sb->s_count++; spin_unlock(&sb_lock); if (flags & SUPER_ITER_UNLOCKED) { f(sb, arg); } else if (super_lock(sb, excl)) { f(sb, arg); super_unlock(sb, excl); } spin_lock(&sb_lock); if (p) __put_super(p); p = sb; } if (p) __put_super(p); } void iterate_supers(void (*f)(struct super_block *, void *), void *arg) { __iterate_supers(f, arg, 0); } /** * iterate_supers_type - call function for superblocks of given type * @type: fs type * @f: function to call * @arg: argument to pass to it * * Scans the superblock list and calls given function, passing it * locked superblock and given argument. */ void iterate_supers_type(struct file_system_type *type, void (*f)(struct super_block *, void *), void *arg) { struct super_block *sb, *p = NULL; spin_lock(&sb_lock); hlist_for_each_entry(sb, &type->fs_supers, s_instances) { bool locked; if (super_flags(sb, SB_DYING)) continue; sb->s_count++; spin_unlock(&sb_lock); locked = super_lock_shared(sb); if (locked) { f(sb, arg); super_unlock_shared(sb); } spin_lock(&sb_lock); if (p) __put_super(p); p = sb; } if (p) __put_super(p); spin_unlock(&sb_lock); } EXPORT_SYMBOL(iterate_supers_type); struct super_block *user_get_super(dev_t dev, bool excl) { struct super_block *sb; spin_lock(&sb_lock); list_for_each_entry(sb, &super_blocks, s_list) { bool locked; if (sb->s_dev != dev) continue; sb->s_count++; spin_unlock(&sb_lock); locked = super_lock(sb, excl); if (locked) return sb; spin_lock(&sb_lock); __put_super(sb); break; } spin_unlock(&sb_lock); return NULL; } /** * reconfigure_super - asks filesystem to change superblock parameters * @fc: The superblock and configuration * * Alters the configuration parameters of a live superblock. */ int reconfigure_super(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; int retval; bool remount_ro = false; bool remount_rw = false; bool force = fc->sb_flags & SB_FORCE; if (fc->sb_flags_mask & ~MS_RMT_MASK) return -EINVAL; if (sb->s_writers.frozen != SB_UNFROZEN) return -EBUSY; retval = security_sb_remount(sb, fc->security); if (retval) return retval; if (fc->sb_flags_mask & SB_RDONLY) { #ifdef CONFIG_BLOCK if (!(fc->sb_flags & SB_RDONLY) && sb->s_bdev && bdev_read_only(sb->s_bdev)) return -EACCES; #endif remount_rw = !(fc->sb_flags & SB_RDONLY) && sb_rdonly(sb); remount_ro = (fc->sb_flags & SB_RDONLY) && !sb_rdonly(sb); } if (remount_ro) { if (!hlist_empty(&sb->s_pins)) { super_unlock_excl(sb); group_pin_kill(&sb->s_pins); __super_lock_excl(sb); if (!sb->s_root) return 0; if (sb->s_writers.frozen != SB_UNFROZEN) return -EBUSY; remount_ro = !sb_rdonly(sb); } } shrink_dcache_sb(sb); /* If we are reconfiguring to RDONLY and current sb is read/write, * make sure there are no files open for writing. */ if (remount_ro) { if (force) { sb_start_ro_state_change(sb); } else { retval = sb_prepare_remount_readonly(sb); if (retval) return retval; } } else if (remount_rw) { /* * Protect filesystem's reconfigure code from writes from * userspace until reconfigure finishes. */ sb_start_ro_state_change(sb); } if (fc->ops->reconfigure) { retval = fc->ops->reconfigure(fc); if (retval) { if (!force) goto cancel_readonly; /* If forced remount, go ahead despite any errors */ WARN(1, "forced remount of a %s fs returned %i\n", sb->s_type->name, retval); } } WRITE_ONCE(sb->s_flags, ((sb->s_flags & ~fc->sb_flags_mask) | (fc->sb_flags & fc->sb_flags_mask))); sb_end_ro_state_change(sb); /* * Some filesystems modify their metadata via some other path than the * bdev buffer cache (eg. use a private mapping, or directories in * pagecache, etc). Also file data modifications go via their own * mappings. So If we try to mount readonly then copy the filesystem * from bdev, we could get stale data, so invalidate it to give a best * effort at coherency. */ if (remount_ro && sb->s_bdev) invalidate_bdev(sb->s_bdev); return 0; cancel_readonly: sb_end_ro_state_change(sb); return retval; } static void do_emergency_remount_callback(struct super_block *sb, void *unused) { if (sb->s_bdev && !sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY | SB_FORCE, SB_RDONLY); if (!IS_ERR(fc)) { if (parse_monolithic_mount_data(fc, NULL) == 0) (void)reconfigure_super(fc); put_fs_context(fc); } } } static void do_emergency_remount(struct work_struct *work) { __iterate_supers(do_emergency_remount_callback, NULL, SUPER_ITER_EXCL | SUPER_ITER_REVERSE); kfree(work); printk("Emergency Remount complete\n"); } void emergency_remount(void) { struct work_struct *work; work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { INIT_WORK(work, do_emergency_remount); schedule_work(work); } } static void do_thaw_all_callback(struct super_block *sb, void *unused) { if (IS_ENABLED(CONFIG_BLOCK)) while (sb->s_bdev && !bdev_thaw(sb->s_bdev)) pr_warn("Emergency Thaw on %pg\n", sb->s_bdev); thaw_super_locked(sb, FREEZE_HOLDER_USERSPACE, NULL); return; } static void do_thaw_all(struct work_struct *work) { __iterate_supers(do_thaw_all_callback, NULL, SUPER_ITER_EXCL); kfree(work); printk(KERN_WARNING "Emergency Thaw complete\n"); } /** * emergency_thaw_all -- forcibly thaw every frozen filesystem * * Used for emergency unfreeze of all filesystems via SysRq */ void emergency_thaw_all(void) { struct work_struct *work; work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { INIT_WORK(work, do_thaw_all); schedule_work(work); } } static inline bool get_active_super(struct super_block *sb) { bool active = false; if (super_lock_excl(sb)) { active = atomic_inc_not_zero(&sb->s_active); super_unlock_excl(sb); } return active; } static const char *filesystems_freeze_ptr = "filesystems_freeze"; static void filesystems_freeze_callback(struct super_block *sb, void *unused) { if (!sb->s_op->freeze_fs && !sb->s_op->freeze_super) return; if (!get_active_super(sb)) return; if (sb->s_op->freeze_super) sb->s_op->freeze_super(sb, FREEZE_EXCL | FREEZE_HOLDER_KERNEL, filesystems_freeze_ptr); else freeze_super(sb, FREEZE_EXCL | FREEZE_HOLDER_KERNEL, filesystems_freeze_ptr); deactivate_super(sb); } void filesystems_freeze(void) { __iterate_supers(filesystems_freeze_callback, NULL, SUPER_ITER_UNLOCKED | SUPER_ITER_REVERSE); } static void filesystems_thaw_callback(struct super_block *sb, void *unused) { if (!sb->s_op->freeze_fs && !sb->s_op->freeze_super) return; if (!get_active_super(sb)) return; if (sb->s_op->thaw_super) sb->s_op->thaw_super(sb, FREEZE_EXCL | FREEZE_HOLDER_KERNEL, filesystems_freeze_ptr); else thaw_super(sb, FREEZE_EXCL | FREEZE_HOLDER_KERNEL, filesystems_freeze_ptr); deactivate_super(sb); } void filesystems_thaw(void) { __iterate_supers(filesystems_thaw_callback, NULL, SUPER_ITER_UNLOCKED); } static DEFINE_IDA(unnamed_dev_ida); /** * get_anon_bdev - Allocate a block device for filesystems which don't have one. * @p: Pointer to a dev_t. * * Filesystems which don't use real block devices can call this function * to allocate a virtual block device. * * Context: Any context. Frequently called while holding sb_lock. * Return: 0 on success, -EMFILE if there are no anonymous bdevs left * or -ENOMEM if memory allocation failed. */ int get_anon_bdev(dev_t *p) { int dev; /* * Many userspace utilities consider an FSID of 0 invalid. * Always return at least 1 from get_anon_bdev. */ dev = ida_alloc_range(&unnamed_dev_ida, 1, (1 << MINORBITS) - 1, GFP_ATOMIC); if (dev == -ENOSPC) dev = -EMFILE; if (dev < 0) return dev; *p = MKDEV(0, dev); return 0; } EXPORT_SYMBOL(get_anon_bdev); void free_anon_bdev(dev_t dev) { ida_free(&unnamed_dev_ida, MINOR(dev)); } EXPORT_SYMBOL(free_anon_bdev); int set_anon_super(struct super_block *s, void *data) { return get_anon_bdev(&s->s_dev); } EXPORT_SYMBOL(set_anon_super); void kill_anon_super(struct super_block *sb) { dev_t dev = sb->s_dev; generic_shutdown_super(sb); kill_super_notify(sb); free_anon_bdev(dev); } EXPORT_SYMBOL(kill_anon_super); void kill_litter_super(struct super_block *sb) { if (sb->s_root) d_genocide(sb->s_root); kill_anon_super(sb); } EXPORT_SYMBOL(kill_litter_super); int set_anon_super_fc(struct super_block *sb, struct fs_context *fc) { return set_anon_super(sb, NULL); } EXPORT_SYMBOL(set_anon_super_fc); static int test_keyed_super(struct super_block *sb, struct fs_context *fc) { return sb->s_fs_info == fc->s_fs_info; } static int test_single_super(struct super_block *s, struct fs_context *fc) { return 1; } static int vfs_get_super(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { struct super_block *sb; int err; sb = sget_fc(fc, test, set_anon_super_fc); if (IS_ERR(sb)) return PTR_ERR(sb); if (!sb->s_root) { err = fill_super(sb, fc); if (err) goto error; sb->s_flags |= SB_ACTIVE; } fc->root = dget(sb->s_root); return 0; error: deactivate_locked_super(sb); return err; } int get_tree_nodev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { return vfs_get_super(fc, NULL, fill_super); } EXPORT_SYMBOL(get_tree_nodev); int get_tree_single(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { return vfs_get_super(fc, test_single_super, fill_super); } EXPORT_SYMBOL(get_tree_single); int get_tree_keyed(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc), void *key) { fc->s_fs_info = key; return vfs_get_super(fc, test_keyed_super, fill_super); } EXPORT_SYMBOL(get_tree_keyed); static int set_bdev_super(struct super_block *s, void *data) { s->s_dev = *(dev_t *)data; return 0; } static int super_s_dev_set(struct super_block *s, struct fs_context *fc) { return set_bdev_super(s, fc->sget_key); } static int super_s_dev_test(struct super_block *s, struct fs_context *fc) { return !(s->s_iflags & SB_I_RETIRED) && s->s_dev == *(dev_t *)fc->sget_key; } /** * sget_dev - Find or create a superblock by device number * @fc: Filesystem context. * @dev: device number * * Find or create a superblock using the provided device number that * will be stored in fc->sget_key. * * If an extant superblock is matched, then that will be returned with * an elevated reference count that the caller must transfer or discard. * * If no match is made, a new superblock will be allocated and basic * initialisation will be performed (s_type, s_fs_info, s_id, s_dev will * be set). The superblock will be published and it will be returned in * a partially constructed state with SB_BORN and SB_ACTIVE as yet * unset. * * Return: an existing or newly created superblock on success, an error * pointer on failure. */ struct super_block *sget_dev(struct fs_context *fc, dev_t dev) { fc->sget_key = &dev; return sget_fc(fc, super_s_dev_test, super_s_dev_set); } EXPORT_SYMBOL(sget_dev); #ifdef CONFIG_BLOCK /* * Lock the superblock that is holder of the bdev. Returns the superblock * pointer if we successfully locked the superblock and it is alive. Otherwise * we return NULL and just unlock bdev->bd_holder_lock. * * The function must be called with bdev->bd_holder_lock and releases it. */ static struct super_block *bdev_super_lock(struct block_device *bdev, bool excl) __releases(&bdev->bd_holder_lock) { struct super_block *sb = bdev->bd_holder; bool locked; lockdep_assert_held(&bdev->bd_holder_lock); lockdep_assert_not_held(&sb->s_umount); lockdep_assert_not_held(&bdev->bd_disk->open_mutex); /* Make sure sb doesn't go away from under us */ spin_lock(&sb_lock); sb->s_count++; spin_unlock(&sb_lock); mutex_unlock(&bdev->bd_holder_lock); locked = super_lock(sb, excl); /* * If the superblock wasn't already SB_DYING then we hold * s_umount and can safely drop our temporary reference. */ put_super(sb); if (!locked) return NULL; if (!sb->s_root || !(sb->s_flags & SB_ACTIVE)) { super_unlock(sb, excl); return NULL; } return sb; } static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise) { struct super_block *sb; sb = bdev_super_lock(bdev, false); if (!sb) return; if (sb->s_op->remove_bdev) { int ret; ret = sb->s_op->remove_bdev(sb, bdev); if (!ret) { super_unlock_shared(sb); return; } /* Fallback to shutdown. */ } if (!surprise) sync_filesystem(sb); shrink_dcache_sb(sb); evict_inodes(sb); if (sb->s_op->shutdown) sb->s_op->shutdown(sb); super_unlock_shared(sb); } static void fs_bdev_sync(struct block_device *bdev) { struct super_block *sb; sb = bdev_super_lock(bdev, false); if (!sb) return; sync_filesystem(sb); super_unlock_shared(sb); } static struct super_block *get_bdev_super(struct block_device *bdev) { bool active = false; struct super_block *sb; sb = bdev_super_lock(bdev, true); if (sb) { active = atomic_inc_not_zero(&sb->s_active); super_unlock_excl(sb); } if (!active) return NULL; return sb; } /** * fs_bdev_freeze - freeze owning filesystem of block device * @bdev: block device * * Freeze the filesystem that owns this block device if it is still * active. * * A filesystem that owns multiple block devices may be frozen from each * block device and won't be unfrozen until all block devices are * unfrozen. Each block device can only freeze the filesystem once as we * nest freezes for block devices in the block layer. * * Return: If the freeze was successful zero is returned. If the freeze * failed a negative error code is returned. */ static int fs_bdev_freeze(struct block_device *bdev) { struct super_block *sb; int error = 0; lockdep_assert_held(&bdev->bd_fsfreeze_mutex); sb = get_bdev_super(bdev); if (!sb) return -EINVAL; if (sb->s_op->freeze_super) error = sb->s_op->freeze_super(sb, FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL); else error = freeze_super(sb, FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL); if (!error) error = sync_blockdev(bdev); deactivate_super(sb); return error; } /** * fs_bdev_thaw - thaw owning filesystem of block device * @bdev: block device * * Thaw the filesystem that owns this block device. * * A filesystem that owns multiple block devices may be frozen from each * block device and won't be unfrozen until all block devices are * unfrozen. Each block device can only freeze the filesystem once as we * nest freezes for block devices in the block layer. * * Return: If the thaw was successful zero is returned. If the thaw * failed a negative error code is returned. If this function * returns zero it doesn't mean that the filesystem is unfrozen * as it may have been frozen multiple times (kernel may hold a * freeze or might be frozen from other block devices). */ static int fs_bdev_thaw(struct block_device *bdev) { struct super_block *sb; int error; lockdep_assert_held(&bdev->bd_fsfreeze_mutex); /* * The block device may have been frozen before it was claimed by a * filesystem. Concurrently another process might try to mount that * frozen block device and has temporarily claimed the block device for * that purpose causing a concurrent fs_bdev_thaw() to end up here. The * mounter is already about to abort mounting because they still saw an * elevanted bdev->bd_fsfreeze_count so get_bdev_super() will return * NULL in that case. */ sb = get_bdev_super(bdev); if (!sb) return -EINVAL; if (sb->s_op->thaw_super) error = sb->s_op->thaw_super(sb, FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL); else error = thaw_super(sb, FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE, NULL); deactivate_super(sb); return error; } const struct blk_holder_ops fs_holder_ops = { .mark_dead = fs_bdev_mark_dead, .sync = fs_bdev_sync, .freeze = fs_bdev_freeze, .thaw = fs_bdev_thaw, }; EXPORT_SYMBOL_GPL(fs_holder_ops); int setup_bdev_super(struct super_block *sb, int sb_flags, struct fs_context *fc) { blk_mode_t mode = sb_open_mode(sb_flags); struct file *bdev_file; struct block_device *bdev; bdev_file = bdev_file_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops); if (IS_ERR(bdev_file)) { if (fc) errorf(fc, "%s: Can't open blockdev", fc->source); return PTR_ERR(bdev_file); } bdev = file_bdev(bdev_file); /* * This really should be in blkdev_get_by_dev, but right now can't due * to legacy issues that require us to allow opening a block device node * writable from userspace even for a read-only block device. */ if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) { bdev_fput(bdev_file); return -EACCES; } /* * It is enough to check bdev was not frozen before we set * s_bdev as freezing will wait until SB_BORN is set. */ if (atomic_read(&bdev->bd_fsfreeze_count) > 0) { if (fc) warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); bdev_fput(bdev_file); return -EBUSY; } spin_lock(&sb_lock); sb->s_bdev_file = bdev_file; sb->s_bdev = bdev; sb->s_bdi = bdi_get(bdev->bd_disk->bdi); if (bdev_stable_writes(bdev)) sb->s_iflags |= SB_I_STABLE_WRITES; spin_unlock(&sb_lock); snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev); shrinker_debugfs_rename(sb->s_shrink, "sb-%s:%s", sb->s_type->name, sb->s_id); sb_set_blocksize(sb, block_size(bdev)); return 0; } EXPORT_SYMBOL_GPL(setup_bdev_super); /** * get_tree_bdev_flags - Get a superblock based on a single block device * @fc: The filesystem context holding the parameters * @fill_super: Helper to initialise a new superblock * @flags: GET_TREE_BDEV_* flags */ int get_tree_bdev_flags(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc), unsigned int flags) { struct super_block *s; int error = 0; dev_t dev; if (!fc->source) return invalf(fc, "No source specified"); error = lookup_bdev(fc->source, &dev); if (error) { if (!(flags & GET_TREE_BDEV_QUIET_LOOKUP)) errorf(fc, "%s: Can't lookup blockdev", fc->source); return error; } fc->sb_flags |= SB_NOSEC; s = sget_dev(fc, dev); if (IS_ERR(s)) return PTR_ERR(s); if (s->s_root) { /* Don't summarily change the RO/RW state. */ if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) { warnf(fc, "%pg: Can't mount, would change RO state", s->s_bdev); deactivate_locked_super(s); return -EBUSY; } } else { error = setup_bdev_super(s, fc->sb_flags, fc); if (!error) error = fill_super(s, fc); if (error) { deactivate_locked_super(s); return error; } s->s_flags |= SB_ACTIVE; } BUG_ON(fc->root); fc->root = dget(s->s_root); return 0; } EXPORT_SYMBOL_GPL(get_tree_bdev_flags); /** * get_tree_bdev - Get a superblock based on a single block device * @fc: The filesystem context holding the parameters * @fill_super: Helper to initialise a new superblock */ int get_tree_bdev(struct fs_context *fc, int (*fill_super)(struct super_block *, struct fs_context *)) { return get_tree_bdev_flags(fc, fill_super, 0); } EXPORT_SYMBOL(get_tree_bdev); void kill_block_super(struct super_block *sb) { struct block_device *bdev = sb->s_bdev; generic_shutdown_super(sb); if (bdev) { sync_blockdev(bdev); bdev_fput(sb->s_bdev_file); } } EXPORT_SYMBOL(kill_block_super); #endif /** * vfs_get_tree - Get the mountable root * @fc: The superblock configuration context. * * The filesystem is invoked to get or create a superblock which can then later * be used for mounting. The filesystem places a pointer to the root to be * used for mounting in @fc->root. */ int vfs_get_tree(struct fs_context *fc) { struct super_block *sb; int error; if (fc->root) return -EBUSY; /* Get the mountable root in fc->root, with a ref on the root and a ref * on the superblock. */ error = fc->ops->get_tree(fc); if (error < 0) return error; if (!fc->root) { pr_err("Filesystem %s get_tree() didn't set fc->root, returned %i\n", fc->fs_type->name, error); /* We don't know what the locking state of the superblock is - * if there is a superblock. */ BUG(); } sb = fc->root->d_sb; WARN_ON(!sb->s_bdi); /* * super_wake() contains a memory barrier which also care of * ordering for super_cache_count(). We place it before setting * SB_BORN as the data dependency between the two functions is * the superblock structure contents that we just set up, not * the SB_BORN flag. */ super_wake(sb, SB_BORN); error = security_sb_set_mnt_opts(sb, fc->security, 0, NULL); if (unlikely(error)) { fc_drop_locked(fc); return error; } /* * filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE * but s_maxbytes was an unsigned long long for many releases. Throw * this warning for a little while to try and catch filesystems that * violate this rule. */ WARN((sb->s_maxbytes < 0), "%s set sb->s_maxbytes to " "negative value (%lld)\n", fc->fs_type->name, sb->s_maxbytes); return 0; } EXPORT_SYMBOL(vfs_get_tree); /* * Setup private BDI for given superblock. It gets automatically cleaned up * in generic_shutdown_super(). */ int super_setup_bdi_name(struct super_block *sb, char *fmt, ...) { struct backing_dev_info *bdi; int err; va_list args; bdi = bdi_alloc(NUMA_NO_NODE); if (!bdi) return -ENOMEM; va_start(args, fmt); err = bdi_register_va(bdi, fmt, args); va_end(args); if (err) { bdi_put(bdi); return err; } WARN_ON(sb->s_bdi != &noop_backing_dev_info); sb->s_bdi = bdi; sb->s_iflags |= SB_I_PERSB_BDI; return 0; } EXPORT_SYMBOL(super_setup_bdi_name); /* * Setup private BDI for given superblock. I gets automatically cleaned up * in generic_shutdown_super(). */ int super_setup_bdi(struct super_block *sb) { static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); return super_setup_bdi_name(sb, "%.28s-%ld", sb->s_type->name, atomic_long_inc_return(&bdi_seq)); } EXPORT_SYMBOL(super_setup_bdi); /** * sb_wait_write - wait until all writers to given file system finish * @sb: the super for which we wait * @level: type of writers we wait for (normal vs page fault) * * This function waits until there are no writers of given type to given file * system. */ static void sb_wait_write(struct super_block *sb, int level) { percpu_down_write(sb->s_writers.rw_sem + level-1); } /* * We are going to return to userspace and forget about these locks, the * ownership goes to the caller of thaw_super() which does unlock(). */ static void lockdep_sb_freeze_release(struct super_block *sb) { int level; for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--) percpu_rwsem_release(sb->s_writers.rw_sem + level, _THIS_IP_); } /* * Tell lockdep we are holding these locks before we call ->unfreeze_fs(sb). */ static void lockdep_sb_freeze_acquire(struct super_block *sb) { int level; for (level = 0; level < SB_FREEZE_LEVELS; ++level) percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_); } static void sb_freeze_unlock(struct super_block *sb, int level) { for (level--; level >= 0; level--) percpu_up_write(sb->s_writers.rw_sem + level); } static int wait_for_partially_frozen(struct super_block *sb) { int ret = 0; do { unsigned short old = sb->s_writers.frozen; up_write(&sb->s_umount); ret = wait_var_event_killable(&sb->s_writers.frozen, sb->s_writers.frozen != old); down_write(&sb->s_umount); } while (ret == 0 && sb->s_writers.frozen != SB_UNFROZEN && sb->s_writers.frozen != SB_FREEZE_COMPLETE); return ret; } #define FREEZE_HOLDERS (FREEZE_HOLDER_KERNEL | FREEZE_HOLDER_USERSPACE) #define FREEZE_FLAGS (FREEZE_HOLDERS | FREEZE_MAY_NEST | FREEZE_EXCL) static inline int freeze_inc(struct super_block *sb, enum freeze_holder who) { WARN_ON_ONCE((who & ~FREEZE_FLAGS)); WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); if (who & FREEZE_HOLDER_KERNEL) ++sb->s_writers.freeze_kcount; if (who & FREEZE_HOLDER_USERSPACE) ++sb->s_writers.freeze_ucount; return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount; } static inline int freeze_dec(struct super_block *sb, enum freeze_holder who) { WARN_ON_ONCE((who & ~FREEZE_FLAGS)); WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); if ((who & FREEZE_HOLDER_KERNEL) && sb->s_writers.freeze_kcount) --sb->s_writers.freeze_kcount; if ((who & FREEZE_HOLDER_USERSPACE) && sb->s_writers.freeze_ucount) --sb->s_writers.freeze_ucount; return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount; } static inline bool may_freeze(struct super_block *sb, enum freeze_holder who, const void *freeze_owner) { lockdep_assert_held(&sb->s_umount); WARN_ON_ONCE((who & ~FREEZE_FLAGS)); WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); if (who & FREEZE_EXCL) { if (WARN_ON_ONCE(!(who & FREEZE_HOLDER_KERNEL))) return false; if (WARN_ON_ONCE(who & ~(FREEZE_EXCL | FREEZE_HOLDER_KERNEL))) return false; if (WARN_ON_ONCE(!freeze_owner)) return false; /* This freeze already has a specific owner. */ if (sb->s_writers.freeze_owner) return false; /* * This is already frozen multiple times so we're just * going to take a reference count and mark the freeze as * being owned by the caller. */ if (sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount) sb->s_writers.freeze_owner = freeze_owner; return true; } if (who & FREEZE_HOLDER_KERNEL) return (who & FREEZE_MAY_NEST) || sb->s_writers.freeze_kcount == 0; if (who & FREEZE_HOLDER_USERSPACE) return (who & FREEZE_MAY_NEST) || sb->s_writers.freeze_ucount == 0; return false; } static inline bool may_unfreeze(struct super_block *sb, enum freeze_holder who, const void *freeze_owner) { lockdep_assert_held(&sb->s_umount); WARN_ON_ONCE((who & ~FREEZE_FLAGS)); WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); if (who & FREEZE_EXCL) { if (WARN_ON_ONCE(!(who & FREEZE_HOLDER_KERNEL))) return false; if (WARN_ON_ONCE(who & ~(FREEZE_EXCL | FREEZE_HOLDER_KERNEL))) return false; if (WARN_ON_ONCE(!freeze_owner)) return false; if (WARN_ON_ONCE(sb->s_writers.freeze_kcount == 0)) return false; /* This isn't exclusively frozen. */ if (!sb->s_writers.freeze_owner) return false; /* This isn't exclusively frozen by us. */ if (sb->s_writers.freeze_owner != freeze_owner) return false; /* * This is still frozen multiple times so we're just * going to drop our reference count and undo our * exclusive freeze. */ if ((sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount) > 1) sb->s_writers.freeze_owner = NULL; return true; } if (who & FREEZE_HOLDER_KERNEL) { /* * Someone's trying to steal the reference belonging to * @sb->s_writers.freeze_owner. */ if (sb->s_writers.freeze_kcount == 1 && sb->s_writers.freeze_owner) return false; return sb->s_writers.freeze_kcount > 0; } if (who & FREEZE_HOLDER_USERSPACE) return sb->s_writers.freeze_ucount > 0; return false; } /** * freeze_super - lock the filesystem and force it into a consistent state * @sb: the super to lock * @who: context that wants to freeze * @freeze_owner: owner of the freeze * * Syncs the super to make sure the filesystem is consistent and calls the fs's * freeze_fs. Subsequent calls to this without first thawing the fs may return * -EBUSY. * * @who should be: * * %FREEZE_HOLDER_USERSPACE if userspace wants to freeze the fs; * * %FREEZE_HOLDER_KERNEL if the kernel wants to freeze the fs. * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed. * * The @who argument distinguishes between the kernel and userspace trying to * freeze the filesystem. Although there cannot be multiple kernel freezes or * multiple userspace freezes in effect at any given time, the kernel and * userspace can both hold a filesystem frozen. The filesystem remains frozen * until there are no kernel or userspace freezes in effect. * * A filesystem may hold multiple devices and thus a filesystems may be * frozen through the block layer via multiple block devices. In this * case the request is marked as being allowed to nest by passing * FREEZE_MAY_NEST. The filesystem remains frozen until all block * devices are unfrozen. If multiple freezes are attempted without * FREEZE_MAY_NEST -EBUSY will be returned. * * During this function, sb->s_writers.frozen goes through these values: * * SB_UNFROZEN: File system is normal, all writes progress as usual. * * SB_FREEZE_WRITE: The file system is in the process of being frozen. New * writes should be blocked, though page faults are still allowed. We wait for * all writes to complete and then proceed to the next stage. * * SB_FREEZE_PAGEFAULT: Freezing continues. Now also page faults are blocked * but internal fs threads can still modify the filesystem (although they * should not dirty new pages or inodes), writeback can run etc. After waiting * for all running page faults we sync the filesystem which will clean all * dirty pages and inodes (no new dirty pages or inodes can be created when * sync is running). * * SB_FREEZE_FS: The file system is frozen. Now all internal sources of fs * modification are blocked (e.g. XFS preallocation truncation on inode * reclaim). This is usually implemented by blocking new transactions for * filesystems that have them and need this additional guard. After all * internal writers are finished we call ->freeze_fs() to finish filesystem * freezing. Then we transition to SB_FREEZE_COMPLETE state. This state is * mostly auxiliary for filesystems to verify they do not modify frozen fs. * * sb->s_writers.frozen is protected by sb->s_umount. * * Return: If the freeze was successful zero is returned. If the freeze * failed a negative error code is returned. */ int freeze_super(struct super_block *sb, enum freeze_holder who, const void *freeze_owner) { int ret; if (!super_lock_excl(sb)) { WARN_ON_ONCE("Dying superblock while freezing!"); return -EINVAL; } atomic_inc(&sb->s_active); retry: if (sb->s_writers.frozen == SB_FREEZE_COMPLETE) { if (may_freeze(sb, who, freeze_owner)) ret = !!WARN_ON_ONCE(freeze_inc(sb, who) == 1); else ret = -EBUSY; /* All freezers share a single active reference. */ deactivate_locked_super(sb); return ret; } if (sb->s_writers.frozen != SB_UNFROZEN) { ret = wait_for_partially_frozen(sb); if (ret) { deactivate_locked_super(sb); return ret; } goto retry; } if (sb_rdonly(sb)) { /* Nothing to do really... */ WARN_ON_ONCE(freeze_inc(sb, who) > 1); sb->s_writers.freeze_owner = freeze_owner; sb->s_writers.frozen = SB_FREEZE_COMPLETE; wake_up_var(&sb->s_writers.frozen); super_unlock_excl(sb); return 0; } sb->s_writers.frozen = SB_FREEZE_WRITE; /* Release s_umount to preserve sb_start_write -> s_umount ordering */ super_unlock_excl(sb); sb_wait_write(sb, SB_FREEZE_WRITE); __super_lock_excl(sb); /* Now we go and block page faults... */ sb->s_writers.frozen = SB_FREEZE_PAGEFAULT; sb_wait_write(sb, SB_FREEZE_PAGEFAULT); /* All writers are done so after syncing there won't be dirty data */ ret = sync_filesystem(sb); if (ret) { sb->s_writers.frozen = SB_UNFROZEN; sb_freeze_unlock(sb, SB_FREEZE_PAGEFAULT); wake_up_var(&sb->s_writers.frozen); deactivate_locked_super(sb); return ret; } /* Now wait for internal filesystem counter */ sb->s_writers.frozen = SB_FREEZE_FS; sb_wait_write(sb, SB_FREEZE_FS); if (sb->s_op->freeze_fs) { ret = sb->s_op->freeze_fs(sb); if (ret) { printk(KERN_ERR "VFS:Filesystem freeze failed\n"); sb->s_writers.frozen = SB_UNFROZEN; sb_freeze_unlock(sb, SB_FREEZE_FS); wake_up_var(&sb->s_writers.frozen); deactivate_locked_super(sb); return ret; } } /* * For debugging purposes so that fs can warn if it sees write activity * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super(). */ WARN_ON_ONCE(freeze_inc(sb, who) > 1); sb->s_writers.freeze_owner = freeze_owner; sb->s_writers.frozen = SB_FREEZE_COMPLETE; wake_up_var(&sb->s_writers.frozen); lockdep_sb_freeze_release(sb); super_unlock_excl(sb); return 0; } EXPORT_SYMBOL(freeze_super); /* * Undoes the effect of a freeze_super_locked call. If the filesystem is * frozen both by userspace and the kernel, a thaw call from either source * removes that state without releasing the other state or unlocking the * filesystem. */ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who, const void *freeze_owner) { int error = -EINVAL; if (sb->s_writers.frozen != SB_FREEZE_COMPLETE) goto out_unlock; if (!may_unfreeze(sb, who, freeze_owner)) goto out_unlock; /* * All freezers share a single active reference. * So just unlock in case there are any left. */ if (freeze_dec(sb, who)) goto out_unlock; if (sb_rdonly(sb)) { sb->s_writers.frozen = SB_UNFROZEN; sb->s_writers.freeze_owner = NULL; wake_up_var(&sb->s_writers.frozen); goto out_deactivate; } lockdep_sb_freeze_acquire(sb); if (sb->s_op->unfreeze_fs) { error = sb->s_op->unfreeze_fs(sb); if (error) { pr_err("VFS: Filesystem thaw failed\n"); freeze_inc(sb, who); lockdep_sb_freeze_release(sb); goto out_unlock; } } sb->s_writers.frozen = SB_UNFROZEN; sb->s_writers.freeze_owner = NULL; wake_up_var(&sb->s_writers.frozen); sb_freeze_unlock(sb, SB_FREEZE_FS); out_deactivate: deactivate_locked_super(sb); return 0; out_unlock: super_unlock_excl(sb); return error; } /** * thaw_super -- unlock filesystem * @sb: the super to thaw * @who: context that wants to freeze * @freeze_owner: owner of the freeze * * Unlocks the filesystem and marks it writeable again after freeze_super() * if there are no remaining freezes on the filesystem. * * @who should be: * * %FREEZE_HOLDER_USERSPACE if userspace wants to thaw the fs; * * %FREEZE_HOLDER_KERNEL if the kernel wants to thaw the fs. * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed * * A filesystem may hold multiple devices and thus a filesystems may * have been frozen through the block layer via multiple block devices. * The filesystem remains frozen until all block devices are unfrozen. */ int thaw_super(struct super_block *sb, enum freeze_holder who, const void *freeze_owner) { if (!super_lock_excl(sb)) { WARN_ON_ONCE("Dying superblock while thawing!"); return -EINVAL; } return thaw_super_locked(sb, who, freeze_owner); } EXPORT_SYMBOL(thaw_super); /* * Create workqueue for deferred direct IO completions. We allocate the * workqueue when it's first needed. This avoids creating workqueue for * filesystems that don't need it and also allows us to create the workqueue * late enough so the we can include s_id in the name of the workqueue. */ int sb_init_dio_done_wq(struct super_block *sb) { struct workqueue_struct *old; struct workqueue_struct *wq = alloc_workqueue("dio/%s", WQ_MEM_RECLAIM | WQ_PERCPU, 0, sb->s_id); if (!wq) return -ENOMEM; old = NULL; /* * This has to be atomic as more DIOs can race to create the workqueue */ if (!try_cmpxchg(&sb->s_dio_done_wq, &old, wq)) { /* Someone created workqueue before us? Free ours... */ destroy_workqueue(wq); } return 0; } EXPORT_SYMBOL_GPL(sb_init_dio_done_wq); |
| 13 14 14 14 14 14 14 14 14 14 14 12 14 14 14 14 14 14 14 14 14 13 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/printk.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Modified to make sys_syslog() more flexible: added commands to * return the last 4k of kernel messages, regardless of whether * they've been read or not. Added option to suppress kernel printk's * to the console. Added hook for sending the console messages * elsewhere, in preparation for a serial line console (someday). * Ted Ts'o, 2/11/93. * Modified for sysctl support, 1/8/97, Chris Horn. * Fixed SMP synchronization, 08/08/99, Manfred Spraul * manfred@colorfullife.com * Rewrote bits to get rid of console_lock * 01Mar01 Andrew Morton */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/mm.h> #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/console.h> #include <linux/init.h> #include <linux/jiffies.h> #include <linux/nmi.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/delay.h> #include <linux/smp.h> #include <linux/security.h> #include <linux/memblock.h> #include <linux/syscalls.h> #include <linux/syscore_ops.h> #include <linux/vmcore_info.h> #include <linux/ratelimit.h> #include <linux/kmsg_dump.h> #include <linux/syslog.h> #include <linux/cpu.h> #include <linux/rculist.h> #include <linux/poll.h> #include <linux/irq_work.h> #include <linux/ctype.h> #include <linux/uio.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/panic.h> #include <linux/uaccess.h> #include <asm/sections.h> #include <trace/events/initcall.h> #define CREATE_TRACE_POINTS #include <trace/events/printk.h> #include "printk_ringbuffer.h" #include "console_cmdline.h" #include "braille.h" #include "internal.h" int console_printk[4] = { CONSOLE_LOGLEVEL_DEFAULT, /* console_loglevel */ MESSAGE_LOGLEVEL_DEFAULT, /* default_message_loglevel */ CONSOLE_LOGLEVEL_MIN, /* minimum_console_loglevel */ CONSOLE_LOGLEVEL_DEFAULT, /* default_console_loglevel */ }; EXPORT_SYMBOL_GPL(console_printk); atomic_t ignore_console_lock_warning __read_mostly = ATOMIC_INIT(0); EXPORT_SYMBOL(ignore_console_lock_warning); EXPORT_TRACEPOINT_SYMBOL_GPL(console); /* * Low level drivers may need that to know if they can schedule in * their unblank() callback or not. So let's export it. */ int oops_in_progress; EXPORT_SYMBOL(oops_in_progress); /* * console_mutex protects console_list updates and console->flags updates. * The flags are synchronized only for consoles that are registered, i.e. * accessible via the console list. */ static DEFINE_MUTEX(console_mutex); /* * console_sem protects updates to console->seq * and also provides serialization for console printing. */ static DEFINE_SEMAPHORE(console_sem, 1); HLIST_HEAD(console_list); EXPORT_SYMBOL_GPL(console_list); DEFINE_STATIC_SRCU(console_srcu); /* * System may need to suppress printk message under certain * circumstances, like after kernel panic happens. */ int __read_mostly suppress_printk; #ifdef CONFIG_LOCKDEP static struct lockdep_map console_lock_dep_map = { .name = "console_lock" }; void lockdep_assert_console_list_lock_held(void) { lockdep_assert_held(&console_mutex); } EXPORT_SYMBOL(lockdep_assert_console_list_lock_held); #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC bool console_srcu_read_lock_is_held(void) { return srcu_read_lock_held(&console_srcu); } EXPORT_SYMBOL(console_srcu_read_lock_is_held); #endif enum devkmsg_log_bits { __DEVKMSG_LOG_BIT_ON = 0, __DEVKMSG_LOG_BIT_OFF, __DEVKMSG_LOG_BIT_LOCK, }; enum devkmsg_log_masks { DEVKMSG_LOG_MASK_ON = BIT(__DEVKMSG_LOG_BIT_ON), DEVKMSG_LOG_MASK_OFF = BIT(__DEVKMSG_LOG_BIT_OFF), DEVKMSG_LOG_MASK_LOCK = BIT(__DEVKMSG_LOG_BIT_LOCK), }; /* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */ #define DEVKMSG_LOG_MASK_DEFAULT 0 static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; static int __control_devkmsg(char *str) { size_t len; if (!str) return -EINVAL; len = str_has_prefix(str, "on"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_ON; return len; } len = str_has_prefix(str, "off"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_OFF; return len; } len = str_has_prefix(str, "ratelimit"); if (len) { devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT; return len; } return -EINVAL; } static int __init control_devkmsg(char *str) { if (__control_devkmsg(str) < 0) { pr_warn("printk.devkmsg: bad option string '%s'\n", str); return 1; } /* * Set sysctl string accordingly: */ if (devkmsg_log == DEVKMSG_LOG_MASK_ON) strscpy(devkmsg_log_str, "on"); else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF) strscpy(devkmsg_log_str, "off"); /* else "ratelimit" which is set by default. */ /* * Sysctl cannot change it anymore. The kernel command line setting of * this parameter is to force the setting to be permanent throughout the * runtime of the system. This is a precation measure against userspace * trying to be a smarta** and attempting to change it up on us. */ devkmsg_log |= DEVKMSG_LOG_MASK_LOCK; return 1; } __setup("printk.devkmsg=", control_devkmsg); char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit"; #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char old_str[DEVKMSG_STR_MAX_SIZE]; unsigned int old; int err; if (write) { if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK) return -EINVAL; old = devkmsg_log; strscpy(old_str, devkmsg_log_str); } err = proc_dostring(table, write, buffer, lenp, ppos); if (err) return err; if (write) { err = __control_devkmsg(devkmsg_log_str); /* * Do not accept an unknown string OR a known string with * trailing crap... */ if (err < 0 || (err + 1 != *lenp)) { /* ... and restore old setting. */ devkmsg_log = old; strscpy(devkmsg_log_str, old_str); return -EINVAL; } } return 0; } #endif /* CONFIG_PRINTK && CONFIG_SYSCTL */ /** * console_list_lock - Lock the console list * * For console list or console->flags updates */ void console_list_lock(void) { /* * In unregister_console() and console_force_preferred_locked(), * synchronize_srcu() is called with the console_list_lock held. * Therefore it is not allowed that the console_list_lock is taken * with the srcu_lock held. * * Detecting if this context is really in the read-side critical * section is only possible if the appropriate debug options are * enabled. */ WARN_ON_ONCE(debug_lockdep_rcu_enabled() && srcu_read_lock_held(&console_srcu)); mutex_lock(&console_mutex); } EXPORT_SYMBOL(console_list_lock); /** * console_list_unlock - Unlock the console list * * Counterpart to console_list_lock() */ void console_list_unlock(void) { mutex_unlock(&console_mutex); } EXPORT_SYMBOL(console_list_unlock); /** * console_srcu_read_lock - Register a new reader for the * SRCU-protected console list * * Use for_each_console_srcu() to iterate the console list * * Context: Any context. * Return: A cookie to pass to console_srcu_read_unlock(). */ int console_srcu_read_lock(void) __acquires(&console_srcu) { return srcu_read_lock_nmisafe(&console_srcu); } EXPORT_SYMBOL(console_srcu_read_lock); /** * console_srcu_read_unlock - Unregister an old reader from * the SRCU-protected console list * @cookie: cookie returned from console_srcu_read_lock() * * Counterpart to console_srcu_read_lock() */ void console_srcu_read_unlock(int cookie) __releases(&console_srcu) { srcu_read_unlock_nmisafe(&console_srcu, cookie); } EXPORT_SYMBOL(console_srcu_read_unlock); /* * Helper macros to handle lockdep when locking/unlocking console_sem. We use * macros instead of functions so that _RET_IP_ contains useful information. */ #define down_console_sem() do { \ down(&console_sem);\ mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);\ } while (0) static int __down_trylock_console_sem(unsigned long ip) { int lock_failed; unsigned long flags; /* * Here and in __up_console_sem() we need to be in safe mode, * because spindump/WARN/etc from under console ->lock will * deadlock in printk()->down_trylock_console_sem() otherwise. */ printk_safe_enter_irqsave(flags); lock_failed = down_trylock(&console_sem); printk_safe_exit_irqrestore(flags); if (lock_failed) return 1; mutex_acquire(&console_lock_dep_map, 0, 1, ip); return 0; } #define down_trylock_console_sem() __down_trylock_console_sem(_RET_IP_) static void __up_console_sem(unsigned long ip) { unsigned long flags; mutex_release(&console_lock_dep_map, ip); printk_safe_enter_irqsave(flags); up(&console_sem); printk_safe_exit_irqrestore(flags); } #define up_console_sem() __up_console_sem(_RET_IP_) /* * This is used for debugging the mess that is the VT code by * keeping track if we have the console semaphore held. It's * definitely not the perfect debug tool (we don't know if _WE_ * hold it and are racing, but it helps tracking those weird code * paths in the console code where we end up in places I want * locked without the console semaphore held). */ static int console_locked; /* * Array of consoles built from command line options (console=) */ #define MAX_CMDLINECONSOLES 8 static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; static int preferred_console = -1; int console_set_on_cmdline; EXPORT_SYMBOL(console_set_on_cmdline); /* Flag: console code may call schedule() */ static int console_may_schedule; enum con_msg_format_flags { MSG_FORMAT_DEFAULT = 0, MSG_FORMAT_SYSLOG = (1 << 0), }; static int console_msg_format = MSG_FORMAT_DEFAULT; /* * The printk log buffer consists of a sequenced collection of records, each * containing variable length message text. Every record also contains its * own meta-data (@info). * * Every record meta-data carries the timestamp in microseconds, as well as * the standard userspace syslog level and syslog facility. The usual kernel * messages use LOG_KERN; userspace-injected messages always carry a matching * syslog facility, by default LOG_USER. The origin of every message can be * reliably determined that way. * * The human readable log message of a record is available in @text, the * length of the message text in @text_len. The stored message is not * terminated. * * Optionally, a record can carry a dictionary of properties (key/value * pairs), to provide userspace with a machine-readable message context. * * Examples for well-defined, commonly used property names are: * DEVICE=b12:8 device identifier * b12:8 block dev_t * c127:3 char dev_t * n8 netdev ifindex * +sound:card0 subsystem:devname * SUBSYSTEM=pci driver-core subsystem name * * Valid characters in property names are [a-zA-Z0-9.-_]. Property names * and values are terminated by a '\0' character. * * Example of record values: * record.text_buf = "it's a line" (unterminated) * record.info.seq = 56 * record.info.ts_nsec = 36863 * record.info.text_len = 11 * record.info.facility = 0 (LOG_KERN) * record.info.flags = 0 * record.info.level = 3 (LOG_ERR) * record.info.caller_id = 299 (task 299) * record.info.dev_info.subsystem = "pci" (terminated) * record.info.dev_info.device = "+pci:0000:00:01.0" (terminated) * * The 'struct printk_info' buffer must never be directly exported to * userspace, it is a kernel-private implementation detail that might * need to be changed in the future, when the requirements change. * * /dev/kmsg exports the structured data in the following line format: * "<level>,<sequnum>,<timestamp>,<contflag>[,additional_values, ... ];<message text>\n" * * Users of the export format should ignore possible additional values * separated by ',', and find the message after the ';' character. * * The optional key/value pairs are attached as continuation lines starting * with a space character and terminated by a newline. All possible * non-prinatable characters are escaped in the "\xff" notation. */ /* syslog_lock protects syslog_* variables and write access to clear_seq. */ static DEFINE_MUTEX(syslog_lock); /* * Specifies if a legacy console is registered. If legacy consoles are * present, it is necessary to perform the console lock/unlock dance * whenever console flushing should occur. */ bool have_legacy_console; /* * Specifies if an nbcon console is registered. If nbcon consoles are present, * synchronous printing of legacy consoles will not occur during panic until * the backtrace has been stored to the ringbuffer. */ bool have_nbcon_console; /* * Specifies if a boot console is registered. If boot consoles are present, * nbcon consoles cannot print simultaneously and must be synchronized by * the console lock. This is because boot consoles and nbcon consoles may * have mapped the same hardware. */ bool have_boot_console; /* See printk_legacy_allow_panic_sync() for details. */ bool legacy_allow_panic_sync; #ifdef CONFIG_PRINTK DECLARE_WAIT_QUEUE_HEAD(log_wait); static DECLARE_WAIT_QUEUE_HEAD(legacy_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ static u64 syslog_seq; static size_t syslog_partial; static bool syslog_time; /* True when _all_ printer threads are available for printing. */ bool printk_kthreads_running; struct latched_seq { seqcount_latch_t latch; u64 val[2]; }; /* * The next printk record to read after the last 'clear' command. There are * two copies (updated with seqcount_latch) so that reads can locklessly * access a valid value. Writers are synchronized by @syslog_lock. */ static struct latched_seq clear_seq = { .latch = SEQCNT_LATCH_ZERO(clear_seq.latch), .val[0] = 0, .val[1] = 0, }; #define LOG_LEVEL(v) ((v) & 0x07) #define LOG_FACILITY(v) ((v) >> 3 & 0xff) /* record buffer */ #define LOG_ALIGN __alignof__(unsigned long) #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) #define LOG_BUF_LEN_MAX ((u32)1 << 31) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); static char *log_buf = __log_buf; static u32 log_buf_len = __LOG_BUF_LEN; /* * Define the average message size. This only affects the number of * descriptors that will be available. Underestimating is better than * overestimating (too many available descriptors is better than not enough). */ #define PRB_AVGBITS 5 /* 32 character average length */ #if CONFIG_LOG_BUF_SHIFT <= PRB_AVGBITS #error CONFIG_LOG_BUF_SHIFT value too small. #endif _DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS, PRB_AVGBITS, &__log_buf[0]); static struct printk_ringbuffer printk_rb_dynamic; struct printk_ringbuffer *prb = &printk_rb_static; /* * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before * per_cpu_areas are initialised. This variable is set to true when * it's safe to access per-CPU data. */ static bool __printk_percpu_data_ready __ro_after_init; bool printk_percpu_data_ready(void) { return __printk_percpu_data_ready; } /* Must be called under syslog_lock. */ static void latched_seq_write(struct latched_seq *ls, u64 val) { write_seqcount_latch_begin(&ls->latch); ls->val[0] = val; write_seqcount_latch(&ls->latch); ls->val[1] = val; write_seqcount_latch_end(&ls->latch); } /* Can be called from any context. */ static u64 latched_seq_read_nolock(struct latched_seq *ls) { unsigned int seq; unsigned int idx; u64 val; do { seq = read_seqcount_latch(&ls->latch); idx = seq & 0x1; val = ls->val[idx]; } while (read_seqcount_latch_retry(&ls->latch, seq)); return val; } /* Return log buffer address */ char *log_buf_addr_get(void) { return log_buf; } /* Return log buffer size */ u32 log_buf_len_get(void) { return log_buf_len; } /* * Define how much of the log buffer we could take at maximum. The value * must be greater than two. Note that only half of the buffer is available * when the index points to the middle. */ #define MAX_LOG_TAKE_PART 4 static const char trunc_msg[] = "<truncated>"; static void truncate_msg(u16 *text_len, u16 *trunc_msg_len) { /* * The message should not take the whole buffer. Otherwise, it might * get removed too soon. */ u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART; if (*text_len > max_text_len) *text_len = max_text_len; /* enable the warning message (if there is room) */ *trunc_msg_len = strlen(trunc_msg); if (*text_len >= *trunc_msg_len) *text_len -= *trunc_msg_len; else *trunc_msg_len = 0; } int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT); static int syslog_action_restricted(int type) { if (dmesg_restrict) return 1; /* * Unless restricted, we allow "read all" and "get buffer size" * for everybody. */ return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER; } static int check_syslog_permissions(int type, int source) { /* * If this is from /proc/kmsg and we've already opened it, then we've * already done the capabilities checks at open time. */ if (source == SYSLOG_FROM_PROC && type != SYSLOG_ACTION_OPEN) goto ok; if (syslog_action_restricted(type)) { if (capable(CAP_SYSLOG)) goto ok; return -EPERM; } ok: return security_syslog(type); } static void append_char(char **pp, char *e, char c) { if (*pp < e) *(*pp)++ = c; } static ssize_t info_print_ext_header(char *buf, size_t size, struct printk_info *info) { u64 ts_usec = info->ts_nsec; char caller[20]; #ifdef CONFIG_PRINTK_CALLER u32 id = info->caller_id; snprintf(caller, sizeof(caller), ",caller=%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); #else caller[0] = '\0'; #endif do_div(ts_usec, 1000); return scnprintf(buf, size, "%u,%llu,%llu,%c%s;", (info->facility << 3) | info->level, info->seq, ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller); } static ssize_t msg_add_ext_text(char *buf, size_t size, const char *text, size_t text_len, unsigned char endc) { char *p = buf, *e = buf + size; size_t i; /* escape non-printable characters */ for (i = 0; i < text_len; i++) { unsigned char c = text[i]; if (c < ' ' || c >= 127 || c == '\\') p += scnprintf(p, e - p, "\\x%02x", c); else append_char(&p, e, c); } append_char(&p, e, endc); return p - buf; } static ssize_t msg_add_dict_text(char *buf, size_t size, const char *key, const char *val) { size_t val_len = strlen(val); ssize_t len; if (!val_len) return 0; len = msg_add_ext_text(buf, size, "", 0, ' '); /* dict prefix */ len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '='); len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n'); return len; } static ssize_t msg_print_ext_body(char *buf, size_t size, char *text, size_t text_len, struct dev_printk_info *dev_info) { ssize_t len; len = msg_add_ext_text(buf, size, text, text_len, '\n'); if (!dev_info) goto out; len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM", dev_info->subsystem); len += msg_add_dict_text(buf + len, size - len, "DEVICE", dev_info->device); out: return len; } /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { atomic64_t seq; struct ratelimit_state rs; struct mutex lock; struct printk_buffers pbufs; }; static __printf(3, 4) __cold int devkmsg_emit(int facility, int level, const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_emit(facility, level, NULL, fmt, args); va_end(args); return r; } static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) { char *buf, *line; int level = default_message_loglevel; int facility = 1; /* LOG_USER */ struct file *file = iocb->ki_filp; struct devkmsg_user *user = file->private_data; size_t len = iov_iter_count(from); ssize_t ret = len; if (len > PRINTKRB_RECORD_MAX) return -EINVAL; /* Ignore when user logging is disabled. */ if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) return len; /* Ratelimit when not explicitly enabled. */ if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) { if (!___ratelimit(&user->rs, current->comm)) return ret; } buf = kmalloc(len+1, GFP_KERNEL); if (buf == NULL) return -ENOMEM; buf[len] = '\0'; if (!copy_from_iter_full(buf, len, from)) { kfree(buf); return -EFAULT; } /* * Extract and skip the syslog prefix <[0-9]*>. Coming from userspace * the decimal value represents 32bit, the lower 3 bit are the log * level, the rest are the log facility. * * If no prefix or no userspace facility is specified, we * enforce LOG_USER, to be able to reliably distinguish * kernel-generated messages from userspace-injected ones. */ line = buf; if (line[0] == '<') { char *endp = NULL; unsigned int u; u = simple_strtoul(line + 1, &endp, 10); if (endp && endp[0] == '>') { level = LOG_LEVEL(u); if (LOG_FACILITY(u) != 0) facility = LOG_FACILITY(u); endp++; line = endp; } } devkmsg_emit(facility, level, "%s", line); kfree(buf); return ret; } static ssize_t devkmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct devkmsg_user *user = file->private_data; char *outbuf = &user->pbufs.outbuf[0]; struct printk_message pmsg = { .pbufs = &user->pbufs, }; ssize_t ret; ret = mutex_lock_interruptible(&user->lock); if (ret) return ret; if (!printk_get_next_message(&pmsg, atomic64_read(&user->seq), true, false)) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; goto out; } /* * Guarantee this task is visible on the waitqueue before * checking the wake condition. * * The full memory barrier within set_current_state() of * prepare_to_wait_event() pairs with the full memory barrier * within wq_has_sleeper(). * * This pairs with __wake_up_klogd:A. */ ret = wait_event_interruptible(log_wait, printk_get_next_message(&pmsg, atomic64_read(&user->seq), true, false)); /* LMM(devkmsg_read:A) */ if (ret) goto out; } if (pmsg.dropped) { /* our last seen message is gone, return error and reset */ atomic64_set(&user->seq, pmsg.seq); ret = -EPIPE; goto out; } atomic64_set(&user->seq, pmsg.seq + 1); if (pmsg.outbuf_len > count) { ret = -EINVAL; goto out; } if (copy_to_user(buf, outbuf, pmsg.outbuf_len)) { ret = -EFAULT; goto out; } ret = pmsg.outbuf_len; out: mutex_unlock(&user->lock); return ret; } /* * Be careful when modifying this function!!! * * Only few operations are supported because the device works only with the * entire variable length messages (records). Non-standard values are * returned in the other cases and has been this way for quite some time. * User space applications might depend on this behavior. */ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence) { struct devkmsg_user *user = file->private_data; loff_t ret = 0; if (offset) return -ESPIPE; switch (whence) { case SEEK_SET: /* the first record */ atomic64_set(&user->seq, prb_first_valid_seq(prb)); break; case SEEK_DATA: /* * The first record after the last SYSLOG_ACTION_CLEAR, * like issued by 'dmesg -c'. Reading /dev/kmsg itself * changes no global state, and does not clear anything. */ atomic64_set(&user->seq, latched_seq_read_nolock(&clear_seq)); break; case SEEK_END: /* after the last record */ atomic64_set(&user->seq, prb_next_seq(prb)); break; default: ret = -EINVAL; } return ret; } static __poll_t devkmsg_poll(struct file *file, poll_table *wait) { struct devkmsg_user *user = file->private_data; struct printk_info info; __poll_t ret = 0; poll_wait(file, &log_wait, wait); if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) { /* return error when data has vanished underneath us */ if (info.seq != atomic64_read(&user->seq)) ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI; else ret = EPOLLIN|EPOLLRDNORM; } return ret; } static int devkmsg_open(struct inode *inode, struct file *file) { struct devkmsg_user *user; int err; if (devkmsg_log & DEVKMSG_LOG_MASK_OFF) return -EPERM; /* write-only does not need any file context */ if ((file->f_flags & O_ACCMODE) != O_WRONLY) { err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, SYSLOG_FROM_READER); if (err) return err; } user = kvmalloc(sizeof(struct devkmsg_user), GFP_KERNEL); if (!user) return -ENOMEM; ratelimit_default_init(&user->rs); ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE); mutex_init(&user->lock); atomic64_set(&user->seq, prb_first_valid_seq(prb)); file->private_data = user; return 0; } static int devkmsg_release(struct inode *inode, struct file *file) { struct devkmsg_user *user = file->private_data; ratelimit_state_exit(&user->rs); mutex_destroy(&user->lock); kvfree(user); return 0; } const struct file_operations kmsg_fops = { .open = devkmsg_open, .read = devkmsg_read, .write_iter = devkmsg_write, .llseek = devkmsg_llseek, .poll = devkmsg_poll, .release = devkmsg_release, }; #ifdef CONFIG_VMCORE_INFO /* * This appends the listed symbols to /proc/vmcore * * /proc/vmcore is used by various utilities, like crash and makedumpfile to * obtain access to symbols that are otherwise very difficult to locate. These * symbols are specifically used so that utilities can access and extract the * dmesg log from a vmcore file after a crash. */ void log_buf_vmcoreinfo_setup(void) { struct dev_printk_info *dev_info = NULL; VMCOREINFO_SYMBOL(prb); VMCOREINFO_SYMBOL(printk_rb_static); VMCOREINFO_SYMBOL(clear_seq); /* * Export struct size and field offsets. User space tools can * parse it and detect any changes to structure down the line. */ VMCOREINFO_STRUCT_SIZE(printk_ringbuffer); VMCOREINFO_OFFSET(printk_ringbuffer, desc_ring); VMCOREINFO_OFFSET(printk_ringbuffer, text_data_ring); VMCOREINFO_OFFSET(printk_ringbuffer, fail); VMCOREINFO_STRUCT_SIZE(prb_desc_ring); VMCOREINFO_OFFSET(prb_desc_ring, count_bits); VMCOREINFO_OFFSET(prb_desc_ring, descs); VMCOREINFO_OFFSET(prb_desc_ring, infos); VMCOREINFO_OFFSET(prb_desc_ring, head_id); VMCOREINFO_OFFSET(prb_desc_ring, tail_id); VMCOREINFO_STRUCT_SIZE(prb_desc); VMCOREINFO_OFFSET(prb_desc, state_var); VMCOREINFO_OFFSET(prb_desc, text_blk_lpos); VMCOREINFO_STRUCT_SIZE(prb_data_blk_lpos); VMCOREINFO_OFFSET(prb_data_blk_lpos, begin); VMCOREINFO_OFFSET(prb_data_blk_lpos, next); VMCOREINFO_STRUCT_SIZE(printk_info); VMCOREINFO_OFFSET(printk_info, seq); VMCOREINFO_OFFSET(printk_info, ts_nsec); VMCOREINFO_OFFSET(printk_info, text_len); VMCOREINFO_OFFSET(printk_info, caller_id); VMCOREINFO_OFFSET(printk_info, dev_info); VMCOREINFO_STRUCT_SIZE(dev_printk_info); VMCOREINFO_OFFSET(dev_printk_info, subsystem); VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem)); VMCOREINFO_OFFSET(dev_printk_info, device); VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device)); VMCOREINFO_STRUCT_SIZE(prb_data_ring); VMCOREINFO_OFFSET(prb_data_ring, size_bits); VMCOREINFO_OFFSET(prb_data_ring, data); VMCOREINFO_OFFSET(prb_data_ring, head_lpos); VMCOREINFO_OFFSET(prb_data_ring, tail_lpos); VMCOREINFO_SIZE(atomic_long_t); VMCOREINFO_TYPE_OFFSET(atomic_long_t, counter); VMCOREINFO_STRUCT_SIZE(latched_seq); VMCOREINFO_OFFSET(latched_seq, val); } #endif /* requested log_buf_len from kernel cmdline */ static unsigned long __initdata new_log_buf_len; /* we practice scaling the ring buffer by powers of 2 */ static void __init log_buf_len_update(u64 size) { if (size > (u64)LOG_BUF_LEN_MAX) { size = (u64)LOG_BUF_LEN_MAX; pr_err("log_buf over 2G is not supported.\n"); } if (size) size = roundup_pow_of_two(size); if (size > log_buf_len) new_log_buf_len = (unsigned long)size; } /* save requested log_buf_len since it's too early to process it */ static int __init log_buf_len_setup(char *str) { u64 size; if (!str) return -EINVAL; size = memparse(str, &str); log_buf_len_update(size); return 0; } early_param("log_buf_len", log_buf_len_setup); #ifdef CONFIG_SMP #define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT) static void __init log_buf_add_cpu(void) { unsigned int cpu_extra; /* * archs should set up cpu_possible_bits properly with * set_cpu_possible() after setup_arch() but just in * case lets ensure this is valid. */ if (num_possible_cpus() == 1) return; cpu_extra = (num_possible_cpus() - 1) * __LOG_CPU_MAX_BUF_LEN; /* by default this will only continue through for large > 64 CPUs */ if (cpu_extra <= __LOG_BUF_LEN / 2) return; pr_info("log_buf_len individual max cpu contribution: %d bytes\n", __LOG_CPU_MAX_BUF_LEN); pr_info("log_buf_len total cpu_extra contributions: %d bytes\n", cpu_extra); pr_info("log_buf_len min size: %d bytes\n", __LOG_BUF_LEN); log_buf_len_update(cpu_extra + __LOG_BUF_LEN); } #else /* !CONFIG_SMP */ static inline void log_buf_add_cpu(void) {} #endif /* CONFIG_SMP */ static void __init set_percpu_data_ready(void) { __printk_percpu_data_ready = true; } static unsigned int __init add_to_rb(struct printk_ringbuffer *rb, struct printk_record *r) { struct prb_reserved_entry e; struct printk_record dest_r; prb_rec_init_wr(&dest_r, r->info->text_len); if (!prb_reserve(&e, rb, &dest_r)) return 0; memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len); dest_r.info->text_len = r->info->text_len; dest_r.info->facility = r->info->facility; dest_r.info->level = r->info->level; dest_r.info->flags = r->info->flags; dest_r.info->ts_nsec = r->info->ts_nsec; dest_r.info->caller_id = r->info->caller_id; memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info)); prb_final_commit(&e); return prb_record_text_space(&e); } static char setup_text_buf[PRINTKRB_RECORD_MAX] __initdata; static void print_log_buf_usage_stats(void) { unsigned int descs_count = log_buf_len >> PRB_AVGBITS; size_t meta_data_size; meta_data_size = descs_count * (sizeof(struct prb_desc) + sizeof(struct printk_info)); pr_info("log buffer data + meta data: %u + %zu = %zu bytes\n", log_buf_len, meta_data_size, log_buf_len + meta_data_size); } void __init setup_log_buf(int early) { struct printk_info *new_infos; unsigned int new_descs_count; struct prb_desc *new_descs; struct printk_info info; struct printk_record r; unsigned int text_size; size_t new_descs_size; size_t new_infos_size; unsigned long flags; char *new_log_buf; unsigned int free; u64 seq; /* * Some archs call setup_log_buf() multiple times - first is very * early, e.g. from setup_arch(), and second - when percpu_areas * are initialised. */ if (!early) set_percpu_data_ready(); if (log_buf != __log_buf) return; if (!early && !new_log_buf_len) log_buf_add_cpu(); if (!new_log_buf_len) { /* Show the memory stats only once. */ if (!early) goto out; return; } new_descs_count = new_log_buf_len >> PRB_AVGBITS; if (new_descs_count == 0) { pr_err("new_log_buf_len: %lu too small\n", new_log_buf_len); goto out; } new_log_buf = memblock_alloc(new_log_buf_len, LOG_ALIGN); if (unlikely(!new_log_buf)) { pr_err("log_buf_len: %lu text bytes not available\n", new_log_buf_len); goto out; } new_descs_size = new_descs_count * sizeof(struct prb_desc); new_descs = memblock_alloc(new_descs_size, LOG_ALIGN); if (unlikely(!new_descs)) { pr_err("log_buf_len: %zu desc bytes not available\n", new_descs_size); goto err_free_log_buf; } new_infos_size = new_descs_count * sizeof(struct printk_info); new_infos = memblock_alloc(new_infos_size, LOG_ALIGN); if (unlikely(!new_infos)) { pr_err("log_buf_len: %zu info bytes not available\n", new_infos_size); goto err_free_descs; } prb_rec_init_rd(&r, &info, &setup_text_buf[0], sizeof(setup_text_buf)); prb_init(&printk_rb_dynamic, new_log_buf, ilog2(new_log_buf_len), new_descs, ilog2(new_descs_count), new_infos); local_irq_save(flags); log_buf_len = new_log_buf_len; log_buf = new_log_buf; new_log_buf_len = 0; free = __LOG_BUF_LEN; prb_for_each_record(0, &printk_rb_static, seq, &r) { text_size = add_to_rb(&printk_rb_dynamic, &r); if (text_size > free) free = 0; else free -= text_size; } prb = &printk_rb_dynamic; local_irq_restore(flags); /* * Copy any remaining messages that might have appeared from * NMI context after copying but before switching to the * dynamic buffer. */ prb_for_each_record(seq, &printk_rb_static, seq, &r) { text_size = add_to_rb(&printk_rb_dynamic, &r); if (text_size > free) free = 0; else free -= text_size; } if (seq != prb_next_seq(&printk_rb_static)) { pr_err("dropped %llu messages\n", prb_next_seq(&printk_rb_static) - seq); } print_log_buf_usage_stats(); pr_info("early log buf free: %u(%u%%)\n", free, (free * 100) / __LOG_BUF_LEN); return; err_free_descs: memblock_free(new_descs, new_descs_size); err_free_log_buf: memblock_free(new_log_buf, new_log_buf_len); out: print_log_buf_usage_stats(); } static bool __read_mostly ignore_loglevel; static int __init ignore_loglevel_setup(char *str) { ignore_loglevel = true; pr_info("debug: ignoring loglevel setting.\n"); return 0; } early_param("ignore_loglevel", ignore_loglevel_setup); module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting (prints all kernel messages to the console)"); static bool suppress_message_printing(int level) { return (level >= console_loglevel && !ignore_loglevel); } #ifdef CONFIG_BOOT_PRINTK_DELAY static int boot_delay; /* msecs delay after each printk during bootup */ static unsigned long long loops_per_msec; /* based on boot_delay */ static int __init boot_delay_setup(char *str) { unsigned long lpj; lpj = preset_lpj ? preset_lpj : 1000000; /* some guess */ loops_per_msec = (unsigned long long)lpj / 1000 * HZ; get_option(&str, &boot_delay); if (boot_delay > 10 * 1000) boot_delay = 0; pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, " "HZ: %d, loops_per_msec: %llu\n", boot_delay, preset_lpj, lpj, HZ, loops_per_msec); return 0; } early_param("boot_delay", boot_delay_setup); static void boot_delay_msec(int level) { unsigned long long k; unsigned long timeout; bool suppress = !is_printk_force_console() && suppress_message_printing(level); if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING) || suppress) return; k = (unsigned long long)loops_per_msec * boot_delay; timeout = jiffies + msecs_to_jiffies(boot_delay); while (k) { k--; cpu_relax(); /* * use (volatile) jiffies to prevent * compiler reduction; loop termination via jiffies * is secondary and may or may not happen. */ if (time_after(jiffies, timeout)) break; touch_nmi_watchdog(); } } #else static inline void boot_delay_msec(int level) { } #endif static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME); module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR); static size_t print_syslog(unsigned int level, char *buf) { return sprintf(buf, "<%u>", level); } static size_t print_time(u64 ts, char *buf) { unsigned long rem_nsec = do_div(ts, 1000000000); return sprintf(buf, "[%5lu.%06lu]", (unsigned long)ts, rem_nsec / 1000); } #ifdef CONFIG_PRINTK_CALLER static size_t print_caller(u32 id, char *buf) { char caller[12]; snprintf(caller, sizeof(caller), "%c%u", id & 0x80000000 ? 'C' : 'T', id & ~0x80000000); return sprintf(buf, "[%6s]", caller); } #else #define print_caller(id, buf) 0 #endif static size_t info_print_prefix(const struct printk_info *info, bool syslog, bool time, char *buf) { size_t len = 0; if (syslog) len = print_syslog((info->facility << 3) | info->level, buf); if (time) len += print_time(info->ts_nsec, buf + len); len += print_caller(info->caller_id, buf + len); if (IS_ENABLED(CONFIG_PRINTK_CALLER) || time) { buf[len++] = ' '; buf[len] = '\0'; } return len; } /* * Prepare the record for printing. The text is shifted within the given * buffer to avoid a need for another one. The following operations are * done: * * - Add prefix for each line. * - Drop truncated lines that no longer fit into the buffer. * - Add the trailing newline that has been removed in vprintk_store(). * - Add a string terminator. * * Since the produced string is always terminated, the maximum possible * return value is @r->text_buf_size - 1; * * Return: The length of the updated/prepared text, including the added * prefixes and the newline. The terminator is not counted. The dropped * line(s) are not counted. */ static size_t record_print_text(struct printk_record *r, bool syslog, bool time) { size_t text_len = r->info->text_len; size_t buf_size = r->text_buf_size; char *text = r->text_buf; char prefix[PRINTK_PREFIX_MAX]; bool truncated = false; size_t prefix_len; size_t line_len; size_t len = 0; char *next; /* * If the message was truncated because the buffer was not large * enough, treat the available text as if it were the full text. */ if (text_len > buf_size) text_len = buf_size; prefix_len = info_print_prefix(r->info, syslog, time, prefix); /* * @text_len: bytes of unprocessed text * @line_len: bytes of current line _without_ newline * @text: pointer to beginning of current line * @len: number of bytes prepared in r->text_buf */ for (;;) { next = memchr(text, '\n', text_len); if (next) { line_len = next - text; } else { /* Drop truncated line(s). */ if (truncated) break; line_len = text_len; } /* * Truncate the text if there is not enough space to add the * prefix and a trailing newline and a terminator. */ if (len + prefix_len + text_len + 1 + 1 > buf_size) { /* Drop even the current line if no space. */ if (len + prefix_len + line_len + 1 + 1 > buf_size) break; text_len = buf_size - len - prefix_len - 1 - 1; truncated = true; } memmove(text + prefix_len, text, text_len); memcpy(text, prefix, prefix_len); /* * Increment the prepared length to include the text and * prefix that were just moved+copied. Also increment for the * newline at the end of this line. If this is the last line, * there is no newline, but it will be added immediately below. */ len += prefix_len + line_len + 1; if (text_len == line_len) { /* * This is the last line. Add the trailing newline * removed in vprintk_store(). */ text[prefix_len + line_len] = '\n'; break; } /* * Advance beyond the added prefix and the related line with * its newline. */ text += prefix_len + line_len + 1; /* * The remaining text has only decreased by the line with its * newline. * * Note that @text_len can become zero. It happens when @text * ended with a newline (either due to truncation or the * original string ending with "\n\n"). The loop is correctly * repeated and (if not truncated) an empty line with a prefix * will be prepared. */ text_len -= line_len + 1; } /* * If a buffer was provided, it will be terminated. Space for the * string terminator is guaranteed to be available. The terminator is * not counted in the return value. */ if (buf_size > 0) r->text_buf[len] = 0; return len; } static size_t get_record_print_text_size(struct printk_info *info, unsigned int line_count, bool syslog, bool time) { char prefix[PRINTK_PREFIX_MAX]; size_t prefix_len; prefix_len = info_print_prefix(info, syslog, time, prefix); /* * Each line will be preceded with a prefix. The intermediate * newlines are already within the text, but a final trailing * newline will be added. */ return ((prefix_len * line_count) + info->text_len + 1); } /* * Beginning with @start_seq, find the first record where it and all following * records up to (but not including) @max_seq fit into @size. * * @max_seq is simply an upper bound and does not need to exist. If the caller * does not require an upper bound, -1 can be used for @max_seq. */ static u64 find_first_fitting_seq(u64 start_seq, u64 max_seq, size_t size, bool syslog, bool time) { struct printk_info info; unsigned int line_count; size_t len = 0; u64 seq; /* Determine the size of the records up to @max_seq. */ prb_for_each_info(start_seq, prb, seq, &info, &line_count) { if (info.seq >= max_seq) break; len += get_record_print_text_size(&info, line_count, syslog, time); } /* * Adjust the upper bound for the next loop to avoid subtracting * lengths that were never added. */ if (seq < max_seq) max_seq = seq; /* * Move first record forward until length fits into the buffer. Ignore * newest messages that were not counted in the above cycle. Messages * might appear and get lost in the meantime. This is a best effort * that prevents an infinite loop that could occur with a retry. */ prb_for_each_info(start_seq, prb, seq, &info, &line_count) { if (len <= size || info.seq >= max_seq) break; len -= get_record_print_text_size(&info, line_count, syslog, time); } return seq; } /* The caller is responsible for making sure @size is greater than 0. */ static int syslog_print(char __user *buf, int size) { struct printk_info info; struct printk_record r; char *text; int len = 0; u64 seq; text = kmalloc(PRINTK_MESSAGE_MAX, GFP_KERNEL); if (!text) return -ENOMEM; prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX); mutex_lock(&syslog_lock); /* * Wait for the @syslog_seq record to be available. @syslog_seq may * change while waiting. */ do { seq = syslog_seq; mutex_unlock(&syslog_lock); /* * Guarantee this task is visible on the waitqueue before * checking the wake condition. * * The full memory barrier within set_current_state() of * prepare_to_wait_event() pairs with the full memory barrier * within wq_has_sleeper(). * * This pairs with __wake_up_klogd:A. */ len = wait_event_interruptible(log_wait, prb_read_valid(prb, seq, NULL)); /* LMM(syslog_print:A) */ mutex_lock(&syslog_lock); if (len) goto out; } while (syslog_seq != seq); /* * Copy records that fit into the buffer. The above cycle makes sure * that the first record is always available. */ do { size_t n; size_t skip; int err; if (!prb_read_valid(prb, syslog_seq, &r)) break; if (r.info->seq != syslog_seq) { /* message is gone, move to next valid one */ syslog_seq = r.info->seq; syslog_partial = 0; } /* * To keep reading/counting partial line consistent, * use printk_time value as of the beginning of a line. */ if (!syslog_partial) syslog_time = printk_time; skip = syslog_partial; n = record_print_text(&r, true, syslog_time); if (n - syslog_partial <= size) { /* message fits into buffer, move forward */ syslog_seq = r.info->seq + 1; n -= syslog_partial; syslog_partial = 0; } else if (!len){ /* partial read(), remember position */ n = size; syslog_partial += n; } else n = 0; if (!n) break; mutex_unlock(&syslog_lock); err = copy_to_user(buf, text + skip, n); mutex_lock(&syslog_lock); if (err) { if (!len) len = -EFAULT; break; } len += n; size -= n; buf += n; } while (size); out: mutex_unlock(&syslog_lock); kfree(text); return len; } static int syslog_print_all(char __user *buf, int size, bool clear) { struct printk_info info; struct printk_record r; char *text; int len = 0; u64 seq; bool time; text = kmalloc(PRINTK_MESSAGE_MAX, GFP_KERNEL); if (!text) return -ENOMEM; time = printk_time; /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. */ seq = find_first_fitting_seq(latched_seq_read_nolock(&clear_seq), -1, size, true, time); prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX); prb_for_each_record(seq, prb, seq, &r) { int textlen; textlen = record_print_text(&r, true, time); if (len + textlen > size) { seq--; break; } if (copy_to_user(buf + len, text, textlen)) len = -EFAULT; else len += textlen; if (len < 0) break; } if (clear) { mutex_lock(&syslog_lock); latched_seq_write(&clear_seq, seq); mutex_unlock(&syslog_lock); } kfree(text); return len; } static void syslog_clear(void) { mutex_lock(&syslog_lock); latched_seq_write(&clear_seq, prb_next_seq(prb)); mutex_unlock(&syslog_lock); } int do_syslog(int type, char __user *buf, int len, int source) { struct printk_info info; bool clear = false; static int saved_console_loglevel = LOGLEVEL_DEFAULT; int error; error = check_syslog_permissions(type, source); if (error) return error; switch (type) { case SYSLOG_ACTION_CLOSE: /* Close log */ break; case SYSLOG_ACTION_OPEN: /* Open log */ break; case SYSLOG_ACTION_READ: /* Read from log */ if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(buf, len)) return -EFAULT; error = syslog_print(buf, len); break; /* Read/clear last kernel messages */ case SYSLOG_ACTION_READ_CLEAR: clear = true; fallthrough; /* Read last kernel messages */ case SYSLOG_ACTION_READ_ALL: if (!buf || len < 0) return -EINVAL; if (!len) return 0; if (!access_ok(buf, len)) return -EFAULT; error = syslog_print_all(buf, len, clear); break; /* Clear ring buffer */ case SYSLOG_ACTION_CLEAR: syslog_clear(); break; /* Disable logging to console */ case SYSLOG_ACTION_CONSOLE_OFF: if (saved_console_loglevel == LOGLEVEL_DEFAULT) saved_console_loglevel = console_loglevel; console_loglevel = minimum_console_loglevel; break; /* Enable logging to console */ case SYSLOG_ACTION_CONSOLE_ON: if (saved_console_loglevel != LOGLEVEL_DEFAULT) { console_loglevel = saved_console_loglevel; saved_console_loglevel = LOGLEVEL_DEFAULT; } break; /* Set level of messages printed to console */ case SYSLOG_ACTION_CONSOLE_LEVEL: if (len < 1 || len > 8) return -EINVAL; if (len < minimum_console_loglevel) len = minimum_console_loglevel; console_loglevel = len; /* Implicitly re-enable logging to console */ saved_console_loglevel = LOGLEVEL_DEFAULT; break; /* Number of chars in the log buffer */ case SYSLOG_ACTION_SIZE_UNREAD: mutex_lock(&syslog_lock); if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) { /* No unread messages. */ mutex_unlock(&syslog_lock); return 0; } if (info.seq != syslog_seq) { /* messages are gone, move to first one */ syslog_seq = info.seq; syslog_partial = 0; } if (source == SYSLOG_FROM_PROC) { /* * Short-cut for poll(/"proc/kmsg") which simply checks * for pending data, not the size; return the count of * records, not the length. */ error = prb_next_seq(prb) - syslog_seq; } else { bool time = syslog_partial ? syslog_time : printk_time; unsigned int line_count; u64 seq; prb_for_each_info(syslog_seq, prb, seq, &info, &line_count) { error += get_record_print_text_size(&info, line_count, true, time); time = printk_time; } error -= syslog_partial; } mutex_unlock(&syslog_lock); break; /* Size of the log buffer */ case SYSLOG_ACTION_SIZE_BUFFER: error = log_buf_len; break; default: error = -EINVAL; break; } return error; } SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { return do_syslog(type, buf, len, SYSLOG_FROM_READER); } /* * Special console_lock variants that help to reduce the risk of soft-lockups. * They allow to pass console_lock to another printk() call using a busy wait. */ #ifdef CONFIG_LOCKDEP static struct lockdep_map console_owner_dep_map = { .name = "console_owner" }; #endif static DEFINE_RAW_SPINLOCK(console_owner_lock); static struct task_struct *console_owner; static bool console_waiter; /** * console_lock_spinning_enable - mark beginning of code where another * thread might safely busy wait * * This basically converts console_lock into a spinlock. This marks * the section where the console_lock owner can not sleep, because * there may be a waiter spinning (like a spinlock). Also it must be * ready to hand over the lock at the end of the section. */ void console_lock_spinning_enable(void) { /* * Do not use spinning in panic(). The panic CPU wants to keep the lock. * Non-panic CPUs abandon the flush anyway. * * Just keep the lockdep annotation. The panic-CPU should avoid * taking console_owner_lock because it might cause a deadlock. * This looks like the easiest way how to prevent false lockdep * reports without handling races a lockless way. */ if (panic_in_progress()) goto lockdep; raw_spin_lock(&console_owner_lock); console_owner = current; raw_spin_unlock(&console_owner_lock); lockdep: /* The waiter may spin on us after setting console_owner */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); } /** * console_lock_spinning_disable_and_check - mark end of code where another * thread was able to busy wait and check if there is a waiter * @cookie: cookie returned from console_srcu_read_lock() * * This is called at the end of the section where spinning is allowed. * It has two functions. First, it is a signal that it is no longer * safe to start busy waiting for the lock. Second, it checks if * there is a busy waiter and passes the lock rights to her. * * Important: Callers lose both the console_lock and the SRCU read lock if * there was a busy waiter. They must not touch items synchronized by * console_lock or SRCU read lock in this case. * * Return: 1 if the lock rights were passed, 0 otherwise. */ int console_lock_spinning_disable_and_check(int cookie) { int waiter; /* * Ignore spinning waiters during panic() because they might get stopped * or blocked at any time, * * It is safe because nobody is allowed to start spinning during panic * in the first place. If there has been a waiter then non panic CPUs * might stay spinning. They would get stopped anyway. The panic context * will never start spinning and an interrupted spin on panic CPU will * never continue. */ if (panic_in_progress()) { /* Keep lockdep happy. */ spin_release(&console_owner_dep_map, _THIS_IP_); return 0; } raw_spin_lock(&console_owner_lock); waiter = READ_ONCE(console_waiter); console_owner = NULL; raw_spin_unlock(&console_owner_lock); if (!waiter) { spin_release(&console_owner_dep_map, _THIS_IP_); return 0; } /* The waiter is now free to continue */ WRITE_ONCE(console_waiter, false); spin_release(&console_owner_dep_map, _THIS_IP_); /* * Preserve lockdep lock ordering. Release the SRCU read lock before * releasing the console_lock. */ console_srcu_read_unlock(cookie); /* * Hand off console_lock to waiter. The waiter will perform * the up(). After this, the waiter is the console_lock owner. */ mutex_release(&console_lock_dep_map, _THIS_IP_); return 1; } /** * console_trylock_spinning - try to get console_lock by busy waiting * * This allows to busy wait for the console_lock when the current * owner is running in specially marked sections. It means that * the current owner is running and cannot reschedule until it * is ready to lose the lock. * * Return: 1 if we got the lock, 0 othrewise */ static int console_trylock_spinning(void) { struct task_struct *owner = NULL; bool waiter; bool spin = false; unsigned long flags; if (console_trylock()) return 1; /* * It's unsafe to spin once a panic has begun. If we are the * panic CPU, we may have already halted the owner of the * console_sem. If we are not the panic CPU, then we should * avoid taking console_sem, so the panic CPU has a better * chance of cleanly acquiring it later. */ if (panic_in_progress()) return 0; printk_safe_enter_irqsave(flags); raw_spin_lock(&console_owner_lock); owner = READ_ONCE(console_owner); waiter = READ_ONCE(console_waiter); if (!waiter && owner && owner != current) { WRITE_ONCE(console_waiter, true); spin = true; } raw_spin_unlock(&console_owner_lock); /* * If there is an active printk() writing to the * consoles, instead of having it write our data too, * see if we can offload that load from the active * printer, and do some printing ourselves. * Go into a spin only if there isn't already a waiter * spinning, and there is an active printer, and * that active printer isn't us (recursive printk?). */ if (!spin) { printk_safe_exit_irqrestore(flags); return 0; } /* We spin waiting for the owner to release us */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); /* Owner will clear console_waiter on hand off */ while (READ_ONCE(console_waiter)) cpu_relax(); spin_release(&console_owner_dep_map, _THIS_IP_); printk_safe_exit_irqrestore(flags); /* * The owner passed the console lock to us. * Since we did not spin on console lock, annotate * this as a trylock. Otherwise lockdep will * complain. */ mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_); /* * Update @console_may_schedule for trylock because the previous * owner may have been schedulable. */ console_may_schedule = 0; return 1; } /* * Recursion is tracked separately on each CPU. If NMIs are supported, an * additional NMI context per CPU is also separately tracked. Until per-CPU * is available, a separate "early tracking" is performed. */ static DEFINE_PER_CPU(u8, printk_count); static u8 printk_count_early; #ifdef CONFIG_HAVE_NMI static DEFINE_PER_CPU(u8, printk_count_nmi); static u8 printk_count_nmi_early; #endif /* * Recursion is limited to keep the output sane. printk() should not require * more than 1 level of recursion (allowing, for example, printk() to trigger * a WARN), but a higher value is used in case some printk-internal errors * exist, such as the ringbuffer validation checks failing. */ #define PRINTK_MAX_RECURSION 3 /* * Return a pointer to the dedicated counter for the CPU+context of the * caller. */ static u8 *__printk_recursion_counter(void) { #ifdef CONFIG_HAVE_NMI if (in_nmi()) { if (printk_percpu_data_ready()) return this_cpu_ptr(&printk_count_nmi); return &printk_count_nmi_early; } #endif if (printk_percpu_data_ready()) return this_cpu_ptr(&printk_count); return &printk_count_early; } /* * Enter recursion tracking. Interrupts are disabled to simplify tracking. * The caller must check the boolean return value to see if the recursion is * allowed. On failure, interrupts are not disabled. * * @recursion_ptr must be a variable of type (u8 *) and is the same variable * that is passed to printk_exit_irqrestore(). */ #define printk_enter_irqsave(recursion_ptr, flags) \ ({ \ bool success = true; \ \ typecheck(u8 *, recursion_ptr); \ local_irq_save(flags); \ (recursion_ptr) = __printk_recursion_counter(); \ if (*(recursion_ptr) > PRINTK_MAX_RECURSION) { \ local_irq_restore(flags); \ success = false; \ } else { \ (*(recursion_ptr))++; \ } \ success; \ }) /* Exit recursion tracking, restoring interrupts. */ #define printk_exit_irqrestore(recursion_ptr, flags) \ do { \ typecheck(u8 *, recursion_ptr); \ (*(recursion_ptr))--; \ local_irq_restore(flags); \ } while (0) int printk_delay_msec __read_mostly; static inline void printk_delay(int level) { boot_delay_msec(level); if (unlikely(printk_delay_msec)) { int m = printk_delay_msec; while (m--) { mdelay(1); touch_nmi_watchdog(); } } } static inline u32 printk_caller_id(void) { return in_task() ? task_pid_nr(current) : 0x80000000 + smp_processor_id(); } /** * printk_parse_prefix - Parse level and control flags. * * @text: The terminated text message. * @level: A pointer to the current level value, will be updated. * @flags: A pointer to the current printk_info flags, will be updated. * * @level may be NULL if the caller is not interested in the parsed value. * Otherwise the variable pointed to by @level must be set to * LOGLEVEL_DEFAULT in order to be updated with the parsed value. * * @flags may be NULL if the caller is not interested in the parsed value. * Otherwise the variable pointed to by @flags will be OR'd with the parsed * value. * * Return: The length of the parsed level and control flags. */ u16 printk_parse_prefix(const char *text, int *level, enum printk_info_flags *flags) { u16 prefix_len = 0; int kern_level; while (*text) { kern_level = printk_get_level(text); if (!kern_level) break; switch (kern_level) { case '0' ... '7': if (level && *level == LOGLEVEL_DEFAULT) *level = kern_level - '0'; break; case 'c': /* KERN_CONT */ if (flags) *flags |= LOG_CONT; } prefix_len += 2; text += 2; } return prefix_len; } __printf(5, 0) static u16 printk_sprint(char *text, u16 size, int facility, enum printk_info_flags *flags, const char *fmt, va_list args) { u16 text_len; text_len = vscnprintf(text, size, fmt, args); /* Mark and strip a trailing newline. */ if (text_len && text[text_len - 1] == '\n') { text_len--; *flags |= LOG_NEWLINE; } /* Strip log level and control flags. */ if (facility == 0) { u16 prefix_len; prefix_len = printk_parse_prefix(text, NULL, NULL); if (prefix_len) { text_len -= prefix_len; memmove(text, text + prefix_len, text_len); } } trace_console(text, text_len); return text_len; } __printf(4, 0) int vprintk_store(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { struct prb_reserved_entry e; enum printk_info_flags flags = 0; struct printk_record r; unsigned long irqflags; u16 trunc_msg_len = 0; char prefix_buf[8]; u8 *recursion_ptr; u16 reserve_size; va_list args2; u32 caller_id; u16 text_len; int ret = 0; u64 ts_nsec; if (!printk_enter_irqsave(recursion_ptr, irqflags)) return 0; /* * Since the duration of printk() can vary depending on the message * and state of the ringbuffer, grab the timestamp now so that it is * close to the call of printk(). This provides a more deterministic * timestamp with respect to the caller. */ ts_nsec = local_clock(); caller_id = printk_caller_id(); /* * The sprintf needs to come first since the syslog prefix might be * passed in as a parameter. An extra byte must be reserved so that * later the vscnprintf() into the reserved buffer has room for the * terminating '\0', which is not counted by vsnprintf(). */ va_copy(args2, args); reserve_size = vsnprintf(&prefix_buf[0], sizeof(prefix_buf), fmt, args2) + 1; va_end(args2); if (reserve_size > PRINTKRB_RECORD_MAX) reserve_size = PRINTKRB_RECORD_MAX; /* Extract log level or control flags. */ if (facility == 0) printk_parse_prefix(&prefix_buf[0], &level, &flags); if (level == LOGLEVEL_DEFAULT) level = default_message_loglevel; if (dev_info) flags |= LOG_NEWLINE; if (is_printk_force_console()) flags |= LOG_FORCE_CON; if (flags & LOG_CONT) { prb_rec_init_wr(&r, reserve_size); if (prb_reserve_in_last(&e, prb, &r, caller_id, PRINTKRB_RECORD_MAX)) { text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size, facility, &flags, fmt, args); r.info->text_len += text_len; if (flags & LOG_FORCE_CON) r.info->flags |= LOG_FORCE_CON; if (flags & LOG_NEWLINE) { r.info->flags |= LOG_NEWLINE; prb_final_commit(&e); } else { prb_commit(&e); } ret = text_len; goto out; } } /* * Explicitly initialize the record before every prb_reserve() call. * prb_reserve_in_last() and prb_reserve() purposely invalidate the * structure when they fail. */ prb_rec_init_wr(&r, reserve_size); if (!prb_reserve(&e, prb, &r)) { /* truncate the message if it is too long for empty buffer */ truncate_msg(&reserve_size, &trunc_msg_len); prb_rec_init_wr(&r, reserve_size + trunc_msg_len); if (!prb_reserve(&e, prb, &r)) goto out; } /* fill message */ text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &flags, fmt, args); if (trunc_msg_len) memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len); r.info->text_len = text_len + trunc_msg_len; r.info->facility = facility; r.info->level = level & 7; r.info->flags = flags & 0x1f; r.info->ts_nsec = ts_nsec; r.info->caller_id = caller_id; if (dev_info) memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info)); /* A message without a trailing newline can be continued. */ if (!(flags & LOG_NEWLINE)) prb_commit(&e); else prb_final_commit(&e); ret = text_len + trunc_msg_len; out: printk_exit_irqrestore(recursion_ptr, irqflags); return ret; } /* * This acts as a one-way switch to allow legacy consoles to print from * the printk() caller context on a panic CPU. It also attempts to flush * the legacy consoles in this context. */ void printk_legacy_allow_panic_sync(void) { struct console_flush_type ft; legacy_allow_panic_sync = true; printk_get_console_flush_type(&ft); if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } } bool __read_mostly debug_non_panic_cpus; #ifdef CONFIG_PRINTK_CALLER static int __init debug_non_panic_cpus_setup(char *str) { debug_non_panic_cpus = true; pr_info("allow messages from non-panic CPUs in panic()\n"); return 0; } early_param("debug_non_panic_cpus", debug_non_panic_cpus_setup); module_param(debug_non_panic_cpus, bool, 0644); MODULE_PARM_DESC(debug_non_panic_cpus, "allow messages from non-panic CPUs in panic()"); #endif asmlinkage int vprintk_emit(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args) { struct console_flush_type ft; int printed_len; /* Suppress unimportant messages after panic happens */ if (unlikely(suppress_printk)) return 0; /* * The messages on the panic CPU are the most important. If * non-panic CPUs are generating any messages, they will be * silently dropped. */ if (panic_on_other_cpu() && !debug_non_panic_cpus && !panic_triggering_all_cpu_backtrace) return 0; printk_get_console_flush_type(&ft); /* If called from the scheduler, we can not call up(). */ if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; ft.legacy_offload |= ft.legacy_direct; ft.legacy_direct = false; } printk_delay(level); printed_len = vprintk_store(facility, level, dev_info, fmt, args); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_direct) { /* * The caller may be holding system-critical or * timing-sensitive locks. Disable preemption during * printing of all remaining records to all consoles so that * this context can return as soon as possible. Hopefully * another printk() caller will take over the printing. */ preempt_disable(); /* * Try to acquire and then immediately release the console * semaphore. The release will print out buffers. With the * spinning variant, this context tries to take over the * printing from another printing context. */ if (console_trylock_spinning()) console_unlock(); preempt_enable(); } if (ft.legacy_offload) defer_console_output(); else wake_up_klogd(); return printed_len; } EXPORT_SYMBOL(vprintk_emit); int vprintk_default(const char *fmt, va_list args) { return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args); } EXPORT_SYMBOL_GPL(vprintk_default); asmlinkage __visible int _printk(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk(fmt, args); va_end(args); return r; } EXPORT_SYMBOL(_printk); static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress); #else /* CONFIG_PRINTK */ #define printk_time false #define prb_read_valid(rb, seq, r) false #define prb_first_valid_seq(rb) 0 #define prb_next_seq(rb) 0 static u64 syslog_seq; static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; } #endif /* CONFIG_PRINTK */ #ifdef CONFIG_EARLY_PRINTK struct console *early_console; asmlinkage __visible void early_printk(const char *fmt, ...) { va_list ap; char buf[512]; int n; if (!early_console) return; va_start(ap, fmt); n = vscnprintf(buf, sizeof(buf), fmt, ap); va_end(ap); early_console->write(early_console, buf, n); } #endif static void set_user_specified(struct console_cmdline *c, bool user_specified) { if (!user_specified) return; /* * @c console was defined by the user on the command line. * Do not clear when added twice also by SPCR or the device tree. */ c->user_specified = true; /* At least one console defined by the user on the command line. */ console_set_on_cmdline = 1; } static int __add_preferred_console(const char *name, const short idx, const char *devname, char *options, char *brl_options, bool user_specified) { struct console_cmdline *c; int i; if (!name && !devname) return -EINVAL; /* * We use a signed short index for struct console for device drivers to * indicate a not yet assigned index or port. However, a negative index * value is not valid when the console name and index are defined on * the command line. */ if (name && idx < 0) return -EINVAL; /* * See if this tty is not yet registered, and * if we have a slot free. */ for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]); i++, c++) { if ((name && strcmp(c->name, name) == 0 && c->index == idx) || (devname && strcmp(c->devname, devname) == 0)) { if (!brl_options) preferred_console = i; set_user_specified(c, user_specified); return 0; } } if (i == MAX_CMDLINECONSOLES) return -E2BIG; if (!brl_options) preferred_console = i; if (name) strscpy(c->name, name); if (devname) strscpy(c->devname, devname); c->options = options; set_user_specified(c, user_specified); braille_set_options(c, brl_options); c->index = idx; return 0; } static int __init console_msg_format_setup(char *str) { if (!strcmp(str, "syslog")) console_msg_format = MSG_FORMAT_SYSLOG; if (!strcmp(str, "default")) console_msg_format = MSG_FORMAT_DEFAULT; return 1; } __setup("console_msg_format=", console_msg_format_setup); /* * Set up a console. Called via do_early_param() in init/main.c * for each "console=" parameter in the boot command line. */ static int __init console_setup(char *str) { static_assert(sizeof(console_cmdline[0].devname) >= sizeof(console_cmdline[0].name) + 4); char buf[sizeof(console_cmdline[0].devname)]; char *brl_options = NULL; char *ttyname = NULL; char *devname = NULL; char *options; char *s; int idx; /* * console="" or console=null have been suggested as a way to * disable console output. Use ttynull that has been created * for exactly this purpose. */ if (str[0] == 0 || strcmp(str, "null") == 0) { __add_preferred_console("ttynull", 0, NULL, NULL, NULL, true); return 1; } if (_braille_console_setup(&str, &brl_options)) return 1; /* For a DEVNAME:0.0 style console the character device is unknown early */ if (strchr(str, ':')) devname = buf; else ttyname = buf; /* * Decode str into name, index, options. */ if (ttyname && isdigit(str[0])) scnprintf(buf, sizeof(buf), "ttyS%s", str); else strscpy(buf, str); options = strchr(str, ','); if (options) *(options++) = 0; #ifdef __sparc__ if (!strcmp(str, "ttya")) strscpy(buf, "ttyS0"); if (!strcmp(str, "ttyb")) strscpy(buf, "ttyS1"); #endif for (s = buf; *s; s++) if ((ttyname && isdigit(*s)) || *s == ',') break; /* @idx will get defined when devname matches. */ if (devname) idx = -1; else idx = simple_strtoul(s, NULL, 10); *s = 0; __add_preferred_console(ttyname, idx, devname, options, brl_options, true); return 1; } __setup("console=", console_setup); /** * add_preferred_console - add a device to the list of preferred consoles. * @name: device name * @idx: device index * @options: options for this console * * The last preferred console added will be used for kernel messages * and stdin/out/err for init. Normally this is used by console_setup * above to handle user-supplied console arguments; however it can also * be used by arch-specific code either to override the user or more * commonly to provide a default console (ie from PROM variables) when * the user has not supplied one. */ int add_preferred_console(const char *name, const short idx, char *options) { return __add_preferred_console(name, idx, NULL, options, NULL, false); } /** * match_devname_and_update_preferred_console - Update a preferred console * when matching devname is found. * @devname: DEVNAME:0.0 style device name * @name: Name of the corresponding console driver, e.g. "ttyS" * @idx: Console index, e.g. port number. * * The function checks whether a device with the given @devname is * preferred via the console=DEVNAME:0.0 command line option. * It fills the missing console driver name and console index * so that a later register_console() call could find (match) * and enable this device. * * It might be used when a driver subsystem initializes particular * devices with already known DEVNAME:0.0 style names. And it * could predict which console driver name and index this device * would later get associated with. * * Return: 0 on success, negative error code on failure. */ int match_devname_and_update_preferred_console(const char *devname, const char *name, const short idx) { struct console_cmdline *c = console_cmdline; int i; if (!devname || !strlen(devname) || !name || !strlen(name) || idx < 0) return -EINVAL; for (i = 0; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]); i++, c++) { if (!strcmp(devname, c->devname)) { pr_info("associate the preferred console \"%s\" with \"%s%d\"\n", devname, name, idx); strscpy(c->name, name); c->index = idx; return 0; } } return -ENOENT; } EXPORT_SYMBOL_GPL(match_devname_and_update_preferred_console); bool console_suspend_enabled = true; EXPORT_SYMBOL(console_suspend_enabled); static int __init console_suspend_disable(char *str) { console_suspend_enabled = false; return 1; } __setup("no_console_suspend", console_suspend_disable); module_param_named(console_suspend, console_suspend_enabled, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(console_suspend, "suspend console during suspend" " and hibernate operations"); static bool printk_console_no_auto_verbose; void console_verbose(void) { if (console_loglevel && !printk_console_no_auto_verbose) console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH; } EXPORT_SYMBOL_GPL(console_verbose); module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool, 0644); MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc"); /** * console_suspend_all - suspend the console subsystem * * This disables printk() while we go into suspend states */ void console_suspend_all(void) { struct console *con; if (!console_suspend_enabled) return; pr_info("Suspending console(s) (use no_console_suspend to debug)\n"); pr_flush(1000, true); console_list_lock(); for_each_console(con) console_srcu_write_flags(con, con->flags | CON_SUSPENDED); console_list_unlock(); /* * Ensure that all SRCU list walks have completed. All printing * contexts must be able to see that they are suspended so that it * is guaranteed that all printing has stopped when this function * completes. */ synchronize_srcu(&console_srcu); } void console_resume_all(void) { struct console_flush_type ft; struct console *con; if (!console_suspend_enabled) return; console_list_lock(); for_each_console(con) console_srcu_write_flags(con, con->flags & ~CON_SUSPENDED); console_list_unlock(); /* * Ensure that all SRCU list walks have completed. All printing * contexts must be able to see they are no longer suspended so * that they are guaranteed to wake up and resume printing. */ synchronize_srcu(&console_srcu); printk_get_console_flush_type(&ft); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_offload) defer_console_output(); pr_flush(1000, true); } /** * console_cpu_notify - print deferred console messages after CPU hotplug * @cpu: unused * * If printk() is called from a CPU that is not online yet, the messages * will be printed on the console only if there are CON_ANYTIME consoles. * This function is called when a new CPU comes online (or fails to come * up) or goes offline. */ static int console_cpu_notify(unsigned int cpu) { struct console_flush_type ft; if (!cpuhp_tasks_frozen) { printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.legacy_direct) { if (console_trylock()) console_unlock(); } } return 0; } /** * console_lock - block the console subsystem from printing * * Acquires a lock which guarantees that no consoles will * be in or enter their write() callback. * * Can sleep, returns nothing. */ void console_lock(void) { might_sleep(); /* On panic, the console_lock must be left to the panic cpu. */ while (panic_on_other_cpu()) msleep(1000); down_console_sem(); console_locked = 1; console_may_schedule = 1; } EXPORT_SYMBOL(console_lock); /** * console_trylock - try to block the console subsystem from printing * * Try to acquire a lock which guarantees that no consoles will * be in or enter their write() callback. * * returns 1 on success, and 0 on failure to acquire the lock. */ int console_trylock(void) { /* On panic, the console_lock must be left to the panic cpu. */ if (panic_on_other_cpu()) return 0; if (down_trylock_console_sem()) return 0; console_locked = 1; console_may_schedule = 0; return 1; } EXPORT_SYMBOL(console_trylock); int is_console_locked(void) { return console_locked; } EXPORT_SYMBOL(is_console_locked); static void __console_unlock(void) { console_locked = 0; up_console_sem(); } #ifdef CONFIG_PRINTK /* * Prepend the message in @pmsg->pbufs->outbuf. This is achieved by shifting * the existing message over and inserting the scratchbuf message. * * @pmsg is the original printk message. * @fmt is the printf format of the message which will prepend the existing one. * * If there is not enough space in @pmsg->pbufs->outbuf, the existing * message text will be sufficiently truncated. * * If @pmsg->pbufs->outbuf is modified, @pmsg->outbuf_len is updated. */ __printf(2, 3) static void console_prepend_message(struct printk_message *pmsg, const char *fmt, ...) { struct printk_buffers *pbufs = pmsg->pbufs; const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf); const size_t outbuf_sz = sizeof(pbufs->outbuf); char *scratchbuf = &pbufs->scratchbuf[0]; char *outbuf = &pbufs->outbuf[0]; va_list args; size_t len; va_start(args, fmt); len = vscnprintf(scratchbuf, scratchbuf_sz, fmt, args); va_end(args); /* * Make sure outbuf is sufficiently large before prepending. * Keep at least the prefix when the message must be truncated. * It is a rather theoretical problem when someone tries to * use a minimalist buffer. */ if (WARN_ON_ONCE(len + PRINTK_PREFIX_MAX >= outbuf_sz)) return; if (pmsg->outbuf_len + len >= outbuf_sz) { /* Truncate the message, but keep it terminated. */ pmsg->outbuf_len = outbuf_sz - (len + 1); outbuf[pmsg->outbuf_len] = 0; } memmove(outbuf + len, outbuf, pmsg->outbuf_len + 1); memcpy(outbuf, scratchbuf, len); pmsg->outbuf_len += len; } /* * Prepend the message in @pmsg->pbufs->outbuf with a "dropped message". * @pmsg->outbuf_len is updated appropriately. * * @pmsg is the printk message to prepend. * * @dropped is the dropped count to report in the dropped message. */ void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped) { console_prepend_message(pmsg, "** %lu printk messages dropped **\n", dropped); } /* * Prepend the message in @pmsg->pbufs->outbuf with a "replay message". * @pmsg->outbuf_len is updated appropriately. * * @pmsg is the printk message to prepend. */ void console_prepend_replay(struct printk_message *pmsg) { console_prepend_message(pmsg, "** replaying previous printk message **\n"); } /* * Read and format the specified record (or a later record if the specified * record is not available). * * @pmsg will contain the formatted result. @pmsg->pbufs must point to a * struct printk_buffers. * * @seq is the record to read and format. If it is not available, the next * valid record is read. * * @is_extended specifies if the message should be formatted for extended * console output. * * @may_supress specifies if records may be skipped based on loglevel. * * Returns false if no record is available. Otherwise true and all fields * of @pmsg are valid. (See the documentation of struct printk_message * for information about the @pmsg fields.) */ bool printk_get_next_message(struct printk_message *pmsg, u64 seq, bool is_extended, bool may_suppress) { struct printk_buffers *pbufs = pmsg->pbufs; const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf); const size_t outbuf_sz = sizeof(pbufs->outbuf); char *scratchbuf = &pbufs->scratchbuf[0]; char *outbuf = &pbufs->outbuf[0]; struct printk_info info; struct printk_record r; size_t len = 0; bool force_con; /* * Formatting extended messages requires a separate buffer, so use the * scratch buffer to read in the ringbuffer text. * * Formatting normal messages is done in-place, so read the ringbuffer * text directly into the output buffer. */ if (is_extended) prb_rec_init_rd(&r, &info, scratchbuf, scratchbuf_sz); else prb_rec_init_rd(&r, &info, outbuf, outbuf_sz); if (!prb_read_valid(prb, seq, &r)) return false; pmsg->seq = r.info->seq; pmsg->dropped = r.info->seq - seq; force_con = r.info->flags & LOG_FORCE_CON; /* * Skip records that are not forced to be printed on consoles and that * has level above the console loglevel. */ if (!force_con && may_suppress && suppress_message_printing(r.info->level)) goto out; if (is_extended) { len = info_print_ext_header(outbuf, outbuf_sz, r.info); len += msg_print_ext_body(outbuf + len, outbuf_sz - len, &r.text_buf[0], r.info->text_len, &r.info->dev_info); } else { len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); } out: pmsg->outbuf_len = len; return true; } /* * Legacy console printing from printk() caller context does not respect * raw_spinlock/spinlock nesting. For !PREEMPT_RT the lockdep warning is a * false positive. For PREEMPT_RT the false positive condition does not * occur. * * This map is used to temporarily establish LD_WAIT_SLEEP context for the * console write() callback when legacy printing to avoid false positive * lockdep complaints, thus allowing lockdep to continue to function for * real issues. */ #ifdef CONFIG_PREEMPT_RT static inline void printk_legacy_allow_spinlock_enter(void) { } static inline void printk_legacy_allow_spinlock_exit(void) { } #else static DEFINE_WAIT_OVERRIDE_MAP(printk_legacy_map, LD_WAIT_SLEEP); static inline void printk_legacy_allow_spinlock_enter(void) { lock_map_acquire_try(&printk_legacy_map); } static inline void printk_legacy_allow_spinlock_exit(void) { lock_map_release(&printk_legacy_map); } #endif /* CONFIG_PREEMPT_RT */ /* * Used as the printk buffers for non-panic, serialized console printing. * This is for legacy (!CON_NBCON) as well as all boot (CON_BOOT) consoles. * Its usage requires the console_lock held. */ struct printk_buffers printk_shared_pbufs; /* * Print one record for the given console. The record printed is whatever * record is the next available record for the given console. * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding both the * console_lock and the SRCU read lock. Otherwise it is set to false. * * @cookie is the cookie from the SRCU read lock. * * Returns false if the given console has no next record to print, otherwise * true. * * Requires the console_lock and the SRCU read lock. */ static bool console_emit_next_record(struct console *con, bool *handover, int cookie) { bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED; char *outbuf = &printk_shared_pbufs.outbuf[0]; struct printk_message pmsg = { .pbufs = &printk_shared_pbufs, }; unsigned long flags; *handover = false; if (!printk_get_next_message(&pmsg, con->seq, is_extended, true)) return false; con->dropped += pmsg.dropped; /* Skip messages of formatted length 0. */ if (pmsg.outbuf_len == 0) { con->seq = pmsg.seq + 1; goto skip; } if (con->dropped && !is_extended) { console_prepend_dropped(&pmsg, con->dropped); con->dropped = 0; } /* Write everything out to the hardware. */ if (force_legacy_kthread() && !panic_in_progress()) { /* * With forced threading this function is in a task context * (either legacy kthread or get_init_console_seq()). There * is no need for concern about printk reentrance, handovers, * or lockdep complaints. */ con->write(con, outbuf, pmsg.outbuf_len); con->seq = pmsg.seq + 1; } else { /* * While actively printing out messages, if another printk() * were to occur on another CPU, it may wait for this one to * finish. This task can not be preempted if there is a * waiter waiting to take over. * * Interrupts are disabled because the hand over to a waiter * must not be interrupted until the hand over is completed * (@console_waiter is cleared). */ printk_safe_enter_irqsave(flags); console_lock_spinning_enable(); /* Do not trace print latency. */ stop_critical_timings(); printk_legacy_allow_spinlock_enter(); con->write(con, outbuf, pmsg.outbuf_len); printk_legacy_allow_spinlock_exit(); start_critical_timings(); con->seq = pmsg.seq + 1; *handover = console_lock_spinning_disable_and_check(cookie); printk_safe_exit_irqrestore(flags); } skip: return true; } #else static bool console_emit_next_record(struct console *con, bool *handover, int cookie) { *handover = false; return false; } static inline void printk_kthreads_check_locked(void) { } #endif /* CONFIG_PRINTK */ /* * Print out all remaining records to all consoles. * * @do_cond_resched is set by the caller. It can be true only in schedulable * context. * * @next_seq is set to the sequence number after the last available record. * The value is valid only when this function returns true. It means that all * usable consoles are completely flushed. * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding the * console_lock. Otherwise it is set to false. * * Returns true when there was at least one usable console and all messages * were flushed to all usable consoles. A returned false informs the caller * that everything was not flushed (either there were no usable consoles or * another context has taken over printing or it is a panic situation and this * is not the panic CPU). Regardless the reason, the caller should assume it * is not useful to immediately try again. * * Requires the console_lock. */ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover) { struct console_flush_type ft; bool any_usable = false; struct console *con; bool any_progress; int cookie; *next_seq = 0; *handover = false; do { any_progress = false; printk_get_console_flush_type(&ft); cookie = console_srcu_read_lock(); for_each_console_srcu(con) { short flags = console_srcu_read_flags(con); u64 printk_seq; bool progress; /* * console_flush_all() is only responsible for nbcon * consoles when the nbcon consoles cannot print via * their atomic or threaded flushing. */ if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload)) continue; if (!console_is_usable(con, flags, !do_cond_resched)) continue; any_usable = true; if (flags & CON_NBCON) { progress = nbcon_legacy_emit_next_record(con, handover, cookie, !do_cond_resched); printk_seq = nbcon_seq_read(con); } else { progress = console_emit_next_record(con, handover, cookie); printk_seq = con->seq; } /* * If a handover has occurred, the SRCU read lock * is already released. */ if (*handover) return false; /* Track the next of the highest seq flushed. */ if (printk_seq > *next_seq) *next_seq = printk_seq; if (!progress) continue; any_progress = true; /* Allow panic_cpu to take over the consoles safely. */ if (panic_on_other_cpu()) goto abandon; if (do_cond_resched) cond_resched(); } console_srcu_read_unlock(cookie); } while (any_progress); return any_usable; abandon: console_srcu_read_unlock(cookie); return false; } static void __console_flush_and_unlock(void) { bool do_cond_resched; bool handover; bool flushed; u64 next_seq; /* * Console drivers are called with interrupts disabled, so * @console_may_schedule should be cleared before; however, we may * end up dumping a lot of lines, for example, if called from * console registration path, and should invoke cond_resched() * between lines if allowable. Not doing so can cause a very long * scheduling stall on a slow console leading to RCU stall and * softlockup warnings which exacerbate the issue with more * messages practically incapacitating the system. Therefore, create * a local to use for the printing loop. */ do_cond_resched = console_may_schedule; do { console_may_schedule = 0; flushed = console_flush_all(do_cond_resched, &next_seq, &handover); if (!handover) __console_unlock(); /* * Abort if there was a failure to flush all messages to all * usable consoles. Either it is not possible to flush (in * which case it would be an infinite loop of retrying) or * another context has taken over printing. */ if (!flushed) break; /* * Some context may have added new records after * console_flush_all() but before unlocking the console. * Re-check if there is a new record to flush. If the trylock * fails, another context is already handling the printing. */ } while (prb_read_valid(prb, next_seq, NULL) && console_trylock()); } /** * console_unlock - unblock the legacy console subsystem from printing * * Releases the console_lock which the caller holds to block printing of * the legacy console subsystem. * * While the console_lock was held, console output may have been buffered * by printk(). If this is the case, console_unlock() emits the output on * legacy consoles prior to releasing the lock. * * console_unlock(); may be called from any context. */ void console_unlock(void) { struct console_flush_type ft; printk_get_console_flush_type(&ft); if (ft.legacy_direct) __console_flush_and_unlock(); else __console_unlock(); } EXPORT_SYMBOL(console_unlock); /** * console_conditional_schedule - yield the CPU if required * * If the console code is currently allowed to sleep, and * if this CPU should yield the CPU to another task, do * so here. * * Must be called within console_lock();. */ void __sched console_conditional_schedule(void) { if (console_may_schedule) cond_resched(); } EXPORT_SYMBOL(console_conditional_schedule); void console_unblank(void) { bool found_unblank = false; struct console *c; int cookie; /* * First check if there are any consoles implementing the unblank() * callback. If not, there is no reason to continue and take the * console lock, which in particular can be dangerous if * @oops_in_progress is set. */ cookie = console_srcu_read_lock(); for_each_console_srcu(c) { short flags = console_srcu_read_flags(c); if (flags & CON_SUSPENDED) continue; if ((flags & CON_ENABLED) && c->unblank) { found_unblank = true; break; } } console_srcu_read_unlock(cookie); if (!found_unblank) return; /* * Stop console printing because the unblank() callback may * assume the console is not within its write() callback. * * If @oops_in_progress is set, this may be an atomic context. * In that case, attempt a trylock as best-effort. */ if (oops_in_progress) { /* Semaphores are not NMI-safe. */ if (in_nmi()) return; /* * Attempting to trylock the console lock can deadlock * if another CPU was stopped while modifying the * semaphore. "Hope and pray" that this is not the * current situation. */ if (down_trylock_console_sem() != 0) return; } else console_lock(); console_locked = 1; console_may_schedule = 0; cookie = console_srcu_read_lock(); for_each_console_srcu(c) { short flags = console_srcu_read_flags(c); if (flags & CON_SUSPENDED) continue; if ((flags & CON_ENABLED) && c->unblank) c->unblank(); } console_srcu_read_unlock(cookie); console_unlock(); if (!oops_in_progress) pr_flush(1000, true); } /* * Rewind all consoles to the oldest available record. * * IMPORTANT: The function is safe only when called under * console_lock(). It is not enforced because * it is used as a best effort in panic(). */ static void __console_rewind_all(void) { struct console *c; short flags; int cookie; u64 seq; seq = prb_first_valid_seq(prb); cookie = console_srcu_read_lock(); for_each_console_srcu(c) { flags = console_srcu_read_flags(c); if (flags & CON_NBCON) { nbcon_seq_force(c, seq); } else { /* * This assignment is safe only when called under * console_lock(). On panic, legacy consoles are * only best effort. */ c->seq = seq; } } console_srcu_read_unlock(cookie); } /** * console_flush_on_panic - flush console content on panic * @mode: flush all messages in buffer or just the pending ones * * Immediately output all pending messages no matter what. */ void console_flush_on_panic(enum con_flush_mode mode) { struct console_flush_type ft; bool handover; u64 next_seq; /* * Ignore the console lock and flush out the messages. Attempting a * trylock would not be useful because: * * - if it is contended, it must be ignored anyway * - console_lock() and console_trylock() block and fail * respectively in panic for non-panic CPUs * - semaphores are not NMI-safe */ /* * If another context is holding the console lock, * @console_may_schedule might be set. Clear it so that * this context does not call cond_resched() while flushing. */ console_may_schedule = 0; if (mode == CONSOLE_REPLAY_ALL) __console_rewind_all(); printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); /* Flush legacy consoles once allowed, even when dangerous. */ if (legacy_allow_panic_sync) console_flush_all(false, &next_seq, &handover); } /* * Return the console tty driver structure and its associated index */ struct tty_driver *console_device(int *index) { struct console *c; struct tty_driver *driver = NULL; int cookie; /* * Take console_lock to serialize device() callback with * other console operations. For example, fg_console is * modified under console_lock when switching vt. */ console_lock(); cookie = console_srcu_read_lock(); for_each_console_srcu(c) { if (!c->device) continue; driver = c->device(c, index); if (driver) break; } console_srcu_read_unlock(cookie); console_unlock(); return driver; } /* * Prevent further output on the passed console device so that (for example) * serial drivers can suspend console output before suspending a port, and can * re-enable output afterwards. */ void console_suspend(struct console *console) { __pr_flush(console, 1000, true); console_list_lock(); console_srcu_write_flags(console, console->flags & ~CON_ENABLED); console_list_unlock(); /* * Ensure that all SRCU list walks have completed. All contexts must * be able to see that this console is disabled so that (for example) * the caller can suspend the port without risk of another context * using the port. */ synchronize_srcu(&console_srcu); } EXPORT_SYMBOL(console_suspend); void console_resume(struct console *console) { struct console_flush_type ft; bool is_nbcon; console_list_lock(); console_srcu_write_flags(console, console->flags | CON_ENABLED); is_nbcon = console->flags & CON_NBCON; console_list_unlock(); /* * Ensure that all SRCU list walks have completed. The related * printing context must be able to see it is enabled so that * it is guaranteed to wake up and resume printing. */ synchronize_srcu(&console_srcu); printk_get_console_flush_type(&ft); if (is_nbcon && ft.nbcon_offload) nbcon_kthread_wake(console); else if (ft.legacy_offload) defer_console_output(); __pr_flush(console, 1000, true); } EXPORT_SYMBOL(console_resume); #ifdef CONFIG_PRINTK static int unregister_console_locked(struct console *console); /* True when system boot is far enough to create printer threads. */ bool printk_kthreads_ready __ro_after_init; static struct task_struct *printk_legacy_kthread; static bool legacy_kthread_should_wakeup(void) { struct console_flush_type ft; struct console *con; bool ret = false; int cookie; if (kthread_should_stop()) return true; printk_get_console_flush_type(&ft); cookie = console_srcu_read_lock(); for_each_console_srcu(con) { short flags = console_srcu_read_flags(con); u64 printk_seq; /* * The legacy printer thread is only responsible for nbcon * consoles when the nbcon consoles cannot print via their * atomic or threaded flushing. */ if ((flags & CON_NBCON) && (ft.nbcon_atomic || ft.nbcon_offload)) continue; if (!console_is_usable(con, flags, false)) continue; if (flags & CON_NBCON) { printk_seq = nbcon_seq_read(con); } else { /* * It is safe to read @seq because only this * thread context updates @seq. */ printk_seq = con->seq; } if (prb_read_valid(prb, printk_seq, NULL)) { ret = true; break; } } console_srcu_read_unlock(cookie); return ret; } static int legacy_kthread_func(void *unused) { for (;;) { wait_event_interruptible(legacy_wait, legacy_kthread_should_wakeup()); if (kthread_should_stop()) break; console_lock(); __console_flush_and_unlock(); } return 0; } static bool legacy_kthread_create(void) { struct task_struct *kt; lockdep_assert_console_list_lock_held(); kt = kthread_run(legacy_kthread_func, NULL, "pr/legacy"); if (WARN_ON(IS_ERR(kt))) { pr_err("failed to start legacy printing thread\n"); return false; } printk_legacy_kthread = kt; /* * It is important that console printing threads are scheduled * shortly after a printk call and with generous runtime budgets. */ sched_set_normal(printk_legacy_kthread, -20); return true; } /** * printk_kthreads_shutdown - shutdown all threaded printers * * On system shutdown all threaded printers are stopped. This allows printk * to transition back to atomic printing, thus providing a robust mechanism * for the final shutdown/reboot messages to be output. */ static void printk_kthreads_shutdown(void) { struct console *con; console_list_lock(); if (printk_kthreads_running) { printk_kthreads_running = false; for_each_console(con) { if (con->flags & CON_NBCON) nbcon_kthread_stop(con); } /* * The threads may have been stopped while printing a * backlog. Flush any records left over. */ nbcon_atomic_flush_pending(); } console_list_unlock(); } static struct syscore_ops printk_syscore_ops = { .shutdown = printk_kthreads_shutdown, }; /* * If appropriate, start nbcon kthreads and set @printk_kthreads_running. * If any kthreads fail to start, those consoles are unregistered. * * Must be called under console_list_lock(). */ static void printk_kthreads_check_locked(void) { struct hlist_node *tmp; struct console *con; lockdep_assert_console_list_lock_held(); if (!printk_kthreads_ready) return; /* Start or stop the legacy kthread when needed. */ if (have_legacy_console || have_boot_console) { if (!printk_legacy_kthread && force_legacy_kthread() && !legacy_kthread_create()) { /* * All legacy consoles must be unregistered. If there * are any nbcon consoles, they will set up their own * kthread. */ hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (con->flags & CON_NBCON) continue; unregister_console_locked(con); } } } else if (printk_legacy_kthread) { kthread_stop(printk_legacy_kthread); printk_legacy_kthread = NULL; } /* * Printer threads cannot be started as long as any boot console is * registered because there is no way to synchronize the hardware * registers between boot console code and regular console code. * It can only be known that there will be no new boot consoles when * an nbcon console is registered. */ if (have_boot_console || !have_nbcon_console) { /* Clear flag in case all nbcon consoles unregistered. */ printk_kthreads_running = false; return; } if (printk_kthreads_running) return; hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (!(con->flags & CON_NBCON)) continue; if (!nbcon_kthread_create(con)) unregister_console_locked(con); } printk_kthreads_running = true; } static int __init printk_set_kthreads_ready(void) { register_syscore_ops(&printk_syscore_ops); console_list_lock(); printk_kthreads_ready = true; printk_kthreads_check_locked(); console_list_unlock(); return 0; } early_initcall(printk_set_kthreads_ready); #endif /* CONFIG_PRINTK */ static int __read_mostly keep_bootcon; static int __init keep_bootcon_setup(char *str) { keep_bootcon = 1; pr_info("debug: skip boot console de-registration.\n"); return 0; } early_param("keep_bootcon", keep_bootcon_setup); static int console_call_setup(struct console *newcon, char *options) { int err; if (!newcon->setup) return 0; /* Synchronize with possible boot console. */ console_lock(); err = newcon->setup(newcon, options); console_unlock(); return err; } /* * This is called by register_console() to try to match * the newly registered console with any of the ones selected * by either the command line or add_preferred_console() and * setup/enable it. * * Care need to be taken with consoles that are statically * enabled such as netconsole */ static int try_enable_preferred_console(struct console *newcon, bool user_specified) { struct console_cmdline *c; int i, err; for (i = 0, c = console_cmdline; i < MAX_CMDLINECONSOLES && (c->name[0] || c->devname[0]); i++, c++) { /* Console not yet initialized? */ if (!c->name[0]) continue; if (c->user_specified != user_specified) continue; if (!newcon->match || newcon->match(newcon, c->name, c->index, c->options) != 0) { /* default matching */ BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name)); if (strcmp(c->name, newcon->name) != 0) continue; if (newcon->index >= 0 && newcon->index != c->index) continue; if (newcon->index < 0) newcon->index = c->index; if (_braille_register_console(newcon, c)) return 0; err = console_call_setup(newcon, c->options); if (err) return err; } newcon->flags |= CON_ENABLED; if (i == preferred_console) newcon->flags |= CON_CONSDEV; return 0; } /* * Some consoles, such as pstore and netconsole, can be enabled even * without matching. Accept the pre-enabled consoles only when match() * and setup() had a chance to be called. */ if (newcon->flags & CON_ENABLED && c->user_specified == user_specified) return 0; return -ENOENT; } /* Try to enable the console unconditionally */ static void try_enable_default_console(struct console *newcon) { if (newcon->index < 0) newcon->index = 0; if (console_call_setup(newcon, NULL) != 0) return; newcon->flags |= CON_ENABLED; if (newcon->device) newcon->flags |= CON_CONSDEV; } /* Return the starting sequence number for a newly registered console. */ static u64 get_init_console_seq(struct console *newcon, bool bootcon_registered) { struct console *con; bool handover; u64 init_seq; if (newcon->flags & (CON_PRINTBUFFER | CON_BOOT)) { /* Get a consistent copy of @syslog_seq. */ mutex_lock(&syslog_lock); init_seq = syslog_seq; mutex_unlock(&syslog_lock); } else { /* Begin with next message added to ringbuffer. */ init_seq = prb_next_seq(prb); /* * If any enabled boot consoles are due to be unregistered * shortly, some may not be caught up and may be the same * device as @newcon. Since it is not known which boot console * is the same device, flush all consoles and, if necessary, * start with the message of the enabled boot console that is * the furthest behind. */ if (bootcon_registered && !keep_bootcon) { /* * Hold the console_lock to stop console printing and * guarantee safe access to console->seq. */ console_lock(); /* * Flush all consoles and set the console to start at * the next unprinted sequence number. */ if (!console_flush_all(true, &init_seq, &handover)) { /* * Flushing failed. Just choose the lowest * sequence of the enabled boot consoles. */ /* * If there was a handover, this context no * longer holds the console_lock. */ if (handover) console_lock(); init_seq = prb_next_seq(prb); for_each_console(con) { u64 seq; if (!(con->flags & CON_BOOT) || !(con->flags & CON_ENABLED)) { continue; } if (con->flags & CON_NBCON) seq = nbcon_seq_read(con); else seq = con->seq; if (seq < init_seq) init_seq = seq; } } console_unlock(); } } return init_seq; } #define console_first() \ hlist_entry(console_list.first, struct console, node) static int unregister_console_locked(struct console *console); /* * The console driver calls this routine during kernel initialization * to register the console printing procedure with printk() and to * print any messages that were printed by the kernel before the * console driver was initialized. * * This can happen pretty early during the boot process (because of * early_printk) - sometimes before setup_arch() completes - be careful * of what kernel features are used - they may not be initialised yet. * * There are two types of consoles - bootconsoles (early_printk) and * "real" consoles (everything which is not a bootconsole) which are * handled differently. * - Any number of bootconsoles can be registered at any time. * - As soon as a "real" console is registered, all bootconsoles * will be unregistered automatically. * - Once a "real" console is registered, any attempt to register a * bootconsoles will be rejected */ void register_console(struct console *newcon) { bool use_device_lock = (newcon->flags & CON_NBCON) && newcon->write_atomic; bool bootcon_registered = false; bool realcon_registered = false; struct console *con; unsigned long flags; u64 init_seq; int err; console_list_lock(); for_each_console(con) { if (WARN(con == newcon, "console '%s%d' already registered\n", con->name, con->index)) { goto unlock; } if (con->flags & CON_BOOT) bootcon_registered = true; else realcon_registered = true; } /* Do not register boot consoles when there already is a real one. */ if ((newcon->flags & CON_BOOT) && realcon_registered) { pr_info("Too late to register bootconsole %s%d\n", newcon->name, newcon->index); goto unlock; } if (newcon->flags & CON_NBCON) { /* * Ensure the nbcon console buffers can be allocated * before modifying any global data. */ if (!nbcon_alloc(newcon)) goto unlock; } /* * See if we want to enable this console driver by default. * * Nope when a console is preferred by the command line, device * tree, or SPCR. * * The first real console with tty binding (driver) wins. More * consoles might get enabled before the right one is found. * * Note that a console with tty binding will have CON_CONSDEV * flag set and will be first in the list. */ if (preferred_console < 0) { if (hlist_empty(&console_list) || !console_first()->device || console_first()->flags & CON_BOOT) { try_enable_default_console(newcon); } } /* See if this console matches one we selected on the command line */ err = try_enable_preferred_console(newcon, true); /* If not, try to match against the platform default(s) */ if (err == -ENOENT) err = try_enable_preferred_console(newcon, false); /* printk() messages are not printed to the Braille console. */ if (err || newcon->flags & CON_BRL) { if (newcon->flags & CON_NBCON) nbcon_free(newcon); goto unlock; } /* * If we have a bootconsole, and are switching to a real console, * don't print everything out again, since when the boot console, and * the real console are the same physical device, it's annoying to * see the beginning boot messages twice */ if (bootcon_registered && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) { newcon->flags &= ~CON_PRINTBUFFER; } newcon->dropped = 0; init_seq = get_init_console_seq(newcon, bootcon_registered); if (newcon->flags & CON_NBCON) { have_nbcon_console = true; nbcon_seq_force(newcon, init_seq); } else { have_legacy_console = true; newcon->seq = init_seq; } if (newcon->flags & CON_BOOT) have_boot_console = true; /* * If another context is actively using the hardware of this new * console, it will not be aware of the nbcon synchronization. This * is a risk that two contexts could access the hardware * simultaneously if this new console is used for atomic printing * and the other context is still using the hardware. * * Use the driver synchronization to ensure that the hardware is not * in use while this new console transitions to being registered. */ if (use_device_lock) newcon->device_lock(newcon, &flags); /* * Put this console in the list - keep the * preferred driver at the head of the list. */ if (hlist_empty(&console_list)) { /* Ensure CON_CONSDEV is always set for the head. */ newcon->flags |= CON_CONSDEV; hlist_add_head_rcu(&newcon->node, &console_list); } else if (newcon->flags & CON_CONSDEV) { /* Only the new head can have CON_CONSDEV set. */ console_srcu_write_flags(console_first(), console_first()->flags & ~CON_CONSDEV); hlist_add_head_rcu(&newcon->node, &console_list); } else { hlist_add_behind_rcu(&newcon->node, console_list.first); } /* * No need to synchronize SRCU here! The caller does not rely * on all contexts being able to see the new console before * register_console() completes. */ /* This new console is now registered. */ if (use_device_lock) newcon->device_unlock(newcon, flags); console_sysfs_notify(); /* * By unregistering the bootconsoles after we enable the real console * we get the "console xxx enabled" message on all the consoles - * boot consoles, real consoles, etc - this is to ensure that end * users know there might be something in the kernel's log buffer that * went to the bootconsole (that they do not see on the real console) */ con_printk(KERN_INFO, newcon, "enabled\n"); if (bootcon_registered && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && !keep_bootcon) { struct hlist_node *tmp; hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (con->flags & CON_BOOT) unregister_console_locked(con); } } /* Changed console list, may require printer threads to start/stop. */ printk_kthreads_check_locked(); unlock: console_list_unlock(); } EXPORT_SYMBOL(register_console); /* Must be called under console_list_lock(). */ static int unregister_console_locked(struct console *console) { bool use_device_lock = (console->flags & CON_NBCON) && console->write_atomic; bool found_legacy_con = false; bool found_nbcon_con = false; bool found_boot_con = false; unsigned long flags; struct console *c; int res; lockdep_assert_console_list_lock_held(); con_printk(KERN_INFO, console, "disabled\n"); res = _braille_unregister_console(console); if (res < 0) return res; if (res > 0) return 0; if (!console_is_registered_locked(console)) res = -ENODEV; else if (console_is_usable(console, console->flags, true)) __pr_flush(console, 1000, true); /* Disable it unconditionally */ console_srcu_write_flags(console, console->flags & ~CON_ENABLED); if (res < 0) return res; /* * Use the driver synchronization to ensure that the hardware is not * in use while this console transitions to being unregistered. */ if (use_device_lock) console->device_lock(console, &flags); hlist_del_init_rcu(&console->node); if (use_device_lock) console->device_unlock(console, flags); /* * <HISTORICAL> * If this isn't the last console and it has CON_CONSDEV set, we * need to set it on the next preferred console. * </HISTORICAL> * * The above makes no sense as there is no guarantee that the next * console has any device attached. Oh well.... */ if (!hlist_empty(&console_list) && console->flags & CON_CONSDEV) console_srcu_write_flags(console_first(), console_first()->flags | CON_CONSDEV); /* * Ensure that all SRCU list walks have completed. All contexts * must not be able to see this console in the list so that any * exit/cleanup routines can be performed safely. */ synchronize_srcu(&console_srcu); /* * With this console gone, the global flags tracking registered * console types may have changed. Update them. */ for_each_console(c) { if (c->flags & CON_BOOT) found_boot_con = true; if (c->flags & CON_NBCON) found_nbcon_con = true; else found_legacy_con = true; } if (!found_boot_con) have_boot_console = found_boot_con; if (!found_legacy_con) have_legacy_console = found_legacy_con; if (!found_nbcon_con) have_nbcon_console = found_nbcon_con; /* @have_nbcon_console must be updated before calling nbcon_free(). */ if (console->flags & CON_NBCON) nbcon_free(console); console_sysfs_notify(); if (console->exit) res = console->exit(console); /* Changed console list, may require printer threads to start/stop. */ printk_kthreads_check_locked(); return res; } int unregister_console(struct console *console) { int res; console_list_lock(); res = unregister_console_locked(console); console_list_unlock(); return res; } EXPORT_SYMBOL(unregister_console); /** * console_force_preferred_locked - force a registered console preferred * @con: The registered console to force preferred. * * Must be called under console_list_lock(). */ void console_force_preferred_locked(struct console *con) { struct console *cur_pref_con; if (!console_is_registered_locked(con)) return; cur_pref_con = console_first(); /* Already preferred? */ if (cur_pref_con == con) return; /* * Delete, but do not re-initialize the entry. This allows the console * to continue to appear registered (via any hlist_unhashed_lockless() * checks), even though it was briefly removed from the console list. */ hlist_del_rcu(&con->node); /* * Ensure that all SRCU list walks have completed so that the console * can be added to the beginning of the console list and its forward * list pointer can be re-initialized. */ synchronize_srcu(&console_srcu); con->flags |= CON_CONSDEV; WARN_ON(!con->device); /* Only the new head can have CON_CONSDEV set. */ console_srcu_write_flags(cur_pref_con, cur_pref_con->flags & ~CON_CONSDEV); hlist_add_head_rcu(&con->node, &console_list); } EXPORT_SYMBOL(console_force_preferred_locked); /* * Initialize the console device. This is called *early*, so * we can't necessarily depend on lots of kernel help here. * Just do some early initializations, and do the complex setup * later. */ void __init console_init(void) { int ret; initcall_t call; initcall_entry_t *ce; #ifdef CONFIG_NULL_TTY_DEFAULT_CONSOLE if (!console_set_on_cmdline) add_preferred_console("ttynull", 0, NULL); #endif /* Setup the default TTY line discipline. */ n_tty_init(); /* * set up the console device so that later boot sequences can * inform about problems etc.. */ ce = __con_initcall_start; trace_initcall_level("console"); while (ce < __con_initcall_end) { call = initcall_from_entry(ce); trace_initcall_start(call); ret = call(); trace_initcall_finish(call, ret); ce++; } } /* * Some boot consoles access data that is in the init section and which will * be discarded after the initcalls have been run. To make sure that no code * will access this data, unregister the boot consoles in a late initcall. * * If for some reason, such as deferred probe or the driver being a loadable * module, the real console hasn't registered yet at this point, there will * be a brief interval in which no messages are logged to the console, which * makes it difficult to diagnose problems that occur during this time. * * To mitigate this problem somewhat, only unregister consoles whose memory * intersects with the init section. Note that all other boot consoles will * get unregistered when the real preferred console is registered. */ static int __init printk_late_init(void) { struct hlist_node *tmp; struct console *con; int ret; console_list_lock(); hlist_for_each_entry_safe(con, tmp, &console_list, node) { if (!(con->flags & CON_BOOT)) continue; /* Check addresses that might be used for enabled consoles. */ if (init_section_intersects(con, sizeof(*con)) || init_section_contains(con->write, 0) || init_section_contains(con->read, 0) || init_section_contains(con->device, 0) || init_section_contains(con->unblank, 0) || init_section_contains(con->data, 0)) { /* * Please, consider moving the reported consoles out * of the init section. */ pr_warn("bootconsole [%s%d] uses init memory and must be disabled even before the real one is ready\n", con->name, con->index); unregister_console_locked(con); } } console_list_unlock(); ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL, console_cpu_notify); WARN_ON(ret < 0); ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online", console_cpu_notify, NULL); WARN_ON(ret < 0); printk_sysctl_init(); return 0; } late_initcall(printk_late_init); #if defined CONFIG_PRINTK /* If @con is specified, only wait for that console. Otherwise wait for all. */ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { unsigned long timeout_jiffies = msecs_to_jiffies(timeout_ms); unsigned long remaining_jiffies = timeout_jiffies; struct console_flush_type ft; struct console *c; u64 last_diff = 0; u64 printk_seq; short flags; int cookie; u64 diff; u64 seq; /* Sorry, pr_flush() will not work this early. */ if (system_state < SYSTEM_SCHEDULING) return false; might_sleep(); seq = prb_next_reserve_seq(prb); /* Flush the consoles so that records up to @seq are printed. */ printk_get_console_flush_type(&ft); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.legacy_direct) { console_lock(); console_unlock(); } for (;;) { unsigned long begin_jiffies; unsigned long slept_jiffies; diff = 0; /* * Hold the console_lock to guarantee safe access to * console->seq. Releasing console_lock flushes more * records in case @seq is still not printed on all * usable consoles. * * Holding the console_lock is not necessary if there * are no legacy or boot consoles. However, such a * console could register at any time. Always hold the * console_lock as a precaution rather than * synchronizing against register_console(). */ console_lock(); cookie = console_srcu_read_lock(); for_each_console_srcu(c) { if (con && con != c) continue; flags = console_srcu_read_flags(c); /* * If consoles are not usable, it cannot be expected * that they make forward progress, so only increment * @diff for usable consoles. */ if (!console_is_usable(c, flags, true) && !console_is_usable(c, flags, false)) { continue; } if (flags & CON_NBCON) { printk_seq = nbcon_seq_read(c); } else { printk_seq = c->seq; } if (printk_seq < seq) diff += seq - printk_seq; } console_srcu_read_unlock(cookie); if (diff != last_diff && reset_on_progress) remaining_jiffies = timeout_jiffies; console_unlock(); /* Note: @diff is 0 if there are no usable consoles. */ if (diff == 0 || remaining_jiffies == 0) break; /* msleep(1) might sleep much longer. Check time by jiffies. */ begin_jiffies = jiffies; msleep(1); slept_jiffies = jiffies - begin_jiffies; remaining_jiffies -= min(slept_jiffies, remaining_jiffies); last_diff = diff; } return (diff == 0); } /** * pr_flush() - Wait for printing threads to catch up. * * @timeout_ms: The maximum time (in ms) to wait. * @reset_on_progress: Reset the timeout if forward progress is seen. * * A value of 0 for @timeout_ms means no waiting will occur. A value of -1 * represents infinite waiting. * * If @reset_on_progress is true, the timeout will be reset whenever any * printer has been seen to make some forward progress. * * Context: Process context. May sleep while acquiring console lock. * Return: true if all usable printers are caught up. */ bool pr_flush(int timeout_ms, bool reset_on_progress) { return __pr_flush(NULL, timeout_ms, reset_on_progress); } /* * Delayed printk version, for scheduler-internal messages: */ #define PRINTK_PENDING_WAKEUP 0x01 #define PRINTK_PENDING_OUTPUT 0x02 static DEFINE_PER_CPU(int, printk_pending); static void wake_up_klogd_work_func(struct irq_work *irq_work) { int pending = this_cpu_xchg(printk_pending, 0); if (pending & PRINTK_PENDING_OUTPUT) { if (force_legacy_kthread()) { if (printk_legacy_kthread) wake_up_interruptible(&legacy_wait); } else { if (console_trylock()) console_unlock(); } } if (pending & PRINTK_PENDING_WAKEUP) wake_up_interruptible(&log_wait); } static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = IRQ_WORK_INIT_LAZY(wake_up_klogd_work_func); static void __wake_up_klogd(int val) { if (!printk_percpu_data_ready()) return; preempt_disable(); /* * Guarantee any new records can be seen by tasks preparing to wait * before this context checks if the wait queue is empty. * * The full memory barrier within wq_has_sleeper() pairs with the full * memory barrier within set_current_state() of * prepare_to_wait_event(), which is called after ___wait_event() adds * the waiter but before it has checked the wait condition. * * This pairs with devkmsg_read:A and syslog_print:A. */ if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */ (val & PRINTK_PENDING_OUTPUT)) { this_cpu_or(printk_pending, val); irq_work_queue(this_cpu_ptr(&wake_up_klogd_work)); } preempt_enable(); } /** * wake_up_klogd - Wake kernel logging daemon * * Use this function when new records have been added to the ringbuffer * and the console printing of those records has already occurred or is * known to be handled by some other context. This function will only * wake the logging daemon. * * Context: Any context. */ void wake_up_klogd(void) { __wake_up_klogd(PRINTK_PENDING_WAKEUP); } /** * defer_console_output - Wake kernel logging daemon and trigger * console printing in a deferred context * * Use this function when new records have been added to the ringbuffer, * this context is responsible for console printing those records, but * the current context is not allowed to perform the console printing. * Trigger an irq_work context to perform the console printing. This * function also wakes the logging daemon. * * Context: Any context. */ void defer_console_output(void) { /* * New messages may have been added directly to the ringbuffer * using vprintk_store(), so wake any waiters as well. */ __wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT); } void printk_trigger_flush(void) { defer_console_output(); } int vprintk_deferred(const char *fmt, va_list args) { return vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args); } int _printk_deferred(const char *fmt, ...) { va_list args; int r; va_start(args, fmt); r = vprintk_deferred(fmt, args); va_end(args); return r; } /* * printk rate limiting, lifted from the networking subsystem. * * This enforces a rate limit: not more than 10 kernel messages * every 5s to make a denial-of-service attack impossible. */ DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10); int __printk_ratelimit(const char *func) { return ___ratelimit(&printk_ratelimit_state, func); } EXPORT_SYMBOL(__printk_ratelimit); /** * printk_timed_ratelimit - caller-controlled printk ratelimiting * @caller_jiffies: pointer to caller's state * @interval_msecs: minimum interval between prints * * printk_timed_ratelimit() returns true if more than @interval_msecs * milliseconds have elapsed since the last time printk_timed_ratelimit() * returned true. */ bool printk_timed_ratelimit(unsigned long *caller_jiffies, unsigned int interval_msecs) { unsigned long elapsed = jiffies - *caller_jiffies; if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs)) return false; *caller_jiffies = jiffies; return true; } EXPORT_SYMBOL(printk_timed_ratelimit); static DEFINE_SPINLOCK(dump_list_lock); static LIST_HEAD(dump_list); /** * kmsg_dump_register - register a kernel log dumper. * @dumper: pointer to the kmsg_dumper structure * * Adds a kernel log dumper to the system. The dump callback in the * structure will be called when the kernel oopses or panics and must be * set. Returns zero on success and %-EINVAL or %-EBUSY otherwise. */ int kmsg_dump_register(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EBUSY; /* The dump callback needs to be set */ if (!dumper->dump) return -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); /* Don't allow registering multiple times */ if (!dumper->registered) { dumper->registered = 1; list_add_tail_rcu(&dumper->list, &dump_list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_register); /** * kmsg_dump_unregister - unregister a kmsg dumper. * @dumper: pointer to the kmsg_dumper structure * * Removes a dump device from the system. Returns zero on success and * %-EINVAL otherwise. */ int kmsg_dump_unregister(struct kmsg_dumper *dumper) { unsigned long flags; int err = -EINVAL; spin_lock_irqsave(&dump_list_lock, flags); if (dumper->registered) { dumper->registered = 0; list_del_rcu(&dumper->list); err = 0; } spin_unlock_irqrestore(&dump_list_lock, flags); synchronize_rcu(); return err; } EXPORT_SYMBOL_GPL(kmsg_dump_unregister); static bool always_kmsg_dump; module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR); const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason) { switch (reason) { case KMSG_DUMP_PANIC: return "Panic"; case KMSG_DUMP_OOPS: return "Oops"; case KMSG_DUMP_EMERG: return "Emergency"; case KMSG_DUMP_SHUTDOWN: return "Shutdown"; default: return "Unknown"; } } EXPORT_SYMBOL_GPL(kmsg_dump_reason_str); /** * kmsg_dump_desc - dump kernel log to kernel message dumpers. * @reason: the reason (oops, panic etc) for dumping * @desc: a short string to describe what caused the panic or oops. Can be NULL * if no additional description is available. * * Call each of the registered dumper's dump() callback, which can * retrieve the kmsg records with kmsg_dump_get_line() or * kmsg_dump_get_buffer(). */ void kmsg_dump_desc(enum kmsg_dump_reason reason, const char *desc) { struct kmsg_dumper *dumper; struct kmsg_dump_detail detail = { .reason = reason, .description = desc}; rcu_read_lock(); list_for_each_entry_rcu(dumper, &dump_list, list) { enum kmsg_dump_reason max_reason = dumper->max_reason; /* * If client has not provided a specific max_reason, default * to KMSG_DUMP_OOPS, unless always_kmsg_dump was set. */ if (max_reason == KMSG_DUMP_UNDEF) { max_reason = always_kmsg_dump ? KMSG_DUMP_MAX : KMSG_DUMP_OOPS; } if (reason > max_reason) continue; /* invoke dumper which will iterate over records */ dumper->dump(dumper, &detail); } rcu_read_unlock(); } /** * kmsg_dump_get_line - retrieve one kmsg log line * @iter: kmsg dump iterator * @syslog: include the "<4>" prefixes * @line: buffer to copy the line to * @size: maximum size of the buffer * @len: length of line placed into buffer * * Start at the beginning of the kmsg buffer, with the oldest kmsg * record, and copy one record into the provided buffer. * * Consecutive calls will return the next available record moving * towards the end of the buffer with the youngest messages. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog, char *line, size_t size, size_t *len) { u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; unsigned int line_count; struct printk_record r; size_t l = 0; bool ret = false; if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; prb_rec_init_rd(&r, &info, line, size); /* Read text or count text lines? */ if (line) { if (!prb_read_valid(prb, iter->cur_seq, &r)) goto out; l = record_print_text(&r, syslog, printk_time); } else { if (!prb_read_valid_info(prb, iter->cur_seq, &info, &line_count)) { goto out; } l = get_record_print_text_size(&info, line_count, syslog, printk_time); } iter->cur_seq = r.info->seq + 1; ret = true; out: if (len) *len = l; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_line); /** * kmsg_dump_get_buffer - copy kmsg log lines * @iter: kmsg dump iterator * @syslog: include the "<4>" prefixes * @buf: buffer to copy the line to * @size: maximum size of the buffer * @len_out: length of line placed into buffer * * Start at the end of the kmsg buffer and fill the provided buffer * with as many of the *youngest* kmsg records that fit into it. * If the buffer is large enough, all available kmsg records will be * copied with a single call. * * Consecutive calls will fill the buffer with the next block of * available older records, not including the earlier retrieved ones. * * A return value of FALSE indicates that there are no more records to * read. */ bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog, char *buf, size_t size, size_t *len_out) { u64 min_seq = latched_seq_read_nolock(&clear_seq); struct printk_info info; struct printk_record r; u64 seq; u64 next_seq; size_t len = 0; bool ret = false; bool time = printk_time; if (!buf || !size) goto out; if (iter->cur_seq < min_seq) iter->cur_seq = min_seq; if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) { if (info.seq != iter->cur_seq) { /* messages are gone, move to first available one */ iter->cur_seq = info.seq; } } /* last entry */ if (iter->cur_seq >= iter->next_seq) goto out; /* * Find first record that fits, including all following records, * into the user-provided buffer for this dump. Pass in size-1 * because this function (by way of record_print_text()) will * not write more than size-1 bytes of text into @buf. */ seq = find_first_fitting_seq(iter->cur_seq, iter->next_seq, size - 1, syslog, time); /* * Next kmsg_dump_get_buffer() invocation will dump block of * older records stored right before this one. */ next_seq = seq; prb_rec_init_rd(&r, &info, buf, size); prb_for_each_record(seq, prb, seq, &r) { if (r.info->seq >= iter->next_seq) break; len += record_print_text(&r, syslog, time); /* Adjust record to store to remaining buffer space. */ prb_rec_init_rd(&r, &info, buf + len, size - len); } iter->next_seq = next_seq; ret = true; out: if (len_out) *len_out = len; return ret; } EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer); /** * kmsg_dump_rewind - reset the iterator * @iter: kmsg dump iterator * * Reset the dumper's iterator so that kmsg_dump_get_line() and * kmsg_dump_get_buffer() can be called again and used multiple * times within the same dumper.dump() callback. */ void kmsg_dump_rewind(struct kmsg_dump_iter *iter) { iter->cur_seq = latched_seq_read_nolock(&clear_seq); iter->next_seq = prb_next_seq(prb); } EXPORT_SYMBOL_GPL(kmsg_dump_rewind); /** * console_try_replay_all - try to replay kernel log on consoles * * Try to obtain lock on console subsystem and replay all * available records in printk buffer on the consoles. * Does nothing if lock is not obtained. * * Context: Any, except for NMI. */ void console_try_replay_all(void) { struct console_flush_type ft; printk_get_console_flush_type(&ft); if (console_trylock()) { __console_rewind_all(); if (ft.nbcon_atomic) nbcon_atomic_flush_pending(); if (ft.nbcon_offload) nbcon_kthreads_wake(); if (ft.legacy_offload) defer_console_output(); /* Consoles are flushed as part of console_unlock(). */ console_unlock(); } } #endif #ifdef CONFIG_SMP static atomic_t printk_cpu_sync_owner = ATOMIC_INIT(-1); static atomic_t printk_cpu_sync_nested = ATOMIC_INIT(0); bool is_printk_cpu_sync_owner(void) { return (atomic_read(&printk_cpu_sync_owner) == raw_smp_processor_id()); } /** * __printk_cpu_sync_wait() - Busy wait until the printk cpu-reentrant * spinning lock is not owned by any CPU. * * Context: Any context. */ void __printk_cpu_sync_wait(void) { do { cpu_relax(); } while (atomic_read(&printk_cpu_sync_owner) != -1); } EXPORT_SYMBOL(__printk_cpu_sync_wait); /** * __printk_cpu_sync_try_get() - Try to acquire the printk cpu-reentrant * spinning lock. * * If no processor has the lock, the calling processor takes the lock and * becomes the owner. If the calling processor is already the owner of the * lock, this function succeeds immediately. * * Context: Any context. Expects interrupts to be disabled. * Return: 1 on success, otherwise 0. */ int __printk_cpu_sync_try_get(void) { int cpu; int old; cpu = smp_processor_id(); /* * Guarantee loads and stores from this CPU when it is the lock owner * are _not_ visible to the previous lock owner. This pairs with * __printk_cpu_sync_put:B. * * Memory barrier involvement: * * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B, * then __printk_cpu_sync_put:A can never read from * __printk_cpu_sync_try_get:B. * * Relies on: * * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B * of the previous CPU * matching * ACQUIRE from __printk_cpu_sync_try_get:A to * __printk_cpu_sync_try_get:B of this CPU */ old = atomic_cmpxchg_acquire(&printk_cpu_sync_owner, -1, cpu); /* LMM(__printk_cpu_sync_try_get:A) */ if (old == -1) { /* * This CPU is now the owner and begins loading/storing * data: LMM(__printk_cpu_sync_try_get:B) */ return 1; } else if (old == cpu) { /* This CPU is already the owner. */ atomic_inc(&printk_cpu_sync_nested); return 1; } return 0; } EXPORT_SYMBOL(__printk_cpu_sync_try_get); /** * __printk_cpu_sync_put() - Release the printk cpu-reentrant spinning lock. * * The calling processor must be the owner of the lock. * * Context: Any context. Expects interrupts to be disabled. */ void __printk_cpu_sync_put(void) { if (atomic_read(&printk_cpu_sync_nested)) { atomic_dec(&printk_cpu_sync_nested); return; } /* * This CPU is finished loading/storing data: * LMM(__printk_cpu_sync_put:A) */ /* * Guarantee loads and stores from this CPU when it was the * lock owner are visible to the next lock owner. This pairs * with __printk_cpu_sync_try_get:A. * * Memory barrier involvement: * * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B, * then __printk_cpu_sync_try_get:B reads from __printk_cpu_sync_put:A. * * Relies on: * * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B * of this CPU * matching * ACQUIRE from __printk_cpu_sync_try_get:A to * __printk_cpu_sync_try_get:B of the next CPU */ atomic_set_release(&printk_cpu_sync_owner, -1); /* LMM(__printk_cpu_sync_put:B) */ } EXPORT_SYMBOL(__printk_cpu_sync_put); #endif /* CONFIG_SMP */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_KSM_H #define __LINUX_KSM_H /* * Memory merging support. * * This code enables dynamic sharing of identical pages found in different * memory areas, even if they are not shared by fork(). */ #include <linux/bitops.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/sched.h> #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, vm_flags_t *vm_flags); vm_flags_t ksm_vma_flags(const struct mm_struct *mm, const struct file *file, vm_flags_t vm_flags); int ksm_enable_merge_any(struct mm_struct *mm); int ksm_disable_merge_any(struct mm_struct *mm); int ksm_disable(struct mm_struct *mm); int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); /* * To identify zeropages that were mapped by KSM, we reuse the dirty bit * in the PTE. If the PTE is dirty, the zeropage was mapped by KSM when * deduplicating memory. */ #define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte)) extern atomic_long_t ksm_zero_pages; static inline void ksm_map_zero_page(struct mm_struct *mm) { atomic_long_inc(&ksm_zero_pages); atomic_long_inc(&mm->ksm_zero_pages); } static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { if (is_ksm_zero_pte(pte)) { atomic_long_dec(&ksm_zero_pages); atomic_long_dec(&mm->ksm_zero_pages); } } static inline long mm_ksm_zero_pages(struct mm_struct *mm) { return atomic_long_read(&mm->ksm_zero_pages); } static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { /* Adding mm to ksm is best effort on fork. */ if (mm_flags_test(MMF_VM_MERGEABLE, oldmm)) { long nr_ksm_zero_pages = atomic_long_read(&mm->ksm_zero_pages); mm->ksm_merging_pages = 0; mm->ksm_rmap_items = 0; atomic_long_add(nr_ksm_zero_pages, &ksm_zero_pages); __ksm_enter(mm); } } static inline int ksm_execve(struct mm_struct *mm) { if (mm_flags_test(MMF_VM_MERGE_ANY, mm)) return __ksm_enter(mm); return 0; } static inline void ksm_exit(struct mm_struct *mm) { if (mm_flags_test(MMF_VM_MERGEABLE, mm)) __ksm_exit(mm); } /* * When do_swap_page() first faults in from swap what used to be a KSM page, * no problem, it will be assigned to this vma's anon_vma; but thereafter, * it might be faulted into a different anon_vma (or perhaps to a different * offset in the same anon_vma). do_swap_page() cannot do all the locking * needed to reconstitute a cross-anon_vma KSM page: for now it has to make * a copy, and leave remerging the pages to a later pass of ksmd. * * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE, * but what if the vma was unmerged while the page was swapped out? */ struct folio *ksm_might_need_to_copy(struct folio *folio, struct vm_area_struct *vma, unsigned long addr); void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); void collect_procs_ksm(const struct folio *folio, const struct page *page, struct list_head *to_kill, int force_early); long ksm_process_profit(struct mm_struct *); bool ksm_process_mergeable(struct mm_struct *mm); #else /* !CONFIG_KSM */ static inline vm_flags_t ksm_vma_flags(const struct mm_struct *mm, const struct file *file, vm_flags_t vm_flags) { return vm_flags; } static inline int ksm_disable(struct mm_struct *mm) { return 0; } static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { } static inline int ksm_execve(struct mm_struct *mm) { return 0; } static inline void ksm_exit(struct mm_struct *mm) { } static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { } static inline void collect_procs_ksm(const struct folio *folio, const struct page *page, struct list_head *to_kill, int force_early) { } #ifdef CONFIG_MMU static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, vm_flags_t *vm_flags) { return 0; } static inline struct folio *ksm_might_need_to_copy(struct folio *folio, struct vm_area_struct *vma, unsigned long addr) { return folio; } static inline void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { } static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old) { } #endif /* CONFIG_MMU */ #endif /* !CONFIG_KSM */ #endif /* __LINUX_KSM_H */ |
| 147 146 146 145 147 113 75 147 577 576 577 577 579 442 262 577 889 892 892 893 888 159 587 147 578 591 131 578 580 580 579 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2021, Google LLC. * Pasha Tatashin <pasha.tatashin@soleen.com> */ #include <linux/kstrtox.h> #include <linux/mm.h> #include <linux/page_table_check.h> #include <linux/swap.h> #include <linux/swapops.h> #undef pr_fmt #define pr_fmt(fmt) "page_table_check: " fmt struct page_table_check { atomic_t anon_map_count; atomic_t file_map_count; }; static bool __page_table_check_enabled __initdata = IS_ENABLED(CONFIG_PAGE_TABLE_CHECK_ENFORCED); DEFINE_STATIC_KEY_TRUE(page_table_check_disabled); EXPORT_SYMBOL(page_table_check_disabled); static int __init early_page_table_check_param(char *buf) { return kstrtobool(buf, &__page_table_check_enabled); } early_param("page_table_check", early_page_table_check_param); static bool __init need_page_table_check(void) { return __page_table_check_enabled; } static void __init init_page_table_check(void) { if (!__page_table_check_enabled) return; static_branch_disable(&page_table_check_disabled); } struct page_ext_operations page_table_check_ops = { .size = sizeof(struct page_table_check), .need = need_page_table_check, .init = init_page_table_check, .need_shared_flags = false, }; static struct page_table_check *get_page_table_check(struct page_ext *page_ext) { BUG_ON(!page_ext); return page_ext_data(page_ext, &page_table_check_ops); } /* * An entry is removed from the page table, decrement the counters for that page * verify that it is of correct type and counters do not become negative. */ static void page_table_check_clear(unsigned long pfn, unsigned long pgcnt) { struct page_ext_iter iter; struct page_ext *page_ext; struct page *page; bool anon; if (!pfn_valid(pfn)) return; page = pfn_to_page(pfn); BUG_ON(PageSlab(page)); anon = PageAnon(page); rcu_read_lock(); for_each_page_ext(page, pgcnt, page_ext, iter) { struct page_table_check *ptc = get_page_table_check(page_ext); if (anon) { BUG_ON(atomic_read(&ptc->file_map_count)); BUG_ON(atomic_dec_return(&ptc->anon_map_count) < 0); } else { BUG_ON(atomic_read(&ptc->anon_map_count)); BUG_ON(atomic_dec_return(&ptc->file_map_count) < 0); } } rcu_read_unlock(); } /* * A new entry is added to the page table, increment the counters for that page * verify that it is of correct type and is not being mapped with a different * type to a different process. */ static void page_table_check_set(unsigned long pfn, unsigned long pgcnt, bool rw) { struct page_ext_iter iter; struct page_ext *page_ext; struct page *page; bool anon; if (!pfn_valid(pfn)) return; page = pfn_to_page(pfn); BUG_ON(PageSlab(page)); anon = PageAnon(page); rcu_read_lock(); for_each_page_ext(page, pgcnt, page_ext, iter) { struct page_table_check *ptc = get_page_table_check(page_ext); if (anon) { BUG_ON(atomic_read(&ptc->file_map_count)); BUG_ON(atomic_inc_return(&ptc->anon_map_count) > 1 && rw); } else { BUG_ON(atomic_read(&ptc->anon_map_count)); BUG_ON(atomic_inc_return(&ptc->file_map_count) < 0); } } rcu_read_unlock(); } /* * page is on free list, or is being allocated, verify that counters are zeroes * crash if they are not. */ void __page_table_check_zero(struct page *page, unsigned int order) { struct page_ext_iter iter; struct page_ext *page_ext; BUG_ON(PageSlab(page)); rcu_read_lock(); for_each_page_ext(page, 1 << order, page_ext, iter) { struct page_table_check *ptc = get_page_table_check(page_ext); BUG_ON(atomic_read(&ptc->anon_map_count)); BUG_ON(atomic_read(&ptc->file_map_count)); } rcu_read_unlock(); } void __page_table_check_pte_clear(struct mm_struct *mm, pte_t pte) { if (&init_mm == mm) return; if (pte_user_accessible_page(pte)) { page_table_check_clear(pte_pfn(pte), PAGE_SIZE >> PAGE_SHIFT); } } EXPORT_SYMBOL(__page_table_check_pte_clear); void __page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd) { if (&init_mm == mm) return; if (pmd_user_accessible_page(pmd)) { page_table_check_clear(pmd_pfn(pmd), PMD_SIZE >> PAGE_SHIFT); } } EXPORT_SYMBOL(__page_table_check_pmd_clear); void __page_table_check_pud_clear(struct mm_struct *mm, pud_t pud) { if (&init_mm == mm) return; if (pud_user_accessible_page(pud)) { page_table_check_clear(pud_pfn(pud), PUD_SIZE >> PAGE_SHIFT); } } EXPORT_SYMBOL(__page_table_check_pud_clear); /* Whether the swap entry cached writable information */ static inline bool swap_cached_writable(swp_entry_t entry) { return is_writable_device_private_entry(entry) || is_writable_migration_entry(entry); } static inline void page_table_check_pte_flags(pte_t pte) { if (pte_present(pte) && pte_uffd_wp(pte)) WARN_ON_ONCE(pte_write(pte)); else if (is_swap_pte(pte) && pte_swp_uffd_wp(pte)) WARN_ON_ONCE(swap_cached_writable(pte_to_swp_entry(pte))); } void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte, unsigned int nr) { unsigned int i; if (&init_mm == mm) return; page_table_check_pte_flags(pte); for (i = 0; i < nr; i++) __page_table_check_pte_clear(mm, ptep_get(ptep + i)); if (pte_user_accessible_page(pte)) page_table_check_set(pte_pfn(pte), nr, pte_write(pte)); } EXPORT_SYMBOL(__page_table_check_ptes_set); static inline void page_table_check_pmd_flags(pmd_t pmd) { if (pmd_present(pmd) && pmd_uffd_wp(pmd)) WARN_ON_ONCE(pmd_write(pmd)); else if (is_swap_pmd(pmd) && pmd_swp_uffd_wp(pmd)) WARN_ON_ONCE(swap_cached_writable(pmd_to_swp_entry(pmd))); } void __page_table_check_pmds_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd, unsigned int nr) { unsigned long stride = PMD_SIZE >> PAGE_SHIFT; unsigned int i; if (&init_mm == mm) return; page_table_check_pmd_flags(pmd); for (i = 0; i < nr; i++) __page_table_check_pmd_clear(mm, *(pmdp + i)); if (pmd_user_accessible_page(pmd)) page_table_check_set(pmd_pfn(pmd), stride * nr, pmd_write(pmd)); } EXPORT_SYMBOL(__page_table_check_pmds_set); void __page_table_check_puds_set(struct mm_struct *mm, pud_t *pudp, pud_t pud, unsigned int nr) { unsigned long stride = PUD_SIZE >> PAGE_SHIFT; unsigned int i; if (&init_mm == mm) return; for (i = 0; i < nr; i++) __page_table_check_pud_clear(mm, *(pudp + i)); if (pud_user_accessible_page(pud)) page_table_check_set(pud_pfn(pud), stride * nr, pud_write(pud)); } EXPORT_SYMBOL(__page_table_check_puds_set); void __page_table_check_pte_clear_range(struct mm_struct *mm, unsigned long addr, pmd_t pmd) { if (&init_mm == mm) return; if (!pmd_bad(pmd) && !pmd_leaf(pmd)) { pte_t *ptep = pte_offset_map(&pmd, addr); unsigned long i; if (WARN_ON(!ptep)) return; for (i = 0; i < PTRS_PER_PTE; i++) { __page_table_check_pte_clear(mm, ptep_get(ptep)); addr += PAGE_SIZE; ptep++; } pte_unmap(ptep - PTRS_PER_PTE); } } |
| 4 4 4 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * PACKET - implements raw packet sockets. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * * Fixes: * Alan Cox : verify_area() now used correctly * Alan Cox : new skbuff lists, look ma no backlogs! * Alan Cox : tidied skbuff lists. * Alan Cox : Now uses generic datagram routines I * added. Also fixed the peek/read crash * from all old Linux datagram code. * Alan Cox : Uses the improved datagram code. * Alan Cox : Added NULL's for socket options. * Alan Cox : Re-commented the code. * Alan Cox : Use new kernel side addressing * Rob Janssen : Correct MTU usage. * Dave Platt : Counter leaks caused by incorrect * interrupt locking and some slightly * dubious gcc output. Can you read * compiler: it said _VOLATILE_ * Richard Kooijman : Timestamp fixes. * Alan Cox : New buffers. Use sk->mac.raw. * Alan Cox : sendmsg/recvmsg support. * Alan Cox : Protocol setting support * Alexey Kuznetsov : Untied from IPv4 stack. * Cyrus Durgin : Fixed kerneld for kmod. * Michal Ostrowski : Module initialization cleanup. * Ulises Alonso : Frame number limit removal and * packet_set_ring memory leak. * Eric Biederman : Allow for > 8 byte hardware addresses. * The convention is that longer addresses * will simply extend the hardware address * byte arrays at the end of sockaddr_ll * and packet_mreq. * Johann Baudy : Added TX RING. * Chetan Loke : Implemented TPACKET_V3 block abstraction * layer. * Copyright (C) 2011, <lokec@ccs.neu.edu> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> #include <linux/wireless.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <asm/page.h> #include <asm/cacheflush.h> #include <asm/io.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/module.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/if_vlan.h> #include <linux/virtio_net.h> #include <linux/errqueue.h> #include <linux/net_tstamp.h> #include <linux/percpu.h> #ifdef CONFIG_INET #include <net/inet_common.h> #endif #include <linux/bpf.h> #include <net/compat.h> #include <linux/netfilter_netdev.h> #include "internal.h" /* Assumptions: - If the device has no dev->header_ops->create, there is no LL header visible above the device. In this case, its hard_header_len should be 0. The device may prepend its own header internally. In this case, its needed_headroom should be set to the space needed for it to add its internal header. For example, a WiFi driver pretending to be an Ethernet driver should set its hard_header_len to be the Ethernet header length, and set its needed_headroom to be (the real WiFi header length - the fake Ethernet header length). - packet socket receives packets with pulled ll header, so that SOCK_RAW should push it back. On receive: ----------- Incoming, dev_has_header(dev) == true mac_header -> ll header data -> data Outgoing, dev_has_header(dev) == true mac_header -> ll header data -> ll header Incoming, dev_has_header(dev) == false mac_header -> data However drivers often make it point to the ll header. This is incorrect because the ll header should be invisible to us. data -> data Outgoing, dev_has_header(dev) == false mac_header -> data. ll header is invisible to us. data -> data Resume If dev_has_header(dev) == false we are unable to restore the ll header, because it is invisible to us. On transmit: ------------ dev_has_header(dev) == true mac_header -> ll header data -> ll header dev_has_header(dev) == false (ll header is invisible to us) mac_header -> data data -> data We should set network_header on output to the correct position, packet classifier depends on it. */ /* Private packet socket structures. */ /* identical to struct packet_mreq except it has * a longer address field. */ struct packet_mreq_max { int mr_ifindex; unsigned short mr_type; unsigned short mr_alen; unsigned char mr_address[MAX_ADDR_LEN]; }; union tpacket_uhdr { struct tpacket_hdr *h1; struct tpacket2_hdr *h2; struct tpacket3_hdr *h3; void *raw; }; static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring); #define V3_ALIGNMENT (8) #define BLK_HDR_LEN (ALIGN(sizeof(struct tpacket_block_desc), V3_ALIGNMENT)) #define BLK_PLUS_PRIV(sz_of_priv) \ (BLK_HDR_LEN + ALIGN((sz_of_priv), V3_ALIGNMENT)) #define BLOCK_STATUS(x) ((x)->hdr.bh1.block_status) #define BLOCK_NUM_PKTS(x) ((x)->hdr.bh1.num_pkts) #define BLOCK_O2FP(x) ((x)->hdr.bh1.offset_to_first_pkt) #define BLOCK_LEN(x) ((x)->hdr.bh1.blk_len) #define BLOCK_SNUM(x) ((x)->hdr.bh1.seq_num) #define BLOCK_O2PRIV(x) ((x)->offset_to_priv) struct packet_sock; static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status); static void packet_increment_head(struct packet_ring_buffer *buff); static int prb_curr_blk_in_use(struct tpacket_block_desc *); static void *prb_dispatch_next_block(struct tpacket_kbdq_core *, struct packet_sock *); static void prb_retire_current_block(struct tpacket_kbdq_core *, struct packet_sock *, unsigned int status); static int prb_queue_frozen(struct tpacket_kbdq_core *); static void prb_open_block(struct tpacket_kbdq_core *, struct tpacket_block_desc *); static enum hrtimer_restart prb_retire_rx_blk_timer_expired(struct hrtimer *); static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_clear_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); static u16 packet_pick_tx_queue(struct sk_buff *skb); struct packet_skb_cb { union { struct sockaddr_pkt pkt; union { /* Trick: alias skb original length with * ll.sll_family and ll.protocol in order * to save room. */ unsigned int origlen; struct sockaddr_ll ll; }; } sa; }; #define vio_le() virtio_legacy_is_little_endian() #define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb)) #define GET_PBDQC_FROM_RB(x) ((struct tpacket_kbdq_core *)(&(x)->prb_bdqc)) #define GET_PBLOCK_DESC(x, bid) \ ((struct tpacket_block_desc *)((x)->pkbdq[(bid)].buffer)) #define GET_CURR_PBLOCK_DESC_FROM_CORE(x) \ ((struct tpacket_block_desc *)((x)->pkbdq[(x)->kactive_blk_num].buffer)) #define GET_NEXT_PRB_BLK_NUM(x) \ (((x)->kactive_blk_num < ((x)->knum_blocks-1)) ? \ ((x)->kactive_blk_num+1) : 0) static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); #ifdef CONFIG_NETFILTER_EGRESS static noinline struct sk_buff *nf_hook_direct_egress(struct sk_buff *skb) { struct sk_buff *next, *head = NULL, *tail; int rc; rcu_read_lock(); for (; skb != NULL; skb = next) { next = skb->next; skb_mark_not_on_list(skb); if (!nf_hook_egress(skb, &rc, skb->dev)) continue; if (!head) head = skb; else tail->next = skb; tail = skb; } rcu_read_unlock(); return head; } #endif static int packet_xmit(const struct packet_sock *po, struct sk_buff *skb) { if (!packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS)) return dev_queue_xmit(skb); #ifdef CONFIG_NETFILTER_EGRESS if (nf_hook_egress_active()) { skb = nf_hook_direct_egress(skb); if (!skb) return NET_XMIT_DROP; } #endif return dev_direct_xmit(skb, packet_pick_tx_queue(skb)); } static struct net_device *packet_cached_dev_get(struct packet_sock *po) { struct net_device *dev; rcu_read_lock(); dev = rcu_dereference(po->cached_dev); dev_hold(dev); rcu_read_unlock(); return dev; } static void packet_cached_dev_assign(struct packet_sock *po, struct net_device *dev) { rcu_assign_pointer(po->cached_dev, dev); } static void packet_cached_dev_reset(struct packet_sock *po) { RCU_INIT_POINTER(po->cached_dev, NULL); } static u16 packet_pick_tx_queue(struct sk_buff *skb) { struct net_device *dev = skb->dev; const struct net_device_ops *ops = dev->netdev_ops; int cpu = raw_smp_processor_id(); u16 queue_index; #ifdef CONFIG_XPS skb->sender_cpu = cpu + 1; #endif skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues); if (ops->ndo_select_queue) { queue_index = ops->ndo_select_queue(dev, skb, NULL); queue_index = netdev_cap_txqueue(dev, queue_index); } else { queue_index = netdev_pick_tx(dev, skb, NULL); } return queue_index; } /* __register_prot_hook must be invoked through register_prot_hook * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). */ static void __register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); if (!packet_sock_flag(po, PACKET_SOCK_RUNNING)) { if (po->fanout) __fanout_link(sk, po); else dev_add_pack(&po->prot_hook); sock_hold(sk); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 1); } } static void register_prot_hook(struct sock *sk) { lockdep_assert_held_once(&pkt_sk(sk)->bind_lock); __register_prot_hook(sk); } /* If the sync parameter is true, we will temporarily drop * the po->bind_lock and do a synchronize_net to make sure no * asynchronous packet processing paths still refer to the elements * of po->prot_hook. If the sync parameter is false, it is the * callers responsibility to take care of this. */ static void __unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); lockdep_assert_held_once(&po->bind_lock); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 0); if (po->fanout) __fanout_unlink(sk, po); else __dev_remove_pack(&po->prot_hook); __sock_put(sk); if (sync) { spin_unlock(&po->bind_lock); synchronize_net(); spin_lock(&po->bind_lock); } } static void unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) __unregister_prot_hook(sk, sync); } static inline struct page * __pure pgv_to_page(void *addr) { if (is_vmalloc_addr(addr)) return vmalloc_to_page(addr); return virt_to_page(addr); } static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } smp_wmb(); } static int __packet_get_status(const struct packet_sock *po, void *frame) { union tpacket_uhdr h; smp_rmb(); /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); return 0; } } static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts, unsigned int flags) { struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); if (shhwtstamps && (flags & SOF_TIMESTAMPING_RAW_HARDWARE) && ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts)) return TP_STATUS_TS_RAW_HARDWARE; if ((flags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb_tstamp(skb), ts)) return TP_STATUS_TS_SOFTWARE; return 0; } static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame, struct sk_buff *skb) { union tpacket_uhdr h; struct timespec64 ts; __u32 ts_status; if (!(ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp)))) return 0; h.raw = frame; /* * versions 1 through 3 overflow the timestamps in y2106, since they * all store the seconds in a 32-bit unsigned integer. * If we create a version 4, that should have a 64-bit timestamp, * either 64-bit seconds + 32-bit nanoseconds, or just 64-bit * nanoseconds. */ switch (po->tp_version) { case TPACKET_V1: h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; break; case TPACKET_V2: h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; break; case TPACKET_V3: h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } /* one flush is safe, as both fields always lie on the same cacheline */ flush_dcache_page(pgv_to_page(&h.h1->tp_sec)); smp_wmb(); return ts_status; } static void *packet_lookup_frame(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int position, int status) { unsigned int pg_vec_pos, frame_offset; union tpacket_uhdr h; pg_vec_pos = position / rb->frames_per_block; frame_offset = position % rb->frames_per_block; h.raw = rb->pg_vec[pg_vec_pos].buffer + (frame_offset * rb->frame_size); if (status != __packet_get_status(po, h.raw)) return NULL; return h.raw; } static void *packet_current_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { return packet_lookup_frame(po, rb, rb->head, status); } static u16 vlan_get_tci(const struct sk_buff *skb, struct net_device *dev) { struct vlan_hdr vhdr, *vh; unsigned int header_len; if (!dev) return 0; /* In the SOCK_DGRAM scenario, skb data starts at the network * protocol, which is after the VLAN headers. The outer VLAN * header is at the hard_header_len offset in non-variable * length link layer headers. If it's a VLAN device, the * min_header_len should be used to exclude the VLAN header * size. */ if (dev->min_header_len == dev->hard_header_len) header_len = dev->hard_header_len; else if (is_vlan_dev(dev)) header_len = dev->min_header_len; else return 0; vh = skb_header_pointer(skb, skb_mac_offset(skb) + header_len, sizeof(vhdr), &vhdr); if (unlikely(!vh)) return 0; return ntohs(vh->h_vlan_TCI); } static __be16 vlan_get_protocol_dgram(const struct sk_buff *skb) { __be16 proto = skb->protocol; if (unlikely(eth_type_vlan(proto))) proto = __vlan_get_protocol_offset(skb, proto, skb_mac_offset(skb), NULL); return proto; } static void prb_shutdown_retire_blk_timer(struct packet_sock *po, struct sk_buff_head *rb_queue) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); hrtimer_cancel(&pkc->retire_blk_timer); } static int prb_calc_retire_blk_tmo(struct packet_sock *po, int blk_size_in_bytes) { struct net_device *dev; unsigned int mbits, div; struct ethtool_link_ksettings ecmd; int err; rtnl_lock(); dev = __dev_get_by_index(sock_net(&po->sk), po->ifindex); if (unlikely(!dev)) { rtnl_unlock(); return DEFAULT_PRB_RETIRE_TOV; } err = __ethtool_get_link_ksettings(dev, &ecmd); rtnl_unlock(); if (err) return DEFAULT_PRB_RETIRE_TOV; /* If the link speed is so slow you don't really * need to worry about perf anyways */ if (ecmd.base.speed < SPEED_1000 || ecmd.base.speed == SPEED_UNKNOWN) return DEFAULT_PRB_RETIRE_TOV; div = ecmd.base.speed / 1000; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); if (div) mbits /= div; if (div) return mbits + 1; return mbits; } static void prb_init_ft_ops(struct tpacket_kbdq_core *p1, union tpacket_req_u *req_u) { p1->feature_req_word = req_u->req3.tp_feature_req_word; } static void init_prb_bdqc(struct packet_sock *po, struct packet_ring_buffer *rb, struct pgv *pg_vec, union tpacket_req_u *req_u) { struct tpacket_kbdq_core *p1 = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd; memset(p1, 0x0, sizeof(*p1)); p1->knxt_seq_num = 1; p1->pkbdq = pg_vec; pbd = (struct tpacket_block_desc *)pg_vec[0].buffer; p1->pkblk_start = pg_vec[0].buffer; p1->kblk_size = req_u->req3.tp_block_size; p1->knum_blocks = req_u->req3.tp_block_nr; p1->hdrlen = po->tp_hdrlen; p1->version = po->tp_version; po->stats.stats3.tp_freeze_q_cnt = 0; if (req_u->req3.tp_retire_blk_tov) p1->interval_ktime = ms_to_ktime(req_u->req3.tp_retire_blk_tov); else p1->interval_ktime = ms_to_ktime(prb_calc_retire_blk_tmo(po, req_u->req3.tp_block_size)); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; rwlock_init(&p1->blk_fill_in_prog_lock); p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); hrtimer_setup(&p1->retire_blk_timer, prb_retire_rx_blk_timer_expired, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); hrtimer_start(&p1->retire_blk_timer, p1->interval_ktime, HRTIMER_MODE_REL_SOFT); prb_open_block(p1, pbd); } /* * With a 1MB block-size, on a 1Gbps line, it will take * i) ~8 ms to fill a block + ii) memcpy etc. * In this cut we are not accounting for the memcpy time. * * Since the tmo granularity is in msecs, it is not too expensive * to refresh the timer, lets say every '8' msecs. * Either the user can set the 'tmo' or we can derive it based on * a) line-speed and b) block-size. * prb_calc_retire_blk_tmo() calculates the tmo. */ static enum hrtimer_restart prb_retire_rx_blk_timer_expired(struct hrtimer *t) { struct packet_sock *po = timer_container_of(po, t, rx_ring.prb_bdqc.retire_blk_timer); struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring); unsigned int frozen; struct tpacket_block_desc *pbd; spin_lock(&po->sk.sk_receive_queue.lock); frozen = prb_queue_frozen(pkc); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* We only need to plug the race when the block is partially filled. * tpacket_rcv: * lock(); increment BLOCK_NUM_PKTS; unlock() * copy_bits() is in progress ... * timer fires on other cpu: * we can't retire the current block because copy_bits * is in progress. * */ if (BLOCK_NUM_PKTS(pbd)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } if (!frozen) { if (BLOCK_NUM_PKTS(pbd)) { /* Not an empty block. Need retire the block. */ prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO); prb_dispatch_next_block(pkc, po); } } else { /* Case 1. Queue was frozen because user-space was * lagging behind. */ if (!prb_curr_blk_in_use(pbd)) { /* Case 2. queue was frozen,user-space caught up, * now the link went idle && the timer fired. * We don't have a block to close.So we open this * block and restart the timer. * opening a block thaws the queue,restarts timer * Thawing/timer-refresh is a side effect. */ prb_open_block(pkc, pbd); } } hrtimer_forward_now(&pkc->retire_blk_timer, pkc->interval_ktime); spin_unlock(&po->sk.sk_receive_queue.lock); return HRTIMER_RESTART; } static void prb_flush_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, __u32 status) { /* Flush everything minus the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 u8 *start, *end; start = (u8 *)pbd1; /* Skip the block header(we know header WILL fit in 4K) */ start += PAGE_SIZE; end = (u8 *)PAGE_ALIGN((unsigned long)pkc1->pkblk_end); for (; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif /* Now update the block status. */ BLOCK_STATUS(pbd1) = status; /* Flush the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 start = (u8 *)pbd1; flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif } /* * Side effect: * * 1) flush the block * 2) Increment active_blk_num * * Note:We DONT refresh the timer on purpose. * Because almost always the next block will be opened. */ static void prb_close_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, struct packet_sock *po, unsigned int stat) { __u32 status = TP_STATUS_USER | stat; struct tpacket3_hdr *last_pkt; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; struct sock *sk = &po->sk; if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; last_pkt = (struct tpacket3_hdr *)pkc1->prev; last_pkt->tp_next_offset = 0; /* Get the ts of the last pkt */ if (BLOCK_NUM_PKTS(pbd1)) { h1->ts_last_pkt.ts_sec = last_pkt->tp_sec; h1->ts_last_pkt.ts_nsec = last_pkt->tp_nsec; } else { /* Ok, we tmo'd - so get the current time. * * It shouldn't really happen as we don't close empty * blocks. See prb_retire_rx_blk_timer_expired(). */ struct timespec64 ts; ktime_get_real_ts64(&ts); h1->ts_last_pkt.ts_sec = ts.tv_sec; h1->ts_last_pkt.ts_nsec = ts.tv_nsec; } smp_wmb(); /* Flush the block */ prb_flush_block(pkc1, pbd1, status); sk->sk_data_ready(sk); pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1); } static void prb_thaw_queue(struct tpacket_kbdq_core *pkc) { pkc->reset_pending_on_curr_blk = 0; } /* * prb_open_block is called by tpacket_rcv or timer callback. * * Reasons why NOT update hrtimer in prb_open_block: * 1) It will increase complexity to distinguish the two caller scenario. * 2) hrtimer_cancel and hrtimer_start need to be called if you want to update * TMO of an already enqueued hrtimer, leading to complex shutdown logic. * * One side effect of NOT update hrtimer when called by tpacket_rcv is that * a newly opened block triggered by tpacket_rcv may be retired earlier than * expected. On the other hand, if timeout is updated in prb_open_block, the * frequent reception of network packets that leads to prb_open_block being * called may cause hrtimer to be removed and enqueued repeatedly. */ static void prb_open_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1) { struct timespec64 ts; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; smp_rmb(); /* We could have just memset this but we will lose the * flexibility of making the priv area sticky */ BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++; BLOCK_NUM_PKTS(pbd1) = 0; BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); ktime_get_real_ts64(&ts); h1->ts_first_pkt.ts_sec = ts.tv_sec; h1->ts_first_pkt.ts_nsec = ts.tv_nsec; pkc1->pkblk_start = (char *)pbd1; pkc1->nxt_offset = pkc1->pkblk_start + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN; pbd1->version = pkc1->version; pkc1->prev = pkc1->nxt_offset; pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size; prb_thaw_queue(pkc1); smp_wmb(); } /* * Queue freeze logic: * 1) Assume tp_block_nr = 8 blocks. * 2) At time 't0', user opens Rx ring. * 3) Some time past 't0', kernel starts filling blocks starting from 0 .. 7 * 4) user-space is either sleeping or processing block '0'. * 5) tpacket_rcv is currently filling block '7', since there is no space left, * it will close block-7,loop around and try to fill block '0'. * call-flow: * __packet_lookup_frame_in_block * prb_retire_current_block() * prb_dispatch_next_block() * |->(BLOCK_STATUS == USER) evaluates to true * 5.1) Since block-0 is currently in-use, we just freeze the queue. * 6) Now there are two cases: * 6.1) Link goes idle right after the queue is frozen. * But remember, the last open_block() refreshed the timer. * When this timer expires,it will refresh itself so that we can * re-open block-0 in near future. * 6.2) Link is busy and keeps on receiving packets. This is a simple * case and __packet_lookup_frame_in_block will check if block-0 * is free and can now be re-used. */ static void prb_freeze_queue(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { pkc->reset_pending_on_curr_blk = 1; po->stats.stats3.tp_freeze_q_cnt++; } #define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN((length), V3_ALIGNMENT)) /* * If the next block is free then we will dispatch it * and return a good offset. * Else, we will freeze the queue. * So, caller must check the return value. */ static void *prb_dispatch_next_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { struct tpacket_block_desc *pbd; smp_rmb(); /* 1. Get current block num */ pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* 2. If this block is currently in_use then freeze the queue */ if (TP_STATUS_USER & BLOCK_STATUS(pbd)) { prb_freeze_queue(pkc, po); return NULL; } /* * 3. * open this block and return the offset where the first packet * needs to get stored. */ prb_open_block(pkc, pbd); return (void *)pkc->nxt_offset; } static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po, unsigned int status) { struct tpacket_block_desc *pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* retire/close the current block */ if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd))) { /* * Plug the case where copy_bits() is in progress on * cpu-0 and tpacket_rcv() got invoked on cpu-1, didn't * have space to copy the pkt in the current block and * called prb_retire_current_block() * * We don't need to worry about the TMO case because * the timer-handler already handled this case. */ if (!(status & TP_STATUS_BLK_TMO)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } prb_close_block(pkc, pbd, po, status); return; } } static int prb_curr_blk_in_use(struct tpacket_block_desc *pbd) { return TP_STATUS_USER & BLOCK_STATUS(pbd); } static int prb_queue_frozen(struct tpacket_kbdq_core *pkc) { return pkc->reset_pending_on_curr_blk; } static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) __releases(&pkc->blk_fill_in_prog_lock) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); read_unlock(&pkc->blk_fill_in_prog_lock); } static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb); } static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = 0; } static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc); if (skb_vlan_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) { ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; ppd->hv1.tp_vlan_tpid = 0; ppd->tp_status = TP_STATUS_AVAILABLE; } } static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_padding = 0; prb_fill_vlan_info(pkc, ppd); if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH) prb_fill_rxhash(pkc, ppd); else prb_clear_rxhash(pkc, ppd); } static void prb_fill_curr_block(char *curr, struct tpacket_kbdq_core *pkc, struct tpacket_block_desc *pbd, unsigned int len) __acquires(&pkc->blk_fill_in_prog_lock) { struct tpacket3_hdr *ppd; ppd = (struct tpacket3_hdr *)curr; ppd->tp_next_offset = TOTAL_PKT_LEN_INCL_ALIGN(len); pkc->prev = curr; pkc->nxt_offset += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_LEN(pbd) += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_NUM_PKTS(pbd) += 1; read_lock(&pkc->blk_fill_in_prog_lock); prb_run_all_ft_ops(pkc, ppd); } /* Assumes caller has the sk->rx_queue.lock */ static void *__packet_lookup_frame_in_block(struct packet_sock *po, struct sk_buff *skb, unsigned int len ) { struct tpacket_kbdq_core *pkc; struct tpacket_block_desc *pbd; char *curr, *end; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* Queue is frozen when user space is lagging behind */ if (prb_queue_frozen(pkc)) { /* * Check if that last block which caused the queue to freeze, * is still in_use by user-space. */ if (prb_curr_blk_in_use(pbd)) { /* Can't record this packet */ return NULL; } else { /* * Ok, the block was released by user-space. * Now let's open that block. * opening a block also thaws the queue. * Thawing is a side effect. */ prb_open_block(pkc, pbd); } } smp_mb(); curr = pkc->nxt_offset; pkc->skb = skb; end = (char *)pbd + pkc->kblk_size; /* first try the current block */ if (curr+TOTAL_PKT_LEN_INCL_ALIGN(len) < end) { prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* Ok, close the current block */ prb_retire_current_block(pkc, po, 0); /* Now, try to dispatch the next block */ curr = (char *)prb_dispatch_next_block(pkc, po); if (curr) { pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* * No free blocks are available.user_space hasn't caught up yet. * Queue was just frozen and now this packet will get dropped. */ return NULL; } static void *packet_current_rx_frame(struct packet_sock *po, struct sk_buff *skb, int status, unsigned int len) { char *curr = NULL; switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: curr = packet_lookup_frame(po, &po->rx_ring, po->rx_ring.head, status); return curr; case TPACKET_V3: return __packet_lookup_frame_in_block(po, skb, len); default: WARN(1, "TPACKET version not supported\n"); BUG(); return NULL; } } static void *prb_lookup_block(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int idx, int status) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx); if (status != BLOCK_STATUS(pbd)) return NULL; return pbd; } static int prb_previous_blk_num(struct packet_ring_buffer *rb) { unsigned int prev; if (rb->prb_bdqc.kactive_blk_num) prev = rb->prb_bdqc.kactive_blk_num-1; else prev = rb->prb_bdqc.knum_blocks-1; return prev; } /* Assumes caller has held the rx_queue.lock */ static void *__prb_previous_block(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = prb_previous_blk_num(rb); return prb_lookup_block(po, rb, previous, status); } static void *packet_previous_rx_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { if (po->tp_version <= TPACKET_V2) return packet_previous_frame(po, rb, status); return __prb_previous_block(po, rb, status); } static void packet_increment_rx_head(struct packet_sock *po, struct packet_ring_buffer *rb) { switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: return packet_increment_head(rb); case TPACKET_V3: default: WARN(1, "TPACKET version not supported.\n"); BUG(); return; } } static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max; return packet_lookup_frame(po, rb, previous, status); } static void packet_increment_head(struct packet_ring_buffer *buff) { buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; } static void packet_inc_pending(struct packet_ring_buffer *rb) { this_cpu_inc(*rb->pending_refcnt); } static void packet_dec_pending(struct packet_ring_buffer *rb) { this_cpu_dec(*rb->pending_refcnt); } static unsigned int packet_read_pending(const struct packet_ring_buffer *rb) { unsigned int refcnt = 0; int cpu; /* We don't use pending refcount in rx_ring. */ if (rb->pending_refcnt == NULL) return 0; for_each_possible_cpu(cpu) refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu); return refcnt; } static int packet_alloc_pending(struct packet_sock *po) { po->rx_ring.pending_refcnt = NULL; po->tx_ring.pending_refcnt = alloc_percpu(unsigned int); if (unlikely(po->tx_ring.pending_refcnt == NULL)) return -ENOBUFS; return 0; } static void packet_free_pending(struct packet_sock *po) { free_percpu(po->tx_ring.pending_refcnt); } #define ROOM_POW_OFF 2 #define ROOM_NONE 0x0 #define ROOM_LOW 0x1 #define ROOM_NORMAL 0x2 static bool __tpacket_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.frame_max) + 1; idx = READ_ONCE(po->rx_ring.head); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static bool __tpacket_v3_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.prb_bdqc.knum_blocks); idx = READ_ONCE(po->rx_ring.prb_bdqc.kactive_blk_num); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static int __packet_rcv_has_room(const struct packet_sock *po, const struct sk_buff *skb) { const struct sock *sk = &po->sk; int ret = ROOM_NONE; if (po->prot_hook.func != tpacket_rcv) { int rcvbuf = READ_ONCE(sk->sk_rcvbuf); int avail = rcvbuf - atomic_read(&sk->sk_rmem_alloc) - (skb ? skb->truesize : 0); if (avail > (rcvbuf >> ROOM_POW_OFF)) return ROOM_NORMAL; else if (avail > 0) return ROOM_LOW; else return ROOM_NONE; } if (po->tp_version == TPACKET_V3) { if (__tpacket_v3_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_v3_has_room(po, 0)) ret = ROOM_LOW; } else { if (__tpacket_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_has_room(po, 0)) ret = ROOM_LOW; } return ret; } static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) { bool pressure; int ret; ret = __packet_rcv_has_room(po, skb); pressure = ret != ROOM_NORMAL; if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) != pressure) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, pressure); return ret; } static void packet_rcv_try_clear_pressure(struct packet_sock *po) { if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, false); } static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive packet socket: %p\n", sk); return; } } static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb) { u32 *history = po->rollover->history; u32 victim, rxhash; int i, count = 0; rxhash = skb_get_hash(skb); for (i = 0; i < ROLLOVER_HLEN; i++) if (READ_ONCE(history[i]) == rxhash) count++; victim = get_random_u32_below(ROLLOVER_HLEN); /* Avoid dirtying the cache line if possible */ if (READ_ONCE(history[victim]) != rxhash) WRITE_ONCE(history[victim], rxhash); return count > (ROLLOVER_HLEN >> 1); } static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return reciprocal_scale(__skb_get_hash_symmetric(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { unsigned int val = atomic_inc_return(&f->rr_cur); return val % num; } static unsigned int fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return smp_processor_id() % num; } static unsigned int fanout_demux_rnd(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return get_random_u32_below(num); } static unsigned int fanout_demux_rollover(struct packet_fanout *f, struct sk_buff *skb, unsigned int idx, bool try_self, unsigned int num) { struct packet_sock *po, *po_next, *po_skip = NULL; unsigned int i, j, room = ROOM_NONE; po = pkt_sk(rcu_dereference(f->arr[idx])); if (try_self) { room = packet_rcv_has_room(po, skb); if (room == ROOM_NORMAL || (room == ROOM_LOW && !fanout_flow_is_huge(po, skb))) return idx; po_skip = po; } i = j = min_t(int, po->rollover->sock, num - 1); do { po_next = pkt_sk(rcu_dereference(f->arr[i])); if (po_next != po_skip && !packet_sock_flag(po_next, PACKET_SOCK_PRESSURE) && packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) { if (i != j) po->rollover->sock = i; atomic_long_inc(&po->rollover->num); if (room == ROOM_LOW) atomic_long_inc(&po->rollover->num_huge); return i; } if (++i == num) i = 0; } while (i != j); atomic_long_inc(&po->rollover->num_failed); return idx; } static unsigned int fanout_demux_qm(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return skb_get_queue_mapping(skb) % num; } static unsigned int fanout_demux_bpf(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { struct bpf_prog *prog; unsigned int ret = 0; rcu_read_lock(); prog = rcu_dereference(f->bpf_prog); if (prog) ret = bpf_prog_run_clear_cb(prog, skb) % num; rcu_read_unlock(); return ret; } static bool fanout_has_flag(struct packet_fanout *f, u16 flag) { return f->flags & (flag >> 8); } static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct packet_fanout *f = pt->af_packet_priv; unsigned int num = READ_ONCE(f->num_members); struct net *net = read_pnet(&f->net); struct packet_sock *po; unsigned int idx; if (!net_eq(dev_net(dev), net) || !num) { kfree_skb(skb); return 0; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) { skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET); if (!skb) return 0; } switch (f->type) { case PACKET_FANOUT_HASH: default: idx = fanout_demux_hash(f, skb, num); break; case PACKET_FANOUT_LB: idx = fanout_demux_lb(f, skb, num); break; case PACKET_FANOUT_CPU: idx = fanout_demux_cpu(f, skb, num); break; case PACKET_FANOUT_RND: idx = fanout_demux_rnd(f, skb, num); break; case PACKET_FANOUT_QM: idx = fanout_demux_qm(f, skb, num); break; case PACKET_FANOUT_ROLLOVER: idx = fanout_demux_rollover(f, skb, 0, false, num); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: idx = fanout_demux_bpf(f, skb, num); break; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER)) idx = fanout_demux_rollover(f, skb, idx, true, num); po = pkt_sk(rcu_dereference(f->arr[idx])); return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev); } DEFINE_MUTEX(fanout_mutex); EXPORT_SYMBOL_GPL(fanout_mutex); static LIST_HEAD(fanout_list); static u16 fanout_next_id; static void __fanout_link(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; spin_lock(&f->lock); rcu_assign_pointer(f->arr[f->num_members], sk); smp_wmb(); f->num_members++; if (f->num_members == 1) dev_add_pack(&f->prot_hook); spin_unlock(&f->lock); } static void __fanout_unlink(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; int i; spin_lock(&f->lock); for (i = 0; i < f->num_members; i++) { if (rcu_dereference_protected(f->arr[i], lockdep_is_held(&f->lock)) == sk) break; } BUG_ON(i >= f->num_members); rcu_assign_pointer(f->arr[i], rcu_dereference_protected(f->arr[f->num_members - 1], lockdep_is_held(&f->lock))); f->num_members--; if (f->num_members == 0) __dev_remove_pack(&f->prot_hook); spin_unlock(&f->lock); } static bool match_fanout_group(struct packet_type *ptype, struct sock *sk) { if (sk->sk_family != PF_PACKET) return false; return ptype->af_packet_priv == pkt_sk(sk)->fanout; } static void fanout_init_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_LB: atomic_set(&f->rr_cur, 0); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: RCU_INIT_POINTER(f->bpf_prog, NULL); break; } } static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new) { struct bpf_prog *old; spin_lock(&f->lock); old = rcu_dereference_protected(f->bpf_prog, lockdep_is_held(&f->lock)); rcu_assign_pointer(f->bpf_prog, new); spin_unlock(&f->lock); if (old) { synchronize_net(); bpf_prog_destroy(old); } } static int fanout_set_data_cbpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; struct sock_fprog fprog; int ret; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; ret = copy_bpf_fprog_from_user(&fprog, data, len); if (ret) return ret; ret = bpf_prog_create_from_user(&new, &fprog, NULL, false); if (ret) return ret; __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data_ebpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; u32 fd; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; if (len != sizeof(fd)) return -EINVAL; if (copy_from_sockptr(&fd, data, len)) return -EFAULT; new = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(new)) return PTR_ERR(new); __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data(struct packet_sock *po, sockptr_t data, unsigned int len) { switch (po->fanout->type) { case PACKET_FANOUT_CBPF: return fanout_set_data_cbpf(po, data, len); case PACKET_FANOUT_EBPF: return fanout_set_data_ebpf(po, data, len); default: return -EINVAL; } } static void fanout_release_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: __fanout_set_data_bpf(f, NULL); } } static bool __fanout_id_is_free(struct sock *sk, u16 candidate_id) { struct packet_fanout *f; list_for_each_entry(f, &fanout_list, list) { if (f->id == candidate_id && read_pnet(&f->net) == sock_net(sk)) { return false; } } return true; } static bool fanout_find_new_id(struct sock *sk, u16 *new_id) { u16 id = fanout_next_id; do { if (__fanout_id_is_free(sk, id)) { *new_id = id; fanout_next_id = id + 1; return true; } id++; } while (id != fanout_next_id); return false; } static int fanout_add(struct sock *sk, struct fanout_args *args) { struct packet_rollover *rollover = NULL; struct packet_sock *po = pkt_sk(sk); u16 type_flags = args->type_flags; struct packet_fanout *f, *match; u8 type = type_flags & 0xff; u8 flags = type_flags >> 8; u16 id = args->id; int err; switch (type) { case PACKET_FANOUT_ROLLOVER: if (type_flags & PACKET_FANOUT_FLAG_ROLLOVER) return -EINVAL; break; case PACKET_FANOUT_HASH: case PACKET_FANOUT_LB: case PACKET_FANOUT_CPU: case PACKET_FANOUT_RND: case PACKET_FANOUT_QM: case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: break; default: return -EINVAL; } mutex_lock(&fanout_mutex); err = -EALREADY; if (po->fanout) goto out; if (type == PACKET_FANOUT_ROLLOVER || (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) { err = -ENOMEM; rollover = kzalloc(sizeof(*rollover), GFP_KERNEL); if (!rollover) goto out; atomic_long_set(&rollover->num, 0); atomic_long_set(&rollover->num_huge, 0); atomic_long_set(&rollover->num_failed, 0); } if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) { if (id != 0) { err = -EINVAL; goto out; } if (!fanout_find_new_id(sk, &id)) { err = -ENOMEM; goto out; } /* ephemeral flag for the first socket in the group: drop it */ flags &= ~(PACKET_FANOUT_FLAG_UNIQUEID >> 8); } match = NULL; list_for_each_entry(f, &fanout_list, list) { if (f->id == id && read_pnet(&f->net) == sock_net(sk)) { match = f; break; } } err = -EINVAL; if (match) { if (match->flags != flags) goto out; if (args->max_num_members && args->max_num_members != match->max_num_members) goto out; } else { if (args->max_num_members > PACKET_FANOUT_MAX) goto out; if (!args->max_num_members) /* legacy PACKET_FANOUT_MAX */ args->max_num_members = 256; err = -ENOMEM; match = kvzalloc(struct_size(match, arr, args->max_num_members), GFP_KERNEL); if (!match) goto out; write_pnet(&match->net, sock_net(sk)); match->id = id; match->type = type; match->flags = flags; INIT_LIST_HEAD(&match->list); spin_lock_init(&match->lock); refcount_set(&match->sk_ref, 0); fanout_init_data(match); match->prot_hook.type = po->prot_hook.type; match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; match->prot_hook.ignore_outgoing = type_flags & PACKET_FANOUT_FLAG_IGNORE_OUTGOING; list_add(&match->list, &fanout_list); } err = -EINVAL; spin_lock(&po->bind_lock); if (po->num && match->type == type && match->prot_hook.type == po->prot_hook.type && match->prot_hook.dev == po->prot_hook.dev) { err = -ENOSPC; if (refcount_read(&match->sk_ref) < match->max_num_members) { /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */ WRITE_ONCE(po->fanout, match); po->rollover = rollover; rollover = NULL; refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { __dev_remove_pack(&po->prot_hook); __fanout_link(sk, po); } err = 0; } } spin_unlock(&po->bind_lock); if (err && !refcount_read(&match->sk_ref)) { list_del(&match->list); kvfree(match); } out: kfree(rollover); mutex_unlock(&fanout_mutex); return err; } /* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout. * It is the responsibility of the caller to call fanout_release_data() and * free the returned packet_fanout (after synchronize_net()) */ static struct packet_fanout *fanout_release(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_fanout *f; mutex_lock(&fanout_mutex); f = po->fanout; if (f) { po->fanout = NULL; if (refcount_dec_and_test(&f->sk_ref)) list_del(&f->list); else f = NULL; } mutex_unlock(&fanout_mutex); return f; } static bool packet_extra_vlan_len_allowed(const struct net_device *dev, struct sk_buff *skb) { /* Earlier code assumed this would be a VLAN pkt, double-check * this now that we have the actual packet in hand. We can only * do this check on Ethernet devices. */ if (unlikely(dev->type != ARPHRD_ETHER)) return false; skb_reset_mac_header(skb); return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q)); } static const struct proto_ops packet_ops; static const struct proto_ops packet_ops_spkt; static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct sock *sk; struct sockaddr_pkt *spkt; /* * When we registered the protocol we saved the socket in the data * field for just this event. */ sk = pt->af_packet_priv; /* * Yank back the headers [hope the device set this * right or kerboom...] * * Incoming packets have ll header pulled, * push it back. * * For outgoing ones skb->data == skb_mac_header(skb) * so that this procedure is noop. */ if (skb->pkt_type == PACKET_LOOPBACK) goto out; if (!net_eq(dev_net(dev), sock_net(sk))) goto out; skb = skb_share_check(skb, GFP_ATOMIC); if (skb == NULL) goto oom; /* drop any routing info */ skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spkt = &PACKET_SKB_CB(skb)->sa.pkt; skb_push(skb, skb->data - skb_mac_header(skb)); /* * The SOCK_PACKET socket receives _all_ frames. */ spkt->spkt_family = dev->type; strscpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); spkt->spkt_protocol = skb->protocol; /* * Charge the memory to the socket. This is done specifically * to prevent sockets using all the memory up. */ if (sock_queue_rcv_skb(sk, skb) == 0) return 0; out: kfree_skb(skb); oom: return 0; } static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { int depth; if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && sock->type == SOCK_RAW) { skb_reset_mac_header(skb); skb->protocol = dev_parse_header_protocol(skb); } /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); skb_probe_transport_header(skb); } /* * Output a raw packet to a device layer. This bypasses all the other * protocol layers and you must therefore supply it with a complete frame */ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name); struct sk_buff *skb = NULL; struct net_device *dev; struct sockcm_cookie sockc; __be16 proto = 0; int err; int extra_len = 0; /* * Get and verify the address. */ if (saddr) { if (msg->msg_namelen < sizeof(struct sockaddr)) return -EINVAL; if (msg->msg_namelen == sizeof(struct sockaddr_pkt)) proto = saddr->spkt_protocol; } else return -ENOTCONN; /* SOCK_PACKET must be sent giving an address */ /* * Find the device first to size check it */ saddr->spkt_device[sizeof(saddr->spkt_device) - 1] = 0; retry: rcu_read_lock(); dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device); err = -ENODEV; if (dev == NULL) goto out_unlock; err = -ENETDOWN; if (!(dev->flags & IFF_UP)) goto out_unlock; /* * You may not queue a frame bigger than the mtu. This is the lowest level * raw protocol and you must do your own fragmentation at this level. */ if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len) goto out_unlock; if (!skb) { size_t reserved = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; rcu_read_unlock(); skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL); if (skb == NULL) return -ENOBUFS; /* FIXME: Save some space for broken drivers that write a hard * header at transmission time by themselves. PPP is the notable * one here. This should really be fixed at the driver level. */ skb_reserve(skb, reserved); skb_reset_network_header(skb); /* Try to align data part correctly */ if (hhlen) { skb->data -= hhlen; skb->tail -= hhlen; if (len < hhlen) skb_reset_network_header(skb); } err = memcpy_from_msg(skb_put(skb, len), msg, len); if (err) goto out_free; goto retry; } if (!dev_validate_header(dev, skb->data, len) || !skb->len) { err = -EINVAL; goto out_unlock; } if (len > (dev->mtu + dev->hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_unlock; } sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } skb->protocol = proto; skb->dev = dev; skb->priority = sockc.priority; skb->mark = sockc.mark; skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); skb_setup_tx_timestamp(skb, &sockc); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); dev_queue_xmit(skb); rcu_read_unlock(); return len; out_unlock: rcu_read_unlock(); out_free: kfree_skb(skb); return err; } static unsigned int run_filter(struct sk_buff *skb, const struct sock *sk, unsigned int res) { struct sk_filter *filter; rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) res = bpf_prog_run_clear_cb(filter->prog, skb); rcu_read_unlock(); return res; } static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, size_t *len, int vnet_hdr_sz) { struct virtio_net_hdr_mrg_rxbuf vnet_hdr = { .num_buffers = 0 }; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (virtio_net_hdr_from_skb(skb, (struct virtio_net_hdr *)&vnet_hdr, vio_le(), true, 0)) return -EINVAL; return memcpy_to_msg(msg, (void *)&vnet_hdr, vnet_hdr_sz); } /* * This function makes lazy skb cloning in hope that most of packets * are discarded by BPF. * * Note tricky part: we DO mangle shared skb! skb->data, skb->len * and skb->cb are mangled. It works because (and until) packets * falling here are owned by current CPU. Output packets are cloned * by dev_queue_xmit_nit(), input packets are processed by net_bh * sequentially, so that if we return skb to original state on exit, * we will not harm anyone. */ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk = NULL; struct sockaddr_ll *sll; struct packet_sock *po; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; skb->dev = dev; if (dev_has_header(dev)) { /* The device has an explicit notion of ll header, * exported to higher levels. * * Otherwise, the device hides details of its frame * structure, so that corresponding packet head is * never delivered to user. */ if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb); res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; if (snaplen > res) snaplen = res; if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto drop_n_acct; if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (nskb == NULL) goto drop_n_acct; if (skb_head != skb->data) { skb->data = skb_head; skb->len = skb_len; } consume_skb(skb); skb = nskb; } sock_skb_cb_check_size(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8); sll = &PACKET_SKB_CB(skb)->sa.ll; sll->sll_hatype = dev->type; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; sll->sll_halen = dev_parse_header(skb, sll->sll_addr); /* sll->sll_family and sll->sll_protocol are set in packet_recvmsg(). * Use their space for storing the original skb length. */ PACKET_SKB_CB(skb)->sa.origlen = skb->len; if (pskb_trim(skb, snaplen)) goto drop_n_acct; skb_set_owner_r(skb, sk); skb->dev = NULL; skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spin_lock(&sk->sk_receive_queue.lock); po->stats.stats1.tp_packets++; sock_skb_set_dropcount(sk, skb); skb_clear_delivery_time(skb); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); return 0; drop_n_acct: atomic_inc(&po->tp_drops); sk_drops_inc(sk); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: sk_skb_reason_drop(sk, skb, drop_reason); return 0; } static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk = NULL; struct packet_sock *po; struct sockaddr_ll *sll; union tpacket_uhdr h; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; unsigned short macoff, hdrlen; unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec64 ts; __u32 ts_status; unsigned int slot_id = 0; int vnet_hdr_sz = 0; /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. * We may add members to them until current aligned size without forcing * userspace to call getsockopt(..., PACKET_HDRLEN, ...). */ BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h2)) != 32); BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h3)) != 48); if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; if (dev_has_header(dev)) { if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb); res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; /* If we are flooded, just give up */ if (__packet_rcv_has_room(po, skb) == ROOM_NONE) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) status |= TP_STATUS_GSO_TCP; if (snaplen > res) snaplen = res; if (sk->sk_type == SOCK_DGRAM) { macoff = netoff = TPACKET_ALIGN(po->tp_hdrlen) + 16 + po->tp_reserve; } else { unsigned int maclen = skb_network_offset(skb); netoff = TPACKET_ALIGN(po->tp_hdrlen + (maclen < 16 ? 16 : maclen)) + po->tp_reserve; vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); if (vnet_hdr_sz) netoff += vnet_hdr_sz; macoff = netoff - maclen; } if (netoff > USHRT_MAX) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (READ_ONCE(po->copy_thresh) && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { if (skb_shared(skb)) { copy_skb = skb_clone(skb, GFP_ATOMIC); } else { copy_skb = skb_get(skb); skb_head = skb->data; } if (copy_skb) { memset(&PACKET_SKB_CB(copy_skb)->sa.ll, 0, sizeof(PACKET_SKB_CB(copy_skb)->sa.ll)); skb_set_owner_r(copy_skb, sk); } } snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) { snaplen = 0; vnet_hdr_sz = 0; } } } else if (unlikely(macoff + snaplen > GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) { u32 nval; nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff; pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n", snaplen, nval, macoff); snaplen = nval; if (unlikely((int)snaplen < 0)) { snaplen = 0; macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len; vnet_hdr_sz = 0; } } spin_lock(&sk->sk_receive_queue.lock); h.raw = packet_current_rx_frame(po, skb, TP_STATUS_KERNEL, (macoff+snaplen)); if (!h.raw) goto drop_n_account; if (po->tp_version <= TPACKET_V2) { slot_id = po->rx_ring.head; if (test_bit(slot_id, po->rx_ring.rx_owner_map)) goto drop_n_account; __set_bit(slot_id, po->rx_ring.rx_owner_map); } if (vnet_hdr_sz && virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), vio_le(), true, 0)) { if (po->tp_version == TPACKET_V3) prb_clear_blk_fill_status(&po->rx_ring); goto drop_n_account; } if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); /* * LOSING will be reported till you read the stats, * because it's COR - Clear On Read. * Anyways, moving it for V1/V2 only as V3 doesn't need this * at packet level. */ if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; } po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; skb_clear_delivery_time(copy_skb); __skb_queue_tail(&sk->sk_receive_queue, copy_skb); } spin_unlock(&sk->sk_receive_queue.lock); skb_copy_bits(skb, 0, h.raw + macoff, snaplen); /* Always timestamp; prefer an existing software timestamp taken * closer to the time of capture. */ ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp) | SOF_TIMESTAMPING_SOFTWARE); if (!ts_status) ktime_get_real_ts64(&ts); status |= ts_status; switch (po->tp_version) { case TPACKET_V1: h.h1->tp_len = skb->len; h.h1->tp_snaplen = snaplen; h.h1->tp_mac = macoff; h.h1->tp_net = netoff; h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; hdrlen = sizeof(*h.h1); break; case TPACKET_V2: h.h2->tp_len = skb->len; h.h2->tp_snaplen = snaplen; h.h2->tp_mac = macoff; h.h2->tp_net = netoff; h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; if (skb_vlan_tag_present(skb)) { h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev); h.h2->tp_vlan_tpid = ntohs(skb->protocol); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; h.h2->tp_vlan_tpid = 0; } memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding)); hdrlen = sizeof(*h.h2); break; case TPACKET_V3: /* tp_nxt_offset,vlan are already populated above. * So DONT clear those fields here */ h.h3->tp_status |= status; h.h3->tp_len = skb->len; h.h3->tp_snaplen = snaplen; h.h3->tp_mac = macoff; h.h3->tp_net = netoff; h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding)); hdrlen = sizeof(*h.h3); break; default: BUG(); } sll = h.raw + TPACKET_ALIGN(hdrlen); sll->sll_halen = dev_parse_header(skb, sll->sll_addr); sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ? vlan_get_protocol_dgram(skb) : skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; smp_mb(); #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 if (po->tp_version <= TPACKET_V2) { u8 *start, *end; end = (u8 *) PAGE_ALIGN((unsigned long) h.raw + macoff + snaplen); for (start = h.raw; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); } smp_wmb(); #endif if (po->tp_version <= TPACKET_V2) { spin_lock(&sk->sk_receive_queue.lock); __packet_set_status(po, h.raw, status); __clear_bit(slot_id, po->rx_ring.rx_owner_map); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); } else if (po->tp_version == TPACKET_V3) { prb_clear_blk_fill_status(&po->rx_ring); } drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: sk_skb_reason_drop(sk, skb, drop_reason); return 0; drop_n_account: spin_unlock(&sk->sk_receive_queue.lock); atomic_inc(&po->tp_drops); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; sk->sk_data_ready(sk); sk_skb_reason_drop(sk, copy_skb, drop_reason); goto drop_n_restore; } static void tpacket_destruct_skb(struct sk_buff *skb) { struct packet_sock *po = pkt_sk(skb->sk); if (likely(po->tx_ring.pg_vec)) { void *ph; __u32 ts; ph = skb_zcopy_get_nouarg(skb); packet_dec_pending(&po->tx_ring); ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); complete(&po->skb_completion); } sock_wfree(skb); } static int __packet_snd_vnet_parse(struct virtio_net_hdr *vnet_hdr, size_t len) { if ((vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && (__virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2 > __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len))) vnet_hdr->hdr_len = __cpu_to_virtio16(vio_le(), __virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2); if (__virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len) > len) return -EINVAL; return 0; } static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len, struct virtio_net_hdr *vnet_hdr, int vnet_hdr_sz) { int ret; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (!copy_from_iter_full(vnet_hdr, sizeof(*vnet_hdr), &msg->msg_iter)) return -EFAULT; ret = __packet_snd_vnet_parse(vnet_hdr, *len); if (ret) return ret; /* move iter to point to the start of mac header */ if (vnet_hdr_sz != sizeof(struct virtio_net_hdr)) iov_iter_advance(&msg->msg_iter, vnet_hdr_sz - sizeof(struct virtio_net_hdr)); return 0; } static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, void *data, int tp_len, __be16 proto, unsigned char *addr, int hlen, int copylen, const struct sockcm_cookie *sockc) { union tpacket_uhdr ph; int to_write, offset, len, nr_frags, len_max; struct socket *sock = po->sk.sk_socket; struct page *page; int err; ph.raw = frame; skb->protocol = proto; skb->dev = dev; skb->priority = sockc->priority; skb->mark = sockc->mark; skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid); skb_setup_tx_timestamp(skb, sockc); skb_zcopy_set_nouarg(skb, ph.raw); skb_reserve(skb, hlen); skb_reset_network_header(skb); to_write = tp_len; if (sock->type == SOCK_DGRAM) { err = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, tp_len); if (unlikely(err < 0)) return -EINVAL; } else if (copylen) { int hdrlen = min_t(int, copylen, tp_len); skb_push(skb, dev->hard_header_len); skb_put(skb, copylen - dev->hard_header_len); err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; if (!dev_validate_header(dev, skb->data, hdrlen)) return -EINVAL; data += hdrlen; to_write -= hdrlen; } offset = offset_in_page(data); len_max = PAGE_SIZE - offset; len = ((to_write > len_max) ? len_max : to_write); skb->data_len = to_write; skb->len += to_write; skb->truesize += to_write; refcount_add(to_write, &po->sk.sk_wmem_alloc); while (likely(to_write)) { nr_frags = skb_shinfo(skb)->nr_frags; if (unlikely(nr_frags >= MAX_SKB_FRAGS)) { pr_err("Packet exceed the number of skb frags(%u)\n", (unsigned int)MAX_SKB_FRAGS); return -EFAULT; } page = pgv_to_page(data); data += len; flush_dcache_page(page); get_page(page); skb_fill_page_desc(skb, nr_frags, page, offset, len); to_write -= len; offset = 0; len_max = PAGE_SIZE; len = ((to_write > len_max) ? len_max : to_write); } packet_parse_headers(skb, sock); return tp_len; } static int tpacket_parse_header(struct packet_sock *po, void *frame, int size_max, void **data) { union tpacket_uhdr ph; int tp_len, off; ph.raw = frame; switch (po->tp_version) { case TPACKET_V3: if (ph.h3->tp_next_offset != 0) { pr_warn_once("variable sized slot not supported"); return -EINVAL; } tp_len = ph.h3->tp_len; break; case TPACKET_V2: tp_len = ph.h2->tp_len; break; default: tp_len = ph.h1->tp_len; break; } if (unlikely(tp_len > size_max)) { pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); return -EMSGSIZE; } if (unlikely(packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF))) { int off_min, off_max; off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll); off_max = po->tx_ring.frame_size - tp_len; if (po->sk.sk_type == SOCK_DGRAM) { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_net; break; case TPACKET_V2: off = ph.h2->tp_net; break; default: off = ph.h1->tp_net; break; } } else { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_mac; break; case TPACKET_V2: off = ph.h2->tp_mac; break; default: off = ph.h1->tp_mac; break; } } if (unlikely((off < off_min) || (off_max < off))) return -EINVAL; } else { off = po->tp_hdrlen - sizeof(struct sockaddr_ll); } *data = frame + off; return tp_len; } static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) { struct sk_buff *skb = NULL; struct net_device *dev; struct virtio_net_hdr *vnet_hdr = NULL; struct sockcm_cookie sockc; __be16 proto; int err, reserve = 0; void *ph; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); bool need_wait = !(msg->msg_flags & MSG_DONTWAIT); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); unsigned char *addr = NULL; int tp_len, size_max; void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; int hlen, tlen, copylen = 0; long timeo; mutex_lock(&po->pg_vec_lock); /* packet_sendmsg() check on tx_ring.pg_vec was lockless, * we need to confirm it under protection of pg_vec_lock. */ if (unlikely(!po->tx_ring.pg_vec)) { err = -EBUSY; goto out; } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); if (po->sk.sk_socket->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_put; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_put; sockcm_init(&sockc, &po->sk); if (msg->msg_controllen) { err = sock_cmsg_send(&po->sk, msg, &sockc); if (unlikely(err)) goto out_put; } if (po->sk.sk_socket->type == SOCK_RAW) reserve = dev->hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !vnet_hdr_sz) size_max = dev->mtu + reserve + VLAN_HLEN; timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); reinit_completion(&po->skb_completion); do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { /* Note: packet_read_pending() might be slow if we * have to call it as it's per_cpu variable, but in * fast-path we don't have to call it, only when ph * is NULL, we need to check the pending_refcnt. */ if (need_wait && packet_read_pending(&po->tx_ring)) { timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo); if (timeo <= 0) { err = !timeo ? -ETIMEDOUT : -ERESTARTSYS; goto out_put; } /* check for additional frames */ continue; } else break; } skb = NULL; tp_len = tpacket_parse_header(po, ph, size_max, &data); if (tp_len < 0) goto tpacket_error; status = TP_STATUS_SEND_REQUEST; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; if (vnet_hdr_sz) { vnet_hdr = data; data += vnet_hdr_sz; tp_len -= vnet_hdr_sz; if (tp_len < 0 || __packet_snd_vnet_parse(vnet_hdr, tp_len)) { tp_len = -EINVAL; goto tpacket_error; } copylen = __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len); } copylen = max_t(int, copylen, dev->hard_header_len); skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll) + (copylen - dev->hard_header_len), !need_wait, &err); if (unlikely(skb == NULL)) { /* we assume the socket was initially writeable ... */ if (likely(len_sum > 0)) err = len_sum; goto out_status; } tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto, addr, hlen, copylen, &sockc); if (likely(tp_len >= 0) && tp_len > dev->mtu + reserve && !vnet_hdr_sz && !packet_extra_vlan_len_allowed(dev, skb)) tp_len = -EMSGSIZE; if (unlikely(tp_len < 0)) { tpacket_error: if (packet_sock_flag(po, PACKET_SOCK_TP_LOSS)) { __packet_set_status(po, ph, TP_STATUS_AVAILABLE); packet_increment_head(&po->tx_ring); kfree_skb(skb); continue; } else { status = TP_STATUS_WRONG_FORMAT; err = tp_len; goto out_status; } } if (vnet_hdr_sz) { if (virtio_net_hdr_to_skb(skb, vnet_hdr, vio_le())) { tp_len = -EINVAL; goto tpacket_error; } virtio_net_hdr_set_proto(skb, vnet_hdr); } skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); status = TP_STATUS_SEND_REQUEST; err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ skb = NULL; goto out_status; } /* * skb was dropped but not destructed yet; * let's treat it like congestion or err < 0 */ err = 0; } packet_increment_head(&po->tx_ring); len_sum += tp_len; } while (1); err = len_sum; goto out_put; out_status: __packet_set_status(po, ph, status); kfree_skb(skb); out_put: dev_put(dev); out: mutex_unlock(&po->pg_vec_lock); return err; } static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad, size_t reserve, size_t len, size_t linear, int noblock, int *err) { struct sk_buff *skb; /* Under a page? Don't bother with paged skb. */ if (prepad + len < PAGE_SIZE || !linear) linear = len; if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER); skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, err, PAGE_ALLOC_COSTLY_ORDER); if (!skb) return NULL; skb_reserve(skb, reserve); skb_put(skb, linear); skb->data_len = len - linear; skb->len += len - linear; return skb; } static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); struct sk_buff *skb; struct net_device *dev; __be16 proto; unsigned char *addr = NULL; int err, reserve = 0; struct sockcm_cookie sockc; struct virtio_net_hdr vnet_hdr = { 0 }; int offset = 0; struct packet_sock *po = pkt_sk(sk); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); int hlen, tlen, linear; int extra_len = 0; /* * Get and verify the address. */ if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); if (sock->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_unlock; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out_unlock; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } if (sock->type == SOCK_RAW) reserve = dev->hard_header_len; if (vnet_hdr_sz) { err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz); if (err) goto out_unlock; } if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + VLAN_HLEN + extra_len)) goto out_unlock; err = -ENOBUFS; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); linear = max(linear, min_t(int, len, dev->hard_header_len)); skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; skb_reset_network_header(skb); err = -EINVAL; if (sock->type == SOCK_DGRAM) { offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (unlikely(offset < 0)) goto out_free; } else if (reserve) { skb_reserve(skb, -reserve); if (len < reserve + sizeof(struct ipv6hdr) && dev->min_header_len != dev->hard_header_len) skb_reset_network_header(skb); } /* Returns -EFAULT on error */ err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len); if (err) goto out_free; if ((sock->type == SOCK_RAW && !dev_validate_header(dev, skb->data, len)) || !skb->len) { err = -EINVAL; goto out_free; } skb_setup_tx_timestamp(skb, &sockc); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_free; } skb->protocol = proto; skb->dev = dev; skb->priority = sockc.priority; skb->mark = sockc.mark; skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); if (vnet_hdr_sz) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) goto out_free; len += vnet_hdr_sz; virtio_net_hdr_set_proto(skb, &vnet_hdr); } err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err) goto out_unlock; } dev_put(dev); return len; out_free: kfree_skb(skb); out_unlock: dev_put(dev); out: return err; } static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); /* Reading tx_ring.pg_vec without holding pg_vec_lock is racy. * tpacket_snd() will redo the check safely. */ if (data_race(po->tx_ring.pg_vec)) return tpacket_snd(po, msg); return packet_snd(sock, msg, len); } /* * Close a PACKET socket. This is fairly simple. We immediately go * to 'closed' state and remove our protocol entry in the device list. */ static int packet_release(struct socket *sock) { struct sock *sk = sock->sk; struct packet_sock *po; struct packet_fanout *f; struct net *net; union tpacket_req_u req_u; if (!sk) return 0; net = sock_net(sk); po = pkt_sk(sk); mutex_lock(&net->packet.sklist_lock); sk_del_node_init_rcu(sk); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, sk->sk_prot, -1); spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); packet_cached_dev_reset(po); if (po->prot_hook.dev) { netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); packet_flush_mclist(sk); lock_sock(sk); if (po->rx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); } if (po->tx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); } release_sock(sk); f = fanout_release(sk); synchronize_net(); kfree(po->rollover); if (f) { fanout_release_data(f); kvfree(f); } /* * Now the socket is dead. No more input will appear. */ sock_orphan(sk); sock->sk = NULL; /* Purge queues */ skb_queue_purge(&sk->sk_receive_queue); packet_free_pending(po); sock_put(sk); return 0; } /* * Attach a packet hook. */ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, __be16 proto) { struct packet_sock *po = pkt_sk(sk); struct net_device *dev = NULL; bool unlisted = false; bool need_rehook; int ret = 0; lock_sock(sk); spin_lock(&po->bind_lock); if (!proto) proto = po->num; rcu_read_lock(); if (po->fanout) { ret = -EINVAL; goto out_unlock; } if (name) { dev = dev_get_by_name_rcu(sock_net(sk), name); if (!dev) { ret = -ENODEV; goto out_unlock; } } else if (ifindex) { dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (!dev) { ret = -ENODEV; goto out_unlock; } } need_rehook = po->prot_hook.type != proto || po->prot_hook.dev != dev; if (need_rehook) { dev_hold(dev); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { rcu_read_unlock(); /* prevents packet_notifier() from calling * register_prot_hook() */ WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); if (dev) unlisted = !dev_get_by_index_rcu(sock_net(sk), dev->ifindex); } BUG_ON(packet_sock_flag(po, PACKET_SOCK_RUNNING)); WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); if (unlikely(unlisted)) { po->prot_hook.dev = NULL; WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { netdev_hold(dev, &po->prot_hook.dev_tracker, GFP_ATOMIC); po->prot_hook.dev = dev; WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } dev_put(dev); } if (proto == 0 || !need_rehook) goto out_unlock; if (!unlisted && (!dev || (dev->flags & IFF_UP))) { register_prot_hook(sk); } else { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } out_unlock: rcu_read_unlock(); spin_unlock(&po->bind_lock); release_sock(sk); return ret; } /* * Bind a packet socket to a device */ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality */ if (addr_len != sizeof(struct sockaddr)) return -EINVAL; /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr; struct sock *sk = sock->sk; /* * Check legality */ if (addr_len < sizeof(struct sockaddr_ll)) return -EINVAL; if (sll->sll_family != AF_PACKET) return -EINVAL; return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { .name = "PACKET", .owner = THIS_MODULE, .obj_size = sizeof(struct packet_sock), }; /* * Create a packet of type SOCK_PACKET. */ static int packet_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct packet_sock *po; __be16 proto = (__force __be16)protocol; /* weird, but documented */ int err; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW && sock->type != SOCK_PACKET) return -ESOCKTNOSUPPORT; sock->state = SS_UNCONNECTED; err = -ENOBUFS; sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto, kern); if (sk == NULL) goto out; sock->ops = &packet_ops; if (sock->type == SOCK_PACKET) sock->ops = &packet_ops_spkt; po = pkt_sk(sk); err = packet_alloc_pending(po); if (err) goto out_sk_free; sock_init_data(sock, sk); init_completion(&po->skb_completion); sk->sk_family = PF_PACKET; po->num = proto; packet_cached_dev_reset(po); sk->sk_destruct = packet_sock_destruct; /* * Attach a protocol block */ spin_lock_init(&po->bind_lock); mutex_init(&po->pg_vec_lock); po->rollover = NULL; po->prot_hook.func = packet_rcv; if (sock->type == SOCK_PACKET) po->prot_hook.func = packet_rcv_spkt; po->prot_hook.af_packet_priv = sk; po->prot_hook.af_packet_net = sock_net(sk); if (proto) { po->prot_hook.type = proto; __register_prot_hook(sk); } mutex_lock(&net->packet.sklist_lock); sk_add_node_tail_rcu(sk, &net->packet.sklist); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, &packet_proto, 1); return 0; out_sk_free: sk_free(sk); out: return err; } /* * Pull a packet from our receive queue and hand it to the user. * If necessary we block. */ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; int vnet_hdr_len = READ_ONCE(pkt_sk(sk)->vnet_hdr_sz); unsigned int origlen = 0; err = -EINVAL; if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT|MSG_ERRQUEUE)) goto out; #if 0 /* What error should we return now? EUNATTACH? */ if (pkt_sk(sk)->ifindex < 0) return -ENODEV; #endif if (flags & MSG_ERRQUEUE) { err = sock_recv_errqueue(sk, msg, len, SOL_PACKET, PACKET_TX_TIMESTAMP); goto out; } /* * Call the generic datagram receiver. This handles all sorts * of horrible races and re-entrancy so we can forget about it * in the protocol layers. * * Now it will return ENETDOWN, if device have just gone down, * but then it will block. */ skb = skb_recv_datagram(sk, flags, &err); /* * An error occurred so return it. Because skb_recv_datagram() * handles the blocking we don't see and worry about blocking * retries. */ if (skb == NULL) goto out; packet_rcv_try_clear_pressure(pkt_sk(sk)); if (vnet_hdr_len) { err = packet_rcv_vnet(msg, skb, &len, vnet_hdr_len); if (err) goto out_free; } /* You lose any data beyond the buffer you gave. If it worries * a user program they can ask the device for its MTU * anyway. */ copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free; if (sock->type != SOCK_PACKET) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; /* Original length was stored in sockaddr_ll fields */ origlen = PACKET_SKB_CB(skb)->sa.origlen; sll->sll_family = AF_PACKET; sll->sll_protocol = (sock->type == SOCK_DGRAM) ? vlan_get_protocol_dgram(skb) : skb->protocol; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { const size_t max_len = min(sizeof(skb->cb), sizeof(struct sockaddr_storage)); int copy_len; /* If the address length field is there to be filled * in, we fill it in now. */ if (sock->type == SOCK_PACKET) { __sockaddr_check_size(sizeof(struct sockaddr_pkt)); msg->msg_namelen = sizeof(struct sockaddr_pkt); copy_len = msg->msg_namelen; } else { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr); copy_len = msg->msg_namelen; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) { memset(msg->msg_name + offsetof(struct sockaddr_ll, sll_addr), 0, sizeof(sll->sll_addr)); msg->msg_namelen = sizeof(struct sockaddr_ll); } } if (WARN_ON_ONCE(copy_len > max_len)) { copy_len = max_len; msg->msg_namelen = copy_len; } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len); } if (packet_sock_flag(pkt_sk(sk), PACKET_SOCK_AUXDATA)) { struct tpacket_auxdata aux; aux.tp_status = TP_STATUS_USER; if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) aux.tp_status |= TP_STATUS_GSO_TCP; aux.tp_len = origlen; aux.tp_snaplen = skb->len; aux.tp_mac = 0; aux.tp_net = skb_network_offset(skb); if (skb_vlan_tag_present(skb)) { aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex); if (dev) { aux.tp_vlan_tci = vlan_get_tci(skb, dev); aux.tp_vlan_tpid = ntohs(skb->protocol); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } rcu_read_unlock(); } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } /* * Free or return the buffer as appropriate. Again this * hides all the races and re-entrancy issues from us. */ err = vnet_hdr_len + ((flags&MSG_TRUNC) ? skb->len : copied); out_free: skb_free_datagram(sk, skb); out: return err; } static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; if (peer) return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); } static int packet_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); int ifindex; if (peer) return -EOPNOTSUPP; ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; sll->sll_ifindex = ifindex; sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; /* Let __fortify_memcpy_chk() know the actual buffer size. */ memcpy(((struct sockaddr_storage *)sll)->__data + offsetof(struct sockaddr_ll, sll_addr) - offsetofend(struct sockaddr_ll, sll_family), dev->dev_addr, dev->addr_len); } else { sll->sll_hatype = 0; /* Bad: we have no ARPHRD_UNSPEC */ sll->sll_halen = 0; } rcu_read_unlock(); return offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen; } static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, int what) { switch (i->type) { case PACKET_MR_MULTICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_mc_add(dev, i->addr); else return dev_mc_del(dev, i->addr); break; case PACKET_MR_PROMISC: return dev_set_promiscuity(dev, what); case PACKET_MR_ALLMULTI: return dev_set_allmulti(dev, what); case PACKET_MR_UNICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_uc_add(dev, i->addr); else return dev_uc_del(dev, i->addr); break; default: break; } return 0; } static void packet_dev_mclist_delete(struct net_device *dev, struct packet_mclist **mlp, struct list_head *list) { struct packet_mclist *ml; while ((ml = *mlp) != NULL) { if (ml->ifindex == dev->ifindex) { list_add(&ml->remove_list, list); *mlp = ml->next; } else mlp = &ml->next; } } static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml, *i; struct net_device *dev; int err; rtnl_lock(); err = -ENODEV; dev = __dev_get_by_index(sock_net(sk), mreq->mr_ifindex); if (!dev) goto done; err = -EINVAL; if (mreq->mr_alen > dev->addr_len) goto done; err = -ENOBUFS; i = kmalloc(sizeof(*i), GFP_KERNEL); if (i == NULL) goto done; err = 0; for (ml = po->mclist; ml; ml = ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { ml->count++; /* Free the new element ... */ kfree(i); goto done; } } i->type = mreq->mr_type; i->ifindex = mreq->mr_ifindex; i->alen = mreq->mr_alen; memcpy(i->addr, mreq->mr_address, i->alen); memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen); i->count = 1; INIT_LIST_HEAD(&i->remove_list); i->next = po->mclist; po->mclist = i; err = packet_dev_mc(dev, i, 1); if (err) { po->mclist = i->next; kfree(i); } done: rtnl_unlock(); return err; } static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_mclist *ml, **mlp; rtnl_lock(); for (mlp = &pkt_sk(sk)->mclist; (ml = *mlp) != NULL; mlp = &ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { if (--ml->count == 0) { struct net_device *dev; *mlp = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev) packet_dev_mc(dev, ml, -1); kfree(ml); } break; } } rtnl_unlock(); return 0; } static void packet_flush_mclist(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml; if (!po->mclist) return; rtnl_lock(); while ((ml = po->mclist) != NULL) { struct net_device *dev; po->mclist = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev != NULL) packet_dev_mc(dev, ml, -1); kfree(ml); } rtnl_unlock(); } static int packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); int ret; if (level != SOL_PACKET) return -ENOPROTOOPT; switch (optname) { case PACKET_ADD_MEMBERSHIP: case PACKET_DROP_MEMBERSHIP: { struct packet_mreq_max mreq; int len = optlen; memset(&mreq, 0, sizeof(mreq)); if (len < sizeof(struct packet_mreq)) return -EINVAL; if (len > sizeof(mreq)) len = sizeof(mreq); if (copy_from_sockptr(&mreq, optval, len)) return -EFAULT; if (len < (mreq.mr_alen + offsetof(struct packet_mreq, mr_address))) return -EINVAL; if (optname == PACKET_ADD_MEMBERSHIP) ret = packet_mc_add(sk, &mreq); else ret = packet_mc_drop(sk, &mreq); return ret; } case PACKET_RX_RING: case PACKET_TX_RING: { union tpacket_req_u req_u; ret = -EINVAL; lock_sock(sk); switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: if (optlen < sizeof(req_u.req)) break; ret = copy_from_sockptr(&req_u.req, optval, sizeof(req_u.req)) ? -EINVAL : 0; break; case TPACKET_V3: default: if (optlen < sizeof(req_u.req3)) break; ret = copy_from_sockptr(&req_u.req3, optval, sizeof(req_u.req3)) ? -EINVAL : 0; break; } if (!ret) ret = packet_set_ring(sk, &req_u, 0, optname == PACKET_TX_RING); release_sock(sk); return ret; } case PACKET_COPY_THRESH: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(pkt_sk(sk)->copy_thresh, val); return 0; } case PACKET_VERSION: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (val) { case TPACKET_V1: case TPACKET_V2: case TPACKET_V3: break; default: return -EINVAL; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_version = val; ret = 0; } release_sock(sk); return ret; } case PACKET_RESERVE: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val > INT_MAX) return -EINVAL; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_reserve = val; ret = 0; } release_sock(sk); return ret; } case PACKET_LOSS: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { packet_sock_flag_set(po, PACKET_SOCK_TP_LOSS, val); ret = 0; } release_sock(sk); return ret; } case PACKET_AUXDATA: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_AUXDATA, val); return 0; } case PACKET_ORIGDEV: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_ORIGDEV, val); return 0; } case PACKET_VNET_HDR: case PACKET_VNET_HDR_SZ: { int val, hdr_len; if (sock->type != SOCK_RAW) return -EINVAL; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (optname == PACKET_VNET_HDR_SZ) { if (val && val != sizeof(struct virtio_net_hdr) && val != sizeof(struct virtio_net_hdr_mrg_rxbuf)) return -EINVAL; hdr_len = val; } else { hdr_len = val ? sizeof(struct virtio_net_hdr) : 0; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { WRITE_ONCE(po->vnet_hdr_sz, hdr_len); ret = 0; } release_sock(sk); return ret; } case PACKET_TIMESTAMP: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(po->tp_tstamp, val); return 0; } case PACKET_FANOUT: { struct fanout_args args = { 0 }; if (optlen != sizeof(int) && optlen != sizeof(args)) return -EINVAL; if (copy_from_sockptr(&args, optval, optlen)) return -EFAULT; return fanout_add(sk, &args); } case PACKET_FANOUT_DATA: { /* Paired with the WRITE_ONCE() in fanout_add() */ if (!READ_ONCE(po->fanout)) return -EINVAL; return fanout_set_data(po, optval, optlen); } case PACKET_IGNORE_OUTGOING: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val < 0 || val > 1) return -EINVAL; WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val); return 0; } case PACKET_TX_HAS_OFF: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (!po->rx_ring.pg_vec && !po->tx_ring.pg_vec) packet_sock_flag_set(po, PACKET_SOCK_TX_HAS_OFF, val); release_sock(sk); return 0; } case PACKET_QDISC_BYPASS: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_QDISC_BYPASS, val); return 0; } default: return -ENOPROTOOPT; } } static int packet_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { int len; int val, lv = sizeof(val); struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); void *data = &val; union tpacket_stats_u st; struct tpacket_rollover_stats rstats; int drops; if (level != SOL_PACKET) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case PACKET_STATISTICS: spin_lock_bh(&sk->sk_receive_queue.lock); memcpy(&st, &po->stats, sizeof(st)); memset(&po->stats, 0, sizeof(po->stats)); spin_unlock_bh(&sk->sk_receive_queue.lock); drops = atomic_xchg(&po->tp_drops, 0); if (po->tp_version == TPACKET_V3) { lv = sizeof(struct tpacket_stats_v3); st.stats3.tp_drops = drops; st.stats3.tp_packets += drops; data = &st.stats3; } else { lv = sizeof(struct tpacket_stats); st.stats1.tp_drops = drops; st.stats1.tp_packets += drops; data = &st.stats1; } break; case PACKET_AUXDATA: val = packet_sock_flag(po, PACKET_SOCK_AUXDATA); break; case PACKET_ORIGDEV: val = packet_sock_flag(po, PACKET_SOCK_ORIGDEV); break; case PACKET_VNET_HDR: val = !!READ_ONCE(po->vnet_hdr_sz); break; case PACKET_VNET_HDR_SZ: val = READ_ONCE(po->vnet_hdr_sz); break; case PACKET_COPY_THRESH: val = READ_ONCE(pkt_sk(sk)->copy_thresh); break; case PACKET_VERSION: val = po->tp_version; break; case PACKET_HDRLEN: if (len > sizeof(int)) len = sizeof(int); if (len < sizeof(int)) return -EINVAL; if (copy_from_user(&val, optval, len)) return -EFAULT; switch (val) { case TPACKET_V1: val = sizeof(struct tpacket_hdr); break; case TPACKET_V2: val = sizeof(struct tpacket2_hdr); break; case TPACKET_V3: val = sizeof(struct tpacket3_hdr); break; default: return -EINVAL; } break; case PACKET_RESERVE: val = po->tp_reserve; break; case PACKET_LOSS: val = packet_sock_flag(po, PACKET_SOCK_TP_LOSS); break; case PACKET_TIMESTAMP: val = READ_ONCE(po->tp_tstamp); break; case PACKET_FANOUT: val = (po->fanout ? ((u32)po->fanout->id | ((u32)po->fanout->type << 16) | ((u32)po->fanout->flags << 24)) : 0); break; case PACKET_IGNORE_OUTGOING: val = READ_ONCE(po->prot_hook.ignore_outgoing); break; case PACKET_ROLLOVER_STATS: if (!po->rollover) return -EINVAL; rstats.tp_all = atomic_long_read(&po->rollover->num); rstats.tp_huge = atomic_long_read(&po->rollover->num_huge); rstats.tp_failed = atomic_long_read(&po->rollover->num_failed); data = &rstats; lv = sizeof(rstats); break; case PACKET_TX_HAS_OFF: val = packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF); break; case PACKET_QDISC_BYPASS: val = packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS); break; default: return -ENOPROTOOPT; } if (len > lv) len = lv; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, data, len)) return -EFAULT; return 0; } static int packet_notifier(struct notifier_block *this, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct packet_mclist *ml, *tmp; LIST_HEAD(mclist); struct sock *sk; rcu_read_lock(); sk_for_each_rcu(sk, &net->packet.sklist) { struct packet_sock *po = pkt_sk(sk); switch (msg) { case NETDEV_UNREGISTER: if (po->mclist) packet_dev_mclist_delete(dev, &po->mclist, &mclist); fallthrough; case NETDEV_DOWN: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); WRITE_ONCE(po->ifindex, -1); netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); } break; case NETDEV_UP: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (po->num) register_prot_hook(sk); spin_unlock(&po->bind_lock); } break; } } rcu_read_unlock(); /* packet_dev_mc might grab instance locks so can't run under rcu */ list_for_each_entry_safe(ml, tmp, &mclist, remove_list) { packet_dev_mc(dev, ml, -1); kfree(ml); } return NOTIFY_DONE; } static int packet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { struct sk_buff *skb; int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } #ifdef CONFIG_INET case SIOCADDRT: case SIOCDELRT: case SIOCDARP: case SIOCGARP: case SIOCSARP: case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCSIFFLAGS: return inet_dgram_ops.ioctl(sock, cmd, arg); #endif default: return -ENOIOCTLCMD; } return 0; } static __poll_t packet_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); __poll_t mask = datagram_poll(file, sock, wait); spin_lock_bh(&sk->sk_receive_queue.lock); if (po->rx_ring.pg_vec) { if (!packet_previous_rx_frame(po, &po->rx_ring, TP_STATUS_KERNEL)) mask |= EPOLLIN | EPOLLRDNORM; } packet_rcv_try_clear_pressure(po); spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE)) mask |= EPOLLOUT | EPOLLWRNORM; } spin_unlock_bh(&sk->sk_write_queue.lock); return mask; } /* Dirty? Well, I still did not learn better way to account * for user mmaps. */ static void packet_mm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_inc(&pkt_sk(sk)->mapped); } static void packet_mm_close(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_dec(&pkt_sk(sk)->mapped); } static const struct vm_operations_struct packet_mmap_ops = { .open = packet_mm_open, .close = packet_mm_close, }; static void free_pg_vec(struct pgv *pg_vec, unsigned int order, unsigned int len) { int i; for (i = 0; i < len; i++) { if (likely(pg_vec[i].buffer)) { if (is_vmalloc_addr(pg_vec[i].buffer)) vfree(pg_vec[i].buffer); else free_pages((unsigned long)pg_vec[i].buffer, order); pg_vec[i].buffer = NULL; } } kfree(pg_vec); } static char *alloc_one_pg_vec_page(unsigned long order) { char *buffer; gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* __get_free_pages failed, fall back to vmalloc */ buffer = vzalloc(array_size((1 << order), PAGE_SIZE)); if (buffer) return buffer; /* vmalloc failed, lets dig into swap here */ gfp_flags &= ~__GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* complete and utter failure */ return NULL; } static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) { unsigned int block_nr = req->tp_block_nr; struct pgv *pg_vec; int i; pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN); if (unlikely(!pg_vec)) goto out; for (i = 0; i < block_nr; i++) { pg_vec[i].buffer = alloc_one_pg_vec_page(order); if (unlikely(!pg_vec[i].buffer)) goto out_free_pgvec; } out: return pg_vec; out_free_pgvec: free_pg_vec(pg_vec, order, block_nr); pg_vec = NULL; goto out; } static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring) { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); unsigned long *rx_owner_map = NULL; int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; __be16 num; int err; /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; rb = tx_ring ? &po->tx_ring : &po->rx_ring; rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; err = -EBUSY; if (!closing) { if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; } if (req->tp_block_nr) { unsigned int min_frame_size; /* Sanity tests and some calculations */ err = -EBUSY; if (unlikely(rb->pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V1: po->tp_hdrlen = TPACKET_HDRLEN; break; case TPACKET_V2: po->tp_hdrlen = TPACKET2_HDRLEN; break; case TPACKET_V3: po->tp_hdrlen = TPACKET3_HDRLEN; break; } err = -EINVAL; if (unlikely((int)req->tp_block_size <= 0)) goto out; if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; min_frame_size = po->tp_hdrlen + po->tp_reserve; if (po->tp_version >= TPACKET_V3 && req->tp_block_size < BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size) goto out; if (unlikely(req->tp_frame_size < min_frame_size)) goto out; if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) goto out; rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) goto out; err = -ENOMEM; order = get_order(req->tp_block_size); pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V3: /* Block transmit is not supported yet */ if (!tx_ring) { init_prb_bdqc(po, rb, pg_vec, req_u); } else { struct tpacket_req3 *req3 = &req_u->req3; if (req3->tp_retire_blk_tov || req3->tp_sizeof_priv || req3->tp_feature_req_word) { err = -EINVAL; goto out_free_pg_vec; } } break; default: if (!tx_ring) { rx_owner_map = bitmap_alloc(req->tp_frame_nr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); if (!rx_owner_map) goto out_free_pg_vec; } break; } } /* Done */ else { err = -EINVAL; if (unlikely(req->tp_frame_nr)) goto out; } /* Detach socket from network */ spin_lock(&po->bind_lock); was_running = packet_sock_flag(po, PACKET_SOCK_RUNNING); num = po->num; WRITE_ONCE(po->num, 0); if (was_running) __unregister_prot_hook(sk, false); spin_unlock(&po->bind_lock); synchronize_net(); err = -EBUSY; mutex_lock(&po->pg_vec_lock); if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); if (po->tp_version <= TPACKET_V2) swap(rb->rx_owner_map, rx_owner_map); rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; spin_unlock_bh(&rb_queue->lock); swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); if (atomic_long_read(&po->mapped)) pr_err("packet_mmap: vma is busy: %ld\n", atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); spin_lock(&po->bind_lock); WRITE_ONCE(po->num, num); if (was_running) register_prot_hook(sk); spin_unlock(&po->bind_lock); if (pg_vec && (po->tp_version > TPACKET_V2)) { /* Because we don't support block-based V3 on tx-ring */ if (!tx_ring) prb_shutdown_retire_blk_timer(po, rb_queue); } out_free_pg_vec: if (pg_vec) { bitmap_free(rx_owner_map); free_pg_vec(pg_vec, order, req->tp_block_nr); } out: return err; } static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); unsigned long size, expected_size; struct packet_ring_buffer *rb; unsigned long start; int err = -EINVAL; int i; if (vma->vm_pgoff) return -EINVAL; mutex_lock(&po->pg_vec_lock); expected_size = 0; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec) { expected_size += rb->pg_vec_len * rb->pg_vec_pages * PAGE_SIZE; } } if (expected_size == 0) goto out; size = vma->vm_end - vma->vm_start; if (size != expected_size) goto out; start = vma->vm_start; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec == NULL) continue; for (i = 0; i < rb->pg_vec_len; i++) { struct page *page; void *kaddr = rb->pg_vec[i].buffer; int pg_num; for (pg_num = 0; pg_num < rb->pg_vec_pages; pg_num++) { page = pgv_to_page(kaddr); err = vm_insert_page(vma, start, page); if (unlikely(err)) goto out; start += PAGE_SIZE; kaddr += PAGE_SIZE; } } } atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; out: mutex_unlock(&po->pg_vec_lock); return err; } static const struct proto_ops packet_ops_spkt = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind_spkt, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname_spkt, .poll = datagram_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = packet_sendmsg_spkt, .recvmsg = packet_recvmsg, .mmap = sock_no_mmap, }; static const struct proto_ops packet_ops = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname, .poll = packet_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = packet_setsockopt, .getsockopt = packet_getsockopt, .sendmsg = packet_sendmsg, .recvmsg = packet_recvmsg, .mmap = packet_mmap, }; static const struct net_proto_family packet_family_ops = { .family = PF_PACKET, .create = packet_create, .owner = THIS_MODULE, }; static struct notifier_block packet_netdev_notifier = { .notifier_call = packet_notifier, }; #ifdef CONFIG_PROC_FS static void *packet_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct net *net = seq_file_net(seq); rcu_read_lock(); return seq_hlist_start_head_rcu(&net->packet.sklist, *pos); } static void *packet_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); return seq_hlist_next_rcu(v, &net->packet.sklist, pos); } static void packet_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int packet_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%*sRefCnt Type Proto Iface R Rmem User Inode\n", IS_ENABLED(CONFIG_64BIT) ? -17 : -9, "sk"); else { struct sock *s = sk_entry(v); const struct packet_sock *po = pkt_sk(s); seq_printf(seq, "%pK %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", s, refcount_read(&s->sk_refcnt), s->sk_type, ntohs(READ_ONCE(po->num)), READ_ONCE(po->ifindex), packet_sock_flag(po, PACKET_SOCK_RUNNING), atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sk_uid(s)), sock_i_ino(s)); } return 0; } static const struct seq_operations packet_seq_ops = { .start = packet_seq_start, .next = packet_seq_next, .stop = packet_seq_stop, .show = packet_seq_show, }; #endif static int __net_init packet_net_init(struct net *net) { mutex_init(&net->packet.sklist_lock); INIT_HLIST_HEAD(&net->packet.sklist); #ifdef CONFIG_PROC_FS if (!proc_create_net("packet", 0, net->proc_net, &packet_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; #endif /* CONFIG_PROC_FS */ return 0; } static void __net_exit packet_net_exit(struct net *net) { remove_proc_entry("packet", net->proc_net); WARN_ON_ONCE(!hlist_empty(&net->packet.sklist)); } static struct pernet_operations packet_net_ops = { .init = packet_net_init, .exit = packet_net_exit, }; static void __exit packet_exit(void) { sock_unregister(PF_PACKET); proto_unregister(&packet_proto); unregister_netdevice_notifier(&packet_netdev_notifier); unregister_pernet_subsys(&packet_net_ops); } static int __init packet_init(void) { int rc; rc = register_pernet_subsys(&packet_net_ops); if (rc) goto out; rc = register_netdevice_notifier(&packet_netdev_notifier); if (rc) goto out_pernet; rc = proto_register(&packet_proto, 0); if (rc) goto out_notifier; rc = sock_register(&packet_family_ops); if (rc) goto out_proto; return 0; out_proto: proto_unregister(&packet_proto); out_notifier: unregister_netdevice_notifier(&packet_netdev_notifier); out_pernet: unregister_pernet_subsys(&packet_net_ops); out: return rc; } module_init(packet_init); module_exit(packet_exit); MODULE_DESCRIPTION("Packet socket support (AF_PACKET)"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_PACKET); |
| 32 44 63 13 178 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * kref.h - library routines for handling generic reference counted objects * * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Corp. * * based on kobject.h which was: * Copyright (C) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (C) 2002-2003 Open Source Development Labs */ #ifndef _KREF_H_ #define _KREF_H_ #include <linux/spinlock.h> #include <linux/refcount.h> struct kref { refcount_t refcount; }; #define KREF_INIT(n) { .refcount = REFCOUNT_INIT(n), } /** * kref_init - initialize object. * @kref: object in question. */ static inline void kref_init(struct kref *kref) { refcount_set(&kref->refcount, 1); } static inline unsigned int kref_read(const struct kref *kref) { return refcount_read(&kref->refcount); } /** * kref_get - increment refcount for object. * @kref: object. */ static inline void kref_get(struct kref *kref) { refcount_inc(&kref->refcount); } /** * kref_put - Decrement refcount for object * @kref: Object * @release: Pointer to the function that will clean up the object when the * last reference to the object is released. * * Decrement the refcount, and if 0, call @release. The caller may not * pass NULL or kfree() as the release function. * * Return: 1 if this call removed the object, otherwise return 0. Beware, * if this function returns 0, another caller may have removed the object * by the time this function returns. The return value is only certain * if you want to see if the object is definitely released. */ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { if (refcount_dec_and_test(&kref->refcount)) { release(kref); return 1; } return 0; } /** * kref_put_mutex - Decrement refcount for object * @kref: Object * @release: Pointer to the function that will clean up the object when the * last reference to the object is released. * @mutex: Mutex which protects the release function. * * This variant of kref_lock() calls the @release function with the @mutex * held. The @release function will release the mutex. */ static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *mutex) { if (refcount_dec_and_mutex_lock(&kref->refcount, mutex)) { release(kref); return 1; } return 0; } /** * kref_put_lock - Decrement refcount for object * @kref: Object * @release: Pointer to the function that will clean up the object when the * last reference to the object is released. * @lock: Spinlock which protects the release function. * * This variant of kref_lock() calls the @release function with the @lock * held. The @release function will release the lock. */ static inline int kref_put_lock(struct kref *kref, void (*release)(struct kref *kref), spinlock_t *lock) { if (refcount_dec_and_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } /** * kref_get_unless_zero - Increment refcount for object unless it is zero. * @kref: object. * * This function is intended to simplify locking around refcounting for * objects that can be looked up from a lookup structure, and which are * removed from that lookup structure in the object destructor. * Operations on such objects require at least a read lock around * lookup + kref_get, and a write lock around kref_put + remove from lookup * structure. Furthermore, RCU implementations become extremely tricky. * With a lookup followed by a kref_get_unless_zero *with return value check* * locking in the kref_put path can be deferred to the actual removal from * the lookup structure and RCU lookups become trivial. * * Return: non-zero if the increment succeeded. Otherwise return 0. */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { return refcount_inc_not_zero(&kref->refcount); } #endif /* _KREF_H_ */ |
| 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 | /* * include/linux/topology.h * * Written by: Matthew Dobson, IBM Corporation * * Copyright (C) 2002, IBM Corp. * * All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or * NON INFRINGEMENT. See the GNU General Public License for more * details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * Send feedback to <colpatch@us.ibm.com> */ #ifndef _LINUX_TOPOLOGY_H #define _LINUX_TOPOLOGY_H #include <linux/arch_topology.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/bitops.h> #include <linux/mmzone.h> #include <linux/smp.h> #include <linux/percpu.h> #include <asm/topology.h> #ifndef nr_cpus_node #define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node)) #endif int arch_update_cpu_topology(void); /* Conform to ACPI 2.0 SLIT distance definitions */ #define LOCAL_DISTANCE 10 #define REMOTE_DISTANCE 20 #define DISTANCE_BITS 8 #ifndef node_distance #define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE) #endif #ifndef RECLAIM_DISTANCE /* * If the distance between nodes in a system is larger than RECLAIM_DISTANCE * (in whatever arch specific measurement units returned by node_distance()) * and node_reclaim_mode is enabled then the VM will only call node_reclaim() * on nodes within this distance. */ #define RECLAIM_DISTANCE 30 #endif /* * The following tunable allows platforms to override the default node * reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are * sufficiently fast that the default value actually hurts * performance. * * AMD EPYC machines use this because even though the 2-hop distance * is 32 (3.2x slower than a local memory access) performance actually * *improves* if allowed to reclaim memory and load balance tasks * between NUMA nodes 2-hops apart. */ extern int __read_mostly node_reclaim_distance; #ifndef PENALTY_FOR_NODE_WITH_CPUS #define PENALTY_FOR_NODE_WITH_CPUS (1) #endif #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DECLARE_PER_CPU(int, numa_node); #ifndef numa_node_id /* Returns the number of the current Node. */ static inline int numa_node_id(void) { return raw_cpu_read(numa_node); } #endif #ifndef cpu_to_node static inline int cpu_to_node(int cpu) { return per_cpu(numa_node, cpu); } #endif #ifndef set_numa_node static inline void set_numa_node(int node) { this_cpu_write(numa_node, node); } #endif #ifndef set_cpu_numa_node static inline void set_cpu_numa_node(int cpu, int node) { per_cpu(numa_node, cpu) = node; } #endif #else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */ /* Returns the number of the current Node. */ #ifndef numa_node_id static inline int numa_node_id(void) { return cpu_to_node(raw_smp_processor_id()); } #endif #endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */ #ifdef CONFIG_HAVE_MEMORYLESS_NODES /* * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem(). */ DECLARE_PER_CPU(int, _numa_mem_); #ifndef set_numa_mem static inline void set_numa_mem(int node) { this_cpu_write(_numa_mem_, node); } #endif #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return raw_cpu_read(_numa_mem_); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return per_cpu(_numa_mem_, cpu); } #endif #ifndef set_cpu_numa_mem static inline void set_cpu_numa_mem(int cpu, int node) { per_cpu(_numa_mem_, cpu) = node; } #endif #else /* !CONFIG_HAVE_MEMORYLESS_NODES */ #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return numa_node_id(); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return cpu_to_node(cpu); } #endif #endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */ #if defined(topology_die_id) && defined(topology_die_cpumask) #define TOPOLOGY_DIE_SYSFS #endif #if defined(topology_cluster_id) && defined(topology_cluster_cpumask) #define TOPOLOGY_CLUSTER_SYSFS #endif #if defined(topology_book_id) && defined(topology_book_cpumask) #define TOPOLOGY_BOOK_SYSFS #endif #if defined(topology_drawer_id) && defined(topology_drawer_cpumask) #define TOPOLOGY_DRAWER_SYSFS #endif #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_die_id #define topology_die_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_cluster_id #define topology_cluster_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif #ifndef topology_book_id #define topology_book_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_drawer_id #define topology_drawer_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_ppin #define topology_ppin(cpu) ((void)(cpu), 0ull) #endif #ifndef topology_sibling_cpumask #define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_cluster_cpumask #define topology_cluster_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_book_cpumask #define topology_book_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_drawer_cpumask #define topology_drawer_cpumask(cpu) cpumask_of(cpu) #endif #if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) { return topology_sibling_cpumask(cpu); } #endif #ifndef topology_is_primary_thread static inline bool topology_is_primary_thread(unsigned int cpu) { /* * When disabling SMT, the primary thread of the SMT will remain * enabled/active. Architectures that have a special primary thread * (e.g. x86) need to override this function. Otherwise the first * thread in the SMT can be made the primary thread. * * The sibling cpumask of an offline CPU always contains the CPU * itself on architectures using the implementation of * CONFIG_GENERIC_ARCH_TOPOLOGY for building their topology. * Other architectures not using CONFIG_GENERIC_ARCH_TOPOLOGY for * building their topology have to check whether to use this default * implementation or to override it. */ return cpu == cpumask_first(topology_sibling_cpumask(cpu)); } #define topology_is_primary_thread topology_is_primary_thread #endif static inline const struct cpumask *cpu_node_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); } #ifdef CONFIG_NUMA int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node); extern const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops); #else static __always_inline int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) { return cpumask_nth_and(cpu, cpus, cpu_online_mask); } static inline const struct cpumask * sched_numa_hop_mask(unsigned int node, unsigned int hops) { return ERR_PTR(-EOPNOTSUPP); } #endif /* CONFIG_NUMA */ /** * for_each_node_numadist() - iterate over nodes in increasing distance * order, starting from a given node * @node: the iteration variable and the starting node. * @unvisited: a nodemask to keep track of the unvisited nodes. * * This macro iterates over NUMA node IDs in increasing distance from the * starting @node and yields MAX_NUMNODES when all the nodes have been * visited. * * Note that by the time the loop completes, the @unvisited nodemask will * be fully cleared, unless the loop exits early. * * The difference between for_each_node() and for_each_node_numadist() is * that the former allows to iterate over nodes in numerical order, whereas * the latter iterates over nodes in increasing order of distance. * * This complexity of this iterator is O(N^2), where N represents the * number of nodes, as each iteration involves scanning all nodes to * find the one with the shortest distance. * * Requires rcu_lock to be held. */ #define for_each_node_numadist(node, unvisited) \ for (int __start = (node), \ (node) = nearest_node_nodemask((__start), &(unvisited)); \ (node) < MAX_NUMNODES; \ node_clear((node), (unvisited)), \ (node) = nearest_node_nodemask((__start), &(unvisited))) /** * for_each_numa_hop_mask - iterate over cpumasks of increasing NUMA distance * from a given node. * @mask: the iteration variable. * @node: the NUMA node to start the search from. * * Requires rcu_lock to be held. * * Yields cpu_online_mask for @node == NUMA_NO_NODE. */ #define for_each_numa_hop_mask(mask, node) \ for (unsigned int __hops = 0; \ mask = (node != NUMA_NO_NODE || __hops) ? \ sched_numa_hop_mask(node, __hops) : \ cpu_online_mask, \ !IS_ERR_OR_NULL(mask); \ __hops++) DECLARE_PER_CPU(unsigned long, cpu_scale); static inline unsigned long topology_get_cpu_scale(int cpu) { return per_cpu(cpu_scale, cpu); } void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity); #endif /* _LINUX_TOPOLOGY_H */ |
| 1165 3 3 3 374 3 376 248 248 10 10 3 146 146 146 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/anon_inodes.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * * Thanks to Arnd Bergmann for code review and suggestions. * More changes for Thomas Gleixner suggestions. * */ #include <linux/cred.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/anon_inodes.h> #include <linux/pseudo_fs.h> #include <linux/uaccess.h> #include "internal.h" static struct vfsmount *anon_inode_mnt __ro_after_init; static struct inode *anon_inode_inode __ro_after_init; /* * User space expects anonymous inodes to have no file type in st_mode. * * In particular, 'lsof' has this legacy logic: * * type = s->st_mode & S_IFMT; * switch (type) { * ... * case 0: * if (!strcmp(p, "anon_inode")) * Lf->ntype = Ntype = N_ANON_INODE; * * to detect our old anon_inode logic. * * Rather than mess with our internal sane inode data, just fix it * up here in getattr() by masking off the format bits. */ int anon_inode_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); stat->mode &= ~S_IFMT; return 0; } int anon_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return -EOPNOTSUPP; } static const struct inode_operations anon_inode_operations = { .getattr = anon_inode_getattr, .setattr = anon_inode_setattr, }; /* * anon_inodefs_dname() is called from d_path(). */ static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "anon_inode:%s", dentry->d_name.name); } static const struct dentry_operations anon_inodefs_dentry_operations = { .d_dname = anon_inodefs_dname, }; static int anon_inodefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, ANON_INODE_FS_MAGIC); if (!ctx) return -ENOMEM; fc->s_iflags |= SB_I_NOEXEC; fc->s_iflags |= SB_I_NODEV; ctx->dops = &anon_inodefs_dentry_operations; return 0; } static struct file_system_type anon_inode_fs_type = { .name = "anon_inodefs", .init_fs_context = anon_inodefs_init_fs_context, .kill_sb = kill_anon_super, }; /** * anon_inode_make_secure_inode - allocate an anonymous inode with security context * @sb: [in] Superblock to allocate from * @name: [in] Name of the class of the newfile (e.g., "secretmem") * @context_inode: * [in] Optional parent inode for security inheritance * * The function ensures proper security initialization through the LSM hook * security_inode_init_security_anon(). * * Return: Pointer to new inode on success, ERR_PTR on failure. */ struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name, const struct inode *context_inode) { struct inode *inode; int error; inode = alloc_anon_inode(sb); if (IS_ERR(inode)) return inode; inode->i_flags &= ~S_PRIVATE; inode->i_op = &anon_inode_operations; error = security_inode_init_security_anon(inode, &QSTR(name), context_inode); if (error) { iput(inode); return ERR_PTR(error); } return inode; } EXPORT_SYMBOL_FOR_MODULES(anon_inode_make_secure_inode, "kvm"); static struct file *__anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool make_inode) { struct inode *inode; struct file *file; if (fops->owner && !try_module_get(fops->owner)) return ERR_PTR(-ENOENT); if (make_inode) { inode = anon_inode_make_secure_inode(anon_inode_mnt->mnt_sb, name, context_inode); if (IS_ERR(inode)) { file = ERR_CAST(inode); goto err; } } else { inode = anon_inode_inode; if (IS_ERR(inode)) { file = ERR_PTR(-ENODEV); goto err; } /* * We know the anon_inode inode count is always * greater than zero, so ihold() is safe. */ ihold(inode); } file = alloc_file_pseudo(inode, anon_inode_mnt, name, flags & (O_ACCMODE | O_NONBLOCK), fops); if (IS_ERR(file)) goto err_iput; file->f_mapping = inode->i_mapping; file->private_data = priv; return file; err_iput: iput(inode); err: module_put(fops->owner); return file; } /** * anon_inode_getfile - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Returns the newly created file* or an error pointer. */ struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfile(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfile); /** * anon_inode_getfile_fmode - creates a new file instance by hooking it up to an * anonymous inode, and a dentry that describe the "class" * of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @f_mode: [in] fmode * * Creates a new file by hooking it on a single inode. This is useful for files * that do not need to have a full-fledged inode in order to operate correctly. * All the files created with anon_inode_getfile() will share a single inode, * hence saving memory and avoiding code duplication for the file/inode/dentry * setup. Allows setting the fmode. Returns the newly created file* or an error * pointer. */ struct file *anon_inode_getfile_fmode(const char *name, const struct file_operations *fops, void *priv, int flags, fmode_t f_mode) { struct file *file; file = __anon_inode_getfile(name, fops, priv, flags, NULL, false); if (!IS_ERR(file)) file->f_mode |= f_mode; return file; } EXPORT_SYMBOL_GPL(anon_inode_getfile_fmode); /** * anon_inode_create_getfile - Like anon_inode_getfile(), but creates a new * !S_PRIVATE anon inode rather than reuse the * singleton anon inode and calls the * inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * Create a new anonymous inode and file pair. This can be done for two * reasons: * * - for the inode to have its own security context, so that LSMs can enforce * policy on the inode's creation; * * - if the caller needs a unique inode, for example in order to customize * the size returned by fstat() * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. * * Returns the newly created file* or an error pointer. */ struct file *anon_inode_create_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfile(name, fops, priv, flags, context_inode, true); } EXPORT_SYMBOL_GPL(anon_inode_create_getfile); static int __anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode, bool make_inode) { int error, fd; struct file *file; error = get_unused_fd_flags(flags); if (error < 0) return error; fd = error; file = __anon_inode_getfile(name, fops, priv, flags, context_inode, make_inode); if (IS_ERR(file)) { error = PTR_ERR(file); goto err_put_unused_fd; } fd_install(fd, file); return fd; err_put_unused_fd: put_unused_fd(fd); return error; } /** * anon_inode_getfd - creates a new file instance by hooking it up to * an anonymous inode and a dentry that describe * the "class" of the file * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * * Creates a new file by hooking it on a single inode. This is * useful for files that do not need to have a full-fledged inode in * order to operate correctly. All the files created with * anon_inode_getfd() will use the same singleton inode, reducing * memory use and avoiding code duplication for the file/inode/dentry * setup. Returns a newly created file descriptor or an error code. */ int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags) { return __anon_inode_getfd(name, fops, priv, flags, NULL, false); } EXPORT_SYMBOL_GPL(anon_inode_getfd); /** * anon_inode_create_getfd - Like anon_inode_getfd(), but creates a new * !S_PRIVATE anon inode rather than reuse the singleton anon inode, and calls * the inode_init_security_anon() LSM hook. * * @name: [in] name of the "class" of the new file * @fops: [in] file operations for the new file * @priv: [in] private data for the new file (will be file's private_data) * @flags: [in] flags * @context_inode: * [in] the logical relationship with the new inode (optional) * * Create a new anonymous inode and file pair. This can be done for two * reasons: * * - for the inode to have its own security context, so that LSMs can enforce * policy on the inode's creation; * * - if the caller needs a unique inode, for example in order to customize * the size returned by fstat() * * The LSM may use @context_inode in inode_init_security_anon(), but a * reference to it is not held. * * Returns a newly created file descriptor or an error code. */ int anon_inode_create_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, const struct inode *context_inode) { return __anon_inode_getfd(name, fops, priv, flags, context_inode, true); } static int __init anon_inode_init(void) { anon_inode_mnt = kern_mount(&anon_inode_fs_type); if (IS_ERR(anon_inode_mnt)) panic("anon_inode_init() kernel mount failed (%ld)\n", PTR_ERR(anon_inode_mnt)); anon_inode_inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(anon_inode_inode)) panic("anon_inode_init() inode allocation failed (%ld)\n", PTR_ERR(anon_inode_inode)); anon_inode_inode->i_op = &anon_inode_operations; return 0; } fs_initcall(anon_inode_init); |
| 123 971 1412 1394 44 1410 430 123 123 788 258 252 418 719 401 300 5 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org> */ #ifndef __ASM_CPUFEATURE_H #define __ASM_CPUFEATURE_H #include <asm/alternative-macros.h> #include <asm/cpucaps.h> #include <asm/cputype.h> #include <asm/hwcap.h> #include <asm/sysreg.h> #define MAX_CPU_FEATURES 192 #define cpu_feature(x) KERNEL_HWCAP_ ## x #define ARM64_SW_FEATURE_OVERRIDE_NOKASLR 0 #define ARM64_SW_FEATURE_OVERRIDE_HVHE 4 #define ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF 8 #ifndef __ASSEMBLY__ #include <linux/bug.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/cpumask.h> /* * CPU feature register tracking * * The safe value of a CPUID feature field is dependent on the implications * of the values assigned to it by the architecture. Based on the relationship * between the values, the features are classified into 3 types - LOWER_SAFE, * HIGHER_SAFE and EXACT. * * The lowest value of all the CPUs is chosen for LOWER_SAFE and highest * for HIGHER_SAFE. It is expected that all CPUs have the same value for * a field when EXACT is specified, failing which, the safe value specified * in the table is chosen. */ enum ftr_type { FTR_EXACT, /* Use a predefined safe value */ FTR_LOWER_SAFE, /* Smaller value is safe */ FTR_HIGHER_SAFE, /* Bigger value is safe */ FTR_HIGHER_OR_ZERO_SAFE, /* Bigger value is safe, but 0 is biggest */ }; #define FTR_STRICT true /* SANITY check strict matching required */ #define FTR_NONSTRICT false /* SANITY check ignored */ #define FTR_SIGNED true /* Value should be treated as signed */ #define FTR_UNSIGNED false /* Value should be treated as unsigned */ #define FTR_VISIBLE true /* Feature visible to the user space */ #define FTR_HIDDEN false /* Feature is hidden from the user */ #define FTR_VISIBLE_IF_IS_ENABLED(config) \ (IS_ENABLED(config) ? FTR_VISIBLE : FTR_HIDDEN) struct arm64_ftr_bits { bool sign; /* Value is signed ? */ bool visible; bool strict; /* CPU Sanity check: strict matching required ? */ enum ftr_type type; u8 shift; u8 width; s64 safe_val; /* safe value for FTR_EXACT features */ }; /* * Describe the early feature override to the core override code: * * @val Values that are to be merged into the final * sanitised value of the register. Only the bitfields * set to 1 in @mask are valid * @mask Mask of the features that are overridden by @val * * A @mask field set to full-1 indicates that the corresponding field * in @val is a valid override. * * A @mask field set to full-0 with the corresponding @val field set * to full-0 denotes that this field has no override * * A @mask field set to full-0 with the corresponding @val field set * to full-1 denotes that this field has an invalid override. */ struct arm64_ftr_override { u64 val; u64 mask; }; /* * @arm64_ftr_reg - Feature register * @strict_mask Bits which should match across all CPUs for sanity. * @sys_val Safe value across the CPUs (system view) */ struct arm64_ftr_reg { const char *name; u64 strict_mask; u64 user_mask; u64 sys_val; u64 user_val; struct arm64_ftr_override *override; const struct arm64_ftr_bits *ftr_bits; }; extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; /* * CPU capabilities: * * We use arm64_cpu_capabilities to represent system features, errata work * arounds (both used internally by kernel and tracked in system_cpucaps) and * ELF HWCAPs (which are exposed to user). * * To support systems with heterogeneous CPUs, we need to make sure that we * detect the capabilities correctly on the system and take appropriate * measures to ensure there are no incompatibilities. * * This comment tries to explain how we treat the capabilities. * Each capability has the following list of attributes : * * 1) Scope of Detection : The system detects a given capability by * performing some checks at runtime. This could be, e.g, checking the * value of a field in CPU ID feature register or checking the cpu * model. The capability provides a call back ( @matches() ) to * perform the check. Scope defines how the checks should be performed. * There are three cases: * * a) SCOPE_LOCAL_CPU: check all the CPUs and "detect" if at least one * matches. This implies, we have to run the check on all the * booting CPUs, until the system decides that state of the * capability is finalised. (See section 2 below) * Or * b) SCOPE_SYSTEM: check all the CPUs and "detect" if all the CPUs * matches. This implies, we run the check only once, when the * system decides to finalise the state of the capability. If the * capability relies on a field in one of the CPU ID feature * registers, we use the sanitised value of the register from the * CPU feature infrastructure to make the decision. * Or * c) SCOPE_BOOT_CPU: Check only on the primary boot CPU to detect the * feature. This category is for features that are "finalised" * (or used) by the kernel very early even before the SMP cpus * are brought up. * * The process of detection is usually denoted by "update" capability * state in the code. * * 2) Finalise the state : The kernel should finalise the state of a * capability at some point during its execution and take necessary * actions if any. Usually, this is done, after all the boot-time * enabled CPUs are brought up by the kernel, so that it can make * better decision based on the available set of CPUs. However, there * are some special cases, where the action is taken during the early * boot by the primary boot CPU. (e.g, running the kernel at EL2 with * Virtualisation Host Extensions). The kernel usually disallows any * changes to the state of a capability once it finalises the capability * and takes any action, as it may be impossible to execute the actions * safely. A CPU brought up after a capability is "finalised" is * referred to as "Late CPU" w.r.t the capability. e.g, all secondary * CPUs are treated "late CPUs" for capabilities determined by the boot * CPU. * * At the moment there are two passes of finalising the capabilities. * a) Boot CPU scope capabilities - Finalised by primary boot CPU via * setup_boot_cpu_capabilities(). * b) Everything except (a) - Run via setup_system_capabilities(). * * 3) Verification: When a CPU is brought online (e.g, by user or by the * kernel), the kernel should make sure that it is safe to use the CPU, * by verifying that the CPU is compliant with the state of the * capabilities finalised already. This happens via : * * secondary_start_kernel()-> check_local_cpu_capabilities() * * As explained in (2) above, capabilities could be finalised at * different points in the execution. Each newly booted CPU is verified * against the capabilities that have been finalised by the time it * boots. * * a) SCOPE_BOOT_CPU : All CPUs are verified against the capability * except for the primary boot CPU. * * b) SCOPE_LOCAL_CPU, SCOPE_SYSTEM: All CPUs hotplugged on by the * user after the kernel boot are verified against the capability. * * If there is a conflict, the kernel takes an action, based on the * severity (e.g, a CPU could be prevented from booting or cause a * kernel panic). The CPU is allowed to "affect" the state of the * capability, if it has not been finalised already. See section 5 * for more details on conflicts. * * 4) Action: As mentioned in (2), the kernel can take an action for each * detected capability, on all CPUs on the system. Appropriate actions * include, turning on an architectural feature, modifying the control * registers (e.g, SCTLR, TCR etc.) or patching the kernel via * alternatives. The kernel patching is batched and performed at later * point. The actions are always initiated only after the capability * is finalised. This is usally denoted by "enabling" the capability. * The actions are initiated as follows : * a) Action is triggered on all online CPUs, after the capability is * finalised, invoked within the stop_machine() context from * enable_cpu_capabilitie(). * * b) Any late CPU, brought up after (1), the action is triggered via: * * check_local_cpu_capabilities() -> verify_local_cpu_capabilities() * * 5) Conflicts: Based on the state of the capability on a late CPU vs. * the system state, we could have the following combinations : * * x-----------------------------x * | Type | System | Late CPU | * |-----------------------------| * | a | y | n | * |-----------------------------| * | b | n | y | * x-----------------------------x * * Two separate flag bits are defined to indicate whether each kind of * conflict can be allowed: * ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU - Case(a) is allowed * ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU - Case(b) is allowed * * Case (a) is not permitted for a capability that the system requires * all CPUs to have in order for the capability to be enabled. This is * typical for capabilities that represent enhanced functionality. * * Case (b) is not permitted for a capability that must be enabled * during boot if any CPU in the system requires it in order to run * safely. This is typical for erratum work arounds that cannot be * enabled after the corresponding capability is finalised. * * In some non-typical cases either both (a) and (b), or neither, * should be permitted. This can be described by including neither * or both flags in the capability's type field. * * In case of a conflict, the CPU is prevented from booting. If the * ARM64_CPUCAP_PANIC_ON_CONFLICT flag is specified for the capability, * then a kernel panic is triggered. */ /* * Decide how the capability is detected. * On any local CPU vs System wide vs the primary boot CPU */ #define ARM64_CPUCAP_SCOPE_LOCAL_CPU ((u16)BIT(0)) #define ARM64_CPUCAP_SCOPE_SYSTEM ((u16)BIT(1)) /* * The capabilitiy is detected on the Boot CPU and is used by kernel * during early boot. i.e, the capability should be "detected" and * "enabled" as early as possibly on all booting CPUs. */ #define ARM64_CPUCAP_SCOPE_BOOT_CPU ((u16)BIT(2)) #define ARM64_CPUCAP_SCOPE_MASK \ (ARM64_CPUCAP_SCOPE_SYSTEM | \ ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ ARM64_CPUCAP_SCOPE_BOOT_CPU) #define SCOPE_SYSTEM ARM64_CPUCAP_SCOPE_SYSTEM #define SCOPE_LOCAL_CPU ARM64_CPUCAP_SCOPE_LOCAL_CPU #define SCOPE_BOOT_CPU ARM64_CPUCAP_SCOPE_BOOT_CPU #define SCOPE_ALL ARM64_CPUCAP_SCOPE_MASK /* * Is it permitted for a late CPU to have this capability when system * hasn't already enabled it ? */ #define ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU ((u16)BIT(4)) /* Is it safe for a late CPU to miss this capability when system has it */ #define ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU ((u16)BIT(5)) /* Panic when a conflict is detected */ #define ARM64_CPUCAP_PANIC_ON_CONFLICT ((u16)BIT(6)) /* * When paired with SCOPE_LOCAL_CPU, all early CPUs must satisfy the * condition. This is different from SCOPE_SYSTEM where the check is performed * only once at the end of the SMP boot on the sanitised ID registers. * SCOPE_SYSTEM is not suitable for cases where the capability depends on * properties local to a CPU like MIDR_EL1. */ #define ARM64_CPUCAP_MATCH_ALL_EARLY_CPUS ((u16)BIT(7)) /* * CPU errata workarounds that need to be enabled at boot time if one or * more CPUs in the system requires it. When one of these capabilities * has been enabled, it is safe to allow any CPU to boot that doesn't * require the workaround. However, it is not safe if a "late" CPU * requires a workaround and the system hasn't enabled it already. */ #define ARM64_CPUCAP_LOCAL_CPU_ERRATUM \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU) /* * CPU feature detected at boot time based on system-wide value of a * feature. It is safe for a late CPU to have this feature even though * the system hasn't enabled it, although the feature will not be used * by Linux in this case. If the system has enabled this feature already, * then every late CPU must have it. */ #define ARM64_CPUCAP_SYSTEM_FEATURE \ (ARM64_CPUCAP_SCOPE_SYSTEM | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) /* * CPU feature detected at boot time based on feature of one or more CPUs. * All possible conflicts for a late CPU are ignored. * NOTE: this means that a late CPU with the feature will *not* cause the * capability to be advertised by cpus_have_*cap()! */ #define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU | \ ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) /* * CPU feature detected at boot time and present on all early CPUs. Late CPUs * are permitted to have the feature even if it hasn't been enabled, although * the feature will not be used by Linux in this case. If all early CPUs have * the feature, then every late CPU must have it. */ #define ARM64_CPUCAP_EARLY_LOCAL_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU | \ ARM64_CPUCAP_MATCH_ALL_EARLY_CPUS) /* * CPU feature detected at boot time, on one or more CPUs. A late CPU * is not allowed to have the capability when the system doesn't have it. * It is Ok for a late CPU to miss the feature. */ #define ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU) /* * CPU feature used early in the boot based on the boot CPU. All secondary * CPUs must match the state of the capability as detected by the boot CPU. In * case of a conflict, a kernel panic is triggered. */ #define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PANIC_ON_CONFLICT) /* * CPU feature used early in the boot based on the boot CPU. It is safe for a * late CPU to have this feature even though the boot CPU hasn't enabled it, * although the feature will not be used by Linux in this case. If the boot CPU * has enabled this feature already, then every late CPU must have it. */ #define ARM64_CPUCAP_BOOT_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) struct arm64_cpu_capabilities { const char *desc; u16 capability; u16 type; bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope); /* * Take the appropriate actions to configure this capability * for this CPU. If the capability is detected by the kernel * this will be called on all the CPUs in the system, * including the hotplugged CPUs, regardless of whether the * capability is available on that specific CPU. This is * useful for some capabilities (e.g, working around CPU * errata), where all the CPUs must take some action (e.g, * changing system control/configuration). Thus, if an action * is required only if the CPU has the capability, then the * routine must check it before taking any action. */ void (*cpu_enable)(const struct arm64_cpu_capabilities *cap); union { struct { /* To be used for erratum handling only */ struct midr_range midr_range; const struct arm64_midr_revidr { u32 midr_rv; /* revision/variant */ u32 revidr_mask; } * const fixed_revs; }; const struct midr_range *midr_range_list; struct { /* Feature register checking */ u32 sys_reg; u8 field_pos; u8 field_width; u8 min_field_value; u8 max_field_value; u8 hwcap_type; bool sign; unsigned long hwcap; }; }; /* * An optional list of "matches/cpu_enable" pair for the same * "capability" of the same "type" as described by the parent. * Only matches(), cpu_enable() and fields relevant to these * methods are significant in the list. The cpu_enable is * invoked only if the corresponding entry "matches()". * However, if a cpu_enable() method is associated * with multiple matches(), care should be taken that either * the match criteria are mutually exclusive, or that the * method is robust against being called multiple times. */ const struct arm64_cpu_capabilities *match_list; const struct cpumask *cpus; }; static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap) { return cap->type & ARM64_CPUCAP_SCOPE_MASK; } static inline bool cpucap_match_all_early_cpus(const struct arm64_cpu_capabilities *cap) { return cap->type & ARM64_CPUCAP_MATCH_ALL_EARLY_CPUS; } /* * Generic helper for handling capabilities with multiple (match,enable) pairs * of call backs, sharing the same capability bit. * Iterate over each entry to see if at least one matches. */ static inline bool cpucap_multi_entry_cap_matches(const struct arm64_cpu_capabilities *entry, int scope) { const struct arm64_cpu_capabilities *caps; for (caps = entry->match_list; caps->matches; caps++) if (caps->matches(caps, scope)) return true; return false; } static __always_inline bool is_vhe_hyp_code(void) { /* Only defined for code run in VHE hyp context */ return __is_defined(__KVM_VHE_HYPERVISOR__); } static __always_inline bool is_nvhe_hyp_code(void) { /* Only defined for code run in NVHE hyp context */ return __is_defined(__KVM_NVHE_HYPERVISOR__); } static __always_inline bool is_hyp_code(void) { return is_vhe_hyp_code() || is_nvhe_hyp_code(); } extern DECLARE_BITMAP(system_cpucaps, ARM64_NCAPS); extern DECLARE_BITMAP(boot_cpucaps, ARM64_NCAPS); #define for_each_available_cap(cap) \ for_each_set_bit(cap, system_cpucaps, ARM64_NCAPS) bool this_cpu_has_cap(unsigned int cap); void cpu_set_feature(unsigned int num); bool cpu_have_feature(unsigned int num); unsigned long cpu_get_elf_hwcap(void); unsigned long cpu_get_elf_hwcap2(void); unsigned long cpu_get_elf_hwcap3(void); #define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name)) #define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name)) static __always_inline bool boot_capabilities_finalized(void) { return alternative_has_cap_likely(ARM64_ALWAYS_BOOT); } static __always_inline bool system_capabilities_finalized(void) { return alternative_has_cap_likely(ARM64_ALWAYS_SYSTEM); } /* * Test for a capability with a runtime check. * * Before the capability is detected, this returns false. */ static __always_inline bool cpus_have_cap(unsigned int num) { if (__builtin_constant_p(num) && !cpucap_is_possible(num)) return false; if (num >= ARM64_NCAPS) return false; return arch_test_bit(num, system_cpucaps); } /* * Test for a capability without a runtime check. * * Before boot capabilities are finalized, this will BUG(). * After boot capabilities are finalized, this is patched to avoid a runtime * check. * * @num must be a compile-time constant. */ static __always_inline bool cpus_have_final_boot_cap(int num) { if (boot_capabilities_finalized()) return alternative_has_cap_unlikely(num); else BUG(); } /* * Test for a capability without a runtime check. * * Before system capabilities are finalized, this will BUG(). * After system capabilities are finalized, this is patched to avoid a runtime * check. * * @num must be a compile-time constant. */ static __always_inline bool cpus_have_final_cap(int num) { if (system_capabilities_finalized()) return alternative_has_cap_unlikely(num); else BUG(); } static inline int __attribute_const__ cpuid_feature_extract_signed_field_width(u64 features, int field, int width) { return (s64)(features << (64 - width - field)) >> (64 - width); } static inline int __attribute_const__ cpuid_feature_extract_signed_field(u64 features, int field) { return cpuid_feature_extract_signed_field_width(features, field, 4); } static __always_inline unsigned int __attribute_const__ cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width) { return (u64)(features << (64 - width - field)) >> (64 - width); } static __always_inline unsigned int __attribute_const__ cpuid_feature_extract_unsigned_field(u64 features, int field) { return cpuid_feature_extract_unsigned_field_width(features, field, 4); } static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp) { return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift); } static inline u64 arm64_ftr_reg_user_value(const struct arm64_ftr_reg *reg) { return (reg->user_val | (reg->sys_val & reg->user_mask)); } static inline int __attribute_const__ cpuid_feature_extract_field_width(u64 features, int field, int width, bool sign) { if (WARN_ON_ONCE(!width)) width = 4; return (sign) ? cpuid_feature_extract_signed_field_width(features, field, width) : cpuid_feature_extract_unsigned_field_width(features, field, width); } static inline int __attribute_const__ cpuid_feature_extract_field(u64 features, int field, bool sign) { return cpuid_feature_extract_field_width(features, field, 4, sign); } static inline s64 arm64_ftr_value(const struct arm64_ftr_bits *ftrp, u64 val) { return (s64)cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width, ftrp->sign); } static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0) { return cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGEND_SHIFT) == 0x1 || cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGENDEL0_SHIFT) == 0x1; } static inline bool id_aa64pfr0_32bit_el1(u64 pfr0) { u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_EL1_SHIFT); return val == ID_AA64PFR0_EL1_EL1_AARCH32; } static inline bool id_aa64pfr0_32bit_el0(u64 pfr0) { u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_EL0_SHIFT); return val == ID_AA64PFR0_EL1_EL0_AARCH32; } static inline bool id_aa64pfr0_sve(u64 pfr0) { u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_SVE_SHIFT); return val > 0; } static inline bool id_aa64pfr1_sme(u64 pfr1) { u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_SME_SHIFT); return val > 0; } static inline bool id_aa64pfr0_mpam(u64 pfr0) { u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_MPAM_SHIFT); return val > 0; } static inline bool id_aa64pfr1_mte(u64 pfr1) { u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_MTE_SHIFT); return val >= ID_AA64PFR1_EL1_MTE_MTE2; } void __init setup_boot_cpu_features(void); void __init setup_system_features(void); void __init setup_user_features(void); void check_local_cpu_capabilities(void); u64 read_sanitised_ftr_reg(u32 id); u64 __read_sysreg_by_encoding(u32 sys_id); static inline bool cpu_supports_mixed_endian_el0(void) { return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1)); } static inline bool supports_csv2p3(int scope) { u64 pfr0; u8 csv2_val; if (scope == SCOPE_LOCAL_CPU) pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1); else pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); csv2_val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_CSV2_SHIFT); return csv2_val == 3; } static inline bool supports_clearbhb(int scope) { u64 isar2; if (scope == SCOPE_LOCAL_CPU) isar2 = read_sysreg_s(SYS_ID_AA64ISAR2_EL1); else isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); return cpuid_feature_extract_unsigned_field(isar2, ID_AA64ISAR2_EL1_CLRBHB_SHIFT); } const struct cpumask *system_32bit_el0_cpumask(void); const struct cpumask *fallback_32bit_el0_cpumask(void); DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0); static inline bool system_supports_32bit_el0(void) { u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); return static_branch_unlikely(&arm64_mismatched_32bit_el0) || id_aa64pfr0_32bit_el0(pfr0); } static inline bool system_supports_4kb_granule(void) { u64 mmfr0; u32 val; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN4_SHIFT); return (val >= ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN) && (val <= ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX); } static inline bool system_supports_64kb_granule(void) { u64 mmfr0; u32 val; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN64_SHIFT); return (val >= ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN) && (val <= ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX); } static inline bool system_supports_16kb_granule(void) { u64 mmfr0; u32 val; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN16_SHIFT); return (val >= ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN) && (val <= ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX); } static inline bool system_supports_mixed_endian_el0(void) { return id_aa64mmfr0_mixed_endian_el0(read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1)); } static inline bool system_supports_mixed_endian(void) { u64 mmfr0; u32 val; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGEND_SHIFT); return val == 0x1; } static __always_inline bool system_supports_fpsimd(void) { return alternative_has_cap_likely(ARM64_HAS_FPSIMD); } static inline bool system_uses_hw_pan(void) { return alternative_has_cap_unlikely(ARM64_HAS_PAN); } static inline bool system_uses_ttbr0_pan(void) { return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) && !system_uses_hw_pan(); } static __always_inline bool system_supports_sve(void) { return alternative_has_cap_unlikely(ARM64_SVE); } static __always_inline bool system_supports_sme(void) { return alternative_has_cap_unlikely(ARM64_SME); } static __always_inline bool system_supports_sme2(void) { return alternative_has_cap_unlikely(ARM64_SME2); } static __always_inline bool system_supports_fa64(void) { return alternative_has_cap_unlikely(ARM64_SME_FA64); } static __always_inline bool system_supports_tpidr2(void) { return system_supports_sme(); } static __always_inline bool system_supports_fpmr(void) { return alternative_has_cap_unlikely(ARM64_HAS_FPMR); } static __always_inline bool system_supports_cnp(void) { return alternative_has_cap_unlikely(ARM64_HAS_CNP); } static inline bool system_supports_address_auth(void) { return cpus_have_final_boot_cap(ARM64_HAS_ADDRESS_AUTH); } static inline bool system_supports_generic_auth(void) { return alternative_has_cap_unlikely(ARM64_HAS_GENERIC_AUTH); } static inline bool system_has_full_ptr_auth(void) { return system_supports_address_auth() && system_supports_generic_auth(); } static __always_inline bool system_uses_irq_prio_masking(void) { return alternative_has_cap_unlikely(ARM64_HAS_GIC_PRIO_MASKING); } static inline bool system_supports_mte(void) { return alternative_has_cap_unlikely(ARM64_MTE); } static inline bool system_has_prio_mask_debugging(void) { return IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING) && system_uses_irq_prio_masking(); } static inline bool system_supports_bti(void) { return cpus_have_final_cap(ARM64_BTI); } static inline bool system_supports_bti_kernel(void) { return IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && cpus_have_final_boot_cap(ARM64_BTI); } static inline bool system_supports_tlb_range(void) { return alternative_has_cap_unlikely(ARM64_HAS_TLB_RANGE); } static inline bool system_supports_lpa2(void) { return cpus_have_final_cap(ARM64_HAS_LPA2); } static inline bool system_supports_poe(void) { return alternative_has_cap_unlikely(ARM64_HAS_S1POE); } static inline bool system_supports_gcs(void) { return alternative_has_cap_unlikely(ARM64_HAS_GCS); } static inline bool system_supports_haft(void) { return cpus_have_final_cap(ARM64_HAFT); } static __always_inline bool system_supports_mpam(void) { return alternative_has_cap_unlikely(ARM64_MPAM); } static __always_inline bool system_supports_mpam_hcr(void) { return alternative_has_cap_unlikely(ARM64_MPAM_HCR); } static inline bool system_supports_pmuv3(void) { return cpus_have_final_cap(ARM64_HAS_PMUV3); } bool cpu_supports_bbml2_noabort(void); static inline bool system_supports_bbml2_noabort(void) { return alternative_has_cap_unlikely(ARM64_HAS_BBML2_NOABORT); } int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt); bool try_emulate_mrs(struct pt_regs *regs, u32 isn); static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange) { switch (parange) { case ID_AA64MMFR0_EL1_PARANGE_32: return 32; case ID_AA64MMFR0_EL1_PARANGE_36: return 36; case ID_AA64MMFR0_EL1_PARANGE_40: return 40; case ID_AA64MMFR0_EL1_PARANGE_42: return 42; case ID_AA64MMFR0_EL1_PARANGE_44: return 44; case ID_AA64MMFR0_EL1_PARANGE_48: return 48; case ID_AA64MMFR0_EL1_PARANGE_52: return 52; /* * A future PE could use a value unknown to the kernel. * However, by the "D10.1.4 Principles of the ID scheme * for fields in ID registers", ARM DDI 0487C.a, any new * value is guaranteed to be higher than what we know already. * As a safe limit, we return the limit supported by the kernel. */ default: return CONFIG_ARM64_PA_BITS; } } /* Check whether hardware update of the Access flag is supported */ static inline bool cpu_has_hw_af(void) { u64 mmfr1; if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM)) return false; /* * Use cached version to avoid emulated msr operation on KVM * guests. */ mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); return cpuid_feature_extract_unsigned_field(mmfr1, ID_AA64MMFR1_EL1_HAFDBS_SHIFT); } static inline bool cpu_has_pan(void) { u64 mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); return cpuid_feature_extract_unsigned_field(mmfr1, ID_AA64MMFR1_EL1_PAN_SHIFT); } #ifdef CONFIG_ARM64_AMU_EXTN /* Check whether the cpu supports the Activity Monitors Unit (AMU) */ extern bool cpu_has_amu_feat(int cpu); #else static inline bool cpu_has_amu_feat(int cpu) { return false; } #endif /* Get a cpu that supports the Activity Monitors Unit (AMU) */ extern int get_cpu_with_amu_feat(void); static inline unsigned int get_vmid_bits(u64 mmfr1) { int vmid_bits; vmid_bits = cpuid_feature_extract_unsigned_field(mmfr1, ID_AA64MMFR1_EL1_VMIDBits_SHIFT); if (vmid_bits == ID_AA64MMFR1_EL1_VMIDBits_16) return 16; /* * Return the default here even if any reserved * value is fetched from the system register. */ return 8; } s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, s64 cur); struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id); extern struct arm64_ftr_override id_aa64mmfr0_override; extern struct arm64_ftr_override id_aa64mmfr1_override; extern struct arm64_ftr_override id_aa64mmfr2_override; extern struct arm64_ftr_override id_aa64pfr0_override; extern struct arm64_ftr_override id_aa64pfr1_override; extern struct arm64_ftr_override id_aa64zfr0_override; extern struct arm64_ftr_override id_aa64smfr0_override; extern struct arm64_ftr_override id_aa64isar1_override; extern struct arm64_ftr_override id_aa64isar2_override; extern struct arm64_ftr_override arm64_sw_feature_override; static inline u64 arm64_apply_feature_override(u64 val, int feat, int width, const struct arm64_ftr_override *override) { u64 oval = override->val; /* * When it encounters an invalid override (e.g., an override that * cannot be honoured due to a missing CPU feature), the early idreg * override code will set the mask to 0x0 and the value to non-zero for * the field in question. In order to determine whether the override is * valid or not for the field we are interested in, we first need to * disregard bits belonging to other fields. */ oval &= GENMASK_ULL(feat + width - 1, feat); /* * The override is valid if all value bits are accounted for in the * mask. If so, replace the masked bits with the override value. */ if (oval == (oval & override->mask)) { val &= ~override->mask; val |= oval; } /* Extract the field from the updated value */ return cpuid_feature_extract_unsigned_field(val, feat); } static inline bool arm64_test_sw_feature_override(int feat) { /* * Software features are pseudo CPU features that have no underlying * CPUID system register value to apply the override to. */ return arm64_apply_feature_override(0, feat, 4, &arm64_sw_feature_override); } static inline bool kaslr_disabled_cmdline(void) { return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOKASLR); } u32 get_kvm_ipa_limit(void); void dump_cpu_features(void); static inline bool cpu_has_bti(void) { if (!IS_ENABLED(CONFIG_ARM64_BTI)) return false; return arm64_apply_feature_override(read_cpuid(ID_AA64PFR1_EL1), ID_AA64PFR1_EL1_BT_SHIFT, 4, &id_aa64pfr1_override); } static inline bool cpu_has_pac(void) { u64 isar1, isar2; if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH)) return false; isar1 = read_cpuid(ID_AA64ISAR1_EL1); isar2 = read_cpuid(ID_AA64ISAR2_EL1); if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_APA_SHIFT, 4, &id_aa64isar1_override)) return true; if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_API_SHIFT, 4, &id_aa64isar1_override)) return true; return arm64_apply_feature_override(isar2, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, &id_aa64isar2_override); } static inline bool cpu_has_lva(void) { u64 mmfr2; mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); mmfr2 &= ~id_aa64mmfr2_override.mask; mmfr2 |= id_aa64mmfr2_override.val; return cpuid_feature_extract_unsigned_field(mmfr2, ID_AA64MMFR2_EL1_VARange_SHIFT); } static inline bool cpu_has_lpa2(void) { #ifdef CONFIG_ARM64_LPA2 u64 mmfr0; int feat; mmfr0 = read_sysreg(id_aa64mmfr0_el1); mmfr0 &= ~id_aa64mmfr0_override.mask; mmfr0 |= id_aa64mmfr0_override.val; feat = cpuid_feature_extract_signed_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN_SHIFT); return feat >= ID_AA64MMFR0_EL1_TGRAN_LPA2; #else return false; #endif } #endif /* __ASSEMBLY__ */ #endif |
| 216 257 64 64 140 257 52 216 142 256 256 256 215 216 142 141 214 125 101 218 218 52 216 216 215 144 31 142 142 142 141 141 218 216 52 52 52 143 143 31 31 275 230 275 33 274 274 616 | 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 | /* 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(const 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(const 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(const struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags.f); 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(const struct folio *folio) { unsigned long flags = READ_ONCE(folio->flags.f); return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1; } static inline bool lru_gen_is_active(const 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(const struct lruvec *lruvec, const struct folio *folio, bool reclaiming) { int gen; int type = folio_is_file_lru(folio); const 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.f, 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.f, 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, const struct folio *old) { unsigned long refs = READ_ONCE(old->flags.f) & LRU_REFS_MASK; set_mask_bits(&new->flags.f, 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, const 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 */ void pfnmap_track_ctx_release(struct kref *ref); 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(const 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(const 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(const 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; } /** * num_pages_contiguous() - determine the number of contiguous pages * that represent contiguous PFNs * @pages: an array of page pointers * @nr_pages: length of the array, at least 1 * * Determine the number of contiguous pages that represent contiguous PFNs * in @pages, starting from the first page. * * In some kernel configs contiguous PFNs will not have contiguous struct * pages. In these configurations num_pages_contiguous() will return a num * smaller than ideal number. The caller should continue to check for pfn * contiguity after each call to num_pages_contiguous(). * * Returns the number of contiguous pages. */ static inline size_t num_pages_contiguous(struct page **pages, size_t nr_pages) { struct page *cur_page = pages[0]; unsigned long section = memdesc_section(cur_page->flags); size_t i; for (i = 1; i < nr_pages; i++) { if (++cur_page != pages[i]) break; /* * In unproblematic kernel configs, page_to_section() == 0 and * the whole check will get optimized out. */ if (memdesc_section(cur_page->flags) != section) break; } return i; } #endif |
| 283 268 | 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 _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H #include <linux/refcount.h> #include <uapi/linux/netfilter/nf_conntrack_common.h> struct ip_conntrack_stat { unsigned int found; unsigned int invalid; unsigned int insert; unsigned int insert_failed; unsigned int clash_resolve; unsigned int drop; unsigned int early_drop; unsigned int error; unsigned int expect_new; unsigned int expect_create; unsigned int expect_delete; unsigned int search_restart; unsigned int chaintoolong; }; #define NFCT_INFOMASK 7UL #define NFCT_PTRMASK ~(NFCT_INFOMASK) struct nf_conntrack { refcount_t use; }; void nf_conntrack_destroy(struct nf_conntrack *nfct); /* like nf_ct_put, but without module dependency on nf_conntrack */ static inline void nf_conntrack_put(struct nf_conntrack *nfct) { if (nfct && refcount_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) refcount_inc(&nfct->use); } #endif /* _NF_CONNTRACK_COMMON_H */ |
| 14 | 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 | /* * linux/include/linux/console.h * * Copyright (C) 1993 Hamish Macdonald * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of this archive * for more details. * * Changed: * 10-Mar-94: Arno Griffioen: Conversion for vt100 emulator port from PC LINUX */ #ifndef _LINUX_CONSOLE_H_ #define _LINUX_CONSOLE_H_ 1 #include <linux/atomic.h> #include <linux/bits.h> #include <linux/irq_work.h> #include <linux/rculist.h> #include <linux/rcuwait.h> #include <linux/types.h> #include <linux/vesa.h> struct vc_data; struct console_font_op; struct console_font; struct module; struct tty_struct; struct notifier_block; enum con_scroll { SM_UP, SM_DOWN, }; enum vc_intensity; /** * struct consw - callbacks for consoles * * @owner: the module to get references of when this console is used * @con_startup: set up the console and return its name (like VGA, EGA, ...) * @con_init: initialize the console on @vc. @init is true for the very first * call on this @vc. * @con_deinit: deinitialize the console from @vc. * @con_clear: erase @count characters at [@x, @y] on @vc. @count >= 1. * @con_putc: emit one character with attributes @ca to [@x, @y] on @vc. * (optional -- @con_putcs would be called instead) * @con_putcs: emit @count characters with attributes @s to [@x, @y] on @vc. * @con_cursor: enable/disable cursor depending on @enable * @con_scroll: move lines from @top to @bottom in direction @dir by @lines. * Return true if no generic handling should be done. * Invoked by csi_M and printing to the console. * @con_switch: notifier about the console switch; it is supposed to return * true if a redraw is needed. * @con_blank: blank/unblank the console. The target mode is passed in @blank. * @mode_switch is set if changing from/to text/graphics. The hook * is supposed to return true if a redraw is needed. * @con_font_set: set console @vc font to @font with height @vpitch. @flags can * be %KD_FONT_FLAG_DONT_RECALC. (optional) * @con_font_get: fetch the current font on @vc of height @vpitch into @font. * (optional) * @con_font_default: set default font on @vc. @name can be %NULL or font name * to search for. @font can be filled back. (optional) * @con_resize: resize the @vc console to @width x @height. @from_user is true * when this change comes from the user space. * @con_set_palette: sets the palette of the console @vc to @table (optional) * @con_scrolldelta: the contents of the console should be scrolled by @lines. * Invoked by user. (optional) * @con_set_origin: set origin (see &vc_data::vc_origin) of the @vc. If not * provided or returns false, the origin is set to * @vc->vc_screenbuf. (optional) * @con_save_screen: save screen content into @vc->vc_screenbuf. Called e.g. * upon entering graphics. (optional) * @con_build_attr: build attributes based on @color, @intensity and other * parameters. The result is used for both normal and erase * characters. (optional) * @con_invert_region: invert a region of length @count on @vc starting at @p. * (optional) * @con_debug_enter: prepare the console for the debugger. This includes, but * is not limited to, unblanking the console, loading an * appropriate palette, and allowing debugger generated output. * (optional) * @con_debug_leave: restore the console to its pre-debug state as closely as * possible. (optional) */ struct consw { struct module *owner; const char *(*con_startup)(void); void (*con_init)(struct vc_data *vc, bool init); void (*con_deinit)(struct vc_data *vc); void (*con_clear)(struct vc_data *vc, unsigned int y, unsigned int x, unsigned int count); void (*con_putc)(struct vc_data *vc, u16 ca, unsigned int y, unsigned int x); void (*con_putcs)(struct vc_data *vc, const u16 *s, unsigned int count, unsigned int ypos, unsigned int xpos); void (*con_cursor)(struct vc_data *vc, bool enable); bool (*con_scroll)(struct vc_data *vc, unsigned int top, unsigned int bottom, enum con_scroll dir, unsigned int lines); bool (*con_switch)(struct vc_data *vc); bool (*con_blank)(struct vc_data *vc, enum vesa_blank_mode blank, bool mode_switch); int (*con_font_set)(struct vc_data *vc, const struct console_font *font, unsigned int vpitch, unsigned int flags); int (*con_font_get)(struct vc_data *vc, struct console_font *font, unsigned int vpitch); int (*con_font_default)(struct vc_data *vc, struct console_font *font, const char *name); int (*con_resize)(struct vc_data *vc, unsigned int width, unsigned int height, bool from_user); void (*con_set_palette)(struct vc_data *vc, const unsigned char *table); void (*con_scrolldelta)(struct vc_data *vc, int lines); bool (*con_set_origin)(struct vc_data *vc); void (*con_save_screen)(struct vc_data *vc); u8 (*con_build_attr)(struct vc_data *vc, u8 color, enum vc_intensity intensity, bool blink, bool underline, bool reverse, bool italic); void (*con_invert_region)(struct vc_data *vc, u16 *p, int count); void (*con_debug_enter)(struct vc_data *vc); void (*con_debug_leave)(struct vc_data *vc); }; extern const struct consw *conswitchp; extern const struct consw dummy_con; /* dummy console buffer */ extern const struct consw vga_con; /* VGA text console */ extern const struct consw newport_con; /* SGI Newport console */ struct screen_info; #ifdef CONFIG_VGA_CONSOLE void vgacon_register_screen(struct screen_info *si); #else static inline void vgacon_register_screen(struct screen_info *si) { } #endif int con_is_bound(const struct consw *csw); int do_unregister_con_driver(const struct consw *csw); int do_take_over_console(const struct consw *sw, int first, int last, int deflt); void give_up_console(const struct consw *sw); #ifdef CONFIG_VT void con_debug_enter(struct vc_data *vc); void con_debug_leave(void); #else static inline void con_debug_enter(struct vc_data *vc) { } static inline void con_debug_leave(void) { } #endif /* * The interface for a console, or any other device that wants to capture * console messages (printer driver?) */ /** * enum cons_flags - General console flags * @CON_PRINTBUFFER: Used by newly registered consoles to avoid duplicate * output of messages that were already shown by boot * consoles or read by userspace via syslog() syscall. * @CON_CONSDEV: Indicates that the console driver is backing * /dev/console. * @CON_ENABLED: Indicates if a console is allowed to print records. If * false, the console also will not advance to later * records. * @CON_BOOT: Marks the console driver as early console driver which * is used during boot before the real driver becomes * available. It will be automatically unregistered * when the real console driver is registered unless * "keep_bootcon" parameter is used. * @CON_ANYTIME: A misnomed historical flag which tells the core code * that the legacy @console::write callback can be invoked * on a CPU which is marked OFFLINE. That is misleading as * it suggests that there is no contextual limit for * invoking the callback. The original motivation was * readiness of the per-CPU areas. * @CON_BRL: Indicates a braille device which is exempt from * receiving the printk spam for obvious reasons. * @CON_EXTENDED: The console supports the extended output format of * /dev/kmesg which requires a larger output buffer. * @CON_SUSPENDED: Indicates if a console is suspended. If true, the * printing callbacks must not be called. * @CON_NBCON: Console can operate outside of the legacy style console_lock * constraints. */ enum cons_flags { CON_PRINTBUFFER = BIT(0), CON_CONSDEV = BIT(1), CON_ENABLED = BIT(2), CON_BOOT = BIT(3), CON_ANYTIME = BIT(4), CON_BRL = BIT(5), CON_EXTENDED = BIT(6), CON_SUSPENDED = BIT(7), CON_NBCON = BIT(8), }; /** * struct nbcon_state - console state for nbcon consoles * @atom: Compound of the state fields for atomic operations * * @req_prio: The priority of a handover request * @prio: The priority of the current owner * @unsafe: Console is busy in a non takeover region * @unsafe_takeover: A hostile takeover in an unsafe state happened in the * past. The console cannot be safe until re-initialized. * @cpu: The CPU on which the owner runs * * To be used for reading and preparing of the value stored in the nbcon * state variable @console::nbcon_state. * * The @prio and @req_prio fields are particularly important to allow * spin-waiting to timeout and give up without the risk of a waiter being * assigned the lock after giving up. */ struct nbcon_state { union { unsigned int atom; struct { unsigned int prio : 2; unsigned int req_prio : 2; unsigned int unsafe : 1; unsigned int unsafe_takeover : 1; unsigned int cpu : 24; }; }; }; /* * The nbcon_state struct is used to easily create and interpret values that * are stored in the @console::nbcon_state variable. Ensure this struct stays * within the size boundaries of the atomic variable's underlying type in * order to avoid any accidental truncation. */ static_assert(sizeof(struct nbcon_state) <= sizeof(int)); /** * enum nbcon_prio - console owner priority for nbcon consoles * @NBCON_PRIO_NONE: Unused * @NBCON_PRIO_NORMAL: Normal (non-emergency) usage * @NBCON_PRIO_EMERGENCY: Emergency output (WARN/OOPS...) * @NBCON_PRIO_PANIC: Panic output * @NBCON_PRIO_MAX: The number of priority levels * * A higher priority context can takeover the console when it is * in the safe state. The final attempt to flush consoles in panic() * can be allowed to do so even in an unsafe state (Hope and pray). */ enum nbcon_prio { NBCON_PRIO_NONE = 0, NBCON_PRIO_NORMAL, NBCON_PRIO_EMERGENCY, NBCON_PRIO_PANIC, NBCON_PRIO_MAX, }; struct console; struct printk_buffers; /** * struct nbcon_context - Context for console acquire/release * @console: The associated console * @spinwait_max_us: Limit for spin-wait acquire * @prio: Priority of the context * @allow_unsafe_takeover: Allow performing takeover even if unsafe. Can * be used only with NBCON_PRIO_PANIC @prio. It * might cause a system freeze when the console * is used later. * @backlog: Ringbuffer has pending records * @pbufs: Pointer to the text buffer for this context * @seq: The sequence number to print for this context */ struct nbcon_context { /* members set by caller */ struct console *console; unsigned int spinwait_max_us; enum nbcon_prio prio; unsigned int allow_unsafe_takeover : 1; /* members set by emit */ unsigned int backlog : 1; /* members set by acquire */ struct printk_buffers *pbufs; u64 seq; }; /** * struct nbcon_write_context - Context handed to the nbcon write callbacks * @ctxt: The core console context * @outbuf: Pointer to the text buffer for output * @len: Length to write * @unsafe_takeover: If a hostile takeover in an unsafe state has occurred */ struct nbcon_write_context { struct nbcon_context __private ctxt; char *outbuf; unsigned int len; bool unsafe_takeover; }; /** * struct console - The console descriptor structure * @name: The name of the console driver * @write: Legacy write callback to output messages (Optional) * @read: Read callback for console input (Optional) * @device: The underlying TTY device driver (Optional) * @unblank: Callback to unblank the console (Optional) * @setup: Callback for initializing the console (Optional) * @exit: Callback for teardown of the console (Optional) * @match: Callback for matching a console (Optional) * @flags: Console flags. See enum cons_flags * @index: Console index, e.g. port number * @cflag: TTY control mode flags * @ispeed: TTY input speed * @ospeed: TTY output speed * @seq: Sequence number of the next ringbuffer record to print * @dropped: Number of unreported dropped ringbuffer records * @data: Driver private data * @node: hlist node for the console list * * @nbcon_state: State for nbcon consoles * @nbcon_seq: Sequence number of the next record for nbcon to print * @nbcon_device_ctxt: Context available for non-printing operations * @nbcon_prev_seq: Seq num the previous nbcon owner was assigned to print * @pbufs: Pointer to nbcon private buffer * @kthread: Printer kthread for this console * @rcuwait: RCU-safe wait object for @kthread waking * @irq_work: Defer @kthread waking to IRQ work context */ struct console { char name[16]; void (*write)(struct console *co, const char *s, unsigned int count); int (*read)(struct console *co, char *s, unsigned int count); struct tty_driver *(*device)(struct console *co, int *index); void (*unblank)(void); int (*setup)(struct console *co, char *options); int (*exit)(struct console *co); int (*match)(struct console *co, char *name, int idx, char *options); short flags; short index; int cflag; uint ispeed; uint ospeed; u64 seq; unsigned long dropped; void *data; struct hlist_node node; /* nbcon console specific members */ /** * @write_atomic: * * NBCON callback to write out text in any context. (Optional) * * This callback is called with the console already acquired. However, * a higher priority context is allowed to take it over by default. * * The callback must call nbcon_enter_unsafe() and nbcon_exit_unsafe() * around any code where the takeover is not safe, for example, when * manipulating the serial port registers. * * nbcon_enter_unsafe() will fail if the context has lost the console * ownership in the meantime. In this case, the callback is no longer * allowed to go forward. It must back out immediately and carefully. * The buffer content is also no longer trusted since it no longer * belongs to the context. * * The callback should allow the takeover whenever it is safe. It * increases the chance to see messages when the system is in trouble. * If the driver must reacquire ownership in order to finalize or * revert hardware changes, nbcon_reacquire_nobuf() can be used. * However, on reacquire the buffer content is no longer available. A * reacquire cannot be used to resume printing. * * The callback can be called from any context (including NMI). * Therefore it must avoid usage of any locking and instead rely * on the console ownership for synchronization. */ void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt); /** * @write_thread: * * NBCON callback to write out text in task context. * * This callback must be called only in task context with both * device_lock() and the nbcon console acquired with * NBCON_PRIO_NORMAL. * * The same rules for console ownership verification and unsafe * sections handling applies as with write_atomic(). * * The console ownership handling is necessary for synchronization * against write_atomic() which is synchronized only via the context. * * The device_lock() provides the primary serialization for operations * on the device. It might be as relaxed (mutex)[*] or as tight * (disabled preemption and interrupts) as needed. It allows * the kthread to operate in the least restrictive mode[**]. * * [*] Standalone nbcon_context_try_acquire() is not safe with * the preemption enabled, see nbcon_owner_matches(). But it * can be safe when always called in the preemptive context * under the device_lock(). * * [**] The device_lock() makes sure that nbcon_context_try_acquire() * would never need to spin which is important especially with * PREEMPT_RT. */ void (*write_thread)(struct console *con, struct nbcon_write_context *wctxt); /** * @device_lock: * * NBCON callback to begin synchronization with driver code. * * Console drivers typically must deal with access to the hardware * via user input/output (such as an interactive login shell) and * output of kernel messages via printk() calls. This callback is * called by the printk-subsystem whenever it needs to synchronize * with hardware access by the driver. It should be implemented to * use whatever synchronization mechanism the driver is using for * itself (for example, the port lock for uart serial consoles). * * The callback is always called from task context. It may use any * synchronization method required by the driver. * * IMPORTANT: The callback MUST disable migration. The console driver * may be using a synchronization mechanism that already takes * care of this (such as spinlocks). Otherwise this function must * explicitly call migrate_disable(). * * The flags argument is provided as a convenience to the driver. It * will be passed again to device_unlock(). It can be ignored if the * driver does not need it. */ void (*device_lock)(struct console *con, unsigned long *flags); /** * @device_unlock: * * NBCON callback to finish synchronization with driver code. * * It is the counterpart to device_lock(). * * This callback is always called from task context. It must * appropriately re-enable migration (depending on how device_lock() * disabled migration). * * The flags argument is the value of the same variable that was * passed to device_lock(). */ void (*device_unlock)(struct console *con, unsigned long flags); atomic_t __private nbcon_state; atomic_long_t __private nbcon_seq; struct nbcon_context __private nbcon_device_ctxt; atomic_long_t __private nbcon_prev_seq; struct printk_buffers *pbufs; struct task_struct *kthread; struct rcuwait rcuwait; struct irq_work irq_work; }; #ifdef CONFIG_LOCKDEP extern void lockdep_assert_console_list_lock_held(void); #else static inline void lockdep_assert_console_list_lock_held(void) { } #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC extern bool console_srcu_read_lock_is_held(void); #else static inline bool console_srcu_read_lock_is_held(void) { return 1; } #endif extern int console_srcu_read_lock(void); extern void console_srcu_read_unlock(int cookie); extern void console_list_lock(void) __acquires(console_mutex); extern void console_list_unlock(void) __releases(console_mutex); extern struct hlist_head console_list; /** * console_srcu_read_flags - Locklessly read flags of a possibly registered * console * @con: struct console pointer of console to read flags from * * Locklessly reading @con->flags provides a consistent read value because * there is at most one CPU modifying @con->flags and that CPU is using only * read-modify-write operations to do so. * * Requires console_srcu_read_lock to be held, which implies that @con might * be a registered console. The purpose of holding console_srcu_read_lock is * to guarantee that the console state is valid (CON_SUSPENDED/CON_ENABLED) * and that no exit/cleanup routines will run if the console is currently * undergoing unregistration. * * If the caller is holding the console_list_lock or it is _certain_ that * @con is not and will not become registered, the caller may read * @con->flags directly instead. * * Context: Any context. * Return: The current value of the @con->flags field. */ static inline short console_srcu_read_flags(const struct console *con) { WARN_ON_ONCE(!console_srcu_read_lock_is_held()); /* * The READ_ONCE() matches the WRITE_ONCE() when @flags are modified * for registered consoles with console_srcu_write_flags(). */ return data_race(READ_ONCE(con->flags)); } /** * console_srcu_write_flags - Write flags for a registered console * @con: struct console pointer of console to write flags to * @flags: new flags value to write * * Only use this function to write flags for registered consoles. It * requires holding the console_list_lock. * * Context: Any context. */ static inline void console_srcu_write_flags(struct console *con, short flags) { lockdep_assert_console_list_lock_held(); /* This matches the READ_ONCE() in console_srcu_read_flags(). */ WRITE_ONCE(con->flags, flags); } /* Variant of console_is_registered() when the console_list_lock is held. */ static inline bool console_is_registered_locked(const struct console *con) { lockdep_assert_console_list_lock_held(); return !hlist_unhashed(&con->node); } /* * console_is_registered - Check if the console is registered * @con: struct console pointer of console to check * * Context: Process context. May sleep while acquiring console list lock. * Return: true if the console is in the console list, otherwise false. * * If false is returned for a console that was previously registered, it * can be assumed that the console's unregistration is fully completed, * including the exit() callback after console list removal. */ static inline bool console_is_registered(const struct console *con) { bool ret; console_list_lock(); ret = console_is_registered_locked(con); console_list_unlock(); return ret; } /** * for_each_console_srcu() - Iterator over registered consoles * @con: struct console pointer used as loop cursor * * Although SRCU guarantees the console list will be consistent, the * struct console fields may be updated by other CPUs while iterating. * * Requires console_srcu_read_lock to be held. Can be invoked from * any context. */ #define for_each_console_srcu(con) \ hlist_for_each_entry_srcu(con, &console_list, node, \ console_srcu_read_lock_is_held()) /** * for_each_console() - Iterator over registered consoles * @con: struct console pointer used as loop cursor * * The console list and the &console.flags are immutable while iterating. * * Requires console_list_lock to be held. */ #define for_each_console(con) \ lockdep_assert_console_list_lock_held(); \ hlist_for_each_entry(con, &console_list, node) #ifdef CONFIG_PRINTK extern void nbcon_cpu_emergency_enter(void); extern void nbcon_cpu_emergency_exit(void); extern bool nbcon_can_proceed(struct nbcon_write_context *wctxt); extern bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt); extern bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt); extern void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt); #else static inline void nbcon_cpu_emergency_enter(void) { } static inline void nbcon_cpu_emergency_exit(void) { } static inline bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { return false; } static inline bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { return false; } static inline void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { } #endif extern int console_set_on_cmdline; extern struct console *early_console; enum con_flush_mode { CONSOLE_FLUSH_PENDING, CONSOLE_REPLAY_ALL, }; extern int add_preferred_console(const char *name, const short idx, char *options); extern void console_force_preferred_locked(struct console *con); extern void register_console(struct console *); extern int unregister_console(struct console *); extern void console_lock(void); extern int console_trylock(void); extern void console_unlock(void); extern void console_conditional_schedule(void); extern void console_unblank(void); extern void console_flush_on_panic(enum con_flush_mode mode); extern struct tty_driver *console_device(int *); extern void console_suspend(struct console *); extern void console_resume(struct console *); extern int is_console_locked(void); extern int braille_register_console(struct console *, int index, char *console_options, char *braille_options); extern int braille_unregister_console(struct console *); #ifdef CONFIG_TTY extern void console_sysfs_notify(void); #else static inline void console_sysfs_notify(void) { } #endif extern bool console_suspend_enabled; /* Suspend and resume console messages over PM events */ extern void console_suspend_all(void); extern void console_resume_all(void); int mda_console_init(void); void vcs_make_sysfs(int index); void vcs_remove_sysfs(int index); /* Some debug stub to catch some of the obvious races in the VT code */ #define WARN_CONSOLE_UNLOCKED() \ WARN_ON(!atomic_read(&ignore_console_lock_warning) && \ !is_console_locked() && !oops_in_progress) /* * Increment ignore_console_lock_warning if you need to quiet * WARN_CONSOLE_UNLOCKED() for debugging purposes. */ extern atomic_t ignore_console_lock_warning; DEFINE_LOCK_GUARD_0(console_lock, console_lock(), console_unlock()); extern void console_init(void); /* For deferred console takeover */ void dummycon_register_output_notifier(struct notifier_block *nb); void dummycon_unregister_output_notifier(struct notifier_block *nb); #endif /* _LINUX_CONSOLE_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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2020 - Google LLC * Author: Quentin Perret <qperret@google.com> */ #ifndef __ARM64_KVM_PKVM_H__ #define __ARM64_KVM_PKVM_H__ #include <linux/arm_ffa.h> #include <linux/memblock.h> #include <linux/scatterlist.h> #include <asm/kvm_pgtable.h> /* Maximum number of VMs that can co-exist under pKVM. */ #define KVM_MAX_PVMS 255 #define HYP_MEMBLOCK_REGIONS 128 int pkvm_init_host_vm(struct kvm *kvm); int pkvm_create_hyp_vm(struct kvm *kvm); bool pkvm_hyp_vm_is_created(struct kvm *kvm); void pkvm_destroy_hyp_vm(struct kvm *kvm); int pkvm_create_hyp_vcpu(struct kvm_vcpu *vcpu); /* * This functions as an allow-list of protected VM capabilities. * Features not explicitly allowed by this function are denied. */ static inline bool kvm_pvm_ext_allowed(long ext) { switch (ext) { case KVM_CAP_IRQCHIP: case KVM_CAP_ARM_PSCI: case KVM_CAP_ARM_PSCI_0_2: case KVM_CAP_NR_VCPUS: case KVM_CAP_MAX_VCPUS: case KVM_CAP_MAX_VCPU_ID: case KVM_CAP_MSI_DEVID: case KVM_CAP_ARM_VM_IPA_SIZE: case KVM_CAP_ARM_PMU_V3: case KVM_CAP_ARM_SVE: case KVM_CAP_ARM_PTRAUTH_ADDRESS: case KVM_CAP_ARM_PTRAUTH_GENERIC: return true; default: return false; } } extern struct memblock_region kvm_nvhe_sym(hyp_memory)[]; extern unsigned int kvm_nvhe_sym(hyp_memblock_nr); static inline unsigned long hyp_vmemmap_memblock_size(struct memblock_region *reg, size_t vmemmap_entry_size) { unsigned long nr_pages = reg->size >> PAGE_SHIFT; unsigned long start, end; start = (reg->base >> PAGE_SHIFT) * vmemmap_entry_size; end = start + nr_pages * vmemmap_entry_size; start = ALIGN_DOWN(start, PAGE_SIZE); end = ALIGN(end, PAGE_SIZE); return end - start; } static inline unsigned long hyp_vmemmap_pages(size_t vmemmap_entry_size) { unsigned long res = 0, i; for (i = 0; i < kvm_nvhe_sym(hyp_memblock_nr); i++) { res += hyp_vmemmap_memblock_size(&kvm_nvhe_sym(hyp_memory)[i], vmemmap_entry_size); } return res >> PAGE_SHIFT; } static inline unsigned long hyp_vm_table_pages(void) { return PAGE_ALIGN(KVM_MAX_PVMS * sizeof(void *)) >> PAGE_SHIFT; } static inline unsigned long __hyp_pgtable_max_pages(unsigned long nr_pages) { unsigned long total = 0; int i; /* Provision the worst case scenario */ for (i = KVM_PGTABLE_FIRST_LEVEL; i <= KVM_PGTABLE_LAST_LEVEL; i++) { nr_pages = DIV_ROUND_UP(nr_pages, PTRS_PER_PTE); total += nr_pages; } return total; } static inline unsigned long __hyp_pgtable_total_pages(void) { unsigned long res = 0, i; /* Cover all of memory with page-granularity */ for (i = 0; i < kvm_nvhe_sym(hyp_memblock_nr); i++) { struct memblock_region *reg = &kvm_nvhe_sym(hyp_memory)[i]; res += __hyp_pgtable_max_pages(reg->size >> PAGE_SHIFT); } return res; } static inline unsigned long hyp_s1_pgtable_pages(void) { unsigned long res; res = __hyp_pgtable_total_pages(); /* Allow 1 GiB for private mappings */ res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT); return res; } static inline unsigned long host_s2_pgtable_pages(void) { unsigned long res; /* * Include an extra 16 pages to safely upper-bound the worst case of * concatenated pgds. */ res = __hyp_pgtable_total_pages() + 16; /* Allow 1 GiB for MMIO mappings */ res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT); return res; } #ifdef CONFIG_NVHE_EL2_DEBUG static inline unsigned long pkvm_selftest_pages(void) { return 32; } #else static inline unsigned long pkvm_selftest_pages(void) { return 0; } #endif #define KVM_FFA_MBOX_NR_PAGES 1 static inline unsigned long hyp_ffa_proxy_pages(void) { size_t desc_max; /* * The hypervisor FFA proxy needs enough memory to buffer a fragmented * descriptor returned from EL3 in response to a RETRIEVE_REQ call. */ desc_max = sizeof(struct ffa_mem_region) + sizeof(struct ffa_mem_region_attributes) + sizeof(struct ffa_composite_mem_region) + SG_MAX_SEGMENTS * sizeof(struct ffa_mem_region_addr_range); /* Plus a page each for the hypervisor's RX and TX mailboxes. */ return (2 * KVM_FFA_MBOX_NR_PAGES) + DIV_ROUND_UP(desc_max, PAGE_SIZE); } static inline size_t pkvm_host_sve_state_size(void) { if (!system_supports_sve()) return 0; return size_add(sizeof(struct cpu_sve_state), SVE_SIG_REGS_SIZE(sve_vq_from_vl(kvm_host_sve_max_vl))); } struct pkvm_mapping { struct rb_node node; u64 gfn; u64 pfn; u64 nr_pages; u64 __subtree_last; /* Internal member for interval tree */ }; int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops); void pkvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt, u64 addr, u64 size); void pkvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt); int pkvm_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 pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size); int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size); int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size); bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold); int pkvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot, enum kvm_pgtable_walk_flags flags); void pkvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_walk_flags flags); int pkvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc); void pkvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level); kvm_pte_t *pkvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level, enum kvm_pgtable_prot prot, void *mc, bool force_pte); #endif /* __ARM64_KVM_PKVM_H__ */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Supplementary group IDs */ #include <linux/cred.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/sort.h> #include <linux/syscalls.h> #include <linux/user_namespace.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> struct group_info *groups_alloc(int gidsetsize) { struct group_info *gi; gi = kvmalloc(struct_size(gi, gid, gidsetsize), GFP_KERNEL_ACCOUNT); if (!gi) return NULL; refcount_set(&gi->usage, 1); gi->ngroups = gidsetsize; return gi; } EXPORT_SYMBOL(groups_alloc); void groups_free(struct group_info *group_info) { kvfree(group_info); } EXPORT_SYMBOL(groups_free); /* export the group_info to a user-space array */ static int groups_to_user(gid_t __user *grouplist, const struct group_info *group_info) { struct user_namespace *user_ns = current_user_ns(); int i; unsigned int count = group_info->ngroups; for (i = 0; i < count; i++) { gid_t gid; gid = from_kgid_munged(user_ns, group_info->gid[i]); if (put_user(gid, grouplist+i)) return -EFAULT; } return 0; } /* fill a group_info from a user-space array - it must be allocated already */ static int groups_from_user(struct group_info *group_info, gid_t __user *grouplist) { struct user_namespace *user_ns = current_user_ns(); int i; unsigned int count = group_info->ngroups; for (i = 0; i < count; i++) { gid_t gid; kgid_t kgid; if (get_user(gid, grouplist+i)) return -EFAULT; kgid = make_kgid(user_ns, gid); if (!gid_valid(kgid)) return -EINVAL; group_info->gid[i] = kgid; } return 0; } static int gid_cmp(const void *_a, const void *_b) { kgid_t a = *(kgid_t *)_a; kgid_t b = *(kgid_t *)_b; return gid_gt(a, b) - gid_lt(a, b); } void groups_sort(struct group_info *group_info) { sort(group_info->gid, group_info->ngroups, sizeof(*group_info->gid), gid_cmp, NULL); } EXPORT_SYMBOL(groups_sort); /* a simple bsearch */ int groups_search(const struct group_info *group_info, kgid_t grp) { unsigned int left, right; if (!group_info) return 0; left = 0; right = group_info->ngroups; while (left < right) { unsigned int mid = (left+right)/2; if (gid_gt(grp, group_info->gid[mid])) left = mid + 1; else if (gid_lt(grp, group_info->gid[mid])) right = mid; else return 1; } return 0; } /** * set_groups - Change a group subscription in a set of credentials * @new: The newly prepared set of credentials to alter * @group_info: The group list to install */ void set_groups(struct cred *new, struct group_info *group_info) { put_group_info(new->group_info); get_group_info(group_info); new->group_info = group_info; } EXPORT_SYMBOL(set_groups); /** * set_current_groups - Change current's group subscription * @group_info: The group list to impose * * Validate a group subscription and, if valid, impose it upon current's task * security record. */ int set_current_groups(struct group_info *group_info) { struct cred *new; const struct cred *old; int retval; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); set_groups(new, group_info); retval = security_task_fix_setgroups(new, old); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } EXPORT_SYMBOL(set_current_groups); SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist) { const struct cred *cred = current_cred(); int i; if (gidsetsize < 0) return -EINVAL; /* no need to grab task_lock here; it cannot change */ i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } if (groups_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: return i; } bool may_setgroups(void) { struct user_namespace *user_ns = current_user_ns(); return ns_capable_setid(user_ns, CAP_SETGID) && userns_may_setgroups(user_ns); } /* * SMP: Our groups are copy-on-write. We can set them safely * without another task interfering. */ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) { struct group_info *group_info; int retval; if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; group_info = groups_alloc(gidsetsize); if (!group_info) return -ENOMEM; retval = groups_from_user(group_info, grouplist); if (retval) { put_group_info(group_info); return retval; } groups_sort(group_info); retval = set_current_groups(group_info); put_group_info(group_info); return retval; } /* * Check whether we're fsgid/egid or in the supplemental group.. */ int in_group_p(kgid_t grp) { const struct cred *cred = current_cred(); int retval = 1; if (!gid_eq(grp, cred->fsgid)) retval = groups_search(cred->group_info, grp); return retval; } EXPORT_SYMBOL(in_group_p); int in_egroup_p(kgid_t grp) { const struct cred *cred = current_cred(); int retval = 1; if (!gid_eq(grp, cred->egid)) retval = groups_search(cred->group_info, grp); return retval; } EXPORT_SYMBOL(in_egroup_p); |
| 9 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __KVM_IODEV_H__ #define __KVM_IODEV_H__ #include <linux/kvm_types.h> #include <linux/errno.h> struct kvm_io_device; struct kvm_vcpu; /** * kvm_io_device_ops are called under kvm slots_lock. * read and write handlers return 0 if the transaction has been handled, * or non-zero to have it passed to the next device. **/ struct kvm_io_device_ops { int (*read)(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, void *val); int (*write)(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, const void *val); void (*destructor)(struct kvm_io_device *this); }; struct kvm_io_device { const struct kvm_io_device_ops *ops; }; static inline void kvm_iodevice_init(struct kvm_io_device *dev, const struct kvm_io_device_ops *ops) { dev->ops = ops; } static inline int kvm_iodevice_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int l, void *v) { return dev->ops->read ? dev->ops->read(vcpu, dev, addr, l, v) : -EOPNOTSUPP; } static inline int kvm_iodevice_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int l, const void *v) { return dev->ops->write ? dev->ops->write(vcpu, dev, addr, l, v) : -EOPNOTSUPP; } #endif /* __KVM_IODEV_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_CLOCK_H #define _LINUX_SCHED_CLOCK_H #include <linux/smp.h> /* * Do not use outside of architecture code which knows its limitations. * * sched_clock() has no promise of monotonicity or bounded drift between * CPUs, use (which you should not) requires disabling IRQs. * * Please use one of the three interfaces below. */ extern u64 sched_clock(void); #if defined(CONFIG_ARCH_WANTS_NO_INSTR) || defined(CONFIG_GENERIC_SCHED_CLOCK) extern u64 sched_clock_noinstr(void); #else static __always_inline u64 sched_clock_noinstr(void) { return sched_clock(); } #endif /* * See the comment in kernel/sched/clock.c */ extern u64 running_clock(void); extern u64 sched_clock_cpu(int cpu); extern void sched_clock_init(void); #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK static inline void sched_clock_tick(void) { } static inline void clear_sched_clock_stable(void) { } static inline void sched_clock_idle_sleep_event(void) { } static inline void sched_clock_idle_wakeup_event(void) { } static inline u64 cpu_clock(int cpu) { return sched_clock(); } static __always_inline u64 local_clock_noinstr(void) { return sched_clock_noinstr(); } static __always_inline u64 local_clock(void) { return sched_clock(); } #else extern int sched_clock_stable(void); extern void clear_sched_clock_stable(void); /* * When sched_clock_stable(), __sched_clock_offset provides the offset * between local_clock() and sched_clock(). */ extern u64 __sched_clock_offset; extern void sched_clock_tick(void); extern void sched_clock_tick_stable(void); extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(void); /* * As outlined in clock.c, provides a fast, high resolution, nanosecond * time source that is monotonic per cpu argument and has bounded drift * between cpus. * * ######################### BIG FAT WARNING ########################## * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can # * # go backwards !! # * #################################################################### */ static inline u64 cpu_clock(int cpu) { return sched_clock_cpu(cpu); } extern u64 local_clock_noinstr(void); extern u64 local_clock(void); #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING /* * An i/f to runtime opt-in for irq time accounting based off of sched_clock. * The reason for this explicit opt-in is not to have perf penalty with * slow sched_clocks. */ extern void enable_sched_clock_irqtime(void); extern void disable_sched_clock_irqtime(void); #else static inline void enable_sched_clock_irqtime(void) {} static inline void disable_sched_clock_irqtime(void) {} #endif #endif /* _LINUX_SCHED_CLOCK_H */ |
| 15 15 15 15 15 655 202 202 6 6 1413 1418 1413 134 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Landlock - Filesystem management and hooks * * Copyright © 2016-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI * Copyright © 2021-2025 Microsoft Corporation * Copyright © 2022 Günther Noack <gnoack3000@gmail.com> * Copyright © 2023-2024 Google LLC */ #include <asm/ioctls.h> #include <kunit/test.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/bits.h> #include <linux/compiler_types.h> #include <linux/dcache.h> #include <linux/err.h> #include <linux/falloc.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/limits.h> #include <linux/list.h> #include <linux/lsm_audit.h> #include <linux/lsm_hooks.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/path.h> #include <linux/pid.h> #include <linux/rcupdate.h> #include <linux/sched/signal.h> #include <linux/spinlock.h> #include <linux/stat.h> #include <linux/types.h> #include <linux/wait_bit.h> #include <linux/workqueue.h> #include <uapi/linux/fiemap.h> #include <uapi/linux/landlock.h> #include "access.h" #include "audit.h" #include "common.h" #include "cred.h" #include "domain.h" #include "fs.h" #include "limits.h" #include "object.h" #include "ruleset.h" #include "setup.h" /* Underlying object management */ static void release_inode(struct landlock_object *const object) __releases(object->lock) { struct inode *const inode = object->underobj; struct super_block *sb; if (!inode) { spin_unlock(&object->lock); return; } /* * Protects against concurrent use by hook_sb_delete() of the reference * to the underlying inode. */ object->underobj = NULL; /* * Makes sure that if the filesystem is concurrently unmounted, * hook_sb_delete() will wait for us to finish iput(). */ sb = inode->i_sb; atomic_long_inc(&landlock_superblock(sb)->inode_refs); spin_unlock(&object->lock); /* * Because object->underobj was not NULL, hook_sb_delete() and * get_inode_object() guarantee that it is safe to reset * landlock_inode(inode)->object while it is not NULL. It is therefore * not necessary to lock inode->i_lock. */ rcu_assign_pointer(landlock_inode(inode)->object, NULL); /* * Now, new rules can safely be tied to @inode with get_inode_object(). */ iput(inode); if (atomic_long_dec_and_test(&landlock_superblock(sb)->inode_refs)) wake_up_var(&landlock_superblock(sb)->inode_refs); } static const struct landlock_object_underops landlock_fs_underops = { .release = release_inode }; /* IOCTL helpers */ /** * is_masked_device_ioctl - Determine whether an IOCTL command is always * permitted with Landlock for device files. These commands can not be * restricted on device files by enforcing a Landlock policy. * * @cmd: The IOCTL command that is supposed to be run. * * By default, any IOCTL on a device file requires the * LANDLOCK_ACCESS_FS_IOCTL_DEV right. However, we blanket-permit some * commands, if: * * 1. The command is implemented in fs/ioctl.c's do_vfs_ioctl(), * not in f_ops->unlocked_ioctl() or f_ops->compat_ioctl(). * * 2. The command is harmless when invoked on devices. * * We also permit commands that do not make sense for devices, but where the * do_vfs_ioctl() implementation returns a more conventional error code. * * Any new IOCTL commands that are implemented in fs/ioctl.c's do_vfs_ioctl() * should be considered for inclusion here. * * Returns: true if the IOCTL @cmd can not be restricted with Landlock for * device files. */ static __attribute_const__ bool is_masked_device_ioctl(const unsigned int cmd) { switch (cmd) { /* * FIOCLEX, FIONCLEX, FIONBIO and FIOASYNC manipulate the FD's * close-on-exec and the file's buffered-IO and async flags. These * operations are also available through fcntl(2), and are * unconditionally permitted in Landlock. */ case FIOCLEX: case FIONCLEX: case FIONBIO: case FIOASYNC: /* * FIOQSIZE queries the size of a regular file, directory, or link. * * We still permit it, because it always returns -ENOTTY for * other file types. */ case FIOQSIZE: /* * FIFREEZE and FITHAW freeze and thaw the file system which the * given file belongs to. Requires CAP_SYS_ADMIN. * * These commands operate on the file system's superblock rather * than on the file itself. The same operations can also be * done through any other file or directory on the same file * system, so it is safe to permit these. */ case FIFREEZE: case FITHAW: /* * FS_IOC_FIEMAP queries information about the allocation of * blocks within a file. * * This IOCTL command only makes sense for regular files and is * not implemented by devices. It is harmless to permit. */ case FS_IOC_FIEMAP: /* * FIGETBSZ queries the file system's block size for a file or * directory. * * This command operates on the file system's superblock rather * than on the file itself. The same operation can also be done * through any other file or directory on the same file system, * so it is safe to permit it. */ case FIGETBSZ: /* * FICLONE, FICLONERANGE and FIDEDUPERANGE make files share * their underlying storage ("reflink") between source and * destination FDs, on file systems which support that. * * These IOCTL commands only apply to regular files * and are harmless to permit for device files. */ case FICLONE: case FICLONERANGE: case FIDEDUPERANGE: /* * FS_IOC_GETFSUUID and FS_IOC_GETFSSYSFSPATH both operate on * the file system superblock, not on the specific file, so * these operations are available through any other file on the * same file system as well. */ case FS_IOC_GETFSUUID: case FS_IOC_GETFSSYSFSPATH: return true; /* * FIONREAD, FS_IOC_GETFLAGS, FS_IOC_SETFLAGS, FS_IOC_FSGETXATTR and * FS_IOC_FSSETXATTR are forwarded to device implementations. */ /* * file_ioctl() commands (FIBMAP, FS_IOC_RESVSP, FS_IOC_RESVSP64, * FS_IOC_UNRESVSP, FS_IOC_UNRESVSP64 and FS_IOC_ZERO_RANGE) are * forwarded to device implementations, so not permitted. */ /* Other commands are guarded by the access right. */ default: return false; } } /* * is_masked_device_ioctl_compat - same as the helper above, but checking the * "compat" IOCTL commands. * * The IOCTL commands with special handling in compat-mode should behave the * same as their non-compat counterparts. */ static __attribute_const__ bool is_masked_device_ioctl_compat(const unsigned int cmd) { switch (cmd) { /* FICLONE is permitted, same as in the non-compat variant. */ case FICLONE: return true; #if defined(CONFIG_X86_64) /* * FS_IOC_RESVSP_32, FS_IOC_RESVSP64_32, FS_IOC_UNRESVSP_32, * FS_IOC_UNRESVSP64_32, FS_IOC_ZERO_RANGE_32: not blanket-permitted, * for consistency with their non-compat variants. */ case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: case FS_IOC_UNRESVSP_32: case FS_IOC_UNRESVSP64_32: case FS_IOC_ZERO_RANGE_32: #endif /* * FS_IOC32_GETFLAGS, FS_IOC32_SETFLAGS are forwarded to their device * implementations. */ case FS_IOC32_GETFLAGS: case FS_IOC32_SETFLAGS: return false; default: return is_masked_device_ioctl(cmd); } } /* Ruleset management */ static struct landlock_object *get_inode_object(struct inode *const inode) { struct landlock_object *object, *new_object; struct landlock_inode_security *inode_sec = landlock_inode(inode); rcu_read_lock(); retry: object = rcu_dereference(inode_sec->object); if (object) { if (likely(refcount_inc_not_zero(&object->usage))) { rcu_read_unlock(); return object; } /* * We are racing with release_inode(), the object is going * away. Wait for release_inode(), then retry. */ spin_lock(&object->lock); spin_unlock(&object->lock); goto retry; } rcu_read_unlock(); /* * If there is no object tied to @inode, then create a new one (without * holding any locks). */ new_object = landlock_create_object(&landlock_fs_underops, inode); if (IS_ERR(new_object)) return new_object; /* * Protects against concurrent calls to get_inode_object() or * hook_sb_delete(). */ spin_lock(&inode->i_lock); if (unlikely(rcu_access_pointer(inode_sec->object))) { /* Someone else just created the object, bail out and retry. */ spin_unlock(&inode->i_lock); kfree(new_object); rcu_read_lock(); goto retry; } /* * @inode will be released by hook_sb_delete() on its superblock * shutdown, or by release_inode() when no more ruleset references the * related object. */ ihold(inode); rcu_assign_pointer(inode_sec->object, new_object); spin_unlock(&inode->i_lock); return new_object; } /* All access rights that can be tied to files. */ /* clang-format off */ #define ACCESS_FILE ( \ LANDLOCK_ACCESS_FS_EXECUTE | \ LANDLOCK_ACCESS_FS_WRITE_FILE | \ LANDLOCK_ACCESS_FS_READ_FILE | \ LANDLOCK_ACCESS_FS_TRUNCATE | \ LANDLOCK_ACCESS_FS_IOCTL_DEV) /* clang-format on */ /* * @path: Should have been checked by get_path_from_fd(). */ int landlock_append_fs_rule(struct landlock_ruleset *const ruleset, const struct path *const path, access_mask_t access_rights) { int err; struct landlock_id id = { .type = LANDLOCK_KEY_INODE, }; /* Files only get access rights that make sense. */ if (!d_is_dir(path->dentry) && (access_rights | ACCESS_FILE) != ACCESS_FILE) return -EINVAL; if (WARN_ON_ONCE(ruleset->num_layers != 1)) return -EINVAL; /* Transforms relative access rights to absolute ones. */ access_rights |= LANDLOCK_MASK_ACCESS_FS & ~landlock_get_fs_access_mask(ruleset, 0); id.key.object = get_inode_object(d_backing_inode(path->dentry)); if (IS_ERR(id.key.object)) return PTR_ERR(id.key.object); mutex_lock(&ruleset->lock); err = landlock_insert_rule(ruleset, id, access_rights); mutex_unlock(&ruleset->lock); /* * No need to check for an error because landlock_insert_rule() * increments the refcount for the new object if needed. */ landlock_put_object(id.key.object); return err; } /* Access-control management */ /* * The lifetime of the returned rule is tied to @domain. * * Returns NULL if no rule is found or if @dentry is negative. */ static const struct landlock_rule * find_rule(const struct landlock_ruleset *const domain, const struct dentry *const dentry) { const struct landlock_rule *rule; const struct inode *inode; struct landlock_id id = { .type = LANDLOCK_KEY_INODE, }; /* Ignores nonexistent leafs. */ if (d_is_negative(dentry)) return NULL; inode = d_backing_inode(dentry); rcu_read_lock(); id.key.object = rcu_dereference(landlock_inode(inode)->object); rule = landlock_find_rule(domain, id); rcu_read_unlock(); return rule; } /* * Allows access to pseudo filesystems that will never be mountable (e.g. * sockfs, pipefs), but can still be reachable through * /proc/<pid>/fd/<file-descriptor> */ static bool is_nouser_or_private(const struct dentry *dentry) { return (dentry->d_sb->s_flags & SB_NOUSER) || (d_is_positive(dentry) && unlikely(IS_PRIVATE(d_backing_inode(dentry)))); } static const struct access_masks any_fs = { .fs = ~0, }; /* * Check that a destination file hierarchy has more restrictions than a source * file hierarchy. This is only used for link and rename actions. * * @layer_masks_child2: Optional child masks. */ static bool no_more_access( const layer_mask_t (*const layer_masks_parent1)[LANDLOCK_NUM_ACCESS_FS], const layer_mask_t (*const layer_masks_child1)[LANDLOCK_NUM_ACCESS_FS], const bool child1_is_directory, const layer_mask_t (*const layer_masks_parent2)[LANDLOCK_NUM_ACCESS_FS], const layer_mask_t (*const layer_masks_child2)[LANDLOCK_NUM_ACCESS_FS], const bool child2_is_directory) { unsigned long access_bit; for (access_bit = 0; access_bit < ARRAY_SIZE(*layer_masks_parent2); access_bit++) { /* Ignores accesses that only make sense for directories. */ const bool is_file_access = !!(BIT_ULL(access_bit) & ACCESS_FILE); if (child1_is_directory || is_file_access) { /* * Checks if the destination restrictions are a * superset of the source ones (i.e. inherited access * rights without child exceptions): * restrictions(parent2) >= restrictions(child1) */ if ((((*layer_masks_parent1)[access_bit] & (*layer_masks_child1)[access_bit]) | (*layer_masks_parent2)[access_bit]) != (*layer_masks_parent2)[access_bit]) return false; } if (!layer_masks_child2) continue; if (child2_is_directory || is_file_access) { /* * Checks inverted restrictions for RENAME_EXCHANGE: * restrictions(parent1) >= restrictions(child2) */ if ((((*layer_masks_parent2)[access_bit] & (*layer_masks_child2)[access_bit]) | (*layer_masks_parent1)[access_bit]) != (*layer_masks_parent1)[access_bit]) return false; } } return true; } #define NMA_TRUE(...) KUNIT_EXPECT_TRUE(test, no_more_access(__VA_ARGS__)) #define NMA_FALSE(...) KUNIT_EXPECT_FALSE(test, no_more_access(__VA_ARGS__)) #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_no_more_access(struct kunit *const test) { const layer_mask_t rx0[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0), [BIT_INDEX(LANDLOCK_ACCESS_FS_READ_FILE)] = BIT_ULL(0), }; const layer_mask_t mx0[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0), [BIT_INDEX(LANDLOCK_ACCESS_FS_MAKE_REG)] = BIT_ULL(0), }; const layer_mask_t x0[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0), }; const layer_mask_t x1[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(1), }; const layer_mask_t x01[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0) | BIT_ULL(1), }; const layer_mask_t allows_all[LANDLOCK_NUM_ACCESS_FS] = {}; /* Checks without restriction. */ NMA_TRUE(&x0, &allows_all, false, &allows_all, NULL, false); NMA_TRUE(&allows_all, &x0, false, &allows_all, NULL, false); NMA_FALSE(&x0, &x0, false, &allows_all, NULL, false); /* * Checks that we can only refer a file if no more access could be * inherited. */ NMA_TRUE(&x0, &x0, false, &rx0, NULL, false); NMA_TRUE(&rx0, &rx0, false, &rx0, NULL, false); NMA_FALSE(&rx0, &rx0, false, &x0, NULL, false); NMA_FALSE(&rx0, &rx0, false, &x1, NULL, false); /* Checks allowed referring with different nested domains. */ NMA_TRUE(&x0, &x1, false, &x0, NULL, false); NMA_TRUE(&x1, &x0, false, &x0, NULL, false); NMA_TRUE(&x0, &x01, false, &x0, NULL, false); NMA_TRUE(&x0, &x01, false, &rx0, NULL, false); NMA_TRUE(&x01, &x0, false, &x0, NULL, false); NMA_TRUE(&x01, &x0, false, &rx0, NULL, false); NMA_FALSE(&x01, &x01, false, &x0, NULL, false); /* Checks that file access rights are also enforced for a directory. */ NMA_FALSE(&rx0, &rx0, true, &x0, NULL, false); /* Checks that directory access rights don't impact file referring... */ NMA_TRUE(&mx0, &mx0, false, &x0, NULL, false); /* ...but only directory referring. */ NMA_FALSE(&mx0, &mx0, true, &x0, NULL, false); /* Checks directory exchange. */ NMA_TRUE(&mx0, &mx0, true, &mx0, &mx0, true); NMA_TRUE(&mx0, &mx0, true, &mx0, &x0, true); NMA_FALSE(&mx0, &mx0, true, &x0, &mx0, true); NMA_FALSE(&mx0, &mx0, true, &x0, &x0, true); NMA_FALSE(&mx0, &mx0, true, &x1, &x1, true); /* Checks file exchange with directory access rights... */ NMA_TRUE(&mx0, &mx0, false, &mx0, &mx0, false); NMA_TRUE(&mx0, &mx0, false, &mx0, &x0, false); NMA_TRUE(&mx0, &mx0, false, &x0, &mx0, false); NMA_TRUE(&mx0, &mx0, false, &x0, &x0, false); /* ...and with file access rights. */ NMA_TRUE(&rx0, &rx0, false, &rx0, &rx0, false); NMA_TRUE(&rx0, &rx0, false, &rx0, &x0, false); NMA_FALSE(&rx0, &rx0, false, &x0, &rx0, false); NMA_FALSE(&rx0, &rx0, false, &x0, &x0, false); NMA_FALSE(&rx0, &rx0, false, &x1, &x1, false); /* * Allowing the following requests should not be a security risk * because domain 0 denies execute access, and domain 1 is always * nested with domain 0. However, adding an exception for this case * would mean to check all nested domains to make sure none can get * more privileges (e.g. processes only sandboxed by domain 0). * Moreover, this behavior (i.e. composition of N domains) could then * be inconsistent compared to domain 1's ruleset alone (e.g. it might * be denied to link/rename with domain 1's ruleset, whereas it would * be allowed if nested on top of domain 0). Another drawback would be * to create a cover channel that could enable sandboxed processes to * infer most of the filesystem restrictions from their domain. To * make it simple, efficient, safe, and more consistent, this case is * always denied. */ NMA_FALSE(&x1, &x1, false, &x0, NULL, false); NMA_FALSE(&x1, &x1, false, &rx0, NULL, false); NMA_FALSE(&x1, &x1, true, &x0, NULL, false); NMA_FALSE(&x1, &x1, true, &rx0, NULL, false); /* Checks the same case of exclusive domains with a file... */ NMA_TRUE(&x1, &x1, false, &x01, NULL, false); NMA_FALSE(&x1, &x1, false, &x01, &x0, false); NMA_FALSE(&x1, &x1, false, &x01, &x01, false); NMA_FALSE(&x1, &x1, false, &x0, &x0, false); /* ...and with a directory. */ NMA_FALSE(&x1, &x1, false, &x0, &x0, true); NMA_FALSE(&x1, &x1, true, &x0, &x0, false); NMA_FALSE(&x1, &x1, true, &x0, &x0, true); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ #undef NMA_TRUE #undef NMA_FALSE static bool is_layer_masks_allowed( layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS]) { return !memchr_inv(layer_masks, 0, sizeof(*layer_masks)); } /* * Removes @layer_masks accesses that are not requested. * * Returns true if the request is allowed, false otherwise. */ static bool scope_to_request(const access_mask_t access_request, layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS]) { const unsigned long access_req = access_request; unsigned long access_bit; if (WARN_ON_ONCE(!layer_masks)) return true; for_each_clear_bit(access_bit, &access_req, ARRAY_SIZE(*layer_masks)) (*layer_masks)[access_bit] = 0; return is_layer_masks_allowed(layer_masks); } #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_scope_to_request_with_exec_none(struct kunit *const test) { /* Allows everything. */ layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; /* Checks and scopes with execute. */ KUNIT_EXPECT_TRUE(test, scope_to_request(LANDLOCK_ACCESS_FS_EXECUTE, &layer_masks)); KUNIT_EXPECT_EQ(test, 0, layer_masks[BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)]); KUNIT_EXPECT_EQ(test, 0, layer_masks[BIT_INDEX(LANDLOCK_ACCESS_FS_WRITE_FILE)]); } static void test_scope_to_request_with_exec_some(struct kunit *const test) { /* Denies execute and write. */ layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0), [BIT_INDEX(LANDLOCK_ACCESS_FS_WRITE_FILE)] = BIT_ULL(1), }; /* Checks and scopes with execute. */ KUNIT_EXPECT_FALSE(test, scope_to_request(LANDLOCK_ACCESS_FS_EXECUTE, &layer_masks)); KUNIT_EXPECT_EQ(test, BIT_ULL(0), layer_masks[BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)]); KUNIT_EXPECT_EQ(test, 0, layer_masks[BIT_INDEX(LANDLOCK_ACCESS_FS_WRITE_FILE)]); } static void test_scope_to_request_without_access(struct kunit *const test) { /* Denies execute and write. */ layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)] = BIT_ULL(0), [BIT_INDEX(LANDLOCK_ACCESS_FS_WRITE_FILE)] = BIT_ULL(1), }; /* Checks and scopes without access request. */ KUNIT_EXPECT_TRUE(test, scope_to_request(0, &layer_masks)); KUNIT_EXPECT_EQ(test, 0, layer_masks[BIT_INDEX(LANDLOCK_ACCESS_FS_EXECUTE)]); KUNIT_EXPECT_EQ(test, 0, layer_masks[BIT_INDEX(LANDLOCK_ACCESS_FS_WRITE_FILE)]); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ /* * Returns true if there is at least one access right different than * LANDLOCK_ACCESS_FS_REFER. */ static bool is_eacces(const layer_mask_t (*const layer_masks)[LANDLOCK_NUM_ACCESS_FS], const access_mask_t access_request) { unsigned long access_bit; /* LANDLOCK_ACCESS_FS_REFER alone must return -EXDEV. */ const unsigned long access_check = access_request & ~LANDLOCK_ACCESS_FS_REFER; if (!layer_masks) return false; for_each_set_bit(access_bit, &access_check, ARRAY_SIZE(*layer_masks)) { if ((*layer_masks)[access_bit]) return true; } return false; } #define IE_TRUE(...) KUNIT_EXPECT_TRUE(test, is_eacces(__VA_ARGS__)) #define IE_FALSE(...) KUNIT_EXPECT_FALSE(test, is_eacces(__VA_ARGS__)) #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST static void test_is_eacces_with_none(struct kunit *const test) { const layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; IE_FALSE(&layer_masks, 0); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_REFER); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_EXECUTE); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_WRITE_FILE); } static void test_is_eacces_with_refer(struct kunit *const test) { const layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_REFER)] = BIT_ULL(0), }; IE_FALSE(&layer_masks, 0); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_REFER); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_EXECUTE); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_WRITE_FILE); } static void test_is_eacces_with_write(struct kunit *const test) { const layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = { [BIT_INDEX(LANDLOCK_ACCESS_FS_WRITE_FILE)] = BIT_ULL(0), }; IE_FALSE(&layer_masks, 0); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_REFER); IE_FALSE(&layer_masks, LANDLOCK_ACCESS_FS_EXECUTE); IE_TRUE(&layer_masks, LANDLOCK_ACCESS_FS_WRITE_FILE); } #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ #undef IE_TRUE #undef IE_FALSE /** * is_access_to_paths_allowed - Check accesses for requests with a common path * * @domain: Domain to check against. * @path: File hierarchy to walk through. * @access_request_parent1: Accesses to check, once @layer_masks_parent1 is * equal to @layer_masks_parent2 (if any). This is tied to the unique * requested path for most actions, or the source in case of a refer action * (i.e. rename or link), or the source and destination in case of * RENAME_EXCHANGE. * @layer_masks_parent1: Pointer to a matrix of layer masks per access * masks, identifying the layers that forbid a specific access. Bits from * this matrix can be unset according to the @path walk. An empty matrix * means that @domain allows all possible Landlock accesses (i.e. not only * those identified by @access_request_parent1). This matrix can * initially refer to domain layer masks and, when the accesses for the * destination and source are the same, to requested layer masks. * @log_request_parent1: Audit request to fill if the related access is denied. * @dentry_child1: Dentry to the initial child of the parent1 path. This * pointer must be NULL for non-refer actions (i.e. not link nor rename). * @access_request_parent2: Similar to @access_request_parent1 but for a * request involving a source and a destination. This refers to the * destination, except in case of RENAME_EXCHANGE where it also refers to * the source. Must be set to 0 when using a simple path request. * @layer_masks_parent2: Similar to @layer_masks_parent1 but for a refer * action. This must be NULL otherwise. * @log_request_parent2: Audit request to fill if the related access is denied. * @dentry_child2: Dentry to the initial child of the parent2 path. This * pointer is only set for RENAME_EXCHANGE actions and must be NULL * otherwise. * * This helper first checks that the destination has a superset of restrictions * compared to the source (if any) for a common path. Because of * RENAME_EXCHANGE actions, source and destinations may be swapped. It then * checks that the collected accesses and the remaining ones are enough to * allow the request. * * Returns: * - true if the access request is granted; * - false otherwise. */ static bool is_access_to_paths_allowed( const struct landlock_ruleset *const domain, const struct path *const path, const access_mask_t access_request_parent1, layer_mask_t (*const layer_masks_parent1)[LANDLOCK_NUM_ACCESS_FS], struct landlock_request *const log_request_parent1, struct dentry *const dentry_child1, const access_mask_t access_request_parent2, layer_mask_t (*const layer_masks_parent2)[LANDLOCK_NUM_ACCESS_FS], struct landlock_request *const log_request_parent2, struct dentry *const dentry_child2) { bool allowed_parent1 = false, allowed_parent2 = false, is_dom_check, child1_is_directory = true, child2_is_directory = true; struct path walker_path; access_mask_t access_masked_parent1, access_masked_parent2; layer_mask_t _layer_masks_child1[LANDLOCK_NUM_ACCESS_FS], _layer_masks_child2[LANDLOCK_NUM_ACCESS_FS]; layer_mask_t(*layer_masks_child1)[LANDLOCK_NUM_ACCESS_FS] = NULL, (*layer_masks_child2)[LANDLOCK_NUM_ACCESS_FS] = NULL; if (!access_request_parent1 && !access_request_parent2) return true; if (WARN_ON_ONCE(!path)) return true; if (is_nouser_or_private(path->dentry)) return true; if (WARN_ON_ONCE(!layer_masks_parent1)) return false; allowed_parent1 = is_layer_masks_allowed(layer_masks_parent1); if (unlikely(layer_masks_parent2)) { if (WARN_ON_ONCE(!dentry_child1)) return false; allowed_parent2 = is_layer_masks_allowed(layer_masks_parent2); /* * For a double request, first check for potential privilege * escalation by looking at domain handled accesses (which are * a superset of the meaningful requested accesses). */ access_masked_parent1 = access_masked_parent2 = landlock_union_access_masks(domain).fs; is_dom_check = true; } else { if (WARN_ON_ONCE(dentry_child1 || dentry_child2)) return false; /* For a simple request, only check for requested accesses. */ access_masked_parent1 = access_request_parent1; access_masked_parent2 = access_request_parent2; is_dom_check = false; } if (unlikely(dentry_child1)) { landlock_unmask_layers( find_rule(domain, dentry_child1), landlock_init_layer_masks( domain, LANDLOCK_MASK_ACCESS_FS, &_layer_masks_child1, LANDLOCK_KEY_INODE), &_layer_masks_child1, ARRAY_SIZE(_layer_masks_child1)); layer_masks_child1 = &_layer_masks_child1; child1_is_directory = d_is_dir(dentry_child1); } if (unlikely(dentry_child2)) { landlock_unmask_layers( find_rule(domain, dentry_child2), landlock_init_layer_masks( domain, LANDLOCK_MASK_ACCESS_FS, &_layer_masks_child2, LANDLOCK_KEY_INODE), &_layer_masks_child2, ARRAY_SIZE(_layer_masks_child2)); layer_masks_child2 = &_layer_masks_child2; child2_is_directory = d_is_dir(dentry_child2); } walker_path = *path; path_get(&walker_path); /* * We need to walk through all the hierarchy to not miss any relevant * restriction. */ while (true) { struct dentry *parent_dentry; const struct landlock_rule *rule; /* * If at least all accesses allowed on the destination are * already allowed on the source, respectively if there is at * least as much as restrictions on the destination than on the * source, then we can safely refer files from the source to * the destination without risking a privilege escalation. * This also applies in the case of RENAME_EXCHANGE, which * implies checks on both direction. This is crucial for * standalone multilayered security policies. Furthermore, * this helps avoid policy writers to shoot themselves in the * foot. */ if (unlikely(is_dom_check && no_more_access( layer_masks_parent1, layer_masks_child1, child1_is_directory, layer_masks_parent2, layer_masks_child2, child2_is_directory))) { /* * Now, downgrades the remaining checks from domain * handled accesses to requested accesses. */ is_dom_check = false; access_masked_parent1 = access_request_parent1; access_masked_parent2 = access_request_parent2; allowed_parent1 = allowed_parent1 || scope_to_request(access_masked_parent1, layer_masks_parent1); allowed_parent2 = allowed_parent2 || scope_to_request(access_masked_parent2, layer_masks_parent2); /* Stops when all accesses are granted. */ if (allowed_parent1 && allowed_parent2) break; } rule = find_rule(domain, walker_path.dentry); allowed_parent1 = allowed_parent1 || landlock_unmask_layers( rule, access_masked_parent1, layer_masks_parent1, ARRAY_SIZE(*layer_masks_parent1)); allowed_parent2 = allowed_parent2 || landlock_unmask_layers( rule, access_masked_parent2, layer_masks_parent2, ARRAY_SIZE(*layer_masks_parent2)); /* Stops when a rule from each layer grants access. */ if (allowed_parent1 && allowed_parent2) break; jump_up: if (walker_path.dentry == walker_path.mnt->mnt_root) { if (follow_up(&walker_path)) { /* Ignores hidden mount points. */ goto jump_up; } else { /* * Stops at the real root. Denies access * because not all layers have granted access. */ break; } } if (unlikely(IS_ROOT(walker_path.dentry))) { /* * Stops at disconnected root directories. Only allows * access to internal filesystems (e.g. nsfs, which is * reachable through /proc/<pid>/ns/<namespace>). */ if (walker_path.mnt->mnt_flags & MNT_INTERNAL) { allowed_parent1 = true; allowed_parent2 = true; } break; } parent_dentry = dget_parent(walker_path.dentry); dput(walker_path.dentry); walker_path.dentry = parent_dentry; } path_put(&walker_path); if (!allowed_parent1) { log_request_parent1->type = LANDLOCK_REQUEST_FS_ACCESS; log_request_parent1->audit.type = LSM_AUDIT_DATA_PATH; log_request_parent1->audit.u.path = *path; log_request_parent1->access = access_masked_parent1; log_request_parent1->layer_masks = layer_masks_parent1; log_request_parent1->layer_masks_size = ARRAY_SIZE(*layer_masks_parent1); } if (!allowed_parent2) { log_request_parent2->type = LANDLOCK_REQUEST_FS_ACCESS; log_request_parent2->audit.type = LSM_AUDIT_DATA_PATH; log_request_parent2->audit.u.path = *path; log_request_parent2->access = access_masked_parent2; log_request_parent2->layer_masks = layer_masks_parent2; log_request_parent2->layer_masks_size = ARRAY_SIZE(*layer_masks_parent2); } return allowed_parent1 && allowed_parent2; } static int current_check_access_path(const struct path *const path, access_mask_t access_request) { const struct access_masks masks = { .fs = access_request, }; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), masks, NULL); layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; struct landlock_request request = {}; if (!subject) return 0; access_request = landlock_init_layer_masks(subject->domain, access_request, &layer_masks, LANDLOCK_KEY_INODE); if (is_access_to_paths_allowed(subject->domain, path, access_request, &layer_masks, &request, NULL, 0, NULL, NULL, NULL)) return 0; landlock_log_denial(subject, &request); return -EACCES; } static __attribute_const__ access_mask_t get_mode_access(const umode_t mode) { switch (mode & S_IFMT) { case S_IFLNK: return LANDLOCK_ACCESS_FS_MAKE_SYM; case S_IFDIR: return LANDLOCK_ACCESS_FS_MAKE_DIR; case S_IFCHR: return LANDLOCK_ACCESS_FS_MAKE_CHAR; case S_IFBLK: return LANDLOCK_ACCESS_FS_MAKE_BLOCK; case S_IFIFO: return LANDLOCK_ACCESS_FS_MAKE_FIFO; case S_IFSOCK: return LANDLOCK_ACCESS_FS_MAKE_SOCK; case S_IFREG: case 0: /* A zero mode translates to S_IFREG. */ default: /* Treats weird files as regular files. */ return LANDLOCK_ACCESS_FS_MAKE_REG; } } static access_mask_t maybe_remove(const struct dentry *const dentry) { if (d_is_negative(dentry)) return 0; return d_is_dir(dentry) ? LANDLOCK_ACCESS_FS_REMOVE_DIR : LANDLOCK_ACCESS_FS_REMOVE_FILE; } /** * collect_domain_accesses - Walk through a file path and collect accesses * * @domain: Domain to check against. * @mnt_root: Last directory to check. * @dir: Directory to start the walk from. * @layer_masks_dom: Where to store the collected accesses. * * This helper is useful to begin a path walk from the @dir directory to a * @mnt_root directory used as a mount point. This mount point is the common * ancestor between the source and the destination of a renamed and linked * file. While walking from @dir to @mnt_root, we record all the domain's * allowed accesses in @layer_masks_dom. * * This is similar to is_access_to_paths_allowed() but much simpler because it * only handles walking on the same mount point and only checks one set of * accesses. * * Returns: * - true if all the domain access rights are allowed for @dir; * - false if the walk reached @mnt_root. */ static bool collect_domain_accesses( const struct landlock_ruleset *const domain, const struct dentry *const mnt_root, struct dentry *dir, layer_mask_t (*const layer_masks_dom)[LANDLOCK_NUM_ACCESS_FS]) { unsigned long access_dom; bool ret = false; if (WARN_ON_ONCE(!domain || !mnt_root || !dir || !layer_masks_dom)) return true; if (is_nouser_or_private(dir)) return true; access_dom = landlock_init_layer_masks(domain, LANDLOCK_MASK_ACCESS_FS, layer_masks_dom, LANDLOCK_KEY_INODE); dget(dir); while (true) { struct dentry *parent_dentry; /* Gets all layers allowing all domain accesses. */ if (landlock_unmask_layers(find_rule(domain, dir), access_dom, layer_masks_dom, ARRAY_SIZE(*layer_masks_dom))) { /* * Stops when all handled accesses are allowed by at * least one rule in each layer. */ ret = true; break; } /* We should not reach a root other than @mnt_root. */ if (dir == mnt_root || WARN_ON_ONCE(IS_ROOT(dir))) break; parent_dentry = dget_parent(dir); dput(dir); dir = parent_dentry; } dput(dir); return ret; } /** * current_check_refer_path - Check if a rename or link action is allowed * * @old_dentry: File or directory requested to be moved or linked. * @new_dir: Destination parent directory. * @new_dentry: Destination file or directory. * @removable: Sets to true if it is a rename operation. * @exchange: Sets to true if it is a rename operation with RENAME_EXCHANGE. * * Because of its unprivileged constraints, Landlock relies on file hierarchies * (and not only inodes) to tie access rights to files. Being able to link or * rename a file hierarchy brings some challenges. Indeed, moving or linking a * file (i.e. creating a new reference to an inode) can have an impact on the * actions allowed for a set of files if it would change its parent directory * (i.e. reparenting). * * To avoid trivial access right bypasses, Landlock first checks if the file or * directory requested to be moved would gain new access rights inherited from * its new hierarchy. Before returning any error, Landlock then checks that * the parent source hierarchy and the destination hierarchy would allow the * link or rename action. If it is not the case, an error with EACCES is * returned to inform user space that there is no way to remove or create the * requested source file type. If it should be allowed but the new inherited * access rights would be greater than the source access rights, then the * kernel returns an error with EXDEV. Prioritizing EACCES over EXDEV enables * user space to abort the whole operation if there is no way to do it, or to * manually copy the source to the destination if this remains allowed, e.g. * because file creation is allowed on the destination directory but not direct * linking. * * To achieve this goal, the kernel needs to compare two file hierarchies: the * one identifying the source file or directory (including itself), and the * destination one. This can be seen as a multilayer partial ordering problem. * The kernel walks through these paths and collects in a matrix the access * rights that are denied per layer. These matrices are then compared to see * if the destination one has more (or the same) restrictions as the source * one. If this is the case, the requested action will not return EXDEV, which * doesn't mean the action is allowed. The parent hierarchy of the source * (i.e. parent directory), and the destination hierarchy must also be checked * to verify that they explicitly allow such action (i.e. referencing, * creation and potentially removal rights). The kernel implementation is then * required to rely on potentially four matrices of access rights: one for the * source file or directory (i.e. the child), a potentially other one for the * other source/destination (in case of RENAME_EXCHANGE), one for the source * parent hierarchy and a last one for the destination hierarchy. These * ephemeral matrices take some space on the stack, which limits the number of * layers to a deemed reasonable number: 16. * * Returns: * - 0 if access is allowed; * - -EXDEV if @old_dentry would inherit new access rights from @new_dir; * - -EACCES if file removal or creation is denied. */ static int current_check_refer_path(struct dentry *const old_dentry, const struct path *const new_dir, struct dentry *const new_dentry, const bool removable, const bool exchange) { const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, NULL); bool allow_parent1, allow_parent2; access_mask_t access_request_parent1, access_request_parent2; struct path mnt_dir; struct dentry *old_parent; layer_mask_t layer_masks_parent1[LANDLOCK_NUM_ACCESS_FS] = {}, layer_masks_parent2[LANDLOCK_NUM_ACCESS_FS] = {}; struct landlock_request request1 = {}, request2 = {}; if (!subject) return 0; if (unlikely(d_is_negative(old_dentry))) return -ENOENT; if (exchange) { if (unlikely(d_is_negative(new_dentry))) return -ENOENT; access_request_parent1 = get_mode_access(d_backing_inode(new_dentry)->i_mode); } else { access_request_parent1 = 0; } access_request_parent2 = get_mode_access(d_backing_inode(old_dentry)->i_mode); if (removable) { access_request_parent1 |= maybe_remove(old_dentry); access_request_parent2 |= maybe_remove(new_dentry); } /* The mount points are the same for old and new paths, cf. EXDEV. */ if (old_dentry->d_parent == new_dir->dentry) { /* * The LANDLOCK_ACCESS_FS_REFER access right is not required * for same-directory referer (i.e. no reparenting). */ access_request_parent1 = landlock_init_layer_masks( subject->domain, access_request_parent1 | access_request_parent2, &layer_masks_parent1, LANDLOCK_KEY_INODE); if (is_access_to_paths_allowed(subject->domain, new_dir, access_request_parent1, &layer_masks_parent1, &request1, NULL, 0, NULL, NULL, NULL)) return 0; landlock_log_denial(subject, &request1); return -EACCES; } access_request_parent1 |= LANDLOCK_ACCESS_FS_REFER; access_request_parent2 |= LANDLOCK_ACCESS_FS_REFER; /* Saves the common mount point. */ mnt_dir.mnt = new_dir->mnt; mnt_dir.dentry = new_dir->mnt->mnt_root; /* * old_dentry may be the root of the common mount point and * !IS_ROOT(old_dentry) at the same time (e.g. with open_tree() and * OPEN_TREE_CLONE). We do not need to call dget(old_parent) because * we keep a reference to old_dentry. */ old_parent = (old_dentry == mnt_dir.dentry) ? old_dentry : old_dentry->d_parent; /* new_dir->dentry is equal to new_dentry->d_parent */ allow_parent1 = collect_domain_accesses(subject->domain, mnt_dir.dentry, old_parent, &layer_masks_parent1); allow_parent2 = collect_domain_accesses(subject->domain, mnt_dir.dentry, new_dir->dentry, &layer_masks_parent2); if (allow_parent1 && allow_parent2) return 0; /* * To be able to compare source and destination domain access rights, * take into account the @old_dentry access rights aggregated with its * parent access rights. This will be useful to compare with the * destination parent access rights. */ if (is_access_to_paths_allowed( subject->domain, &mnt_dir, access_request_parent1, &layer_masks_parent1, &request1, old_dentry, access_request_parent2, &layer_masks_parent2, &request2, exchange ? new_dentry : NULL)) return 0; if (request1.access) { request1.audit.u.path.dentry = old_parent; landlock_log_denial(subject, &request1); } if (request2.access) { request2.audit.u.path.dentry = new_dir->dentry; landlock_log_denial(subject, &request2); } /* * This prioritizes EACCES over EXDEV for all actions, including * renames with RENAME_EXCHANGE. */ if (likely(is_eacces(&layer_masks_parent1, access_request_parent1) || is_eacces(&layer_masks_parent2, access_request_parent2))) return -EACCES; /* * Gracefully forbids reparenting if the destination directory * hierarchy is not a superset of restrictions of the source directory * hierarchy, or if LANDLOCK_ACCESS_FS_REFER is not allowed by the * source or the destination. */ return -EXDEV; } /* Inode hooks */ static void hook_inode_free_security_rcu(void *inode_security) { struct landlock_inode_security *inode_sec; /* * All inodes must already have been untied from their object by * release_inode() or hook_sb_delete(). */ inode_sec = inode_security + landlock_blob_sizes.lbs_inode; WARN_ON_ONCE(inode_sec->object); } /* Super-block hooks */ /* * Release the inodes used in a security policy. * * Cf. fsnotify_unmount_inodes() and evict_inodes() */ static void hook_sb_delete(struct super_block *const sb) { struct inode *inode, *prev_inode = NULL; if (!landlock_initialized) return; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { struct landlock_object *object; /* Only handles referenced inodes. */ if (!icount_read(inode)) continue; /* * Protects against concurrent modification of inode (e.g. * from get_inode_object()). */ spin_lock(&inode->i_lock); /* * Checks I_FREEING and I_WILL_FREE to protect against a race * condition when release_inode() just called iput(), which * could lead to a NULL dereference of inode->security or a * second call to iput() for the same Landlock object. Also * checks I_NEW because such inode cannot be tied to an object. */ if (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW)) { spin_unlock(&inode->i_lock); continue; } rcu_read_lock(); object = rcu_dereference(landlock_inode(inode)->object); if (!object) { rcu_read_unlock(); spin_unlock(&inode->i_lock); continue; } /* Keeps a reference to this inode until the next loop walk. */ __iget(inode); spin_unlock(&inode->i_lock); /* * If there is no concurrent release_inode() ongoing, then we * are in charge of calling iput() on this inode, otherwise we * will just wait for it to finish. */ spin_lock(&object->lock); if (object->underobj == inode) { object->underobj = NULL; spin_unlock(&object->lock); rcu_read_unlock(); /* * Because object->underobj was not NULL, * release_inode() and get_inode_object() guarantee * that it is safe to reset * landlock_inode(inode)->object while it is not NULL. * It is therefore not necessary to lock inode->i_lock. */ rcu_assign_pointer(landlock_inode(inode)->object, NULL); /* * At this point, we own the ihold() reference that was * originally set up by get_inode_object() and the * __iget() reference that we just set in this loop * walk. Therefore the following call to iput() will * not sleep nor drop the inode because there is now at * least two references to it. */ iput(inode); } else { spin_unlock(&object->lock); rcu_read_unlock(); } if (prev_inode) { /* * At this point, we still own the __iget() reference * that we just set in this loop walk. Therefore we * can drop the list lock and know that the inode won't * disappear from under us until the next loop walk. */ spin_unlock(&sb->s_inode_list_lock); /* * We can now actually put the inode reference from the * previous loop walk, which is not needed anymore. */ iput(prev_inode); cond_resched(); spin_lock(&sb->s_inode_list_lock); } prev_inode = inode; } spin_unlock(&sb->s_inode_list_lock); /* Puts the inode reference from the last loop walk, if any. */ if (prev_inode) iput(prev_inode); /* Waits for pending iput() in release_inode(). */ wait_var_event(&landlock_superblock(sb)->inode_refs, !atomic_long_read(&landlock_superblock(sb)->inode_refs)); } static void log_fs_change_topology_path(const struct landlock_cred_security *const subject, size_t handle_layer, const struct path *const path) { landlock_log_denial(subject, &(struct landlock_request) { .type = LANDLOCK_REQUEST_FS_CHANGE_TOPOLOGY, .audit = { .type = LSM_AUDIT_DATA_PATH, .u.path = *path, }, .layer_plus_one = handle_layer + 1, }); } static void log_fs_change_topology_dentry( const struct landlock_cred_security *const subject, size_t handle_layer, struct dentry *const dentry) { landlock_log_denial(subject, &(struct landlock_request) { .type = LANDLOCK_REQUEST_FS_CHANGE_TOPOLOGY, .audit = { .type = LSM_AUDIT_DATA_DENTRY, .u.dentry = dentry, }, .layer_plus_one = handle_layer + 1, }); } /* * Because a Landlock security policy is defined according to the filesystem * topology (i.e. the mount namespace), changing it may grant access to files * not previously allowed. * * To make it simple, deny any filesystem topology modification by landlocked * processes. Non-landlocked processes may still change the namespace of a * landlocked process, but this kind of threat must be handled by a system-wide * access-control security policy. * * This could be lifted in the future if Landlock can safely handle mount * namespace updates requested by a landlocked process. Indeed, we could * update the current domain (which is currently read-only) by taking into * account the accesses of the source and the destination of a new mount point. * However, it would also require to make all the child domains dynamically * inherit these new constraints. Anyway, for backward compatibility reasons, * a dedicated user space option would be required (e.g. as a ruleset flag). */ static int hook_sb_mount(const char *const dev_name, const struct path *const path, const char *const type, const unsigned long flags, void *const data) { size_t handle_layer; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, &handle_layer); if (!subject) return 0; log_fs_change_topology_path(subject, handle_layer, path); return -EPERM; } static int hook_move_mount(const struct path *const from_path, const struct path *const to_path) { size_t handle_layer; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, &handle_layer); if (!subject) return 0; log_fs_change_topology_path(subject, handle_layer, to_path); return -EPERM; } /* * Removing a mount point may reveal a previously hidden file hierarchy, which * may then grant access to files, which may have previously been forbidden. */ static int hook_sb_umount(struct vfsmount *const mnt, const int flags) { size_t handle_layer; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, &handle_layer); if (!subject) return 0; log_fs_change_topology_dentry(subject, handle_layer, mnt->mnt_root); return -EPERM; } static int hook_sb_remount(struct super_block *const sb, void *const mnt_opts) { size_t handle_layer; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, &handle_layer); if (!subject) return 0; log_fs_change_topology_dentry(subject, handle_layer, sb->s_root); return -EPERM; } /* * pivot_root(2), like mount(2), changes the current mount namespace. It must * then be forbidden for a landlocked process. * * However, chroot(2) may be allowed because it only changes the relative root * directory of the current process. Moreover, it can be used to restrict the * view of the filesystem. */ static int hook_sb_pivotroot(const struct path *const old_path, const struct path *const new_path) { size_t handle_layer; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(current_cred(), any_fs, &handle_layer); if (!subject) return 0; log_fs_change_topology_path(subject, handle_layer, new_path); return -EPERM; } /* Path hooks */ static int hook_path_link(struct dentry *const old_dentry, const struct path *const new_dir, struct dentry *const new_dentry) { return current_check_refer_path(old_dentry, new_dir, new_dentry, false, false); } static int hook_path_rename(const struct path *const old_dir, struct dentry *const old_dentry, const struct path *const new_dir, struct dentry *const new_dentry, const unsigned int flags) { /* old_dir refers to old_dentry->d_parent and new_dir->mnt */ return current_check_refer_path(old_dentry, new_dir, new_dentry, true, !!(flags & RENAME_EXCHANGE)); } static int hook_path_mkdir(const struct path *const dir, struct dentry *const dentry, const umode_t mode) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_DIR); } static int hook_path_mknod(const struct path *const dir, struct dentry *const dentry, const umode_t mode, const unsigned int dev) { return current_check_access_path(dir, get_mode_access(mode)); } static int hook_path_symlink(const struct path *const dir, struct dentry *const dentry, const char *const old_name) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_MAKE_SYM); } static int hook_path_unlink(const struct path *const dir, struct dentry *const dentry) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_FILE); } static int hook_path_rmdir(const struct path *const dir, struct dentry *const dentry) { return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_DIR); } static int hook_path_truncate(const struct path *const path) { return current_check_access_path(path, LANDLOCK_ACCESS_FS_TRUNCATE); } /* File hooks */ /** * get_required_file_open_access - Get access needed to open a file * * @file: File being opened. * * Returns the access rights that are required for opening the given file, * depending on the file type and open mode. */ static access_mask_t get_required_file_open_access(const struct file *const file) { access_mask_t access = 0; if (file->f_mode & FMODE_READ) { /* A directory can only be opened in read mode. */ if (S_ISDIR(file_inode(file)->i_mode)) return LANDLOCK_ACCESS_FS_READ_DIR; access = LANDLOCK_ACCESS_FS_READ_FILE; } if (file->f_mode & FMODE_WRITE) access |= LANDLOCK_ACCESS_FS_WRITE_FILE; /* __FMODE_EXEC is indeed part of f_flags, not f_mode. */ if (file->f_flags & __FMODE_EXEC) access |= LANDLOCK_ACCESS_FS_EXECUTE; return access; } static int hook_file_alloc_security(struct file *const file) { /* * Grants all access rights, even if most of them are not checked later * on. It is more consistent. * * Notably, file descriptors for regular files can also be acquired * without going through the file_open hook, for example when using * memfd_create(2). */ landlock_file(file)->allowed_access = LANDLOCK_MASK_ACCESS_FS; return 0; } static bool is_device(const struct file *const file) { const struct inode *inode = file_inode(file); return S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode); } static int hook_file_open(struct file *const file) { layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; access_mask_t open_access_request, full_access_request, allowed_access, optional_access; const struct landlock_cred_security *const subject = landlock_get_applicable_subject(file->f_cred, any_fs, NULL); struct landlock_request request = {}; if (!subject) return 0; /* * Because a file may be opened with O_PATH, get_required_file_open_access() * may return 0. This case will be handled with a future Landlock * evolution. */ open_access_request = get_required_file_open_access(file); /* * We look up more access than what we immediately need for open(), so * that we can later authorize operations on opened files. */ optional_access = LANDLOCK_ACCESS_FS_TRUNCATE; if (is_device(file)) optional_access |= LANDLOCK_ACCESS_FS_IOCTL_DEV; full_access_request = open_access_request | optional_access; if (is_access_to_paths_allowed( subject->domain, &file->f_path, landlock_init_layer_masks(subject->domain, full_access_request, &layer_masks, LANDLOCK_KEY_INODE), &layer_masks, &request, NULL, 0, NULL, NULL, NULL)) { allowed_access = full_access_request; } else { unsigned long access_bit; const unsigned long access_req = full_access_request; /* * Calculate the actual allowed access rights from layer_masks. * Add each access right to allowed_access which has not been * vetoed by any layer. */ allowed_access = 0; for_each_set_bit(access_bit, &access_req, ARRAY_SIZE(layer_masks)) { if (!layer_masks[access_bit]) allowed_access |= BIT_ULL(access_bit); } } /* * For operations on already opened files (i.e. ftruncate()), it is the * access rights at the time of open() which decide whether the * operation is permitted. Therefore, we record the relevant subset of * file access rights in the opened struct file. */ landlock_file(file)->allowed_access = allowed_access; #ifdef CONFIG_AUDIT landlock_file(file)->deny_masks = landlock_get_deny_masks( _LANDLOCK_ACCESS_FS_OPTIONAL, optional_access, &layer_masks, ARRAY_SIZE(layer_masks)); #endif /* CONFIG_AUDIT */ if ((open_access_request & allowed_access) == open_access_request) return 0; /* Sets access to reflect the actual request. */ request.access = open_access_request; landlock_log_denial(subject, &request); return -EACCES; } static int hook_file_truncate(struct file *const file) { /* * Allows truncation if the truncate right was available at the time of * opening the file, to get a consistent access check as for read, write * and execute operations. * * Note: For checks done based on the file's Landlock allowed access, we * enforce them independently of whether the current thread is in a * Landlock domain, so that open files passed between independent * processes retain their behaviour. */ if (landlock_file(file)->allowed_access & LANDLOCK_ACCESS_FS_TRUNCATE) return 0; landlock_log_denial(landlock_cred(file->f_cred), &(struct landlock_request) { .type = LANDLOCK_REQUEST_FS_ACCESS, .audit = { .type = LSM_AUDIT_DATA_FILE, .u.file = file, }, .all_existing_optional_access = _LANDLOCK_ACCESS_FS_OPTIONAL, .access = LANDLOCK_ACCESS_FS_TRUNCATE, #ifdef CONFIG_AUDIT .deny_masks = landlock_file(file)->deny_masks, #endif /* CONFIG_AUDIT */ }); return -EACCES; } static int hook_file_ioctl_common(const struct file *const file, const unsigned int cmd, const bool is_compat) { access_mask_t allowed_access = landlock_file(file)->allowed_access; /* * It is the access rights at the time of opening the file which * determine whether IOCTL can be used on the opened file later. * * The access right is attached to the opened file in hook_file_open(). */ if (allowed_access & LANDLOCK_ACCESS_FS_IOCTL_DEV) return 0; if (!is_device(file)) return 0; if (unlikely(is_compat) ? is_masked_device_ioctl_compat(cmd) : is_masked_device_ioctl(cmd)) return 0; landlock_log_denial(landlock_cred(file->f_cred), &(struct landlock_request) { .type = LANDLOCK_REQUEST_FS_ACCESS, .audit = { .type = LSM_AUDIT_DATA_IOCTL_OP, .u.op = &(struct lsm_ioctlop_audit) { .path = file->f_path, .cmd = cmd, }, }, .all_existing_optional_access = _LANDLOCK_ACCESS_FS_OPTIONAL, .access = LANDLOCK_ACCESS_FS_IOCTL_DEV, #ifdef CONFIG_AUDIT .deny_masks = landlock_file(file)->deny_masks, #endif /* CONFIG_AUDIT */ }); return -EACCES; } static int hook_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return hook_file_ioctl_common(file, cmd, false); } static int hook_file_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return hook_file_ioctl_common(file, cmd, true); } /* * Always allow sending signals between threads of the same process. This * ensures consistency with hook_task_kill(). */ static bool control_current_fowner(struct fown_struct *const fown) { struct task_struct *p; /* * Lock already held by __f_setown(), see commit 26f204380a3c ("fs: Fix * file_set_fowner LSM hook inconsistencies"). */ lockdep_assert_held(&fown->lock); /* * Some callers (e.g. fcntl_dirnotify) may not be in an RCU read-side * critical section. */ guard(rcu)(); p = pid_task(fown->pid, fown->pid_type); if (!p) return true; return !same_thread_group(p, current); } static void hook_file_set_fowner(struct file *file) { struct landlock_ruleset *prev_dom; struct landlock_cred_security fown_subject = {}; size_t fown_layer = 0; if (control_current_fowner(file_f_owner(file))) { static const struct access_masks signal_scope = { .scope = LANDLOCK_SCOPE_SIGNAL, }; const struct landlock_cred_security *new_subject = landlock_get_applicable_subject( current_cred(), signal_scope, &fown_layer); if (new_subject) { landlock_get_ruleset(new_subject->domain); fown_subject = *new_subject; } } prev_dom = landlock_file(file)->fown_subject.domain; landlock_file(file)->fown_subject = fown_subject; #ifdef CONFIG_AUDIT landlock_file(file)->fown_layer = fown_layer; #endif /* CONFIG_AUDIT*/ /* May be called in an RCU read-side critical section. */ landlock_put_ruleset_deferred(prev_dom); } static void hook_file_free_security(struct file *file) { landlock_put_ruleset_deferred(landlock_file(file)->fown_subject.domain); } static struct security_hook_list landlock_hooks[] __ro_after_init = { LSM_HOOK_INIT(inode_free_security_rcu, hook_inode_free_security_rcu), LSM_HOOK_INIT(sb_delete, hook_sb_delete), LSM_HOOK_INIT(sb_mount, hook_sb_mount), LSM_HOOK_INIT(move_mount, hook_move_mount), LSM_HOOK_INIT(sb_umount, hook_sb_umount), LSM_HOOK_INIT(sb_remount, hook_sb_remount), LSM_HOOK_INIT(sb_pivotroot, hook_sb_pivotroot), LSM_HOOK_INIT(path_link, hook_path_link), LSM_HOOK_INIT(path_rename, hook_path_rename), LSM_HOOK_INIT(path_mkdir, hook_path_mkdir), LSM_HOOK_INIT(path_mknod, hook_path_mknod), LSM_HOOK_INIT(path_symlink, hook_path_symlink), LSM_HOOK_INIT(path_unlink, hook_path_unlink), LSM_HOOK_INIT(path_rmdir, hook_path_rmdir), LSM_HOOK_INIT(path_truncate, hook_path_truncate), LSM_HOOK_INIT(file_alloc_security, hook_file_alloc_security), LSM_HOOK_INIT(file_open, hook_file_open), LSM_HOOK_INIT(file_truncate, hook_file_truncate), LSM_HOOK_INIT(file_ioctl, hook_file_ioctl), LSM_HOOK_INIT(file_ioctl_compat, hook_file_ioctl_compat), LSM_HOOK_INIT(file_set_fowner, hook_file_set_fowner), LSM_HOOK_INIT(file_free_security, hook_file_free_security), }; __init void landlock_add_fs_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), &landlock_lsmid); } #ifdef CONFIG_SECURITY_LANDLOCK_KUNIT_TEST /* clang-format off */ static struct kunit_case test_cases[] = { KUNIT_CASE(test_no_more_access), KUNIT_CASE(test_scope_to_request_with_exec_none), KUNIT_CASE(test_scope_to_request_with_exec_some), KUNIT_CASE(test_scope_to_request_without_access), KUNIT_CASE(test_is_eacces_with_none), KUNIT_CASE(test_is_eacces_with_refer), KUNIT_CASE(test_is_eacces_with_write), {} }; /* clang-format on */ static struct kunit_suite test_suite = { .name = "landlock_fs", .test_cases = test_cases, }; kunit_test_suite(test_suite); #endif /* CONFIG_SECURITY_LANDLOCK_KUNIT_TEST */ |
| 1724 1725 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_IRQFLAGS_H #define __ASM_IRQFLAGS_H #include <asm/barrier.h> #include <asm/ptrace.h> #include <asm/sysreg.h> /* * Aarch64 has flags for masking: Debug, Asynchronous (serror), Interrupts and * FIQ exceptions, in the 'daif' register. We mask and unmask them in 'daif' * order: * Masking debug exceptions causes all other exceptions to be masked too/ * Masking SError masks IRQ/FIQ, but not debug exceptions. IRQ and FIQ are * always masked and unmasked together, and have no side effects for other * flags. Keeping to this order makes it easier for entry.S to know which * exceptions should be unmasked. */ static __always_inline void __daif_local_irq_enable(void) { barrier(); asm volatile("msr daifclr, #3"); barrier(); } static __always_inline void __pmr_local_irq_enable(void) { if (IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING)) { u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1); WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF); } barrier(); write_sysreg_s(GIC_PRIO_IRQON, SYS_ICC_PMR_EL1); pmr_sync(); barrier(); } static inline void arch_local_irq_enable(void) { if (system_uses_irq_prio_masking()) { __pmr_local_irq_enable(); } else { __daif_local_irq_enable(); } } static __always_inline void __daif_local_irq_disable(void) { barrier(); asm volatile("msr daifset, #3"); barrier(); } static __always_inline void __pmr_local_irq_disable(void) { if (IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING)) { u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1); WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF); } barrier(); write_sysreg_s(GIC_PRIO_IRQOFF, SYS_ICC_PMR_EL1); barrier(); } static inline void arch_local_irq_disable(void) { if (system_uses_irq_prio_masking()) { __pmr_local_irq_disable(); } else { __daif_local_irq_disable(); } } static __always_inline unsigned long __daif_local_save_flags(void) { return read_sysreg(daif); } static __always_inline unsigned long __pmr_local_save_flags(void) { return read_sysreg_s(SYS_ICC_PMR_EL1); } /* * Save the current interrupt enable state. */ static inline unsigned long arch_local_save_flags(void) { if (system_uses_irq_prio_masking()) { return __pmr_local_save_flags(); } else { return __daif_local_save_flags(); } } static __always_inline bool __daif_irqs_disabled_flags(unsigned long flags) { return flags & PSR_I_BIT; } static __always_inline bool __pmr_irqs_disabled_flags(unsigned long flags) { return flags != GIC_PRIO_IRQON; } static inline bool arch_irqs_disabled_flags(unsigned long flags) { if (system_uses_irq_prio_masking()) { return __pmr_irqs_disabled_flags(flags); } else { return __daif_irqs_disabled_flags(flags); } } static __always_inline bool __daif_irqs_disabled(void) { return __daif_irqs_disabled_flags(__daif_local_save_flags()); } static __always_inline bool __pmr_irqs_disabled(void) { return __pmr_irqs_disabled_flags(__pmr_local_save_flags()); } static inline bool arch_irqs_disabled(void) { if (system_uses_irq_prio_masking()) { return __pmr_irqs_disabled(); } else { return __daif_irqs_disabled(); } } static __always_inline unsigned long __daif_local_irq_save(void) { unsigned long flags = __daif_local_save_flags(); __daif_local_irq_disable(); return flags; } static __always_inline unsigned long __pmr_local_irq_save(void) { unsigned long flags = __pmr_local_save_flags(); /* * There are too many states with IRQs disabled, just keep the current * state if interrupts are already disabled/masked. */ if (!__pmr_irqs_disabled_flags(flags)) __pmr_local_irq_disable(); return flags; } static inline unsigned long arch_local_irq_save(void) { if (system_uses_irq_prio_masking()) { return __pmr_local_irq_save(); } else { return __daif_local_irq_save(); } } static __always_inline void __daif_local_irq_restore(unsigned long flags) { barrier(); write_sysreg(flags, daif); barrier(); } static __always_inline void __pmr_local_irq_restore(unsigned long flags) { barrier(); write_sysreg_s(flags, SYS_ICC_PMR_EL1); pmr_sync(); barrier(); } /* * restore saved IRQ state */ static inline void arch_local_irq_restore(unsigned long flags) { if (system_uses_irq_prio_masking()) { __pmr_local_irq_restore(flags); } else { __daif_local_irq_restore(flags); } } #endif /* __ASM_IRQFLAGS_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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/barrier.h * * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_BARRIER_H #define __ASM_BARRIER_H #ifndef __ASSEMBLY__ #include <linux/kasan-checks.h> #include <asm/alternative-macros.h> #define __nops(n) ".rept " #n "\nnop\n.endr\n" #define nops(n) asm volatile(__nops(n)) #define sev() asm volatile("sev" : : : "memory") #define wfe() asm volatile("wfe" : : : "memory") #define wfet(val) asm volatile("msr s0_3_c1_c0_0, %0" \ : : "r" (val) : "memory") #define wfi() asm volatile("wfi" : : : "memory") #define wfit(val) asm volatile("msr s0_3_c1_c0_1, %0" \ : : "r" (val) : "memory") #define isb() asm volatile("isb" : : : "memory") #define dmb(opt) asm volatile("dmb " #opt : : : "memory") #define dsb(opt) asm volatile("dsb " #opt : : : "memory") #define psb_csync() asm volatile("hint #17" : : : "memory") #define __tsb_csync() asm volatile("hint #18" : : : "memory") #define csdb() asm volatile("hint #20" : : : "memory") /* * Data Gathering Hint: * This instruction prevents merging memory accesses with Normal-NC or * Device-GRE attributes before the hint instruction with any memory accesses * appearing after the hint instruction. */ #define dgh() asm volatile("hint #6" : : : "memory") #define spec_bar() asm volatile(ALTERNATIVE("dsb nsh\nisb\n", \ SB_BARRIER_INSN"nop\n", \ ARM64_HAS_SB)) #define gsb_ack() asm volatile(GSB_ACK_BARRIER_INSN : : : "memory") #define gsb_sys() asm volatile(GSB_SYS_BARRIER_INSN : : : "memory") #ifdef CONFIG_ARM64_PSEUDO_NMI #define pmr_sync() \ do { \ asm volatile( \ ALTERNATIVE_CB("dsb sy", \ ARM64_HAS_GIC_PRIO_RELAXED_SYNC, \ alt_cb_patch_nops) \ ); \ } while(0) #else #define pmr_sync() do {} while (0) #endif #define __mb() dsb(sy) #define __rmb() dsb(ld) #define __wmb() dsb(st) #define __dma_mb() dmb(osh) #define __dma_rmb() dmb(oshld) #define __dma_wmb() dmb(oshst) #define io_stop_wc() dgh() #define tsb_csync() \ do { \ /* \ * CPUs affected by Arm Erratum 2054223 or 2067961 needs \ * another TSB to ensure the trace is flushed. The barriers \ * don't have to be strictly back to back, as long as the \ * CPU is in trace prohibited state. \ */ \ if (cpus_have_final_cap(ARM64_WORKAROUND_TSB_FLUSH_FAILURE)) \ __tsb_csync(); \ __tsb_csync(); \ } while (0) /* * Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz * and 0 otherwise. */ #define array_index_mask_nospec array_index_mask_nospec static inline unsigned long array_index_mask_nospec(unsigned long idx, unsigned long sz) { unsigned long mask; asm volatile( " cmp %1, %2\n" " sbc %0, xzr, xzr\n" : "=r" (mask) : "r" (idx), "Ir" (sz) : "cc"); csdb(); return mask; } /* * Ensure that reads of the counter are treated the same as memory reads * for the purposes of ordering by subsequent memory barriers. * * This insanity brought to you by speculative system register reads, * out-of-order memory accesses, sequence locks and Thomas Gleixner. * * https://lore.kernel.org/r/alpine.DEB.2.21.1902081950260.1662@nanos.tec.linutronix.de/ */ #define arch_counter_enforce_ordering(val) do { \ u64 tmp, _val = (val); \ \ asm volatile( \ " eor %0, %1, %1\n" \ " add %0, sp, %0\n" \ " ldr xzr, [%0]" \ : "=r" (tmp) : "r" (_val)); \ } while (0) #define __smp_mb() dmb(ish) #define __smp_rmb() dmb(ishld) #define __smp_wmb() dmb(ishst) #define __smp_store_release(p, v) \ do { \ typeof(p) __p = (p); \ union { __unqual_scalar_typeof(*p) __val; char __c[1]; } __u = \ { .__val = (__force __unqual_scalar_typeof(*p)) (v) }; \ compiletime_assert_atomic_type(*p); \ kasan_check_write(__p, sizeof(*p)); \ switch (sizeof(*p)) { \ case 1: \ asm volatile ("stlrb %w1, %0" \ : "=Q" (*__p) \ : "rZ" (*(__u8 *)__u.__c) \ : "memory"); \ break; \ case 2: \ asm volatile ("stlrh %w1, %0" \ : "=Q" (*__p) \ : "rZ" (*(__u16 *)__u.__c) \ : "memory"); \ break; \ case 4: \ asm volatile ("stlr %w1, %0" \ : "=Q" (*__p) \ : "rZ" (*(__u32 *)__u.__c) \ : "memory"); \ break; \ case 8: \ asm volatile ("stlr %x1, %0" \ : "=Q" (*__p) \ : "rZ" (*(__u64 *)__u.__c) \ : "memory"); \ break; \ } \ } while (0) #define __smp_load_acquire(p) \ ({ \ union { __unqual_scalar_typeof(*p) __val; char __c[1]; } __u; \ typeof(p) __p = (p); \ compiletime_assert_atomic_type(*p); \ kasan_check_read(__p, sizeof(*p)); \ switch (sizeof(*p)) { \ case 1: \ asm volatile ("ldarb %w0, %1" \ : "=r" (*(__u8 *)__u.__c) \ : "Q" (*__p) : "memory"); \ break; \ case 2: \ asm volatile ("ldarh %w0, %1" \ : "=r" (*(__u16 *)__u.__c) \ : "Q" (*__p) : "memory"); \ break; \ case 4: \ asm volatile ("ldar %w0, %1" \ : "=r" (*(__u32 *)__u.__c) \ : "Q" (*__p) : "memory"); \ break; \ case 8: \ asm volatile ("ldar %0, %1" \ : "=r" (*(__u64 *)__u.__c) \ : "Q" (*__p) : "memory"); \ break; \ } \ (typeof(*p))__u.__val; \ }) #define smp_cond_load_relaxed(ptr, cond_expr) \ ({ \ typeof(ptr) __PTR = (ptr); \ __unqual_scalar_typeof(*ptr) VAL; \ for (;;) { \ VAL = READ_ONCE(*__PTR); \ if (cond_expr) \ break; \ __cmpwait_relaxed(__PTR, VAL); \ } \ (typeof(*ptr))VAL; \ }) #define smp_cond_load_acquire(ptr, cond_expr) \ ({ \ typeof(ptr) __PTR = (ptr); \ __unqual_scalar_typeof(*ptr) VAL; \ for (;;) { \ VAL = smp_load_acquire(__PTR); \ if (cond_expr) \ break; \ __cmpwait_relaxed(__PTR, VAL); \ } \ (typeof(*ptr))VAL; \ }) #include <asm-generic/barrier.h> #endif /* __ASSEMBLY__ */ #endif /* __ASM_BARRIER_H */ |
| 203 767 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Security-Enhanced Linux (SELinux) security module * * This file contains the SELinux security data structures for kernel objects. * * Author(s): Stephen Smalley, <stephen.smalley.work@gmail.com> * Chris Vance, <cvance@nai.com> * Wayne Salamon, <wsalamon@nai.com> * James Morris <jmorris@redhat.com> * * Copyright (C) 2001,2002 Networks Associates Technology, Inc. * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> * Copyright (C) 2016 Mellanox Technologies */ #ifndef _SELINUX_OBJSEC_H_ #define _SELINUX_OBJSEC_H_ #include <linux/list.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/binfmts.h> #include <linux/in.h> #include <linux/spinlock.h> #include <linux/lsm_hooks.h> #include <linux/msg.h> #include <net/net_namespace.h> #include <linux/bpf.h> #include "flask.h" #include "avc.h" struct avdc_entry { u32 isid; /* inode SID */ u32 allowed; /* allowed permission bitmask */ u32 audited; /* audited permission bitmask */ bool permissive; /* AVC permissive flag */ }; struct task_security_struct { u32 osid; /* SID prior to last execve */ u32 sid; /* current SID */ u32 exec_sid; /* exec SID */ u32 create_sid; /* fscreate SID */ u32 keycreate_sid; /* keycreate SID */ u32 sockcreate_sid; /* fscreate SID */ #define TSEC_AVDC_DIR_SIZE (1 << 2) struct { u32 sid; /* current SID for cached entries */ u32 seqno; /* AVC sequence number */ unsigned int dir_spot; /* dir cache index to check first */ struct avdc_entry dir[TSEC_AVDC_DIR_SIZE]; /* dir entries */ bool permissive_neveraudit; /* permissive and neveraudit */ } avdcache; } __randomize_layout; static inline bool task_avdcache_permnoaudit(struct task_security_struct *tsec) { return (tsec->avdcache.permissive_neveraudit && tsec->sid == tsec->avdcache.sid && tsec->avdcache.seqno == avc_policy_seqno()); } enum label_initialized { LABEL_INVALID, /* invalid or not initialized */ LABEL_INITIALIZED, /* initialized */ LABEL_PENDING }; struct inode_security_struct { struct inode *inode; /* back pointer to inode object */ struct list_head list; /* list of inode_security_struct */ u32 task_sid; /* SID of creating task */ u32 sid; /* SID of this object */ u16 sclass; /* security class of this object */ unsigned char initialized; /* initialization flag */ spinlock_t lock; }; struct file_security_struct { u32 sid; /* SID of open file description */ u32 fown_sid; /* SID of file owner (for SIGIO) */ u32 isid; /* SID of inode at the time of file open */ u32 pseqno; /* Policy seqno at the time of file open */ }; struct superblock_security_struct { u32 sid; /* SID of file system superblock */ u32 def_sid; /* default SID for labeling */ u32 mntpoint_sid; /* SECURITY_FS_USE_MNTPOINT context for files */ unsigned short behavior; /* labeling behavior */ unsigned short flags; /* which mount options were specified */ struct mutex lock; struct list_head isec_head; spinlock_t isec_lock; }; struct msg_security_struct { u32 sid; /* SID of message */ }; struct ipc_security_struct { u16 sclass; /* security class of this object */ u32 sid; /* SID of IPC resource */ }; struct netif_security_struct { const struct net *ns; /* network namespace */ int ifindex; /* device index */ u32 sid; /* SID for this interface */ }; struct netnode_security_struct { union { __be32 ipv4; /* IPv4 node address */ struct in6_addr ipv6; /* IPv6 node address */ } addr; u32 sid; /* SID for this node */ u16 family; /* address family */ }; struct netport_security_struct { u32 sid; /* SID for this node */ u16 port; /* port number */ u8 protocol; /* transport protocol */ }; struct sk_security_struct { #ifdef CONFIG_NETLABEL enum { /* NetLabel state */ NLBL_UNSET = 0, NLBL_REQUIRE, NLBL_LABELED, NLBL_REQSKB, NLBL_CONNLABELED, } nlbl_state; struct netlbl_lsm_secattr *nlbl_secattr; /* NetLabel sec attributes */ #endif u32 sid; /* SID of this object */ u32 peer_sid; /* SID of peer */ u16 sclass; /* sock security class */ enum { /* SCTP association state */ SCTP_ASSOC_UNSET = 0, SCTP_ASSOC_SET, } sctp_assoc_state; }; struct tun_security_struct { u32 sid; /* SID for the tun device sockets */ }; struct key_security_struct { u32 sid; /* SID of key */ }; struct ib_security_struct { u32 sid; /* SID of the queue pair or MAD agent */ }; struct pkey_security_struct { u64 subnet_prefix; /* Port subnet prefix */ u16 pkey; /* PKey number */ u32 sid; /* SID of pkey */ }; struct bpf_security_struct { u32 sid; /* SID of bpf obj creator */ }; struct perf_event_security_struct { u32 sid; /* SID of perf_event obj creator */ }; extern struct lsm_blob_sizes selinux_blob_sizes; static inline struct task_security_struct *selinux_cred(const struct cred *cred) { return cred->security + selinux_blob_sizes.lbs_cred; } static inline struct file_security_struct *selinux_file(const struct file *file) { return file->f_security + selinux_blob_sizes.lbs_file; } static inline struct inode_security_struct * selinux_inode(const struct inode *inode) { if (unlikely(!inode->i_security)) return NULL; return inode->i_security + selinux_blob_sizes.lbs_inode; } static inline struct msg_security_struct * selinux_msg_msg(const struct msg_msg *msg_msg) { return msg_msg->security + selinux_blob_sizes.lbs_msg_msg; } static inline struct ipc_security_struct * selinux_ipc(const struct kern_ipc_perm *ipc) { return ipc->security + selinux_blob_sizes.lbs_ipc; } /* * get the subjective security ID of the current task */ static inline u32 current_sid(void) { const struct task_security_struct *tsec = selinux_cred(current_cred()); return tsec->sid; } static inline struct superblock_security_struct * selinux_superblock(const struct super_block *superblock) { return superblock->s_security + selinux_blob_sizes.lbs_superblock; } #ifdef CONFIG_KEYS static inline struct key_security_struct *selinux_key(const struct key *key) { return key->security + selinux_blob_sizes.lbs_key; } #endif /* CONFIG_KEYS */ static inline struct sk_security_struct *selinux_sock(const struct sock *sock) { return sock->sk_security + selinux_blob_sizes.lbs_sock; } static inline struct tun_security_struct *selinux_tun_dev(void *security) { return security + selinux_blob_sizes.lbs_tun_dev; } static inline struct ib_security_struct *selinux_ib(void *ib_sec) { return ib_sec + selinux_blob_sizes.lbs_ib; } static inline struct perf_event_security_struct * selinux_perf_event(void *perf_event) { return perf_event + selinux_blob_sizes.lbs_perf_event; } #ifdef CONFIG_BPF_SYSCALL static inline struct bpf_security_struct * selinux_bpf_map_security(struct bpf_map *map) { return map->security + selinux_blob_sizes.lbs_bpf_map; } static inline struct bpf_security_struct * selinux_bpf_prog_security(struct bpf_prog *prog) { return prog->aux->security + selinux_blob_sizes.lbs_bpf_prog; } static inline struct bpf_security_struct * selinux_bpf_token_security(struct bpf_token *token) { return token->security + selinux_blob_sizes.lbs_bpf_token; } #endif /* CONFIG_BPF_SYSCALL */ #endif /* _SELINUX_OBJSEC_H_ */ |
| 1455 1458 1451 1454 1457 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/domain.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/binfmts.h> #include <linux/slab.h> #include <linux/rculist.h> /* Variables definitions.*/ /* The initial domain. */ struct tomoyo_domain_info tomoyo_kernel_domain; /** * tomoyo_update_policy - Update an entry for exception policy. * * @new_entry: Pointer to "struct tomoyo_acl_info". * @size: Size of @new_entry in bytes. * @param: Pointer to "struct tomoyo_acl_param". * @check_duplicate: Callback function to find duplicated entry. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_update_policy(struct tomoyo_acl_head *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate)(const struct tomoyo_acl_head *, const struct tomoyo_acl_head *)) { int error = param->is_delete ? -ENOENT : -ENOMEM; struct tomoyo_acl_head *entry; struct list_head *list = param->list; if (mutex_lock_interruptible(&tomoyo_policy_lock)) return -ENOMEM; list_for_each_entry_rcu(entry, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!check_duplicate(entry, new_entry)) continue; entry->is_deleted = param->is_delete; error = 0; break; } if (error && !param->is_delete) { entry = tomoyo_commit_ok(new_entry, size); if (entry) { list_add_tail_rcu(&entry->list, list); error = 0; } } mutex_unlock(&tomoyo_policy_lock); return error; } /** * tomoyo_same_acl_head - Check for duplicated "struct tomoyo_acl_info" entry. * * @a: Pointer to "struct tomoyo_acl_info". * @b: Pointer to "struct tomoyo_acl_info". * * Returns true if @a == @b, false otherwise. */ static inline bool tomoyo_same_acl_head(const struct tomoyo_acl_info *a, const struct tomoyo_acl_info *b) { return a->type == b->type && a->cond == b->cond; } /** * tomoyo_update_domain - Update an entry for domain policy. * * @new_entry: Pointer to "struct tomoyo_acl_info". * @size: Size of @new_entry in bytes. * @param: Pointer to "struct tomoyo_acl_param". * @check_duplicate: Callback function to find duplicated entry. * @merge_duplicate: Callback function to merge duplicated entry. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_update_domain(struct tomoyo_acl_info *new_entry, const int size, struct tomoyo_acl_param *param, bool (*check_duplicate)(const struct tomoyo_acl_info *, const struct tomoyo_acl_info *), bool (*merge_duplicate)(struct tomoyo_acl_info *, struct tomoyo_acl_info *, const bool)) { const bool is_delete = param->is_delete; int error = is_delete ? -ENOENT : -ENOMEM; struct tomoyo_acl_info *entry; struct list_head * const list = param->list; if (param->data[0]) { new_entry->cond = tomoyo_get_condition(param); if (!new_entry->cond) return -EINVAL; /* * Domain transition preference is allowed for only * "file execute" entries. */ if (new_entry->cond->transit && !(new_entry->type == TOMOYO_TYPE_PATH_ACL && container_of(new_entry, struct tomoyo_path_acl, head) ->perm == 1 << TOMOYO_TYPE_EXECUTE)) goto out; } if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; list_for_each_entry_rcu(entry, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (entry->is_deleted == TOMOYO_GC_IN_PROGRESS) continue; if (!tomoyo_same_acl_head(entry, new_entry) || !check_duplicate(entry, new_entry)) continue; if (merge_duplicate) entry->is_deleted = merge_duplicate(entry, new_entry, is_delete); else entry->is_deleted = is_delete; error = 0; break; } if (error && !is_delete) { entry = tomoyo_commit_ok(new_entry, size); if (entry) { list_add_tail_rcu(&entry->list, list); error = 0; } } mutex_unlock(&tomoyo_policy_lock); out: tomoyo_put_condition(new_entry->cond); return error; } /** * tomoyo_check_acl - Do permission check. * * @r: Pointer to "struct tomoyo_request_info". * @check_entry: Callback function to check type specific parameters. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ void tomoyo_check_acl(struct tomoyo_request_info *r, bool (*check_entry)(struct tomoyo_request_info *, const struct tomoyo_acl_info *)) { const struct tomoyo_domain_info *domain = r->domain; struct tomoyo_acl_info *ptr; const struct list_head *list = &domain->acl_info_list; u16 i = 0; retry: list_for_each_entry_rcu(ptr, list, list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->is_deleted || ptr->type != r->param_type) continue; if (!check_entry(r, ptr)) continue; if (!tomoyo_condition(r, ptr->cond)) continue; r->matched_acl = ptr; r->granted = true; return; } for (; i < TOMOYO_MAX_ACL_GROUPS; i++) { if (!test_bit(i, domain->group)) continue; list = &domain->ns->acl_group[i++]; goto retry; } r->granted = false; } /* The list for "struct tomoyo_domain_info". */ LIST_HEAD(tomoyo_domain_list); /** * tomoyo_last_word - Get last component of a domainname. * * @name: Domainname to check. * * Returns the last word of @domainname. */ static const char *tomoyo_last_word(const char *name) { const char *cp = strrchr(name, ' '); if (cp) return cp + 1; return name; } /** * tomoyo_same_transition_control - Check for duplicated "struct tomoyo_transition_control" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_transition_control(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { const struct tomoyo_transition_control *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_transition_control *p2 = container_of(b, typeof(*p2), head); return p1->type == p2->type && p1->is_last_name == p2->is_last_name && p1->domainname == p2->domainname && p1->program == p2->program; } /** * tomoyo_write_transition_control - Write "struct tomoyo_transition_control" list. * * @param: Pointer to "struct tomoyo_acl_param". * @type: Type of this entry. * * Returns 0 on success, negative value otherwise. */ int tomoyo_write_transition_control(struct tomoyo_acl_param *param, const u8 type) { struct tomoyo_transition_control e = { .type = type }; int error = param->is_delete ? -ENOENT : -ENOMEM; char *program = param->data; char *domainname = strstr(program, " from "); if (domainname) { *domainname = '\0'; domainname += 6; } else if (type == TOMOYO_TRANSITION_CONTROL_NO_KEEP || type == TOMOYO_TRANSITION_CONTROL_KEEP) { domainname = program; program = NULL; } if (program && strcmp(program, "any")) { if (!tomoyo_correct_path(program)) return -EINVAL; e.program = tomoyo_get_name(program); if (!e.program) goto out; } if (domainname && strcmp(domainname, "any")) { if (!tomoyo_correct_domain(domainname)) { if (!tomoyo_correct_path(domainname)) goto out; e.is_last_name = true; } e.domainname = tomoyo_get_name(domainname); if (!e.domainname) goto out; } param->list = ¶m->ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL]; error = tomoyo_update_policy(&e.head, sizeof(e), param, tomoyo_same_transition_control); out: tomoyo_put_name(e.domainname); tomoyo_put_name(e.program); return error; } /** * tomoyo_scan_transition - Try to find specific domain transition type. * * @list: Pointer to "struct list_head". * @domainname: The name of current domain. * @program: The name of requested program. * @last_name: The last component of @domainname. * @type: One of values in "enum tomoyo_transition_type". * * Returns true if found one, false otherwise. * * Caller holds tomoyo_read_lock(). */ static inline bool tomoyo_scan_transition (const struct list_head *list, const struct tomoyo_path_info *domainname, const struct tomoyo_path_info *program, const char *last_name, const enum tomoyo_transition_type type) { const struct tomoyo_transition_control *ptr; list_for_each_entry_rcu(ptr, list, head.list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || ptr->type != type) continue; if (ptr->domainname) { if (!ptr->is_last_name) { if (ptr->domainname != domainname) continue; } else { /* * Use direct strcmp() since this is * unlikely used. */ if (strcmp(ptr->domainname->name, last_name)) continue; } } if (ptr->program && tomoyo_pathcmp(ptr->program, program)) continue; return true; } return false; } /** * tomoyo_transition_type - Get domain transition type. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @domainname: The name of current domain. * @program: The name of requested program. * * Returns TOMOYO_TRANSITION_CONTROL_TRANSIT if executing @program causes * domain transition across namespaces, TOMOYO_TRANSITION_CONTROL_INITIALIZE if * executing @program reinitializes domain transition within that namespace, * TOMOYO_TRANSITION_CONTROL_KEEP if executing @program stays at @domainname , * others otherwise. * * Caller holds tomoyo_read_lock(). */ static enum tomoyo_transition_type tomoyo_transition_type (const struct tomoyo_policy_namespace *ns, const struct tomoyo_path_info *domainname, const struct tomoyo_path_info *program) { const char *last_name = tomoyo_last_word(domainname->name); enum tomoyo_transition_type type = TOMOYO_TRANSITION_CONTROL_NO_RESET; while (type < TOMOYO_MAX_TRANSITION_TYPE) { const struct list_head * const list = &ns->policy_list[TOMOYO_ID_TRANSITION_CONTROL]; if (!tomoyo_scan_transition(list, domainname, program, last_name, type)) { type++; continue; } if (type != TOMOYO_TRANSITION_CONTROL_NO_RESET && type != TOMOYO_TRANSITION_CONTROL_NO_INITIALIZE) break; /* * Do not check for reset_domain if no_reset_domain matched. * Do not check for initialize_domain if no_initialize_domain * matched. */ type++; type++; } return type; } /** * tomoyo_same_aggregator - Check for duplicated "struct tomoyo_aggregator" entry. * * @a: Pointer to "struct tomoyo_acl_head". * @b: Pointer to "struct tomoyo_acl_head". * * Returns true if @a == @b, false otherwise. */ static bool tomoyo_same_aggregator(const struct tomoyo_acl_head *a, const struct tomoyo_acl_head *b) { const struct tomoyo_aggregator *p1 = container_of(a, typeof(*p1), head); const struct tomoyo_aggregator *p2 = container_of(b, typeof(*p2), head); return p1->original_name == p2->original_name && p1->aggregated_name == p2->aggregated_name; } /** * tomoyo_write_aggregator - Write "struct tomoyo_aggregator" list. * * @param: Pointer to "struct tomoyo_acl_param". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_write_aggregator(struct tomoyo_acl_param *param) { struct tomoyo_aggregator e = { }; int error = param->is_delete ? -ENOENT : -ENOMEM; const char *original_name = tomoyo_read_token(param); const char *aggregated_name = tomoyo_read_token(param); if (!tomoyo_correct_word(original_name) || !tomoyo_correct_path(aggregated_name)) return -EINVAL; e.original_name = tomoyo_get_name(original_name); e.aggregated_name = tomoyo_get_name(aggregated_name); if (!e.original_name || !e.aggregated_name || e.aggregated_name->is_patterned) /* No patterns allowed. */ goto out; param->list = ¶m->ns->policy_list[TOMOYO_ID_AGGREGATOR]; error = tomoyo_update_policy(&e.head, sizeof(e), param, tomoyo_same_aggregator); out: tomoyo_put_name(e.original_name); tomoyo_put_name(e.aggregated_name); return error; } /** * tomoyo_find_namespace - Find specified namespace. * * @name: Name of namespace to find. * @len: Length of @name. * * Returns pointer to "struct tomoyo_policy_namespace" if found, * NULL otherwise. * * Caller holds tomoyo_read_lock(). */ static struct tomoyo_policy_namespace *tomoyo_find_namespace (const char *name, const unsigned int len) { struct tomoyo_policy_namespace *ns; list_for_each_entry(ns, &tomoyo_namespace_list, namespace_list) { if (strncmp(name, ns->name, len) || (name[len] && name[len] != ' ')) continue; return ns; } return NULL; } /** * tomoyo_assign_namespace - Create a new namespace. * * @domainname: Name of namespace to create. * * Returns pointer to "struct tomoyo_policy_namespace" on success, * NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_policy_namespace *tomoyo_assign_namespace(const char *domainname) { struct tomoyo_policy_namespace *ptr; struct tomoyo_policy_namespace *entry; const char *cp = domainname; unsigned int len = 0; while (*cp && *cp++ != ' ') len++; ptr = tomoyo_find_namespace(domainname, len); if (ptr) return ptr; if (len >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_domain_def(domainname)) return NULL; entry = kzalloc(sizeof(*entry) + len + 1, GFP_NOFS | __GFP_NOWARN); if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; ptr = tomoyo_find_namespace(domainname, len); if (!ptr && tomoyo_memory_ok(entry)) { char *name = (char *) (entry + 1); ptr = entry; memmove(name, domainname, len); name[len] = '\0'; entry->name = name; tomoyo_init_policy_namespace(entry); entry = NULL; } mutex_unlock(&tomoyo_policy_lock); out: kfree(entry); return ptr; } /** * tomoyo_namespace_jump - Check for namespace jump. * * @domainname: Name of domain. * * Returns true if namespace differs, false otherwise. */ static bool tomoyo_namespace_jump(const char *domainname) { const char *namespace = tomoyo_current_namespace()->name; const int len = strlen(namespace); return strncmp(domainname, namespace, len) || (domainname[len] && domainname[len] != ' '); } /** * tomoyo_assign_domain - Create a domain or a namespace. * * @domainname: The name of domain. * @transit: True if transit to domain found or created. * * Returns pointer to "struct tomoyo_domain_info" on success, NULL otherwise. * * Caller holds tomoyo_read_lock(). */ struct tomoyo_domain_info *tomoyo_assign_domain(const char *domainname, const bool transit) { struct tomoyo_domain_info e = { }; struct tomoyo_domain_info *entry = tomoyo_find_domain(domainname); bool created = false; if (entry) { if (transit) { /* * Since namespace is created at runtime, profiles may * not be created by the moment the process transits to * that domain. Do not perform domain transition if * profile for that domain is not yet created. */ if (tomoyo_policy_loaded && !entry->ns->profile_ptr[entry->profile]) return NULL; } return entry; } /* Requested domain does not exist. */ /* Don't create requested domain if domainname is invalid. */ if (strlen(domainname) >= TOMOYO_EXEC_TMPSIZE - 10 || !tomoyo_correct_domain(domainname)) return NULL; /* * Since definition of profiles and acl_groups may differ across * namespaces, do not inherit "use_profile" and "use_group" settings * by automatically creating requested domain upon domain transition. */ if (transit && tomoyo_namespace_jump(domainname)) return NULL; e.ns = tomoyo_assign_namespace(domainname); if (!e.ns) return NULL; /* * "use_profile" and "use_group" settings for automatically created * domains are inherited from current domain. These are 0 for manually * created domains. */ if (transit) { const struct tomoyo_domain_info *domain = tomoyo_domain(); e.profile = domain->profile; memcpy(e.group, domain->group, sizeof(e.group)); } e.domainname = tomoyo_get_name(domainname); if (!e.domainname) return NULL; if (mutex_lock_interruptible(&tomoyo_policy_lock)) goto out; entry = tomoyo_find_domain(domainname); if (!entry) { entry = tomoyo_commit_ok(&e, sizeof(e)); if (entry) { INIT_LIST_HEAD(&entry->acl_info_list); list_add_tail_rcu(&entry->list, &tomoyo_domain_list); created = true; } } mutex_unlock(&tomoyo_policy_lock); out: tomoyo_put_name(e.domainname); if (entry && transit) { if (created) { struct tomoyo_request_info r; int i; tomoyo_init_request_info(&r, entry, TOMOYO_MAC_FILE_EXECUTE); r.granted = false; tomoyo_write_log(&r, "use_profile %u\n", entry->profile); for (i = 0; i < TOMOYO_MAX_ACL_GROUPS; i++) if (test_bit(i, entry->group)) tomoyo_write_log(&r, "use_group %u\n", i); tomoyo_update_stat(TOMOYO_STAT_POLICY_UPDATES); } } return entry; } /** * tomoyo_environ - Check permission for environment variable names. * * @ee: Pointer to "struct tomoyo_execve". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_environ(struct tomoyo_execve *ee) { struct tomoyo_request_info *r = &ee->r; struct linux_binprm *bprm = ee->bprm; /* env_page.data is allocated by tomoyo_dump_page(). */ struct tomoyo_page_dump env_page = { }; char *arg_ptr; /* Size is TOMOYO_EXEC_TMPSIZE bytes */ int arg_len = 0; unsigned long pos = bprm->p; int offset = pos % PAGE_SIZE; int argv_count = bprm->argc; int envp_count = bprm->envc; int error = -ENOMEM; ee->r.type = TOMOYO_MAC_ENVIRON; ee->r.profile = r->domain->profile; ee->r.mode = tomoyo_get_mode(r->domain->ns, ee->r.profile, TOMOYO_MAC_ENVIRON); if (!r->mode || !envp_count) return 0; arg_ptr = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); if (!arg_ptr) goto out; while (error == -ENOMEM) { if (!tomoyo_dump_page(bprm, pos, &env_page)) goto out; pos += PAGE_SIZE - offset; /* Read. */ while (argv_count && offset < PAGE_SIZE) { if (!env_page.data[offset++]) argv_count--; } if (argv_count) { offset = 0; continue; } while (offset < PAGE_SIZE) { const unsigned char c = env_page.data[offset++]; if (c && arg_len < TOMOYO_EXEC_TMPSIZE - 10) { if (c == '=') { arg_ptr[arg_len++] = '\0'; } else 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; if (tomoyo_env_perm(r, arg_ptr)) { error = -EPERM; break; } if (!--envp_count) { error = 0; break; } arg_len = 0; } offset = 0; } out: if (r->mode != TOMOYO_CONFIG_ENFORCING) error = 0; kfree(env_page.data); kfree(arg_ptr); return error; } /** * tomoyo_find_next_domain - Find a domain. * * @bprm: Pointer to "struct linux_binprm". * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ int tomoyo_find_next_domain(struct linux_binprm *bprm) { struct tomoyo_domain_info *old_domain = tomoyo_domain(); struct tomoyo_domain_info *domain = NULL; const char *original_name = bprm->filename; int retval = -ENOMEM; bool reject_on_transition_failure = false; const struct tomoyo_path_info *candidate; struct tomoyo_path_info exename; struct tomoyo_execve *ee = kzalloc(sizeof(*ee), GFP_NOFS); if (!ee) return -ENOMEM; ee->tmp = kzalloc(TOMOYO_EXEC_TMPSIZE, GFP_NOFS); if (!ee->tmp) { kfree(ee); return -ENOMEM; } /* ee->dump->data is allocated by tomoyo_dump_page(). */ tomoyo_init_request_info(&ee->r, NULL, TOMOYO_MAC_FILE_EXECUTE); ee->r.ee = ee; ee->bprm = bprm; ee->r.obj = &ee->obj; ee->obj.path1 = bprm->file->f_path; /* * Get symlink's pathname of program, but fallback to realpath if * symlink's pathname does not exist or symlink's pathname refers * to proc filesystem (e.g. /dev/fd/<num> or /proc/self/fd/<num> ). */ exename.name = tomoyo_realpath_nofollow(original_name); if (exename.name && !strncmp(exename.name, "proc:/", 6)) { kfree(exename.name); exename.name = NULL; } if (!exename.name) { exename.name = tomoyo_realpath_from_path(&bprm->file->f_path); if (!exename.name) goto out; } tomoyo_fill_path_info(&exename); retry: /* Check 'aggregator' directive. */ { struct tomoyo_aggregator *ptr; struct list_head *list = &old_domain->ns->policy_list[TOMOYO_ID_AGGREGATOR]; /* Check 'aggregator' directive. */ candidate = &exename; list_for_each_entry_rcu(ptr, list, head.list, srcu_read_lock_held(&tomoyo_ss)) { if (ptr->head.is_deleted || !tomoyo_path_matches_pattern(&exename, ptr->original_name)) continue; candidate = ptr->aggregated_name; break; } } /* Check execute permission. */ retval = tomoyo_execute_permission(&ee->r, candidate); if (retval == TOMOYO_RETRY_REQUEST) goto retry; if (retval < 0) goto out; /* * To be able to specify domainnames with wildcards, use the * pathname specified in the policy (which may contain * wildcard) rather than the pathname passed to execve() * (which never contains wildcard). */ if (ee->r.param.path.matched_path) candidate = ee->r.param.path.matched_path; /* * Check for domain transition preference if "file execute" matched. * If preference is given, make execve() fail if domain transition * has failed, for domain transition preference should be used with * destination domain defined. */ if (ee->transition) { const char *domainname = ee->transition->name; reject_on_transition_failure = true; if (!strcmp(domainname, "keep")) goto force_keep_domain; if (!strcmp(domainname, "child")) goto force_child_domain; if (!strcmp(domainname, "reset")) goto force_reset_domain; if (!strcmp(domainname, "initialize")) goto force_initialize_domain; if (!strcmp(domainname, "parent")) { char *cp; strscpy(ee->tmp, old_domain->domainname->name, TOMOYO_EXEC_TMPSIZE); cp = strrchr(ee->tmp, ' '); if (cp) *cp = '\0'; } else if (*domainname == '<') strscpy(ee->tmp, domainname, TOMOYO_EXEC_TMPSIZE); else snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->domainname->name, domainname); goto force_jump_domain; } /* * No domain transition preference specified. * Calculate domain to transit to. */ switch (tomoyo_transition_type(old_domain->ns, old_domain->domainname, candidate)) { case TOMOYO_TRANSITION_CONTROL_RESET: force_reset_domain: /* Transit to the root of specified namespace. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "<%s>", candidate->name); /* * Make execve() fail if domain transition across namespaces * has failed. */ reject_on_transition_failure = true; break; case TOMOYO_TRANSITION_CONTROL_INITIALIZE: force_initialize_domain: /* Transit to the child of current namespace's root. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->ns->name, candidate->name); break; case TOMOYO_TRANSITION_CONTROL_KEEP: force_keep_domain: /* Keep current domain. */ domain = old_domain; break; default: if (old_domain == &tomoyo_kernel_domain && !tomoyo_policy_loaded) { /* * Needn't to transit from kernel domain before * starting /sbin/init. But transit from kernel domain * if executing initializers because they might start * before /sbin/init. */ domain = old_domain; break; } force_child_domain: /* Normal domain transition. */ snprintf(ee->tmp, TOMOYO_EXEC_TMPSIZE - 1, "%s %s", old_domain->domainname->name, candidate->name); break; } force_jump_domain: if (!domain) domain = tomoyo_assign_domain(ee->tmp, true); if (domain) retval = 0; else if (reject_on_transition_failure) { pr_warn("ERROR: Domain '%s' not ready.\n", ee->tmp); retval = -ENOMEM; } else if (ee->r.mode == TOMOYO_CONFIG_ENFORCING) retval = -ENOMEM; else { retval = 0; if (!old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED]) { old_domain->flags[TOMOYO_DIF_TRANSITION_FAILED] = true; ee->r.granted = false; tomoyo_write_log(&ee->r, "%s", tomoyo_dif [TOMOYO_DIF_TRANSITION_FAILED]); pr_warn("ERROR: Domain '%s' not defined.\n", ee->tmp); } } out: if (!domain) domain = old_domain; /* Update reference count on "struct tomoyo_domain_info". */ { struct tomoyo_task *s = tomoyo_task(current); s->old_domain_info = s->domain_info; s->domain_info = domain; atomic_inc(&domain->users); } kfree(exename.name); if (!retval) { ee->r.domain = domain; retval = tomoyo_environ(ee); } kfree(ee->tmp); kfree(ee->dump.data); kfree(ee); return retval; } /** * tomoyo_dump_page - Dump a page to buffer. * * @bprm: Pointer to "struct linux_binprm". * @pos: Location to dump. * @dump: Pointer to "struct tomoyo_page_dump". * * Returns true on success, false otherwise. */ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, struct tomoyo_page_dump *dump) { struct page *page; #ifdef CONFIG_MMU int ret; #endif /* dump->data is released by tomoyo_find_next_domain(). */ if (!dump->data) { dump->data = kzalloc(PAGE_SIZE, GFP_NOFS); if (!dump->data) return false; } /* Same with get_arg_page(bprm, pos, 0) in fs/exec.c */ #ifdef CONFIG_MMU /* * This is called at execve() time in order to dig around * in the argv/environment of the new process * (represented by bprm). */ mmap_read_lock(bprm->mm); ret = get_user_pages_remote(bprm->mm, pos, 1, FOLL_FORCE, &page, NULL); mmap_read_unlock(bprm->mm); if (ret <= 0) return false; #else page = bprm->page[pos / PAGE_SIZE]; #endif if (page != dump->page) { const unsigned int offset = pos % PAGE_SIZE; /* * Maybe kmap()/kunmap() should be used here. * But remove_arg_zero() uses kmap_atomic()/kunmap_atomic(). * So do I. */ char *kaddr = kmap_atomic(page); dump->page = page; memcpy(dump->data + offset, kaddr + offset, PAGE_SIZE - offset); kunmap_atomic(kaddr); } /* Same with put_arg_page(page) in fs/exec.c */ #ifdef CONFIG_MMU put_page(page); #endif return true; } |
| 250 176 176 177 128 128 128 65 64 65 26 26 253 256 55 56 56 56 296 297 292 292 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017 - Columbia University and Linaro Ltd. * Author: Jintack Lim <jintack.lim@linaro.org> */ #include <linux/bitfield.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <asm/fixmap.h> #include <asm/kvm_arm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include <asm/kvm_nested.h> #include <asm/sysreg.h> #include "sys_regs.h" struct vncr_tlb { /* The guest's VNCR_EL2 */ u64 gva; struct s1_walk_info wi; struct s1_walk_result wr; u64 hpa; /* -1 when not mapped on a CPU */ int cpu; /* * true if the TLB is valid. Can only be changed with the * mmu_lock held. */ bool valid; }; /* * Ratio of live shadow S2 MMU per vcpu. This is a trade-off between * memory usage and potential number of different sets of S2 PTs in * the guests. Running out of S2 MMUs only affects performance (we * will invalidate them more often). */ #define S2_MMU_PER_VCPU 2 void kvm_init_nested(struct kvm *kvm) { kvm->arch.nested_mmus = NULL; kvm->arch.nested_mmus_size = 0; atomic_set(&kvm->arch.vncr_map_count, 0); } static int init_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu) { /* * We only initialise the IPA range on the canonical MMU, which * defines the contract between KVM and userspace on where the * "hardware" is in the IPA space. This affects the validity of MMIO * exits forwarded to userspace, for example. * * For nested S2s, we use the PARange as exposed to the guest, as it * is allowed to use it at will to expose whatever memory map it * wants to its own guests as it would be on real HW. */ return kvm_init_stage2_mmu(kvm, mmu, kvm_get_pa_bits(kvm)); } int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct kvm_s2_mmu *tmp; int num_mmus, ret = 0; if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features) && !cpus_have_final_cap(ARM64_HAS_HCR_NV1)) return -EINVAL; if (!vcpu->arch.ctxt.vncr_array) vcpu->arch.ctxt.vncr_array = (u64 *)__get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!vcpu->arch.ctxt.vncr_array) return -ENOMEM; /* * Let's treat memory allocation failures as benign: If we fail to * allocate anything, return an error and keep the allocated array * alive. Userspace may try to recover by intializing the vcpu * again, and there is no reason to affect the whole VM for this. */ num_mmus = atomic_read(&kvm->online_vcpus) * S2_MMU_PER_VCPU; tmp = kvrealloc(kvm->arch.nested_mmus, size_mul(sizeof(*kvm->arch.nested_mmus), num_mmus), GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!tmp) return -ENOMEM; swap(kvm->arch.nested_mmus, tmp); /* * If we went through a realocation, adjust the MMU back-pointers in * the previously initialised kvm_pgtable structures. */ if (kvm->arch.nested_mmus != tmp) for (int i = 0; i < kvm->arch.nested_mmus_size; i++) kvm->arch.nested_mmus[i].pgt->mmu = &kvm->arch.nested_mmus[i]; for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++) ret = init_nested_s2_mmu(kvm, &kvm->arch.nested_mmus[i]); if (ret) { for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++) kvm_free_stage2_pgd(&kvm->arch.nested_mmus[i]); free_page((unsigned long)vcpu->arch.ctxt.vncr_array); vcpu->arch.ctxt.vncr_array = NULL; return ret; } kvm->arch.nested_mmus_size = num_mmus; return 0; } struct s2_walk_info { u64 baddr; unsigned int max_oa_bits; unsigned int pgshift; unsigned int sl; unsigned int t0sz; bool be; bool ha; }; static u32 compute_fsc(int level, u32 fsc) { return fsc | (level & 0x3); } static int esr_s2_fault(struct kvm_vcpu *vcpu, int level, u32 fsc) { u32 esr; esr = kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC; esr |= compute_fsc(level, fsc); return esr; } static int get_ia_size(struct s2_walk_info *wi) { return 64 - wi->t0sz; } static int check_base_s2_limits(struct s2_walk_info *wi, int level, int input_size, int stride) { int start_size, ia_size; ia_size = get_ia_size(wi); /* Check translation limits */ switch (BIT(wi->pgshift)) { case SZ_64K: if (level == 0 || (level == 1 && ia_size <= 42)) return -EFAULT; break; case SZ_16K: if (level == 0 || (level == 1 && ia_size <= 40)) return -EFAULT; break; case SZ_4K: if (level < 0 || (level == 0 && ia_size <= 42)) return -EFAULT; break; } /* Check input size limits */ if (input_size > ia_size) return -EFAULT; /* Check number of entries in starting level table */ start_size = input_size - ((3 - level) * stride + wi->pgshift); if (start_size < 1 || start_size > stride + 4) return -EFAULT; return 0; } /* Check if output is within boundaries */ static int check_output_size(struct s2_walk_info *wi, phys_addr_t output) { unsigned int output_size = wi->max_oa_bits; if (output_size != 48 && (output & GENMASK_ULL(47, output_size))) return -1; return 0; } static int read_guest_s2_desc(struct kvm_vcpu *vcpu, phys_addr_t pa, u64 *desc, struct s2_walk_info *wi) { u64 val; int r; r = kvm_read_guest(vcpu->kvm, pa, &val, sizeof(val)); if (r) return r; /* * Handle reversedescriptors if endianness differs between the * host and the guest hypervisor. */ if (wi->be) *desc = be64_to_cpu((__force __be64)val); else *desc = le64_to_cpu((__force __le64)val); return 0; } static int swap_guest_s2_desc(struct kvm_vcpu *vcpu, phys_addr_t pa, u64 old, u64 new, struct s2_walk_info *wi) { if (wi->be) { old = cpu_to_be64(old); new = cpu_to_be64(new); } else { old = cpu_to_le64(old); new = cpu_to_le64(new); } return __kvm_at_swap_desc(vcpu->kvm, pa, old, new); } /* * This is essentially a C-version of the pseudo code from the ARM ARM * AArch64.TranslationTableWalk function. I strongly recommend looking at * that pseudocode in trying to understand this. * * Must be called with the kvm->srcu read lock held */ static int walk_nested_s2_pgd(struct kvm_vcpu *vcpu, phys_addr_t ipa, struct s2_walk_info *wi, struct kvm_s2_trans *out) { int first_block_level, level, stride, input_size, base_lower_bound; phys_addr_t base_addr; unsigned int addr_top, addr_bottom; u64 desc, new_desc; /* page table entry */ int ret; phys_addr_t paddr; switch (BIT(wi->pgshift)) { default: case SZ_64K: case SZ_16K: level = 3 - wi->sl; first_block_level = 2; break; case SZ_4K: level = 2 - wi->sl; first_block_level = 1; break; } stride = wi->pgshift - 3; input_size = get_ia_size(wi); if (input_size > 48 || input_size < 25) return -EFAULT; ret = check_base_s2_limits(wi, level, input_size, stride); if (WARN_ON(ret)) return ret; base_lower_bound = 3 + input_size - ((3 - level) * stride + wi->pgshift); base_addr = wi->baddr & GENMASK_ULL(47, base_lower_bound); if (check_output_size(wi, base_addr)) { out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ); return 1; } addr_top = input_size - 1; while (1) { phys_addr_t index; addr_bottom = (3 - level) * stride + wi->pgshift; index = (ipa & GENMASK_ULL(addr_top, addr_bottom)) >> (addr_bottom - 3); paddr = base_addr | index; ret = read_guest_s2_desc(vcpu, paddr, &desc, wi); if (ret < 0) return ret; new_desc = desc; /* Check for valid descriptor at this point */ if (!(desc & KVM_PTE_VALID)) { out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT); out->desc = desc; return 1; } if (FIELD_GET(KVM_PTE_TYPE, desc) == KVM_PTE_TYPE_BLOCK) { if (level < 3) break; out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT); out->desc = desc; return 1; } /* We're at the final level */ if (level == 3) break; if (check_output_size(wi, desc)) { out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ); out->desc = desc; return 1; } base_addr = desc & GENMASK_ULL(47, wi->pgshift); level += 1; addr_top = addr_bottom - 1; } if (level < first_block_level) { out->esr = compute_fsc(level, ESR_ELx_FSC_FAULT); out->desc = desc; return 1; } if (check_output_size(wi, desc)) { out->esr = compute_fsc(level, ESR_ELx_FSC_ADDRSZ); out->desc = desc; return 1; } if (wi->ha) new_desc |= KVM_PTE_LEAF_ATTR_LO_S2_AF; if (new_desc != desc) { ret = swap_guest_s2_desc(vcpu, paddr, desc, new_desc, wi); if (ret) return ret; desc = new_desc; } if (!(desc & KVM_PTE_LEAF_ATTR_LO_S2_AF)) { out->esr = compute_fsc(level, ESR_ELx_FSC_ACCESS); out->desc = desc; return 1; } addr_bottom += contiguous_bit_shift(desc, wi, level); /* Calculate and return the result */ paddr = (desc & GENMASK_ULL(47, addr_bottom)) | (ipa & GENMASK_ULL(addr_bottom - 1, 0)); out->output = paddr; out->block_size = 1UL << ((3 - level) * stride + wi->pgshift); out->readable = desc & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R; out->writable = desc & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W; out->level = level; out->desc = desc; return 0; } static void vtcr_to_walk_info(u64 vtcr, struct s2_walk_info *wi) { wi->t0sz = vtcr & TCR_EL2_T0SZ_MASK; switch (vtcr & VTCR_EL2_TG0_MASK) { case VTCR_EL2_TG0_4K: wi->pgshift = 12; break; case VTCR_EL2_TG0_16K: wi->pgshift = 14; break; case VTCR_EL2_TG0_64K: default: /* IMPDEF: treat any other value as 64k */ wi->pgshift = 16; break; } wi->sl = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); /* Global limit for now, should eventually be per-VM */ wi->max_oa_bits = min(get_kvm_ipa_limit(), ps_to_output_size(FIELD_GET(VTCR_EL2_PS_MASK, vtcr), false)); wi->ha = vtcr & VTCR_EL2_HA; } int kvm_walk_nested_s2(struct kvm_vcpu *vcpu, phys_addr_t gipa, struct kvm_s2_trans *result) { u64 vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2); struct s2_walk_info wi; int ret; result->esr = 0; if (!vcpu_has_nv(vcpu)) return 0; wi.baddr = vcpu_read_sys_reg(vcpu, VTTBR_EL2); vtcr_to_walk_info(vtcr, &wi); wi.be = vcpu_read_sys_reg(vcpu, SCTLR_EL2) & SCTLR_ELx_EE; ret = walk_nested_s2_pgd(vcpu, gipa, &wi, result); if (ret) result->esr |= (kvm_vcpu_get_esr(vcpu) & ~ESR_ELx_FSC); return ret; } static unsigned int ttl_to_size(u8 ttl) { int level = ttl & 3; int gran = (ttl >> 2) & 3; unsigned int max_size = 0; switch (gran) { case TLBI_TTL_TG_4K: switch (level) { case 0: break; case 1: max_size = SZ_1G; break; case 2: max_size = SZ_2M; break; case 3: max_size = SZ_4K; break; } break; case TLBI_TTL_TG_16K: switch (level) { case 0: case 1: break; case 2: max_size = SZ_32M; break; case 3: max_size = SZ_16K; break; } break; case TLBI_TTL_TG_64K: switch (level) { case 0: case 1: /* No 52bit IPA support */ break; case 2: max_size = SZ_512M; break; case 3: max_size = SZ_64K; break; } break; default: /* No size information */ break; } return max_size; } static u8 pgshift_level_to_ttl(u16 shift, u8 level) { u8 ttl; switch(shift) { case 12: ttl = TLBI_TTL_TG_4K; break; case 14: ttl = TLBI_TTL_TG_16K; break; case 16: ttl = TLBI_TTL_TG_64K; break; default: BUG(); } ttl <<= 2; ttl |= level & 3; return ttl; } /* * Compute the equivalent of the TTL field by parsing the shadow PT. The * granule size is extracted from the cached VTCR_EL2.TG0 while the level is * retrieved from first entry carrying the level as a tag. */ static u8 get_guest_mapping_ttl(struct kvm_s2_mmu *mmu, u64 addr) { u64 tmp, sz = 0, vtcr = mmu->tlb_vtcr; kvm_pte_t pte; u8 ttl, level; lockdep_assert_held_write(&kvm_s2_mmu_to_kvm(mmu)->mmu_lock); switch (vtcr & VTCR_EL2_TG0_MASK) { case VTCR_EL2_TG0_4K: ttl = (TLBI_TTL_TG_4K << 2); break; case VTCR_EL2_TG0_16K: ttl = (TLBI_TTL_TG_16K << 2); break; case VTCR_EL2_TG0_64K: default: /* IMPDEF: treat any other value as 64k */ ttl = (TLBI_TTL_TG_64K << 2); break; } tmp = addr; again: /* Iteratively compute the block sizes for a particular granule size */ switch (vtcr & VTCR_EL2_TG0_MASK) { case VTCR_EL2_TG0_4K: if (sz < SZ_4K) sz = SZ_4K; else if (sz < SZ_2M) sz = SZ_2M; else if (sz < SZ_1G) sz = SZ_1G; else sz = 0; break; case VTCR_EL2_TG0_16K: if (sz < SZ_16K) sz = SZ_16K; else if (sz < SZ_32M) sz = SZ_32M; else sz = 0; break; case VTCR_EL2_TG0_64K: default: /* IMPDEF: treat any other value as 64k */ if (sz < SZ_64K) sz = SZ_64K; else if (sz < SZ_512M) sz = SZ_512M; else sz = 0; break; } if (sz == 0) return 0; tmp &= ~(sz - 1); if (kvm_pgtable_get_leaf(mmu->pgt, tmp, &pte, NULL)) goto again; if (!(pte & PTE_VALID)) goto again; level = FIELD_GET(KVM_NV_GUEST_MAP_SZ, pte); if (!level) goto again; ttl |= level; /* * We now have found some level information in the shadow S2. Check * that the resulting range is actually including the original IPA. */ sz = ttl_to_size(ttl); if (addr < (tmp + sz)) return ttl; return 0; } unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val) { struct kvm *kvm = kvm_s2_mmu_to_kvm(mmu); unsigned long max_size; u8 ttl; ttl = FIELD_GET(TLBI_TTL_MASK, val); if (!ttl || !kvm_has_feat(kvm, ID_AA64MMFR2_EL1, TTL, IMP)) { /* No TTL, check the shadow S2 for a hint */ u64 addr = (val & GENMASK_ULL(35, 0)) << 12; ttl = get_guest_mapping_ttl(mmu, addr); } max_size = ttl_to_size(ttl); if (!max_size) { /* Compute the maximum extent of the invalidation */ switch (mmu->tlb_vtcr & VTCR_EL2_TG0_MASK) { case VTCR_EL2_TG0_4K: max_size = SZ_1G; break; case VTCR_EL2_TG0_16K: max_size = SZ_32M; break; case VTCR_EL2_TG0_64K: default: /* IMPDEF: treat any other value as 64k */ /* * No, we do not support 52bit IPA in nested yet. Once * we do, this should be 4TB. */ max_size = SZ_512M; break; } } WARN_ON(!max_size); return max_size; } /* * We can have multiple *different* MMU contexts with the same VMID: * * - S2 being enabled or not, hence differing by the HCR_EL2.VM bit * * - Multiple vcpus using private S2s (huh huh...), hence differing by the * VBBTR_EL2.BADDR address * * - A combination of the above... * * We can always identify which MMU context to pick at run-time. However, * TLB invalidation involving a VMID must take action on all the TLBs using * this particular VMID. This translates into applying the same invalidation * operation to all the contexts that are using this VMID. Moar phun! */ void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid, const union tlbi_info *info, void (*tlbi_callback)(struct kvm_s2_mmu *, const union tlbi_info *)) { write_lock(&kvm->mmu_lock); for (int i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (!kvm_s2_mmu_valid(mmu)) continue; if (vmid == get_vmid(mmu->tlb_vttbr)) tlbi_callback(mmu, info); } write_unlock(&kvm->mmu_lock); } struct kvm_s2_mmu *lookup_s2_mmu(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; bool nested_stage2_enabled; u64 vttbr, vtcr, hcr; lockdep_assert_held_write(&kvm->mmu_lock); vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2); vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2); hcr = vcpu_read_sys_reg(vcpu, HCR_EL2); nested_stage2_enabled = hcr & HCR_VM; /* Don't consider the CnP bit for the vttbr match */ vttbr &= ~VTTBR_CNP_BIT; /* * Two possibilities when looking up a S2 MMU context: * * - either S2 is enabled in the guest, and we need a context that is * S2-enabled and matches the full VTTBR (VMID+BADDR) and VTCR, * which makes it safe from a TLB conflict perspective (a broken * guest won't be able to generate them), * * - or S2 is disabled, and we need a context that is S2-disabled * and matches the VMID only, as all TLBs are tagged by VMID even * if S2 translation is disabled. */ for (int i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (!kvm_s2_mmu_valid(mmu)) continue; if (nested_stage2_enabled && mmu->nested_stage2_enabled && vttbr == mmu->tlb_vttbr && vtcr == mmu->tlb_vtcr) return mmu; if (!nested_stage2_enabled && !mmu->nested_stage2_enabled && get_vmid(vttbr) == get_vmid(mmu->tlb_vttbr)) return mmu; } return NULL; } static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct kvm_s2_mmu *s2_mmu; int i; lockdep_assert_held_write(&vcpu->kvm->mmu_lock); s2_mmu = lookup_s2_mmu(vcpu); if (s2_mmu) goto out; /* * Make sure we don't always search from the same point, or we * will always reuse a potentially active context, leaving * free contexts unused. */ for (i = kvm->arch.nested_mmus_next; i < (kvm->arch.nested_mmus_size + kvm->arch.nested_mmus_next); i++) { s2_mmu = &kvm->arch.nested_mmus[i % kvm->arch.nested_mmus_size]; if (atomic_read(&s2_mmu->refcnt) == 0) break; } BUG_ON(atomic_read(&s2_mmu->refcnt)); /* We have struct MMUs to spare */ /* Set the scene for the next search */ kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size; /* Make sure we don't forget to do the laundry */ if (kvm_s2_mmu_valid(s2_mmu)) s2_mmu->pending_unmap = true; /* * The virtual VMID (modulo CnP) will be used as a key when matching * an existing kvm_s2_mmu. * * We cache VTCR at allocation time, once and for all. It'd be great * if the guest didn't screw that one up, as this is not very * forgiving... */ s2_mmu->tlb_vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2) & ~VTTBR_CNP_BIT; s2_mmu->tlb_vtcr = vcpu_read_sys_reg(vcpu, VTCR_EL2); s2_mmu->nested_stage2_enabled = vcpu_read_sys_reg(vcpu, HCR_EL2) & HCR_VM; out: atomic_inc(&s2_mmu->refcnt); /* * Set the vCPU request to perform an unmap, even if the pending unmap * originates from another vCPU. This guarantees that the MMU has been * completely unmapped before any vCPU actually uses it, and allows * multiple vCPUs to lend a hand with completing the unmap. */ if (s2_mmu->pending_unmap) kvm_make_request(KVM_REQ_NESTED_S2_UNMAP, vcpu); return s2_mmu; } void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu) { /* CnP being set denotes an invalid entry */ mmu->tlb_vttbr = VTTBR_CNP_BIT; mmu->nested_stage2_enabled = false; atomic_set(&mmu->refcnt, 0); } void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu) { /* * If the vCPU kept its reference on the MMU after the last put, * keep rolling with it. */ if (is_hyp_ctxt(vcpu)) { if (!vcpu->arch.hw_mmu) vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; } else { if (!vcpu->arch.hw_mmu) { scoped_guard(write_lock, &vcpu->kvm->mmu_lock) vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu); } if (__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV) kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu); } } void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu) { /* Unconditionally drop the VNCR mapping if we have one */ if (host_data_test_flag(L1_VNCR_MAPPED)) { BUG_ON(vcpu->arch.vncr_tlb->cpu != smp_processor_id()); BUG_ON(is_hyp_ctxt(vcpu)); clear_fixmap(vncr_fixmap(vcpu->arch.vncr_tlb->cpu)); vcpu->arch.vncr_tlb->cpu = -1; host_data_clear_flag(L1_VNCR_MAPPED); atomic_dec(&vcpu->kvm->arch.vncr_map_count); } /* * Keep a reference on the associated stage-2 MMU if the vCPU is * scheduling out and not in WFI emulation, suggesting it is likely to * reuse the MMU sometime soon. */ if (vcpu->scheduled_out && !vcpu_get_flag(vcpu, IN_WFI)) return; if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu)) atomic_dec(&vcpu->arch.hw_mmu->refcnt); vcpu->arch.hw_mmu = NULL; } /* * Returns non-zero if permission fault is handled by injecting it to the next * level hypervisor. */ int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu, struct kvm_s2_trans *trans) { bool forward_fault = false; trans->esr = 0; if (!kvm_vcpu_trap_is_permission_fault(vcpu)) return 0; if (kvm_vcpu_trap_is_iabt(vcpu)) { if (vcpu_mode_priv(vcpu)) forward_fault = !kvm_s2_trans_exec_el1(vcpu->kvm, trans); else forward_fault = !kvm_s2_trans_exec_el0(vcpu->kvm, trans); } else { bool write_fault = kvm_is_write_fault(vcpu); forward_fault = ((write_fault && !trans->writable) || (!write_fault && !trans->readable)); } if (forward_fault) trans->esr = esr_s2_fault(vcpu, trans->level, ESR_ELx_FSC_PERM); return forward_fault; } int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2) { vcpu_write_sys_reg(vcpu, vcpu->arch.fault.far_el2, FAR_EL2); vcpu_write_sys_reg(vcpu, vcpu->arch.fault.hpfar_el2, HPFAR_EL2); return kvm_inject_nested_sync(vcpu, esr_el2); } static void invalidate_vncr(struct vncr_tlb *vt) { vt->valid = false; if (vt->cpu != -1) clear_fixmap(vncr_fixmap(vt->cpu)); } static void kvm_invalidate_vncr_ipa(struct kvm *kvm, u64 start, u64 end) { struct kvm_vcpu *vcpu; unsigned long i; lockdep_assert_held_write(&kvm->mmu_lock); if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY)) return; kvm_for_each_vcpu(i, vcpu, kvm) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; u64 ipa_start, ipa_end, ipa_size; /* * Careful here: We end-up here from an MMU notifier, * and this can race against a vcpu not being onlined * yet, without the pseudo-TLB being allocated. * * Skip those, as they obviously don't participate in * the invalidation at this stage. */ if (!vt) continue; if (!vt->valid) continue; ipa_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift, vt->wr.level)); ipa_start = vt->wr.pa & ~(ipa_size - 1); ipa_end = ipa_start + ipa_size; if (ipa_end <= start || ipa_start >= end) continue; invalidate_vncr(vt); } } struct s1e2_tlbi_scope { enum { TLBI_ALL, TLBI_VA, TLBI_VAA, TLBI_ASID, } type; u16 asid; u64 va; u64 size; }; static void invalidate_vncr_va(struct kvm *kvm, struct s1e2_tlbi_scope *scope) { struct kvm_vcpu *vcpu; unsigned long i; lockdep_assert_held_write(&kvm->mmu_lock); kvm_for_each_vcpu(i, vcpu, kvm) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; u64 va_start, va_end, va_size; if (!vt->valid) continue; va_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift, vt->wr.level)); va_start = vt->gva & ~(va_size - 1); va_end = va_start + va_size; switch (scope->type) { case TLBI_ALL: break; case TLBI_VA: if (va_end <= scope->va || va_start >= (scope->va + scope->size)) continue; if (vt->wr.nG && vt->wr.asid != scope->asid) continue; break; case TLBI_VAA: if (va_end <= scope->va || va_start >= (scope->va + scope->size)) continue; break; case TLBI_ASID: if (!vt->wr.nG || vt->wr.asid != scope->asid) continue; break; } invalidate_vncr(vt); } } #define tlbi_va_s1_to_va(v) (u64)sign_extend64((v) << 12, 48) static void compute_s1_tlbi_range(struct kvm_vcpu *vcpu, u32 inst, u64 val, struct s1e2_tlbi_scope *scope) { switch (inst) { 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: scope->type = TLBI_ALL; 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: 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: scope->type = TLBI_VA; scope->size = ttl_to_size(FIELD_GET(TLBI_TTL_MASK, val)); if (!scope->size) scope->size = SZ_1G; scope->va = tlbi_va_s1_to_va(val) & ~(scope->size - 1); scope->asid = FIELD_GET(TLBIR_ASID_MASK, val); 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: scope->type = TLBI_ASID; scope->asid = FIELD_GET(TLBIR_ASID_MASK, val); 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: case OP_TLBI_VAALE1: case OP_TLBI_VAALE1IS: case OP_TLBI_VAALE1OS: case OP_TLBI_VAALE1NXS: case OP_TLBI_VAALE1ISNXS: case OP_TLBI_VAALE1OSNXS: scope->type = TLBI_VAA; scope->size = ttl_to_size(FIELD_GET(TLBI_TTL_MASK, val)); if (!scope->size) scope->size = SZ_1G; scope->va = tlbi_va_s1_to_va(val) & ~(scope->size - 1); 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: 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: scope->type = TLBI_VA; scope->va = decode_range_tlbi(val, &scope->size, &scope->asid); 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: case OP_TLBI_RVAALE1: case OP_TLBI_RVAALE1IS: case OP_TLBI_RVAALE1OS: case OP_TLBI_RVAALE1NXS: case OP_TLBI_RVAALE1ISNXS: case OP_TLBI_RVAALE1OSNXS: scope->type = TLBI_VAA; scope->va = decode_range_tlbi(val, &scope->size, NULL); break; } } void kvm_handle_s1e2_tlbi(struct kvm_vcpu *vcpu, u32 inst, u64 val) { struct s1e2_tlbi_scope scope = {}; compute_s1_tlbi_range(vcpu, inst, val, &scope); guard(write_lock)(&vcpu->kvm->mmu_lock); invalidate_vncr_va(vcpu->kvm, &scope); } void kvm_nested_s2_wp(struct kvm *kvm) { int i; lockdep_assert_held_write(&kvm->mmu_lock); for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (kvm_s2_mmu_valid(mmu)) kvm_stage2_wp_range(mmu, 0, kvm_phys_size(mmu)); } kvm_invalidate_vncr_ipa(kvm, 0, BIT(kvm->arch.mmu.pgt->ia_bits)); } void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block) { int i; lockdep_assert_held_write(&kvm->mmu_lock); for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (kvm_s2_mmu_valid(mmu)) kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), may_block); } kvm_invalidate_vncr_ipa(kvm, 0, BIT(kvm->arch.mmu.pgt->ia_bits)); } void kvm_nested_s2_flush(struct kvm *kvm) { int i; lockdep_assert_held_write(&kvm->mmu_lock); for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (kvm_s2_mmu_valid(mmu)) kvm_stage2_flush_range(mmu, 0, kvm_phys_size(mmu)); } } void kvm_arch_flush_shadow_all(struct kvm *kvm) { int i; for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; if (!WARN_ON(atomic_read(&mmu->refcnt))) kvm_free_stage2_pgd(mmu); } kvfree(kvm->arch.nested_mmus); kvm->arch.nested_mmus = NULL; kvm->arch.nested_mmus_size = 0; kvm_uninit_stage2_mmu(kvm); } /* * Dealing with VNCR_EL2 exposed by the *guest* is a complicated matter: * * - We introduce an internal representation of a vcpu-private TLB, * representing the mapping between the guest VA contained in VNCR_EL2, * the IPA the guest's EL2 PTs point to, and the actual PA this lives at. * * - On translation fault from a nested VNCR access, we create such a TLB. * If there is no mapping to describe, the guest inherits the fault. * Crucially, no actual mapping is done at this stage. * * - On vcpu_load() in a non-HYP context with HCR_EL2.NV==1, if the above * TLB exists, we map it in the fixmap for this CPU, and run with it. We * have to respect the permissions dictated by the guest, but not the * memory type (FWB is a must). * * - Note that we usually don't do a vcpu_load() on the back of a fault * (unless we are preempted), so the resolution of a translation fault * must go via a request that will map the VNCR page in the fixmap. * vcpu_load() might as well use the same mechanism. * * - On vcpu_put() in a non-HYP context with HCR_EL2.NV==1, if the TLB was * mapped, we unmap it. Yes it is that simple. The TLB still exists * though, and may be reused at a later load. * * - On permission fault, we simply forward the fault to the guest's EL2. * Get out of my way. * * - On any TLBI for the EL2&0 translation regime, we must find any TLB that * intersects with the TLBI request, invalidate it, and unmap the page * from the fixmap. Because we need to look at all the vcpu-private TLBs, * this requires some wide-ranging locking to ensure that nothing races * against it. This may require some refcounting to avoid the search when * no such TLB is present. * * - On MMU notifiers, we must invalidate our TLB in a similar way, but * looking at the IPA instead. The funny part is that there may not be a * stage-2 mapping for this page if L1 hasn't accessed it using LD/ST * instructions. */ int kvm_vcpu_allocate_vncr_tlb(struct kvm_vcpu *vcpu) { if (!kvm_has_feat(vcpu->kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY)) return 0; vcpu->arch.vncr_tlb = kzalloc(sizeof(*vcpu->arch.vncr_tlb), GFP_KERNEL_ACCOUNT); if (!vcpu->arch.vncr_tlb) return -ENOMEM; return 0; } static u64 read_vncr_el2(struct kvm_vcpu *vcpu) { return (u64)sign_extend64(__vcpu_sys_reg(vcpu, VNCR_EL2), 48); } static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem) { struct kvm_memory_slot *memslot; bool write_fault, writable; unsigned long mmu_seq; struct vncr_tlb *vt; struct page *page; u64 va, pfn, gfn; int ret; vt = vcpu->arch.vncr_tlb; /* * If we're about to walk the EL2 S1 PTs, we must invalidate the * current TLB, as it could be sampled from another vcpu doing a * TLBI *IS. A real CPU wouldn't do that, but we only keep a single * translation, so not much of a choice. * * We also prepare the next walk wilst we're at it. */ scoped_guard(write_lock, &vcpu->kvm->mmu_lock) { invalidate_vncr(vt); vt->wi = (struct s1_walk_info) { .regime = TR_EL20, .as_el0 = false, .pan = false, }; vt->wr = (struct s1_walk_result){}; } guard(srcu)(&vcpu->kvm->srcu); va = read_vncr_el2(vcpu); ret = __kvm_translate_va(vcpu, &vt->wi, &vt->wr, va); if (ret) return ret; write_fault = kvm_is_write_fault(vcpu); mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); gfn = vt->wr.pa >> PAGE_SHIFT; memslot = gfn_to_memslot(vcpu->kvm, gfn); if (!memslot) return -EFAULT; *is_gmem = kvm_slot_has_gmem(memslot); if (!*is_gmem) { pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0, &writable, &page); if (is_error_noslot_pfn(pfn) || (write_fault && !writable)) return -EFAULT; } else { ret = kvm_gmem_get_pfn(vcpu->kvm, memslot, gfn, &pfn, &page, NULL); if (ret) { kvm_prepare_memory_fault_exit(vcpu, vt->wr.pa, PAGE_SIZE, write_fault, false, false); return ret; } } scoped_guard(write_lock, &vcpu->kvm->mmu_lock) { if (mmu_invalidate_retry(vcpu->kvm, mmu_seq)) return -EAGAIN; vt->gva = va; vt->hpa = pfn << PAGE_SHIFT; vt->valid = true; vt->cpu = -1; kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu); kvm_release_faultin_page(vcpu->kvm, page, false, vt->wr.pw); } if (vt->wr.pw) mark_page_dirty(vcpu->kvm, gfn); return 0; } static void inject_vncr_perm(struct kvm_vcpu *vcpu) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; u64 esr = kvm_vcpu_get_esr(vcpu); /* Adjust the fault level to reflect that of the guest's */ esr &= ~ESR_ELx_FSC; esr |= FIELD_PREP(ESR_ELx_FSC, ESR_ELx_FSC_PERM_L(vt->wr.level)); kvm_inject_nested_sync(vcpu, esr); } static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; lockdep_assert_held_read(&vcpu->kvm->mmu_lock); if (!vt->valid) return false; if (read_vncr_el2(vcpu) != vt->gva) return false; if (vt->wr.nG) { u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); u64 ttbr = ((tcr & TCR_A1) ? vcpu_read_sys_reg(vcpu, TTBR1_EL2) : vcpu_read_sys_reg(vcpu, TTBR0_EL2)); u16 asid; asid = FIELD_GET(TTBR_ASID_MASK, ttbr); if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || !(tcr & TCR_ASID16)) asid &= GENMASK(7, 0); return asid == vt->wr.asid; } return true; } int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; u64 esr = kvm_vcpu_get_esr(vcpu); WARN_ON_ONCE(!(esr & ESR_ELx_VNCR)); if (kvm_vcpu_abt_issea(vcpu)) return kvm_handle_guest_sea(vcpu); if (esr_fsc_is_permission_fault(esr)) { inject_vncr_perm(vcpu); } else if (esr_fsc_is_translation_fault(esr)) { bool valid, is_gmem = false; int ret; scoped_guard(read_lock, &vcpu->kvm->mmu_lock) valid = kvm_vncr_tlb_lookup(vcpu); if (!valid) ret = kvm_translate_vncr(vcpu, &is_gmem); else ret = -EPERM; switch (ret) { case -EAGAIN: /* Let's try again... */ break; case -ENOMEM: /* * For guest_memfd, this indicates that it failed to * create a folio to back the memory. Inform userspace. */ if (is_gmem) return 0; /* Otherwise, let's try again... */ break; case -EFAULT: case -EIO: case -EHWPOISON: if (is_gmem) return 0; fallthrough; case -EINVAL: case -ENOENT: case -EACCES: /* * Translation failed, inject the corresponding * exception back to EL2. */ BUG_ON(!vt->wr.failed); esr &= ~ESR_ELx_FSC; esr |= FIELD_PREP(ESR_ELx_FSC, vt->wr.fst); kvm_inject_nested_sync(vcpu, esr); break; case -EPERM: /* Hack to deal with POE until we get kernel support */ inject_vncr_perm(vcpu); break; case 0: break; } } else { WARN_ONCE(1, "Unhandled VNCR abort, ESR=%llx\n", esr); } return 1; } static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu) { struct vncr_tlb *vt = vcpu->arch.vncr_tlb; pgprot_t prot; guard(preempt)(); guard(read_lock)(&vcpu->kvm->mmu_lock); /* * The request to map VNCR may have raced against some other * event, such as an interrupt, and may not be valid anymore. */ if (is_hyp_ctxt(vcpu)) return; /* * Check that the pseudo-TLB is valid and that VNCR_EL2 still * contains the expected value. If it doesn't, we simply bail out * without a mapping -- a transformed MSR/MRS will generate the * fault and allows us to populate the pseudo-TLB. */ if (!vt->valid) return; if (read_vncr_el2(vcpu) != vt->gva) return; if (vt->wr.nG) { u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); u64 ttbr = ((tcr & TCR_A1) ? vcpu_read_sys_reg(vcpu, TTBR1_EL2) : vcpu_read_sys_reg(vcpu, TTBR0_EL2)); u16 asid; asid = FIELD_GET(TTBR_ASID_MASK, ttbr); if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || !(tcr & TCR_ASID16)) asid &= GENMASK(7, 0); if (asid != vt->wr.asid) return; } vt->cpu = smp_processor_id(); if (vt->wr.pw && vt->wr.pr) prot = PAGE_KERNEL; else if (vt->wr.pr) prot = PAGE_KERNEL_RO; else prot = PAGE_NONE; /* * We can't map write-only (or no permission at all) in the kernel, * but the guest can do it if using POE, so we'll have to turn a * translation fault into a permission fault at runtime. * FIXME: WO doesn't work at all, need POE support in the kernel. */ if (pgprot_val(prot) != pgprot_val(PAGE_NONE)) { __set_fixmap(vncr_fixmap(vt->cpu), vt->hpa, prot); host_data_set_flag(L1_VNCR_MAPPED); atomic_inc(&vcpu->kvm->arch.vncr_map_count); } } #define has_tgran_2(__r, __sz) \ ({ \ u64 _s1, _s2, _mmfr0 = __r; \ \ _s2 = SYS_FIELD_GET(ID_AA64MMFR0_EL1, \ TGRAN##__sz##_2, _mmfr0); \ \ _s1 = SYS_FIELD_GET(ID_AA64MMFR0_EL1, \ TGRAN##__sz, _mmfr0); \ \ ((_s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_NI && \ _s2 != ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz) || \ (_s2 == ID_AA64MMFR0_EL1_TGRAN##__sz##_2_TGRAN##__sz && \ _s1 != ID_AA64MMFR0_EL1_TGRAN##__sz##_NI)); \ }) /* * Our emulated CPU doesn't support all the possible features. For the * sake of simplicity (and probably mental sanity), wipe out a number * of feature bits we don't intend to support for the time being. * This list should get updated as new features get added to the NV * support, and new extension to the architecture. */ u64 limit_nv_id_reg(struct kvm *kvm, u32 reg, u64 val) { u64 orig_val = val; switch (reg) { case SYS_ID_AA64ISAR0_EL1: /* Support everything but TME */ val &= ~ID_AA64ISAR0_EL1_TME; break; case SYS_ID_AA64ISAR1_EL1: /* Support everything but LS64 and Spec Invalidation */ val &= ~(ID_AA64ISAR1_EL1_LS64 | ID_AA64ISAR1_EL1_SPECRES); break; case SYS_ID_AA64PFR0_EL1: /* No RME, AMU, MPAM, or S-EL2 */ val &= ~(ID_AA64PFR0_EL1_RME | ID_AA64PFR0_EL1_AMU | ID_AA64PFR0_EL1_MPAM | ID_AA64PFR0_EL1_SEL2 | ID_AA64PFR0_EL1_EL3 | ID_AA64PFR0_EL1_EL2 | ID_AA64PFR0_EL1_EL1 | ID_AA64PFR0_EL1_EL0); /* 64bit only at any EL */ val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL0, IMP); val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL1, IMP); val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL2, IMP); val |= SYS_FIELD_PREP_ENUM(ID_AA64PFR0_EL1, EL3, IMP); break; case SYS_ID_AA64PFR1_EL1: /* Only support BTI, SSBS, CSV2_frac */ val &= ~(ID_AA64PFR1_EL1_PFAR | ID_AA64PFR1_EL1_MTEX | ID_AA64PFR1_EL1_THE | ID_AA64PFR1_EL1_GCS | ID_AA64PFR1_EL1_MTE_frac | ID_AA64PFR1_EL1_NMI | ID_AA64PFR1_EL1_SME | ID_AA64PFR1_EL1_RES0 | ID_AA64PFR1_EL1_MPAM_frac | ID_AA64PFR1_EL1_MTE); break; case SYS_ID_AA64MMFR0_EL1: /* Hide ExS, Secure Memory */ val &= ~(ID_AA64MMFR0_EL1_EXS | ID_AA64MMFR0_EL1_TGRAN4_2 | ID_AA64MMFR0_EL1_TGRAN16_2 | ID_AA64MMFR0_EL1_TGRAN64_2 | ID_AA64MMFR0_EL1_SNSMEM); /* Hide CNTPOFF if present */ val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR0_EL1, ECV, IMP); /* Disallow unsupported S2 page sizes */ switch (PAGE_SIZE) { case SZ_64K: val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, NI); fallthrough; case SZ_16K: val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, NI); fallthrough; case SZ_4K: /* Support everything */ break; } /* * Since we can't support a guest S2 page size smaller * than the host's own page size (due to KVM only * populating its own S2 using the kernel's page * size), advertise the limitation using FEAT_GTG. */ switch (PAGE_SIZE) { case SZ_4K: if (has_tgran_2(orig_val, 4)) val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN4_2, IMP); fallthrough; case SZ_16K: if (has_tgran_2(orig_val, 16)) val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN16_2, IMP); fallthrough; case SZ_64K: if (has_tgran_2(orig_val, 64)) val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR0_EL1, TGRAN64_2, IMP); break; } /* Cap PARange to 48bits */ val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR0_EL1, PARANGE, 48); break; case SYS_ID_AA64MMFR1_EL1: val &= ~(ID_AA64MMFR1_EL1_CMOW | ID_AA64MMFR1_EL1_nTLBPA | ID_AA64MMFR1_EL1_ETS); /* FEAT_E2H0 implies no VHE */ if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features)) val &= ~ID_AA64MMFR1_EL1_VH; val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64MMFR1_EL1, HAFDBS, AF); break; case SYS_ID_AA64MMFR2_EL1: val &= ~(ID_AA64MMFR2_EL1_BBM | ID_AA64MMFR2_EL1_TTL | GENMASK_ULL(47, 44) | ID_AA64MMFR2_EL1_ST | ID_AA64MMFR2_EL1_CCIDX | ID_AA64MMFR2_EL1_VARange); /* Force TTL support */ val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR2_EL1, TTL, IMP); break; case SYS_ID_AA64MMFR4_EL1: /* * You get EITHER * * - FEAT_VHE without FEAT_E2H0 * - FEAT_NV limited to FEAT_NV2 * - HCR_EL2.NV1 being RES0 * * OR * * - FEAT_E2H0 without FEAT_VHE nor FEAT_NV * * Life is too short for anything else. */ if (test_bit(KVM_ARM_VCPU_HAS_EL2_E2H0, kvm->arch.vcpu_features)) { val = 0; } else { val = SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY); val |= SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, E2H0, NI_NV1); } break; case SYS_ID_AA64DFR0_EL1: /* Only limited support for PMU, Debug, BPs, WPs, and HPMN0 */ val &= ~(ID_AA64DFR0_EL1_ExtTrcBuff | ID_AA64DFR0_EL1_BRBE | ID_AA64DFR0_EL1_MTPMU | ID_AA64DFR0_EL1_TraceBuffer | ID_AA64DFR0_EL1_TraceFilt | ID_AA64DFR0_EL1_PMSVer | ID_AA64DFR0_EL1_CTX_CMPs | ID_AA64DFR0_EL1_SEBEP | ID_AA64DFR0_EL1_PMSS | ID_AA64DFR0_EL1_TraceVer); /* * FEAT_Debugv8p9 requires support for extended breakpoints / * watchpoints. */ val = ID_REG_LIMIT_FIELD_ENUM(val, ID_AA64DFR0_EL1, DebugVer, V8P8); break; } return val; } u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *vcpu, enum vcpu_sysreg sr, u64 v) { struct kvm_sysreg_masks *masks; masks = vcpu->kvm->arch.sysreg_masks; if (masks) { sr -= __SANITISED_REG_START__; v &= ~masks->mask[sr].res0; v |= masks->mask[sr].res1; } return v; } static __always_inline void set_sysreg_masks(struct kvm *kvm, int sr, u64 res0, u64 res1) { int i = sr - __SANITISED_REG_START__; BUILD_BUG_ON(!__builtin_constant_p(sr)); BUILD_BUG_ON(sr < __SANITISED_REG_START__); BUILD_BUG_ON(sr >= NR_SYS_REGS); kvm->arch.sysreg_masks->mask[i].res0 = res0; kvm->arch.sysreg_masks->mask[i].res1 = res1; } int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; u64 res0, res1; lockdep_assert_held(&kvm->arch.config_lock); if (kvm->arch.sysreg_masks) goto out; kvm->arch.sysreg_masks = kzalloc(sizeof(*(kvm->arch.sysreg_masks)), GFP_KERNEL_ACCOUNT); if (!kvm->arch.sysreg_masks) return -ENOMEM; /* VTTBR_EL2 */ res0 = res1 = 0; if (!kvm_has_feat_enum(kvm, ID_AA64MMFR1_EL1, VMIDBits, 16)) res0 |= GENMASK(63, 56); if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, CnP, IMP)) res0 |= VTTBR_CNP_BIT; set_sysreg_masks(kvm, VTTBR_EL2, res0, res1); /* VTCR_EL2 */ res0 = GENMASK(63, 32) | GENMASK(30, 20); res1 = BIT(31); set_sysreg_masks(kvm, VTCR_EL2, res0, res1); /* VMPIDR_EL2 */ res0 = GENMASK(63, 40) | GENMASK(30, 24); res1 = BIT(31); set_sysreg_masks(kvm, VMPIDR_EL2, res0, res1); /* HCR_EL2 */ get_reg_fixed_bits(kvm, HCR_EL2, &res0, &res1); set_sysreg_masks(kvm, HCR_EL2, res0, res1); /* HCRX_EL2 */ get_reg_fixed_bits(kvm, HCRX_EL2, &res0, &res1); set_sysreg_masks(kvm, HCRX_EL2, res0, res1); /* HFG[RW]TR_EL2 */ get_reg_fixed_bits(kvm, HFGRTR_EL2, &res0, &res1); set_sysreg_masks(kvm, HFGRTR_EL2, res0, res1); get_reg_fixed_bits(kvm, HFGWTR_EL2, &res0, &res1); set_sysreg_masks(kvm, HFGWTR_EL2, res0, res1); /* HDFG[RW]TR_EL2 */ get_reg_fixed_bits(kvm, HDFGRTR_EL2, &res0, &res1); set_sysreg_masks(kvm, HDFGRTR_EL2, res0, res1); get_reg_fixed_bits(kvm, HDFGWTR_EL2, &res0, &res1); set_sysreg_masks(kvm, HDFGWTR_EL2, res0, res1); /* HFGITR_EL2 */ get_reg_fixed_bits(kvm, HFGITR_EL2, &res0, &res1); set_sysreg_masks(kvm, HFGITR_EL2, res0, res1); /* HAFGRTR_EL2 - not a lot to see here */ get_reg_fixed_bits(kvm, HAFGRTR_EL2, &res0, &res1); set_sysreg_masks(kvm, HAFGRTR_EL2, res0, res1); /* HFG[RW]TR2_EL2 */ get_reg_fixed_bits(kvm, HFGRTR2_EL2, &res0, &res1); set_sysreg_masks(kvm, HFGRTR2_EL2, res0, res1); get_reg_fixed_bits(kvm, HFGWTR2_EL2, &res0, &res1); set_sysreg_masks(kvm, HFGWTR2_EL2, res0, res1); /* HDFG[RW]TR2_EL2 */ get_reg_fixed_bits(kvm, HDFGRTR2_EL2, &res0, &res1); set_sysreg_masks(kvm, HDFGRTR2_EL2, res0, res1); get_reg_fixed_bits(kvm, HDFGWTR2_EL2, &res0, &res1); set_sysreg_masks(kvm, HDFGWTR2_EL2, res0, res1); /* HFGITR2_EL2 */ get_reg_fixed_bits(kvm, HFGITR2_EL2, &res0, &res1); set_sysreg_masks(kvm, HFGITR2_EL2, res0, res1); /* TCR2_EL2 */ get_reg_fixed_bits(kvm, TCR2_EL2, &res0, &res1); set_sysreg_masks(kvm, TCR2_EL2, res0, res1); /* SCTLR_EL1 */ get_reg_fixed_bits(kvm, SCTLR_EL1, &res0, &res1); set_sysreg_masks(kvm, SCTLR_EL1, res0, res1); /* SCTLR2_ELx */ get_reg_fixed_bits(kvm, SCTLR2_EL1, &res0, &res1); set_sysreg_masks(kvm, SCTLR2_EL1, res0, res1); get_reg_fixed_bits(kvm, SCTLR2_EL2, &res0, &res1); set_sysreg_masks(kvm, SCTLR2_EL2, res0, res1); /* MDCR_EL2 */ get_reg_fixed_bits(kvm, MDCR_EL2, &res0, &res1); set_sysreg_masks(kvm, MDCR_EL2, res0, res1); /* CNTHCTL_EL2 */ res0 = GENMASK(63, 20); res1 = 0; if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RME, IMP)) res0 |= CNTHCTL_CNTPMASK | CNTHCTL_CNTVMASK; if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, ECV, CNTPOFF)) { res0 |= CNTHCTL_ECV; if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, ECV, IMP)) res0 |= (CNTHCTL_EL1TVT | CNTHCTL_EL1TVCT | CNTHCTL_EL1NVPCT | CNTHCTL_EL1NVVCT); } if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP)) res0 |= GENMASK(11, 8); set_sysreg_masks(kvm, CNTHCTL_EL2, res0, res1); /* ICH_HCR_EL2 */ res0 = ICH_HCR_EL2_RES0; res1 = ICH_HCR_EL2_RES1; if (!(kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_EL2_TDS)) res0 |= ICH_HCR_EL2_TDIR; /* No GICv4 is presented to the guest */ res0 |= ICH_HCR_EL2_DVIM | ICH_HCR_EL2_vSGIEOICount; set_sysreg_masks(kvm, ICH_HCR_EL2, res0, res1); /* VNCR_EL2 */ set_sysreg_masks(kvm, VNCR_EL2, VNCR_EL2_RES0, VNCR_EL2_RES1); out: for (enum vcpu_sysreg sr = __SANITISED_REG_START__; sr < NR_SYS_REGS; sr++) __vcpu_rmw_sys_reg(vcpu, sr, |=, 0); return 0; } void check_nested_vcpu_requests(struct kvm_vcpu *vcpu) { if (kvm_check_request(KVM_REQ_NESTED_S2_UNMAP, vcpu)) { struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu; write_lock(&vcpu->kvm->mmu_lock); if (mmu->pending_unmap) { kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), true); mmu->pending_unmap = false; } write_unlock(&vcpu->kvm->mmu_lock); } if (kvm_check_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu)) kvm_map_l1_vncr(vcpu); /* Must be last, as may switch context! */ if (kvm_check_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu)) kvm_inject_nested_irq(vcpu); } /* * One of the many architectural bugs in FEAT_NV2 is that the guest hypervisor * can write to HCR_EL2 behind our back, potentially changing the exception * routing / masking for even the host context. * * What follows is some slop to (1) react to exception routing / masking and (2) * preserve the pending SError state across translation regimes. */ void kvm_nested_flush_hwstate(struct kvm_vcpu *vcpu) { if (!vcpu_has_nv(vcpu)) return; if (unlikely(vcpu_test_and_clear_flag(vcpu, NESTED_SERROR_PENDING))) kvm_inject_serror_esr(vcpu, vcpu_get_vsesr(vcpu)); } void kvm_nested_sync_hwstate(struct kvm_vcpu *vcpu) { unsigned long *hcr = vcpu_hcr(vcpu); if (!vcpu_has_nv(vcpu)) return; /* * We previously decided that an SError was deliverable to the guest. * Reap the pending state from HCR_EL2 and... */ if (unlikely(__test_and_clear_bit(__ffs(HCR_VSE), hcr))) vcpu_set_flag(vcpu, NESTED_SERROR_PENDING); /* * Re-attempt SError injection in case the deliverability has changed, * which is necessary to faithfully emulate WFI the case of a pending * SError being a wakeup condition. */ if (unlikely(vcpu_test_and_clear_flag(vcpu, NESTED_SERROR_PENDING))) kvm_inject_serror_esr(vcpu, vcpu_get_vsesr(vcpu)); } /* * KVM unconditionally sets most of these traps anyway but use an allowlist * to document the guest hypervisor traps that may take precedence and guard * against future changes to the non-nested trap configuration. */ #define NV_MDCR_GUEST_INCLUDE (MDCR_EL2_TDE | \ MDCR_EL2_TDA | \ MDCR_EL2_TDRA | \ MDCR_EL2_TTRF | \ MDCR_EL2_TPMS | \ MDCR_EL2_TPM | \ MDCR_EL2_TPMCR | \ MDCR_EL2_TDCC | \ MDCR_EL2_TDOSA) void kvm_nested_setup_mdcr_el2(struct kvm_vcpu *vcpu) { u64 guest_mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2); if (is_nested_ctxt(vcpu)) vcpu->arch.mdcr_el2 |= (guest_mdcr & NV_MDCR_GUEST_INCLUDE); /* * In yet another example where FEAT_NV2 is fscking broken, accesses * to MDSCR_EL1 are redirected to the VNCR despite having an effect * at EL2. Use a big hammer to apply sanity. * * Unless of course we have FEAT_FGT, in which case we can precisely * trap MDSCR_EL1. */ else if (!cpus_have_final_cap(ARM64_HAS_FGT)) vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; } |
| 14 14 14 42 15 38 42 29 17 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 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 | // 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 <linux/shmem_fs.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; /* * 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) { vm_dirty_bytes = 0; writeback_set_ratelimit(); } 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 = timer_container_of(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) { timer_delete_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 = dtc->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. * * 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, 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, 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 = timer_container_of(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) timer_delete(&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 folios in writeback to aggregate I/O until * the writeback iteration finishes, we do not loop back to the * start of the file. Doing so causes a folio lock/folio * writeback access order inversion - we should only ever lock * multiple folios in ascending folio->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); 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 /* 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; /* * Shmem writeback relies on swap, and swap writeback is LRU based, * not using the dirty mark. */ VM_WARN_ON_ONCE(folio_test_swapcache(folio) || shmem_mapping(mapping)); 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, 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 bdi_writeback *wb; 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, PAGECACHE_TAG_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) 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); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, folio->index); struct inode *inode = mapping->host; struct bdi_writeback *wb; 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); 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) 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); |
| 298 300 297 2 5 300 298 299 299 299 300 299 300 1 2 2 1 298 271 271 270 1 1 5 5 2 1 1 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 | // 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> static int cpu_has_spe(u64 dfr0) { return cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) && !(read_sysreg_s(SYS_PMBIDR_EL1) & PMBIDR_EL1_P); } /** * 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; if (vcpu_has_nv(vcpu)) kvm_nested_setup_mdcr_el2(vcpu); /* 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 (cpu_has_spe(dfr0)) host_data_set_flag(HAS_SPE); if (has_vhe()) return; /* Check if we have BRBE implemented and available at the host */ if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_BRBE_SHIFT)) host_data_set_flag(HAS_BRBE); 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); } } void kvm_debug_init_vhe(void) { /* Clear PMSCR_EL1.E{0,1}SPE which reset to UNKNOWN values. */ if (host_data_test_flag(HAS_SPE)) write_sysreg_el1(0, SYS_PMSCR); } /* * 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); if (has_vhe()) *host_data_ptr(host_debug_state.mdcr_el2) = read_sysreg(mdcr_el2); /* * 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 (has_vhe()) write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2); 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_rmw_sys_reg(vcpu, OSLSR_EL1, |=, OSLSR_EL1_OSLK); else __vcpu_rmw_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(); } static bool skip_trbe_access(bool skip_condition) { return (WARN_ON_ONCE(preemptible()) || skip_condition || is_protected_kvm_enabled() || !is_kvm_arm_initialised()); } void kvm_enable_trbe(void) { if (!skip_trbe_access(has_vhe())) host_data_set_flag(TRBE_ENABLED); } EXPORT_SYMBOL_GPL(kvm_enable_trbe); void kvm_disable_trbe(void) { if (!skip_trbe_access(has_vhe())) host_data_clear_flag(TRBE_ENABLED); } EXPORT_SYMBOL_GPL(kvm_disable_trbe); void kvm_tracing_set_el1_configuration(u64 trfcr_while_in_guest) { if (skip_trbe_access(false)) 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); |
| 1 1 2 9 4 1 5 5 5 248 248 26 26 6 1 5 10 9 4 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * KVM coalesced MMIO * * Copyright (c) 2008 Bull S.A.S. * Copyright 2009 Red Hat, Inc. and/or its affiliates. * * Author: Laurent Vivier <Laurent.Vivier@bull.net> * */ #include <kvm/iodev.h> #include <linux/kvm_host.h> #include <linux/slab.h> #include <linux/kvm.h> #include "coalesced_mmio.h" static inline struct kvm_coalesced_mmio_dev *to_mmio(struct kvm_io_device *dev) { return container_of(dev, struct kvm_coalesced_mmio_dev, dev); } static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev, gpa_t addr, int len) { /* is it in a batchable area ? * (addr,len) is fully included in * (zone->addr, zone->size) */ if (len < 0) return 0; if (addr + len < addr) return 0; if (addr < dev->zone.addr) return 0; if (addr + len > dev->zone.addr + dev->zone.size) return 0; return 1; } static int coalesced_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, const void *val) { struct kvm_coalesced_mmio_dev *dev = to_mmio(this); struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring; __u32 insert; if (!coalesced_mmio_in_range(dev, addr, len)) return -EOPNOTSUPP; spin_lock(&dev->kvm->ring_lock); /* * last is the index of the entry to fill. Verify userspace hasn't * set last to be out of range, and that there is room in the ring. * Leave one entry free in the ring so that userspace can differentiate * between an empty ring and a full ring. */ insert = READ_ONCE(ring->last); if (insert >= KVM_COALESCED_MMIO_MAX || (insert + 1) % KVM_COALESCED_MMIO_MAX == READ_ONCE(ring->first)) { spin_unlock(&dev->kvm->ring_lock); return -EOPNOTSUPP; } /* copy data in first free entry of the ring */ ring->coalesced_mmio[insert].phys_addr = addr; ring->coalesced_mmio[insert].len = len; memcpy(ring->coalesced_mmio[insert].data, val, len); ring->coalesced_mmio[insert].pio = dev->zone.pio; smp_wmb(); ring->last = (insert + 1) % KVM_COALESCED_MMIO_MAX; spin_unlock(&dev->kvm->ring_lock); return 0; } static void coalesced_mmio_destructor(struct kvm_io_device *this) { struct kvm_coalesced_mmio_dev *dev = to_mmio(this); list_del(&dev->list); kfree(dev); } static const struct kvm_io_device_ops coalesced_mmio_ops = { .write = coalesced_mmio_write, .destructor = coalesced_mmio_destructor, }; int kvm_coalesced_mmio_init(struct kvm *kvm) { struct page *page; page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) return -ENOMEM; kvm->coalesced_mmio_ring = page_address(page); /* * We're using this spinlock to sync access to the coalesced ring. * The list doesn't need its own lock since device registration and * unregistration should only happen when kvm->slots_lock is held. */ spin_lock_init(&kvm->ring_lock); INIT_LIST_HEAD(&kvm->coalesced_zones); return 0; } void kvm_coalesced_mmio_free(struct kvm *kvm) { if (kvm->coalesced_mmio_ring) free_page((unsigned long)kvm->coalesced_mmio_ring); } int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_zone *zone) { int ret; struct kvm_coalesced_mmio_dev *dev; if (zone->pio != 1 && zone->pio != 0) return -EINVAL; dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL_ACCOUNT); if (!dev) return -ENOMEM; kvm_iodevice_init(&dev->dev, &coalesced_mmio_ops); dev->kvm = kvm; dev->zone = *zone; mutex_lock(&kvm->slots_lock); ret = kvm_io_bus_register_dev(kvm, zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, zone->addr, zone->size, &dev->dev); if (ret < 0) goto out_free_dev; list_add_tail(&dev->list, &kvm->coalesced_zones); mutex_unlock(&kvm->slots_lock); return 0; out_free_dev: mutex_unlock(&kvm->slots_lock); kfree(dev); return ret; } int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, struct kvm_coalesced_mmio_zone *zone) { struct kvm_coalesced_mmio_dev *dev, *tmp; int r; if (zone->pio != 1 && zone->pio != 0) return -EINVAL; mutex_lock(&kvm->slots_lock); list_for_each_entry_safe(dev, tmp, &kvm->coalesced_zones, list) { if (zone->pio == dev->zone.pio && coalesced_mmio_in_range(dev, zone->addr, zone->size)) { r = kvm_io_bus_unregister_dev(kvm, zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev); /* * On failure, unregister destroys all devices on the * bus, including the target device. There's no need * to restart the walk as there aren't any zones left. */ if (r) break; } } mutex_unlock(&kvm->slots_lock); /* * Ignore the result of kvm_io_bus_unregister_dev(), from userspace's * perspective, the coalesced MMIO is most definitely unregistered. */ return 0; } |
| 4 4 | 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 | /* * 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/netdev_lock.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 struct ipoib_ifupdown_work { struct work_struct work; struct net_device *dev; netdevice_tracker dev_tracker; bool up; }; static void ipoib_ifupdown_task(struct work_struct *work) { struct ipoib_ifupdown_work *pwork = container_of(work, struct ipoib_ifupdown_work, work); struct net_device *dev = pwork->dev; unsigned int flags; rtnl_lock(); flags = dev->flags; if (pwork->up) flags |= IFF_UP; else flags &= ~IFF_UP; if (dev->flags != flags) dev_change_flags(dev, flags, NULL); rtnl_unlock(); netdev_put(dev, &pwork->dev_tracker); kfree(pwork); } static void ipoib_schedule_ifupdown_task(struct net_device *dev, bool up) { struct ipoib_ifupdown_work *work; if ((up && (dev->flags & IFF_UP)) || (!up && !(dev->flags & IFF_UP))) return; work = kmalloc(sizeof(*work), GFP_KERNEL); if (!work) return; work->dev = dev; netdev_hold(dev, &work->dev_tracker, GFP_KERNEL); work->up = up; INIT_WORK(&work->work, ipoib_ifupdown_task); queue_work(ipoib_workqueue, &work->work); } 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 */ netdev_lock_ops_to_full(dev); list_for_each_entry(cpriv, &priv->child_intfs, list) ipoib_schedule_ifupdown_task(cpriv->dev, true); netdev_unlock_full_to_ops(dev); } 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 */ netdev_lock_ops_to_full(dev); list_for_each_entry(cpriv, &priv->child_intfs, list) ipoib_schedule_ifupdown_task(cpriv->dev, false); netdev_unlock_full_to_ops(dev); } 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 L2 master net_device on top of the given net_device. * @dev: base IPoIB net_device * * Returns the L2 master net_device with reference held if the L2 master * exists (such as bond netdevice), or returns same netdev with reference * held when master does not exist or when L3 master (such as VRF netdev). */ 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); if (!master || netif_is_l3_master(master)) master = dev; dev_hold(master); rcu_read_unlock(); return master; } 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; } } if (test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) return matches; /* Check child interfaces */ netdev_lock(priv->dev); 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; } netdev_unlock(priv->dev); 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 pkey and GID */ 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 pkey and GID 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_lock_ops(dev); netdev_update_features(dev); netif_set_mtu(dev, ipoib_cm_max_mtu(dev)); netif_set_real_num_tx_queues(dev, 1); netdev_unlock_ops(dev); 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_lock_ops(dev); netdev_update_features(dev); netif_set_mtu(dev, min(priv->mcast_mtu, dev->mtu)); netif_set_real_num_tx_queues(dev, dev->num_tx_queues); netdev_unlock_ops(dev); 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(); netdev_lock_ops(priv->dev); 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: netdev_unlock_ops(priv->dev); 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); netdev_lock(priv->parent); list_add_tail(&priv->list, &ppriv->child_intfs); netdev_unlock(priv->parent); } return 0; } static void ipoib_ndo_uninit(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); /* * 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); netdev_lock(ppriv->dev); list_del(&priv->list); netdev_unlock(ppriv->dev); } 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); 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)) { netdev_lock_ops_to_full(priv->dev); list_for_each_entry(child_priv, &priv->child_intfs, list) set_base_guid(child_priv, gid); netdev_unlock_full_to_ops(priv->dev); } } 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)); if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) { struct ipoib_dev_priv *cpriv; netdev_lock_ops_to_full(dev); list_for_each_entry(cpriv, &priv->child_intfs, list) queue_work(ipoib_workqueue, &cpriv->flush_light); netdev_unlock_full_to_ops(dev); } 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 */ ipoib_queue_work(priv, IPOIB_FLUSH_HEAVY); ndev->rtnl_link_ops = ipoib_get_link_ops(); dev_net_set(ndev, rdma_dev_net(hca)); 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(); netdev_lock(priv->dev); list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) unregister_netdevice_queue(cpriv->dev, &head); netdev_unlock(priv->dev); 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); |
| 258 256 256 256 239 239 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_MMAN_H__ #define __ASM_MMAN_H__ #include <uapi/asm/mman.h> #ifndef BUILD_VDSO #include <linux/compiler.h> #include <linux/fs.h> #include <linux/hugetlb.h> #include <linux/shmem_fs.h> #include <linux/types.h> static inline vm_flags_t arch_calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { vm_flags_t ret = 0; if (system_supports_bti() && (prot & PROT_BTI)) ret |= VM_ARM64_BTI; if (system_supports_mte() && (prot & PROT_MTE)) ret |= VM_MTE; #ifdef CONFIG_ARCH_HAS_PKEYS if (system_supports_poe()) { ret |= pkey & BIT(0) ? VM_PKEY_BIT0 : 0; ret |= pkey & BIT(1) ? VM_PKEY_BIT1 : 0; ret |= pkey & BIT(2) ? VM_PKEY_BIT2 : 0; } #endif return ret; } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) static inline vm_flags_t arch_calc_vm_flag_bits(struct file *file, unsigned long flags) { /* * Only allow MTE on anonymous mappings as these are guaranteed to be * backed by tags-capable memory. The vm_flags may be overridden by a * filesystem supporting MTE (RAM-based). */ if (system_supports_mte()) { if (flags & (MAP_ANONYMOUS | MAP_HUGETLB)) return VM_MTE_ALLOWED; if (shmem_file(file) || is_file_hugepages(file)) return VM_MTE_ALLOWED; } return 0; } #define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags) static inline bool arch_validate_prot(unsigned long prot, unsigned long addr __always_unused) { unsigned long supported = PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM; if (system_supports_bti()) supported |= PROT_BTI; if (system_supports_mte()) supported |= PROT_MTE; return (prot & ~supported) == 0; } #define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr) static inline bool arch_validate_flags(vm_flags_t vm_flags) { if (system_supports_mte()) { /* * only allow VM_MTE if VM_MTE_ALLOWED has been set * previously */ if ((vm_flags & VM_MTE) && !(vm_flags & VM_MTE_ALLOWED)) return false; } if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) { /* An executable GCS isn't a good idea. */ if (vm_flags & VM_EXEC) return false; /* The memory management core should prevent this */ VM_WARN_ON(vm_flags & VM_SHARED); } return true; } #define arch_validate_flags(vm_flags) arch_validate_flags(vm_flags) #endif /* !BUILD_VDSO */ #endif /* ! __ASM_MMAN_H__ */ |
| 74 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_ERR_H #define _LINUX_ERR_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/errno.h> /* * Kernel pointers have redundant information, so we can use a * scheme where we can return either an error code or a normal * pointer with the same return value. * * This should be a per-architecture thing, to allow different * error and pointer decisions. */ #define MAX_ERRNO 4095 #ifndef __ASSEMBLY__ /** * IS_ERR_VALUE - Detect an error pointer. * @x: The pointer to check. * * Like IS_ERR(), but does not generate a compiler warning if result is unused. */ #define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO) /** * ERR_PTR - Create an error pointer. * @error: A negative error code. * * Encodes @error into a pointer value. Users should consider the result * opaque and not assume anything about how the error is encoded. * * Return: A pointer with @error encoded within its value. */ static inline void * __must_check ERR_PTR(long error) { return (void *) error; } /* Return the pointer in the percpu address space. */ #define ERR_PTR_PCPU(error) ((void __percpu *)(unsigned long)ERR_PTR(error)) /* Cast an error pointer to __iomem. */ #define IOMEM_ERR_PTR(error) (__force void __iomem *)ERR_PTR(error) /** * PTR_ERR - Extract the error code from an error pointer. * @ptr: An error pointer. * Return: The error code within @ptr. */ static inline long __must_check PTR_ERR(__force const void *ptr) { return (long) ptr; } /* Read an error pointer from the percpu address space. */ #define PTR_ERR_PCPU(ptr) (PTR_ERR((const void *)(__force const unsigned long)(ptr))) /** * IS_ERR - Detect an error pointer. * @ptr: The pointer to check. * Return: true if @ptr is an error pointer, false otherwise. */ static inline bool __must_check IS_ERR(__force const void *ptr) { return IS_ERR_VALUE((unsigned long)ptr); } /* Read an error pointer from the percpu address space. */ #define IS_ERR_PCPU(ptr) (IS_ERR((const void *)(__force const unsigned long)(ptr))) /** * IS_ERR_OR_NULL - Detect an error pointer or a null pointer. * @ptr: The pointer to check. * * Like IS_ERR(), but also returns true for a null pointer. */ static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) { return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); } /** * ERR_CAST - Explicitly cast an error-valued pointer to another pointer type * @ptr: The pointer to cast. * * Explicitly cast an error-valued pointer to another pointer type in such a * way as to make it clear that's what's going on. */ static inline void * __must_check ERR_CAST(__force const void *ptr) { /* cast away the const */ return (void *) ptr; } /** * PTR_ERR_OR_ZERO - Extract the error code from a pointer if it has one. * @ptr: A potential error pointer. * * Convenience function that can be used inside a function that returns * an error code to propagate errors received as error pointers. * For example, ``return PTR_ERR_OR_ZERO(ptr);`` replaces: * * .. code-block:: c * * if (IS_ERR(ptr)) * return PTR_ERR(ptr); * else * return 0; * * Return: The error code within @ptr if it is an error pointer; 0 otherwise. */ static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr) { if (IS_ERR(ptr)) return PTR_ERR(ptr); else return 0; } #endif #endif /* _LINUX_ERR_H */ |
| 4 3 4 | 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 | // 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/netdev_lock.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, "option obsolete, use_carrier cannot be disabled"); 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; DEFINE_STATIC_KEY_FALSE(bond_bcast_neigh_enabled); 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; } } bool bond_xdp_check(struct bonding *bond, int mode) { switch (mode) { 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; 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 * @bond_dev: pointer to the bond net device * @xs: pointer to transformer state struct * @extack: extack point to fill failure reason **/ static int bond_ipsec_add_sa(struct net_device *bond_dev, struct xfrm_state *xs, struct netlink_ext_ack *extack) { 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; } err = real_dev->xfrmdev_ops->xdo_dev_state_add(real_dev, xs, extack); if (!err) { xs->xso.real_dev = real_dev; 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; if (real_dev->xfrmdev_ops->xdo_dev_state_add(real_dev, ipsec->xs, NULL)) { slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__); continue; } spin_lock_bh(&ipsec->xs->lock); /* xs might have been killed by the user during the migration * to the new dev, but bond_ipsec_del_sa() should have done * nothing, as xso.real_dev is NULL. * Delete it from the device we just added it to. The pending * bond_ipsec_free_sa() call will do the rest of the cleanup. */ if (ipsec->xs->km.state == XFRM_STATE_DEAD && real_dev->xfrmdev_ops->xdo_dev_state_delete) real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev, ipsec->xs); ipsec->xs->xso.real_dev = real_dev; spin_unlock_bh(&ipsec->xs->lock); } out: mutex_unlock(&bond->ipsec_lock); } /** * bond_ipsec_del_sa - clear out this specific SA * @bond_dev: pointer to the bond net device * @xs: pointer to transformer state struct **/ static void bond_ipsec_del_sa(struct net_device *bond_dev, struct xfrm_state *xs) { struct net_device *real_dev; if (!bond_dev || !xs->xso.real_dev) return; real_dev = xs->xso.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__); return; } real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev, xs); } 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__); continue; } spin_lock_bh(&ipsec->xs->lock); ipsec->xs->xso.real_dev = NULL; /* Don't double delete states killed by the user. */ if (ipsec->xs->km.state != XFRM_STATE_DEAD) real_dev->xfrmdev_ops->xdo_dev_state_delete(real_dev, ipsec->xs); spin_unlock_bh(&ipsec->xs->lock); if (real_dev->xfrmdev_ops->xdo_dev_state_free) real_dev->xfrmdev_ops->xdo_dev_state_free(real_dev, ipsec->xs); } mutex_unlock(&bond->ipsec_lock); } static void bond_ipsec_free_sa(struct net_device *bond_dev, struct xfrm_state *xs) { struct net_device *real_dev; struct bond_ipsec *ipsec; struct bonding *bond; if (!bond_dev) return; bond = netdev_priv(bond_dev); mutex_lock(&bond->ipsec_lock); if (!xs->xso.real_dev) goto out; real_dev = xs->xso.real_dev; xs->xso.real_dev = NULL; if (real_dev->xfrmdev_ops && real_dev->xfrmdev_ops->xdo_dev_state_free) real_dev->xfrmdev_ops->xdo_dev_state_free(real_dev, xs); out: 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); } /** * 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; rcu_read_lock(); real_dev = bond_ipsec_dev(xs); if (!real_dev || netif_is_bond_master(real_dev)) { rcu_read_unlock(); return false; } rcu_read_unlock(); return true; } /** * 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"; } } /*----------------------------- 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 = netif_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, &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, &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 bond_up_slave *usable; struct slave *slave = NULL; if (!bond->send_peer_notif || bond->send_peer_notif % max(1, bond->params.peer_notif_delay) != 0 || !netif_carrier_ok(bond->dev)) return false; /* The send_peer_notif is set by active-backup or 8023ad * mode, and cleared in bond_close() when changing mode. * It is safe to only check bond mode here. */ if (BOND_MODE(bond) == BOND_MODE_8023AD) { usable = rcu_dereference_rtnl(bond->usable_slaves); if (!usable || !READ_ONCE(usable->count)) return false; } else { slave = rcu_dereference_rtnl(bond->curr_active_slave); if (!slave || 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 : "all"); 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_MODE(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 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; } /* 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); } else if (bond->params.fail_over_mac == BOND_FOM_FOLLOW && BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && bond_has_slaves(bond) && memcmp(slave_dev->dev_addr, bond_dev->dev_addr, bond_dev->addr_len) == 0) { /* Set slave to random address to avoid duplicate mac * address in later fail over. */ eth_random_addr(ss.__data); } else { goto skip_mac_set; } ss.ss_family = slave_dev->type; res = dev_set_mac_address(slave_dev, &ss, extack); if (res) { slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res); goto err_restore_mtu; } skip_mac_set: /* 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; /* check for initial state */ new_slave->link = BOND_LINK_NOCHANGE; if (bond->params.miimon) { if (netif_carrier_ok(slave_dev)) { 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(); } /* broadcast mode uses the all_slaves to loop through slaves. */ if (bond_mode_can_use_xmit_hash(bond) || BOND_MODE(bond) == BOND_MODE_BROADCAST) 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, &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_MODE(bond) == BOND_MODE_BROADCAST) 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_FOM_ACTIVE || 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, &ss, NULL); } if (unregister) { netdev_lock_ops(slave_dev); __netif_set_mtu(slave_dev, slave->original_mtu); netdev_unlock_ops(slave_dev); } 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 = netif_carrier_ok(slave->dev); 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; 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); rcu_read_unlock(); if (commit || bond->send_peer_notif) { /* Race avoidance with bond_close cancel of workqueue */ if (!rtnl_trylock()) { delay = 1; goto re_arm; } if (commit) { bond_for_each_slave(bond, slave, iter) { bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER); } bond_miimon_commit(bond); } if (bond->send_peer_notif) { bond->send_peer_notif--; if (should_notify_peers) call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); } rtnl_unlock(); /* might sleep, hold no other locks */ } re_arm: if (bond->params.miimon) queue_delayed_work(bond->wq, &bond->mii_work, delay); } 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]; 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); } 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->params.broadcast_neighbor) static_branch_inc(&bond_bcast_neigh_enabled); } 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_MODE(bond) == BOND_MODE_8023AD && bond->params.broadcast_neighbor) static_branch_dec(&bond_bcast_neigh_enabled); 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, &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]; } static bool bond_should_broadcast_neighbor(struct sk_buff *skb, struct net_device *dev) { struct bonding *bond = netdev_priv(dev); struct { struct ipv6hdr ip6; struct icmp6hdr icmp6; } *combined, _combined; if (!static_branch_unlikely(&bond_bcast_neigh_enabled)) return false; if (!bond->params.broadcast_neighbor) return false; if (skb->protocol == htons(ETH_P_ARP)) return true; if (skb->protocol == htons(ETH_P_IPV6)) { combined = skb_header_pointer(skb, skb_mac_header_len(skb), sizeof(_combined), &_combined); if (combined && combined->ip6.nexthdr == NEXTHDR_ICMP && (combined->icmp6.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION || combined->icmp6.icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT)) return true; } return false; } /* 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 or usable slave interfaces. * under rcu_read_lock when this function is called. */ static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev, bool all_slaves) { struct bonding *bond = netdev_priv(bond_dev); struct bond_up_slave *slaves; bool xmit_suc = false; bool skb_used = false; int slaves_count, i; if (all_slaves) slaves = rcu_dereference(bond->all_slaves); else slaves = rcu_dereference(bond->usable_slaves); slaves_count = slaves ? READ_ONCE(slaves->count) : 0; for (i = 0; i < slaves_count; i++) { struct slave *slave = slaves->arr[i]; 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: if (bond_should_broadcast_neighbor(skb, dev)) return bond_xmit_broadcast(skb, dev, false); fallthrough; case BOND_MODE_XOR: return bond_3ad_xor_xmit(skb, dev); case BOND_MODE_BROADCAST: return bond_xmit_broadcast(skb, dev, true); 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_MODE(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_immutable = 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 != 1) { pr_err("Error: invalid use_carrier parameter (%d)\n", use_carrier); return -EINVAL; } 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->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; params->broadcast_neighbor = 0; 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_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_rtnl(struct net *net, struct list_head *dev_kill_list) { struct bond_net *bn = net_generic(net, bond_net_id); struct bonding *bond, *tmp_bond; /* Kill off any bonds created after unregistering bond rtnl ops */ 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_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_rtnl = bond_net_exit_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"); MODULE_IMPORT_NS("NETDEV_INTERNAL"); |
| 584 43 1396 65 1391 23 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: common low-level thread information accessors * * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds */ #ifndef _LINUX_THREAD_INFO_H #define _LINUX_THREAD_INFO_H #include <linux/types.h> #include <linux/limits.h> #include <linux/bug.h> #include <linux/restart_block.h> #include <linux/errno.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels, * including <asm/current.h> can cause a circular dependency on some platforms. */ #include <asm/current.h> #define current_thread_info() ((struct thread_info *)current) #endif #include <linux/bitops.h> /* * For per-arch arch_within_stack_frames() implementations, defined in * asm/thread_info.h. */ enum { BAD_STACK = -1, NOT_STACK = 0, GOOD_FRAME, GOOD_STACK, }; #ifdef CONFIG_GENERIC_ENTRY enum syscall_work_bit { SYSCALL_WORK_BIT_SECCOMP, SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT, SYSCALL_WORK_BIT_SYSCALL_TRACE, SYSCALL_WORK_BIT_SYSCALL_EMU, SYSCALL_WORK_BIT_SYSCALL_AUDIT, SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH, SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP, }; #define SYSCALL_WORK_SECCOMP BIT(SYSCALL_WORK_BIT_SECCOMP) #define SYSCALL_WORK_SYSCALL_TRACEPOINT BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT) #define SYSCALL_WORK_SYSCALL_TRACE BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE) #define SYSCALL_WORK_SYSCALL_EMU BIT(SYSCALL_WORK_BIT_SYSCALL_EMU) #define SYSCALL_WORK_SYSCALL_AUDIT BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT) #define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH) #define SYSCALL_WORK_SYSCALL_EXIT_TRAP BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP) #endif #include <asm/thread_info.h> #ifndef TIF_NEED_RESCHED_LAZY #ifdef CONFIG_ARCH_HAS_PREEMPT_LAZY #error Inconsistent PREEMPT_LAZY #endif #define TIF_NEED_RESCHED_LAZY TIF_NEED_RESCHED #define _TIF_NEED_RESCHED_LAZY _TIF_NEED_RESCHED #endif #ifdef __KERNEL__ #ifndef arch_set_restart_data #define arch_set_restart_data(restart) do { } while (0) #endif static inline long set_restart_fn(struct restart_block *restart, long (*fn)(struct restart_block *)) { restart->fn = fn; arch_set_restart_data(restart); return -ERESTART_RESTARTBLOCK; } #ifndef THREAD_ALIGN #define THREAD_ALIGN THREAD_SIZE #endif #define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions */ static inline void set_ti_thread_flag(struct thread_info *ti, int flag) { set_bit(flag, (unsigned long *)&ti->flags); } static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) { clear_bit(flag, (unsigned long *)&ti->flags); } static inline void update_ti_thread_flag(struct thread_info *ti, int flag, bool value) { if (value) set_ti_thread_flag(ti, flag); else clear_ti_thread_flag(ti, flag); } static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_ti_thread_flag(struct thread_info *ti, int flag) { return test_bit(flag, (unsigned long *)&ti->flags); } /* * This may be used in noinstr code, and needs to be __always_inline to prevent * inadvertent instrumentation. */ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti) { return READ_ONCE(ti->flags); } #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) #define update_thread_flag(flag, value) \ update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) #define read_thread_flags() \ read_ti_thread_flags(current_thread_info()) #define read_task_thread_flags(t) \ read_ti_thread_flags(task_thread_info(t)) #ifdef CONFIG_GENERIC_ENTRY #define set_syscall_work(fl) \ set_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define test_syscall_work(fl) \ test_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define clear_syscall_work(fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define set_task_syscall_work(t, fl) \ set_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define test_task_syscall_work(t, fl) \ test_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define clear_task_syscall_work(t, fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #else /* CONFIG_GENERIC_ENTRY */ #define set_syscall_work(fl) \ set_ti_thread_flag(current_thread_info(), TIF_##fl) #define test_syscall_work(fl) \ test_ti_thread_flag(current_thread_info(), TIF_##fl) #define clear_syscall_work(fl) \ clear_ti_thread_flag(current_thread_info(), TIF_##fl) #define set_task_syscall_work(t, fl) \ set_ti_thread_flag(task_thread_info(t), TIF_##fl) #define test_task_syscall_work(t, fl) \ test_ti_thread_flag(task_thread_info(t), TIF_##fl) #define clear_task_syscall_work(t, fl) \ clear_ti_thread_flag(task_thread_info(t), TIF_##fl) #endif /* !CONFIG_GENERIC_ENTRY */ #ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H static __always_inline bool tif_test_bit(int bit) { return arch_test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #else static __always_inline bool tif_test_bit(int bit) { return test_bit(bit, (unsigned long *)(¤t_thread_info()->flags)); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ static __always_inline bool tif_need_resched(void) { return tif_test_bit(TIF_NEED_RESCHED); } #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) { return 0; } #endif #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif void arch_task_cache_init(void); /* for CONFIG_SH */ void arch_release_task_struct(struct task_struct *tsk); int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ |
| 4 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * Event handling for HSR and PRP devices. */ #include <linux/netdevice.h> #include <net/rtnetlink.h> #include <linux/rculist.h> #include <linux/timer.h> #include <linux/etherdevice.h> #include "hsr_main.h" #include "hsr_device.h" #include "hsr_netlink.h" #include "hsr_framereg.h" #include "hsr_slave.h" static bool hsr_slave_empty(struct hsr_priv *hsr) { struct hsr_port *port; hsr_for_each_port_rtnl(hsr, port) if (port->type != HSR_PT_MASTER) return false; return true; } static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, void *ptr) { struct hsr_port *port, *master; struct net_device *dev; struct hsr_priv *hsr; LIST_HEAD(list_kill); int mtu_max; int res; dev = netdev_notifier_info_to_dev(ptr); port = hsr_port_get_rtnl(dev); if (!port) { if (!is_hsr_master(dev)) return NOTIFY_DONE; /* Not an HSR device */ hsr = netdev_priv(dev); port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (!port) { /* Resend of notification concerning removed device? */ return NOTIFY_DONE; } } else { hsr = port->hsr; } switch (event) { case NETDEV_UP: /* Administrative state DOWN */ case NETDEV_DOWN: /* Administrative state UP */ case NETDEV_CHANGE: /* Link (carrier) state changes */ hsr_check_carrier_and_operstate(hsr); break; case NETDEV_CHANGENAME: if (is_hsr_master(dev)) hsr_debugfs_rename(dev); break; case NETDEV_CHANGEADDR: if (port->type == HSR_PT_MASTER) { /* This should not happen since there's no * ndo_set_mac_address() for HSR devices - i.e. not * supported. */ break; } master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port->type == HSR_PT_SLAVE_A) { eth_hw_addr_set(master->dev, dev->dev_addr); call_netdevice_notifiers(NETDEV_CHANGEADDR, master->dev); if (hsr->prot_version == PRP_V1) { port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) { eth_hw_addr_set(port->dev, dev->dev_addr); call_netdevice_notifiers(NETDEV_CHANGEADDR, port->dev); } } } /* Make sure we recognize frames from ourselves in hsr_rcv() */ port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); res = hsr_create_self_node(hsr, master->dev->dev_addr, port ? port->dev->dev_addr : master->dev->dev_addr); if (res) netdev_warn(master->dev, "Could not update HSR node address.\n"); break; case NETDEV_CHANGEMTU: if (port->type == HSR_PT_MASTER) break; /* Handled in ndo_change_mtu() */ mtu_max = hsr_get_max_mtu(port->hsr); master = hsr_port_get_hsr(port->hsr, HSR_PT_MASTER); WRITE_ONCE(master->dev->mtu, mtu_max); break; case NETDEV_UNREGISTER: if (!is_hsr_master(dev)) { master = hsr_port_get_hsr(port->hsr, HSR_PT_MASTER); hsr_del_port(port); if (hsr_slave_empty(master->hsr)) { const struct rtnl_link_ops *ops; ops = master->dev->rtnl_link_ops; ops->dellink(master->dev, &list_kill); unregister_netdevice_many(&list_kill); } } break; case NETDEV_PRE_TYPE_CHANGE: /* HSR works only on Ethernet devices. Refuse slave to change * its type. */ return NOTIFY_BAD; } return NOTIFY_DONE; } struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt) { struct hsr_port *port; hsr_for_each_port_rtnl(hsr, port) if (port->type == pt) return port; return NULL; } int hsr_get_version(struct net_device *dev, enum hsr_version *ver) { struct hsr_priv *hsr; hsr = netdev_priv(dev); *ver = hsr->prot_version; return 0; } EXPORT_SYMBOL(hsr_get_version); static struct notifier_block hsr_nb = { .notifier_call = hsr_netdev_notify, /* Slave event notifications */ }; static int __init hsr_init(void) { int err; BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_HLEN); err = register_netdevice_notifier(&hsr_nb); if (err) return err; err = hsr_netlink_init(); if (err) { unregister_netdevice_notifier(&hsr_nb); return err; } return 0; } static void __exit hsr_exit(void) { hsr_netlink_exit(); hsr_debugfs_remove_root(); unregister_netdevice_notifier(&hsr_nb); } module_init(hsr_init); module_exit(hsr_exit); MODULE_DESCRIPTION("High-availability Seamless Redundancy (HSR) driver"); MODULE_LICENSE("GPL"); |
| 1 778 204 33 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This header provides generic wrappers for memory access instrumentation that * the compiler cannot emit for: KASAN, KCSAN, KMSAN. */ #ifndef _LINUX_INSTRUMENTED_H #define _LINUX_INSTRUMENTED_H #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> #include <linux/kmsan-checks.h> #include <linux/types.h> /** * instrument_read - instrument regular read access * @v: address of access * @size: size of access * * Instrument a regular read access. The instrumentation should be inserted * before the actual read happens. */ static __always_inline void instrument_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_read(v, size); } /** * instrument_write - instrument regular write access * @v: address of access * @size: size of access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. */ static __always_inline void instrument_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_write(v, size); } /** * instrument_read_write - instrument regular read-write access * @v: address of access * @size: size of access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. */ static __always_inline void instrument_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_read_write(v, size); } /** * instrument_atomic_read - instrument atomic read access * @v: address of access * @size: size of access * * Instrument an atomic read access. The instrumentation should be inserted * before the actual read happens. */ static __always_inline void instrument_atomic_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_atomic_read(v, size); } /** * instrument_atomic_write - instrument atomic write access * @v: address of access * @size: size of access * * Instrument an atomic write access. The instrumentation should be inserted * before the actual write happens. */ static __always_inline void instrument_atomic_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_write(v, size); } /** * instrument_atomic_read_write - instrument atomic read-write access * @v: address of access * @size: size of access * * Instrument an atomic read-write access. The instrumentation should be * inserted before the actual write happens. */ static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_read_write(v, size); } /** * instrument_copy_to_user - instrument reads of copy_to_user * @to: destination address * @from: source address * @n: number of bytes to copy * * Instrument reads from kernel memory, that are due to copy_to_user (and * variants). The instrumentation must be inserted before the accesses. */ static __always_inline void instrument_copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); kcsan_check_read(from, n); kmsan_copy_to_user(to, from, n, 0); } /** * instrument_copy_from_user_before - add instrumentation before copy_from_user * @to: destination address * @from: source address * @n: number of bytes to copy * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. */ static __always_inline void instrument_copy_from_user_before(const void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); kcsan_check_write(to, n); } /** * instrument_copy_from_user_after - add instrumentation after copy_from_user * @to: destination address * @from: source address * @n: number of bytes to copy * @left: number of bytes not copied (as returned by copy_from_user) * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted after the accesses. */ static __always_inline void instrument_copy_from_user_after(const void *to, const void __user *from, unsigned long n, unsigned long left) { kmsan_unpoison_memory(to, n - left); } /** * instrument_memcpy_before - add instrumentation before non-instrumented memcpy * @to: destination address * @from: source address * @n: number of bytes to copy * * Instrument memory accesses that happen in custom memcpy implementations. The * instrumentation should be inserted before the memcpy call. */ static __always_inline void instrument_memcpy_before(void *to, const void *from, unsigned long n) { kasan_check_write(to, n); kasan_check_read(from, n); kcsan_check_write(to, n); kcsan_check_read(from, n); } /** * instrument_memcpy_after - add instrumentation after non-instrumented memcpy * @to: destination address * @from: source address * @n: number of bytes to copy * @left: number of bytes not copied (if known) * * Instrument memory accesses that happen in custom memcpy implementations. The * instrumentation should be inserted after the memcpy call. */ static __always_inline void instrument_memcpy_after(void *to, const void *from, unsigned long n, unsigned long left) { kmsan_memmove(to, from, n - left); } /** * instrument_get_user() - add instrumentation to get_user()-like macros * @to: destination variable, may not be address-taken * * get_user() and friends are fragile, so it may depend on the implementation * whether the instrumentation happens before or after the data is copied from * the userspace. */ #define instrument_get_user(to) \ ({ \ u64 __tmp = (u64)(to); \ kmsan_unpoison_memory(&__tmp, sizeof(__tmp)); \ to = __tmp; \ }) /** * instrument_put_user() - add instrumentation to put_user()-like macros * @from: source address * @ptr: userspace pointer to copy to * @size: number of bytes to copy * * put_user() and friends are fragile, so it may depend on the implementation * whether the instrumentation happens before or after the data is copied from * the userspace. */ #define instrument_put_user(from, ptr, size) \ ({ \ kmsan_copy_to_user(ptr, &from, sizeof(from), 0); \ }) #endif /* _LINUX_INSTRUMENTED_H */ |
| 94 95 7 92 95 101 7 7 7 7 101 7 144 7 102 146 144 146 146 145 57 93 93 7 7 7 57 56 57 8 8 8 54 57 56 7 56 56 7 56 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the SID table type. * * Original author: Stephen Smalley, <stephen.smalley.work@gmail.com> * Author: Ondrej Mosnacek, <omosnacek@gmail.com> * * Copyright (C) 2018 Red Hat, Inc. */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <asm/barrier.h> #include "flask.h" #include "security.h" #include "sidtab.h" #include "services.h" struct sidtab_str_cache { struct rcu_head rcu_member; struct list_head lru_member; struct sidtab_entry *parent; u32 len; char str[] __counted_by(len); }; #define index_to_sid(index) ((index) + SECINITSID_NUM + 1) #define sid_to_index(sid) ((sid) - (SECINITSID_NUM + 1)) int sidtab_init(struct sidtab *s) { u32 i; memset(s->roots, 0, sizeof(s->roots)); for (i = 0; i < SECINITSID_NUM; i++) s->isids[i].set = 0; s->frozen = false; s->count = 0; s->convert = NULL; hash_init(s->context_to_sid); spin_lock_init(&s->lock); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 s->cache_free_slots = CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE; INIT_LIST_HEAD(&s->cache_lru_list); spin_lock_init(&s->cache_lock); #endif return 0; } static u32 context_to_sid(struct sidtab *s, struct context *context, u32 hash) { struct sidtab_entry *entry; u32 sid = 0; rcu_read_lock(); hash_for_each_possible_rcu(s->context_to_sid, entry, list, hash) { if (entry->hash != hash) continue; if (context_equal(&entry->context, context)) { sid = entry->sid; break; } } rcu_read_unlock(); return sid; } int sidtab_set_initial(struct sidtab *s, u32 sid, struct context *context) { struct sidtab_isid_entry *isid; u32 hash; int rc; if (sid == 0 || sid > SECINITSID_NUM) return -EINVAL; isid = &s->isids[sid - 1]; rc = context_cpy(&isid->entry.context, context); if (rc) return rc; #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 isid->entry.cache = NULL; #endif isid->set = 1; hash = context_compute_hash(context); /* * Multiple initial sids may map to the same context. Check that this * context is not already represented in the context_to_sid hashtable * to avoid duplicate entries and long linked lists upon hash * collision. */ if (!context_to_sid(s, context, hash)) { isid->entry.sid = sid; isid->entry.hash = hash; hash_add(s->context_to_sid, &isid->entry.list, hash); } return 0; } int sidtab_hash_stats(struct sidtab *sidtab, char *page) { unsigned int i; int chain_len = 0; int slots_used = 0; int entries = 0; int max_chain_len = 0; unsigned int cur_bucket = 0; struct sidtab_entry *entry; rcu_read_lock(); hash_for_each_rcu(sidtab->context_to_sid, i, entry, list) { entries++; if (i == cur_bucket) { chain_len++; if (chain_len == 1) slots_used++; } else { cur_bucket = i; if (chain_len > max_chain_len) max_chain_len = chain_len; chain_len = 0; } } rcu_read_unlock(); if (chain_len > max_chain_len) max_chain_len = chain_len; return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n" "longest chain: %d\n", entries, slots_used, SIDTAB_HASH_BUCKETS, max_chain_len); } static u32 sidtab_level_from_count(u32 count) { u32 capacity = SIDTAB_LEAF_ENTRIES; u32 level = 0; while (count > capacity) { capacity <<= SIDTAB_INNER_SHIFT; ++level; } return level; } static int sidtab_alloc_roots(struct sidtab *s, u32 level) { u32 l; if (!s->roots[0].ptr_leaf) { s->roots[0].ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[0].ptr_leaf) return -ENOMEM; } for (l = 1; l <= level; ++l) if (!s->roots[l].ptr_inner) { s->roots[l].ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!s->roots[l].ptr_inner) return -ENOMEM; s->roots[l].ptr_inner->entries[0] = s->roots[l - 1]; } return 0; } static struct sidtab_entry *sidtab_do_lookup(struct sidtab *s, u32 index, int alloc) { union sidtab_entry_inner *entry; u32 level, capacity_shift, leaf_index = index / SIDTAB_LEAF_ENTRIES; /* find the level of the subtree we need */ level = sidtab_level_from_count(index + 1); capacity_shift = level * SIDTAB_INNER_SHIFT; /* allocate roots if needed */ if (alloc && sidtab_alloc_roots(s, level) != 0) return NULL; /* lookup inside the subtree */ entry = &s->roots[level]; while (level != 0) { capacity_shift -= SIDTAB_INNER_SHIFT; --level; entry = &entry->ptr_inner->entries[leaf_index >> capacity_shift]; leaf_index &= ((u32)1 << capacity_shift) - 1; if (!entry->ptr_inner) { if (alloc) entry->ptr_inner = kzalloc( SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_inner) return NULL; } } if (!entry->ptr_leaf) { if (alloc) entry->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_ATOMIC); if (!entry->ptr_leaf) return NULL; } return &entry->ptr_leaf->entries[index % SIDTAB_LEAF_ENTRIES]; } static struct sidtab_entry *sidtab_lookup(struct sidtab *s, u32 index) { /* read entries only after reading count */ u32 count = smp_load_acquire(&s->count); if (index >= count) return NULL; return sidtab_do_lookup(s, index, 0); } static struct sidtab_entry *sidtab_lookup_initial(struct sidtab *s, u32 sid) { return s->isids[sid - 1].set ? &s->isids[sid - 1].entry : NULL; } static struct sidtab_entry *sidtab_search_core(struct sidtab *s, u32 sid, int force) { if (sid != 0) { struct sidtab_entry *entry; if (sid > SECINITSID_NUM) entry = sidtab_lookup(s, sid_to_index(sid)); else entry = sidtab_lookup_initial(s, sid); if (entry && (!entry->context.len || force)) return entry; } return sidtab_lookup_initial(s, SECINITSID_UNLABELED); } struct sidtab_entry *sidtab_search_entry(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 0); } struct sidtab_entry *sidtab_search_entry_force(struct sidtab *s, u32 sid) { return sidtab_search_core(s, sid, 1); } int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid) { unsigned long flags; u32 count, hash = context_compute_hash(context); struct sidtab_convert_params *convert; struct sidtab_entry *dst, *dst_convert; int rc; *sid = context_to_sid(s, context, hash); if (*sid) return 0; /* lock-free search failed: lock, re-search, and insert if not found */ spin_lock_irqsave(&s->lock, flags); rc = 0; *sid = context_to_sid(s, context, hash); if (*sid) goto out_unlock; if (unlikely(s->frozen)) { /* * This sidtab is now frozen - tell the caller to abort and * get the new one. */ rc = -ESTALE; goto out_unlock; } count = s->count; /* bail out if we already reached max entries */ rc = -EOVERFLOW; if (count >= SIDTAB_MAX) goto out_unlock; /* insert context into new entry */ rc = -ENOMEM; dst = sidtab_do_lookup(s, count, 1); if (!dst) goto out_unlock; dst->sid = index_to_sid(count); dst->hash = hash; rc = context_cpy(&dst->context, context); if (rc) goto out_unlock; /* * if we are building a new sidtab, we need to convert the context * and insert it there as well */ convert = s->convert; if (convert) { struct sidtab *target = convert->target; rc = -ENOMEM; dst_convert = sidtab_do_lookup(target, count, 1); if (!dst_convert) { context_destroy(&dst->context); goto out_unlock; } rc = services_convert_context(convert->args, context, &dst_convert->context, GFP_ATOMIC); if (rc) { context_destroy(&dst->context); goto out_unlock; } dst_convert->sid = index_to_sid(count); dst_convert->hash = context_compute_hash(&dst_convert->context); target->count = count + 1; hash_add_rcu(target->context_to_sid, &dst_convert->list, dst_convert->hash); } if (context->len) pr_info("SELinux: Context %s is not valid (left unmapped).\n", context->str); *sid = index_to_sid(count); /* write entries before updating count */ smp_store_release(&s->count, count + 1); hash_add_rcu(s->context_to_sid, &dst->list, dst->hash); rc = 0; out_unlock: spin_unlock_irqrestore(&s->lock, flags); return rc; } static void sidtab_convert_hashtable(struct sidtab *s, u32 count) { struct sidtab_entry *entry; u32 i; for (i = 0; i < count; i++) { entry = sidtab_do_lookup(s, i, 0); entry->sid = index_to_sid(i); entry->hash = context_compute_hash(&entry->context); hash_add_rcu(s->context_to_sid, &entry->list, entry->hash); } } static int sidtab_convert_tree(union sidtab_entry_inner *edst, union sidtab_entry_inner *esrc, u32 *pos, u32 count, u32 level, struct sidtab_convert_params *convert) { int rc; u32 i; if (level != 0) { if (!edst->ptr_inner) { edst->ptr_inner = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_inner) return -ENOMEM; } i = 0; while (i < SIDTAB_INNER_ENTRIES && *pos < count) { rc = sidtab_convert_tree(&edst->ptr_inner->entries[i], &esrc->ptr_inner->entries[i], pos, count, level - 1, convert); if (rc) return rc; i++; } } else { if (!edst->ptr_leaf) { edst->ptr_leaf = kzalloc(SIDTAB_NODE_ALLOC_SIZE, GFP_KERNEL); if (!edst->ptr_leaf) return -ENOMEM; } i = 0; while (i < SIDTAB_LEAF_ENTRIES && *pos < count) { rc = services_convert_context( convert->args, &esrc->ptr_leaf->entries[i].context, &edst->ptr_leaf->entries[i].context, GFP_KERNEL); if (rc) return rc; (*pos)++; i++; } cond_resched(); } return 0; } int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params) { unsigned long flags; u32 count, level, pos; int rc; spin_lock_irqsave(&s->lock, flags); /* concurrent policy loads are not allowed */ if (s->convert) { spin_unlock_irqrestore(&s->lock, flags); return -EBUSY; } count = s->count; level = sidtab_level_from_count(count); /* allocate last leaf in the new sidtab (to avoid race with * live convert) */ rc = sidtab_do_lookup(params->target, count - 1, 1) ? 0 : -ENOMEM; if (rc) { spin_unlock_irqrestore(&s->lock, flags); return rc; } /* set count in case no new entries are added during conversion */ params->target->count = count; /* enable live convert of new entries */ s->convert = params; /* we can safely convert the tree outside the lock */ spin_unlock_irqrestore(&s->lock, flags); pr_info("SELinux: Converting %u SID table entries...\n", count); /* convert all entries not covered by live convert */ pos = 0; rc = sidtab_convert_tree(¶ms->target->roots[level], &s->roots[level], &pos, count, level, params); if (rc) { /* we need to keep the old table - disable live convert */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); return rc; } /* * The hashtable can also be modified in sidtab_context_to_sid() * so we must re-acquire the lock here. */ spin_lock_irqsave(&s->lock, flags); sidtab_convert_hashtable(params->target, count); spin_unlock_irqrestore(&s->lock, flags); return 0; } void sidtab_cancel_convert(struct sidtab *s) { unsigned long flags; /* cancelling policy load - disable live convert of sidtab */ spin_lock_irqsave(&s->lock, flags); s->convert = NULL; spin_unlock_irqrestore(&s->lock, flags); } void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock) { spin_lock_irqsave(&s->lock, *flags); s->frozen = true; s->convert = NULL; } void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock) { spin_unlock_irqrestore(&s->lock, *flags); } static void sidtab_destroy_entry(struct sidtab_entry *entry) { context_destroy(&entry->context); #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 kfree(rcu_dereference_raw(entry->cache)); #endif } static void sidtab_destroy_tree(union sidtab_entry_inner entry, u32 level) { u32 i; if (level != 0) { struct sidtab_node_inner *node = entry.ptr_inner; if (!node) return; for (i = 0; i < SIDTAB_INNER_ENTRIES; i++) sidtab_destroy_tree(node->entries[i], level - 1); kfree(node); } else { struct sidtab_node_leaf *node = entry.ptr_leaf; if (!node) return; for (i = 0; i < SIDTAB_LEAF_ENTRIES; i++) sidtab_destroy_entry(&node->entries[i]); kfree(node); } } void sidtab_destroy(struct sidtab *s) { u32 i, level; for (i = 0; i < SECINITSID_NUM; i++) if (s->isids[i].set) sidtab_destroy_entry(&s->isids[i].entry); level = SIDTAB_MAX_LEVEL; while (level && !s->roots[level].ptr_inner) --level; sidtab_destroy_tree(s->roots[level], level); /* * The context_to_sid hashtable's objects are all shared * with the isids array and context tree, and so don't need * to be cleaned up here. */ } #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 void sidtab_sid2str_put(struct sidtab *s, struct sidtab_entry *entry, const char *str, u32 str_len) { struct sidtab_str_cache *cache, *victim = NULL; unsigned long flags; /* do not cache invalid contexts */ if (entry->context.len) return; spin_lock_irqsave(&s->cache_lock, flags); cache = rcu_dereference_protected(entry->cache, lockdep_is_held(&s->cache_lock)); if (cache) { /* entry in cache - just bump to the head of LRU list */ list_move(&cache->lru_member, &s->cache_lru_list); goto out_unlock; } cache = kmalloc(struct_size(cache, str, str_len), GFP_ATOMIC); if (!cache) goto out_unlock; if (s->cache_free_slots == 0) { /* pop a cache entry from the tail and free it */ victim = container_of(s->cache_lru_list.prev, struct sidtab_str_cache, lru_member); list_del(&victim->lru_member); rcu_assign_pointer(victim->parent->cache, NULL); } else { s->cache_free_slots--; } cache->parent = entry; cache->len = str_len; memcpy(cache->str, str, str_len); list_add(&cache->lru_member, &s->cache_lru_list); rcu_assign_pointer(entry->cache, cache); out_unlock: spin_unlock_irqrestore(&s->cache_lock, flags); kfree_rcu(victim, rcu_member); } int sidtab_sid2str_get(struct sidtab *s, struct sidtab_entry *entry, char **out, u32 *out_len) { struct sidtab_str_cache *cache; int rc = 0; if (entry->context.len) return -ENOENT; /* do not cache invalid contexts */ rcu_read_lock(); cache = rcu_dereference(entry->cache); if (!cache) { rc = -ENOENT; } else { *out_len = cache->len; if (out) { *out = kmemdup(cache->str, cache->len, GFP_ATOMIC); if (!*out) rc = -ENOMEM; } } rcu_read_unlock(); if (!rc && out) sidtab_sid2str_put(s, entry, *out, *out_len); return rc; } #endif /* CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 */ |
| 157 20 271 17 440 63 218 216 218 217 768 159 488 92 39 120 33 3 7 4 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: mm/ internal definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H #include <linux/fs.h> #include <linux/khugepaged.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/pagemap.h> #include <linux/pagewalk.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include <linux/tracepoint-defs.h> /* Internal core VMA manipulation functions. */ #include "vma.h" struct folio_batch; /* * Maintains state across a page table move. The operation assumes both source * and destination VMAs already exist and are specified by the user. * * Partial moves are permitted, but the old and new ranges must both reside * within a VMA. * * mmap lock must be held in write and VMA write locks must be held on any VMA * that is visible. * * Use the PAGETABLE_MOVE() macro to initialise this struct. * * The old_addr and new_addr fields are updated as the page table move is * executed. * * NOTE: The page table move is affected by reading from [old_addr, old_end), * and old_addr may be updated for better page table alignment, so len_in * represents the length of the range being copied as specified by the user. */ struct pagetable_move_control { struct vm_area_struct *old; /* Source VMA. */ struct vm_area_struct *new; /* Destination VMA. */ unsigned long old_addr; /* Address from which the move begins. */ unsigned long old_end; /* Exclusive address at which old range ends. */ unsigned long new_addr; /* Address to move page tables to. */ unsigned long len_in; /* Bytes to remap specified by user. */ bool need_rmap_locks; /* Do rmap locks need to be taken? */ bool for_stack; /* Is this an early temp stack being moved? */ }; #define PAGETABLE_MOVE(name, old_, new_, old_addr_, new_addr_, len_) \ struct pagetable_move_control name = { \ .old = old_, \ .new = new_, \ .old_addr = old_addr_, \ .old_end = (old_addr_) + (len_), \ .new_addr = new_addr_, \ .len_in = len_, \ } /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_NOLOCKDEP) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation cpuset and node placement constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) /* * Different from WARN_ON_ONCE(), no warning will be issued * when we specify __GFP_NOWARN. */ #define WARN_ON_ONCE_GFP(cond, gfp) ({ \ static bool __section(".data..once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \ __warned = true; \ WARN_ON(1); \ } \ unlikely(__ret_warn_once); \ }) void page_writeback_init(void); /* * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages, * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently * leaves nr_pages_mapped at 0, but avoid surprise if it participates later. */ #define ENTIRELY_MAPPED 0x800000 #define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1) /* * Flags passed to __show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ /* * How many individual pages have an elevated _mapcount. Excludes * the folio's entire_mapcount. * * Don't use this function outside of debugging code. */ static inline int folio_nr_pages_mapped(const struct folio *folio) { if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) return -1; return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; } /* * Retrieve the first entry of a folio based on a provided entry within the * folio. We cannot rely on folio->swap as there is no guarantee that it has * been initialized. Used for calling arch_swap_restore() */ static inline swp_entry_t folio_swap(swp_entry_t entry, const struct folio *folio) { swp_entry_t swap = { .val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)), }; return swap; } static inline void *folio_raw_mapping(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; return (void *)(mapping & ~FOLIO_MAPPING_FLAGS); } /* * This is a file-backed mapping, and is about to be memory mapped - invoke its * mmap hook and safely handle error conditions. On error, VMA hooks will be * mutated. * * @file: File which backs the mapping. * @vma: VMA which we are mapping. * * Returns: 0 if success, error otherwise. */ static inline int mmap_file(struct file *file, struct vm_area_struct *vma) { int err = vfs_mmap(file, vma); if (likely(!err)) return 0; /* * OK, we tried to call the file hook for mmap(), but an error * arose. The mapping is in an inconsistent state and we most not invoke * any further hooks on it. */ vma->vm_ops = &vma_dummy_vm_ops; return err; } /* * If the VMA has a close hook then close it, and since closing it might leave * it in an inconsistent state which makes the use of any hooks suspect, clear * them down by installing dummy empty hooks. */ static inline void vma_close(struct vm_area_struct *vma) { if (vma->vm_ops && vma->vm_ops->close) { vma->vm_ops->close(vma); /* * The mapping is in an inconsistent state, and no further hooks * may be invoked upon it. */ vma->vm_ops = &vma_dummy_vm_ops; } } #ifdef CONFIG_MMU /* Flags for folio_pte_batch(). */ typedef int __bitwise fpb_t; /* Compare PTEs respecting the dirty bit. */ #define FPB_RESPECT_DIRTY ((__force fpb_t)BIT(0)) /* Compare PTEs respecting the soft-dirty bit. */ #define FPB_RESPECT_SOFT_DIRTY ((__force fpb_t)BIT(1)) /* Compare PTEs respecting the writable bit. */ #define FPB_RESPECT_WRITE ((__force fpb_t)BIT(2)) /* * Merge PTE write bits: if any PTE in the batch is writable, modify the * PTE at @ptentp to be writable. */ #define FPB_MERGE_WRITE ((__force fpb_t)BIT(3)) /* * Merge PTE young and dirty bits: if any PTE in the batch is young or dirty, * modify the PTE at @ptentp to be young or dirty, respectively. */ #define FPB_MERGE_YOUNG_DIRTY ((__force fpb_t)BIT(4)) static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) { if (!(flags & FPB_RESPECT_DIRTY)) pte = pte_mkclean(pte); if (likely(!(flags & FPB_RESPECT_SOFT_DIRTY))) pte = pte_clear_soft_dirty(pte); if (likely(!(flags & FPB_RESPECT_WRITE))) pte = pte_wrprotect(pte); return pte_mkold(pte); } /** * folio_pte_batch_flags - detect a PTE batch for a large folio * @folio: The large folio to detect a PTE batch for. * @vma: The VMA. Only relevant with FPB_MERGE_WRITE, otherwise can be NULL. * @ptep: Page table pointer for the first entry. * @ptentp: Pointer to a COPY of the first page table entry whose flags this * function updates based on @flags if appropriate. * @max_nr: The maximum number of table entries to consider. * @flags: Flags to modify the PTE batch semantics. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio in a single VMA and a single page table. * * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN, * the accessed bit, writable bit, dirty bit (unless FPB_RESPECT_DIRTY is set) * and soft-dirty bit (unless FPB_RESPECT_SOFT_DIRTY is set). * * @ptep must map any page of the folio. max_nr must be at least one and * must be limited by the caller so scanning cannot exceed a single VMA and * a single page table. * * Depending on the FPB_MERGE_* flags, the pte stored at @ptentp will * be updated: it's crucial that a pointer to a COPY of the first * page table entry, obtained through ptep_get(), is provided as @ptentp. * * This function will be inlined to optimize based on the input parameters; * consider using folio_pte_batch() instead if applicable. * * Return: the number of table entries in the batch. */ static inline unsigned int folio_pte_batch_flags(struct folio *folio, struct vm_area_struct *vma, pte_t *ptep, pte_t *ptentp, unsigned int max_nr, fpb_t flags) { bool any_writable = false, any_young = false, any_dirty = false; pte_t expected_pte, pte = *ptentp; unsigned int nr, cur_nr; VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); /* * Ensure this is a pointer to a copy not a pointer into a page table. * If this is a stack value, it won't be a valid virtual address, but * that's fine because it also cannot be pointing into the page table. */ VM_WARN_ON(virt_addr_valid(ptentp) && PageTable(virt_to_page(ptentp))); /* Limit max_nr to the actual remaining PFNs in the folio we could batch. */ max_nr = min_t(unsigned long, max_nr, folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte)); nr = pte_batch_hint(ptep, pte); expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); ptep = ptep + nr; while (nr < max_nr) { pte = ptep_get(ptep); if (!pte_same(__pte_batch_clear_ignored(pte, flags), expected_pte)) break; if (flags & FPB_MERGE_WRITE) any_writable |= pte_write(pte); if (flags & FPB_MERGE_YOUNG_DIRTY) { any_young |= pte_young(pte); any_dirty |= pte_dirty(pte); } cur_nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, cur_nr); ptep += cur_nr; nr += cur_nr; } if (any_writable) *ptentp = pte_mkwrite(*ptentp, vma); if (any_young) *ptentp = pte_mkyoung(*ptentp); if (any_dirty) *ptentp = pte_mkdirty(*ptentp); return min(nr, max_nr); } unsigned int folio_pte_batch(struct folio *folio, pte_t *ptep, pte_t pte, unsigned int max_nr); /** * pte_move_swp_offset - Move the swap entry offset field of a swap pte * forward or backward by delta * @pte: The initial pte state; is_swap_pte(pte) must be true and * non_swap_entry() must be false. * @delta: The direction and the offset we are moving; forward if delta * is positive; backward if delta is negative * * Moves the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_move_swp_offset(pte_t pte, long delta) { swp_entry_t entry = pte_to_swp_entry(pte); pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry), (swp_offset(entry) + delta))); if (pte_swp_soft_dirty(pte)) new = pte_swp_mksoft_dirty(new); if (pte_swp_exclusive(pte)) new = pte_swp_mkexclusive(new); if (pte_swp_uffd_wp(pte)) new = pte_swp_mkuffd_wp(new); return new; } /** * pte_next_swp_offset - Increment the swap entry offset field of a swap pte. * @pte: The initial pte state; is_swap_pte(pte) must be true and * non_swap_entry() must be false. * * Increments the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_next_swp_offset(pte_t pte) { return pte_move_swp_offset(pte, 1); } /** * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries * @start_ptep: Page table pointer for the first entry. * @max_nr: The maximum number of table entries to consider. * @pte: Page table entry for the first entry. * * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs * containing swap entries all with consecutive offsets and targeting the same * swap type, all with matching swp pte bits. * * max_nr must be at least one and must be limited by the caller so scanning * cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte) { pte_t expected_pte = pte_next_swp_offset(pte); const pte_t *end_ptep = start_ptep + max_nr; swp_entry_t entry = pte_to_swp_entry(pte); pte_t *ptep = start_ptep + 1; unsigned short cgroup_id; VM_WARN_ON(max_nr < 1); VM_WARN_ON(!is_swap_pte(pte)); VM_WARN_ON(non_swap_entry(entry)); cgroup_id = lookup_swap_cgroup_id(entry); while (ptep < end_ptep) { pte = ptep_get(ptep); if (!pte_same(pte, expected_pte)) break; if (lookup_swap_cgroup_id(pte_to_swp_entry(pte)) != cgroup_id) break; expected_pte = pte_next_swp_offset(expected_pte); ptep++; } return ptep - start_ptep; } #endif /* CONFIG_MMU */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled); static inline void acct_reclaim_writeback(struct folio *folio) { pg_data_t *pgdat = folio_pgdat(folio); int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); if (nr_throttled) __acct_reclaim_writeback(pgdat, folio, nr_throttled); } static inline void wake_throttle_isolated(pg_data_t *pgdat) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED]; if (waitqueue_active(wqh)) wake_up(wqh); } vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf); static inline vm_fault_t vmf_anon_prepare(struct vm_fault *vmf) { vm_fault_t ret = __vmf_anon_prepare(vmf); if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vmf->vma); return ret; } vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); bool __folio_end_writeback(struct folio *folio); void deactivate_file_folio(struct folio *folio); void folio_activate(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling, bool mm_wr_locked); void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); struct zap_details; void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); void zap_page_range_single_batched(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long size, struct zap_details *details); int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio, gfp_t gfp); void page_cache_ra_order(struct readahead_control *, struct file_ra_state *); void force_page_cache_ra(struct readahead_control *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index); force_page_cache_ra(&ractl, nr_to_read); } unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); void filemap_free_folio(struct address_space *mapping, struct folio *folio); int truncate_inode_folio(struct address_space *mapping, struct folio *folio); bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end); long mapping_evict_folio(struct address_space *mapping, struct folio *folio); unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed); /** * folio_evictable - Test whether a folio is evictable. * @folio: The folio to test. * * Test whether @folio is evictable -- i.e., should be placed on * active/inactive lists vs unevictable list. * * Reasons folio might not be evictable: * 1. folio's mapping marked unevictable * 2. One of the pages in the folio is part of an mlocked VMA */ static inline bool folio_evictable(struct folio *folio) { bool ret; /* Prevent address_space of inode and swap cache from being freed */ rcu_read_lock(); ret = !mapping_unevictable(folio_mapping(folio)) && !folio_test_mlocked(folio); rcu_read_unlock(); return ret; } /* * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1); } /* * Return true if a folio needs ->release_folio() calling upon it. */ static inline bool folio_needs_release(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); return folio_has_private(folio) || (mapping && mapping_release_always(mapping)); } extern unsigned long highest_memmap_pfn; /* * Maximum number of reclaim retries without progress before the OOM * killer is consider the only way forward. */ #define MAX_RECLAIM_RETRIES 16 /* * in mm/vmscan.c: */ bool folio_isolate_lru(struct folio *folio); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); #ifdef CONFIG_NUMA int user_proactive_reclaim(char *buf, struct mem_cgroup *memcg, pg_data_t *pgdat); #else static inline int user_proactive_reclaim(char *buf, struct mem_cgroup *memcg, pg_data_t *pgdat) { return 0; } #endif /* * in mm/rmap.c: */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/page_alloc.c */ #define K(x) ((x) << (PAGE_SHIFT-10)) extern char * const zone_names[MAX_NR_ZONES]; /* perform sanity checks on struct pages being allocated or freed */ DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); extern int min_free_kbytes; extern int defrag_mode; void setup_per_zone_wmarks(void); void calculate_min_free_kbytes(void); int __meminit init_per_zone_wmark_min(void); void page_alloc_sysctl_init(void); /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* * family of functions. * * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages() and then never change. * * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole structure * by a const pointer. */ struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; /* * highest_zoneidx represents highest usable zone index of * the allocation request. Due to the nature of the zone, * memory on lower zone than the highest_zoneidx will be * protected by lowmem_reserve[highest_zoneidx]. * * highest_zoneidx is also used by reclaim/compaction to limit * the target zone since higher zone than this index cannot be * usable for this allocation request. */ enum zone_type highest_zoneidx; bool spread_dirty_pages; }; /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the * page from being allocated in parallel and returning garbage as the order. * If a caller does not hold page_zone(page)->lock, it must guarantee that the * page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use buddy_order_unsafe() below. */ static inline unsigned int buddy_order(struct page *page) { /* PageBuddy() must be checked by the caller */ return page_private(page); } /* * Like buddy_order(), but for callers who cannot afford to hold the zone lock. * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) /* * This function checks whether a page is free && is the buddy * we can coalesce a page and its buddy if * (a) the buddy is not in a hole (check before calling!) && * (b) the buddy is in the buddy system && * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * * For recording whether a page is in the buddy system, we set PageBuddy. * Setting, clearing, and testing PageBuddy is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ static inline bool page_is_buddy(struct page *page, struct page *buddy, unsigned int order) { if (!page_is_guard(buddy) && !PageBuddy(buddy)) return false; if (buddy_order(buddy) != order) return false; /* * zone check is done late to avoid uselessly calculating * zone/node ids for pages that could never merge. */ if (page_zone_id(page) != page_zone_id(buddy)) return false; VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); return true; } /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * * 1) Any buddy B1 will have an order O twin B2 which satisfies * the following equation: * B2 = B1 ^ (1 << O) * For example, if the starting buddy (buddy2) is #8 its order * 1 buddy is #10: * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 * * 2) Any buddy B will have an order O+1 parent P which * satisfies the following equation: * P = B & ~(1 << O) * * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) { return page_pfn ^ (1 << order); } /* * Find the buddy of @page and validate it. * @page: The input page * @pfn: The pfn of the page, it saves a call to page_to_pfn() when the * function is used in the performance-critical __free_one_page(). * @order: The order of the page * @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to * page_to_pfn(). * * The found buddy can be a non PageBuddy, out of @page's zone, or its order is * not the same as @page. The validation is necessary before use it. * * Return: the found buddy page or NULL if not found. */ static inline struct page *find_buddy_page_pfn(struct page *page, unsigned long pfn, unsigned int order, unsigned long *buddy_pfn) { unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order); struct page *buddy; buddy = page + (__buddy_pfn - pfn); if (buddy_pfn) *buddy_pfn = __buddy_pfn; if (page_is_buddy(page, buddy, order)) return buddy; return NULL; } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) { if (zone->contiguous) return pfn_to_page(start_pfn); return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } void set_zone_contiguous(struct zone *zone); bool pfn_range_intersects_zones(int nid, unsigned long start_pfn, unsigned long nr_pages); static inline void clear_zone_contiguous(struct zone *zone) { zone->contiguous = false; } extern int __isolate_free_page(struct page *page, unsigned int order); extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order, enum meminit_context context); /* * This will have no effect, other than possibly generating a warning, if the * caller passes in a non-large folio. */ static inline void folio_set_order(struct folio *folio, unsigned int order) { if (WARN_ON_ONCE(!order || !folio_test_large(folio))) return; VM_WARN_ON_ONCE(order > MAX_FOLIO_ORDER); folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order; #ifdef NR_PAGES_IN_LARGE_FOLIO folio->_nr_pages = 1U << order; #endif } bool __folio_unqueue_deferred_split(struct folio *folio); static inline bool folio_unqueue_deferred_split(struct folio *folio) { if (folio_order(folio) <= 1 || !folio_test_large_rmappable(folio)) return false; /* * At this point, there is no one trying to add the folio to * deferred_list. If folio is not in deferred_list, it's safe * to check without acquiring the split_queue_lock. */ if (data_race(list_empty(&folio->_deferred_list))) return false; return __folio_unqueue_deferred_split(folio); } static inline struct folio *page_rmappable_folio(struct page *page) { struct folio *folio = (struct folio *)page; if (folio && folio_test_large(folio)) folio_set_large_rmappable(folio); return folio; } static inline void prep_compound_head(struct page *page, unsigned int order) { struct folio *folio = (struct folio *)page; folio_set_order(folio, order); atomic_set(&folio->_large_mapcount, -1); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) atomic_set(&folio->_nr_pages_mapped, 0); if (IS_ENABLED(CONFIG_MM_ID)) { folio->_mm_ids = 0; folio->_mm_id_mapcount[0] = -1; folio->_mm_id_mapcount[1] = -1; } if (IS_ENABLED(CONFIG_64BIT) || order > 1) { atomic_set(&folio->_pincount, 0); atomic_set(&folio->_entire_mapcount, -1); } if (order > 1) INIT_LIST_HEAD(&folio->_deferred_list); } static inline void prep_compound_tail(struct page *head, int tail_idx) { struct page *p = head + tail_idx; p->mapping = TAIL_MAPPING; set_compound_head(p, head); set_page_private(p, 0); } void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern bool free_pages_prepare(struct page *page, unsigned int order); extern int user_min_free_kbytes; struct page *__alloc_frozen_pages_noprof(gfp_t, unsigned int order, int nid, nodemask_t *); #define __alloc_frozen_pages(...) \ alloc_hooks(__alloc_frozen_pages_noprof(__VA_ARGS__)) void free_frozen_pages(struct page *page, unsigned int order); void free_unref_folios(struct folio_batch *fbatch); #ifdef CONFIG_NUMA struct page *alloc_frozen_pages_noprof(gfp_t, unsigned int order); #else static inline struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned int order) { return __alloc_frozen_pages_noprof(gfp, order, numa_node_id(), NULL); } #endif #define alloc_frozen_pages(...) \ alloc_hooks(alloc_frozen_pages_noprof(__VA_ARGS__)) struct page *alloc_frozen_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned int order); #define alloc_frozen_pages_nolock(...) \ alloc_hooks(alloc_frozen_pages_nolock_noprof(__VA_ARGS__)) extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); extern void zone_pcp_init(struct zone *zone); extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, int nid, bool exact_nid); void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int, bool); #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* * in mm/compaction.c */ /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts * at the end of a zone and migrate_pfn begins at the start. Movable pages * are moved to the end of a zone during a compaction run and the run * completes when free_pfn <= migrate_pfn */ struct compact_control { struct list_head freepages[NR_PAGE_ORDERS]; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ /* * Acts as an in/out parameter to page isolation for migration. * isolate_migratepages uses it as a search base. * isolate_migratepages_block will update the value to the next pfn * after the last isolated one. */ unsigned long migrate_pfn; unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; unsigned short fast_search_fail;/* failures to use free list searches */ short search_order; /* order to start a fast search at */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock contention */ bool finish_pageblock; /* Scan the remainder of a pageblock. Used * when there are potentially transient * isolation or migration failures to * ensure forward progress. */ bool alloc_contig; /* alloc_contig_range allocation */ }; /* * Used in direct compaction when a page should be taken from the freelists * immediately when one is created during the free path. */ struct capture_control { struct compact_control *cc; struct page *page; }; unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void init_cma_reserved_pageblock(struct page *page); #endif /* CONFIG_COMPACTION || CONFIG_CMA */ struct cma; #ifdef CONFIG_CMA void *cma_reserve_early(struct cma *cma, unsigned long size); void init_cma_pageblock(struct page *page); #else static inline void *cma_reserve_early(struct cma *cma, unsigned long size) { return NULL; } static inline void init_cma_pageblock(struct page *page) { } #endif int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool claimable); static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } /* mm/util.c */ struct anon_vma *folio_anon_vma(const struct folio *folio); #ifdef CONFIG_MMU void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); extern long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked); bool mlock_future_ok(const struct mm_struct *mm, vm_flags_t vm_flags, unsigned long bytes); /* * NOTE: This function can't tell whether the folio is "fully mapped" in the * range. * "fully mapped" means all the pages of folio is associated with the page * table of range while this function just check whether the folio range is * within the range [start, end). Function caller needs to do page table * check if it cares about the page table association. * * Typical usage (like mlock or madvise) is: * Caller knows at least 1 page of folio is associated with page table of VMA * and the range [start, end) is intersect with the VMA range. Caller wants * to know whether the folio is fully associated with the range. It calls * this function to check whether the folio is in the range first. Then checks * the page table to know whether the folio is fully mapped to the range. */ static inline bool folio_within_range(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end) { pgoff_t pgoff, addr; unsigned long vma_pglen = vma_pages(vma); VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); if (start > end) return false; if (start < vma->vm_start) start = vma->vm_start; if (end > vma->vm_end) end = vma->vm_end; pgoff = folio_pgoff(folio); /* if folio start address is not in vma range */ if (!in_range(pgoff, vma->vm_pgoff, vma_pglen)) return false; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); return !(addr < start || end - addr < folio_size(folio)); } static inline bool folio_within_vma(struct folio *folio, struct vm_area_struct *vma) { return folio_within_range(folio, vma, vma->vm_start, vma->vm_end); } /* * mlock_vma_folio() and munlock_vma_folio(): * should be called with vma's mmap_lock held for read or write, * under page table lock for the pte/pmd being added or removed. * * mlock is usually called at the end of folio_add_*_rmap_*(), munlock at * the end of folio_remove_rmap_*(); but new anon folios are managed by * folio_add_lru_vma() calling mlock_new_folio(). */ void mlock_folio(struct folio *folio); static inline void mlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * The VM_SPECIAL check here serves two purposes. * 1) VM_IO check prevents migration from double-counting during mlock. * 2) Although mmap_region() and mlock_fixup() take care that VM_LOCKED * is never left set on a VM_SPECIAL vma, there is an interval while * file->f_op->mmap() is using vm_insert_page(s), when VM_LOCKED may * still be set while VM_SPECIAL bits are added: so ignore it then. */ if (unlikely((vma->vm_flags & (VM_LOCKED|VM_SPECIAL)) == VM_LOCKED)) mlock_folio(folio); } void munlock_folio(struct folio *folio); static inline void munlock_vma_folio(struct folio *folio, struct vm_area_struct *vma) { /* * munlock if the function is called. Ideally, we should only * do munlock if any page of folio is unmapped from VMA and * cause folio not fully mapped to VMA. * * But it's not easy to confirm that's the situation. So we * always munlock the folio and page reclaim will correct it * if it's wrong. */ if (unlikely(vma->vm_flags & VM_LOCKED)) munlock_folio(folio); } void mlock_new_folio(struct folio *folio); bool need_mlock_drain(int cpu); void mlock_drain_local(void); void mlock_drain_remote(int cpu); extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /** * vma_address - Find the virtual address a page range is mapped at * @vma: The vma which maps this object. * @pgoff: The page offset within its object. * @nr_pages: The number of pages to consider. * * If any page in this range is mapped by this VMA, return the first address * where any of these pages appear. Otherwise, return -EFAULT. */ static inline unsigned long vma_address(const struct vm_area_struct *vma, pgoff_t pgoff, unsigned long nr_pages) { unsigned long address; if (pgoff >= vma->vm_pgoff) { address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address >= vma->vm_end) address = -EFAULT; } else if (pgoff + nr_pages - 1 >= vma->vm_pgoff) { /* Test above avoids possibility of wrap to 0 on 32-bit */ address = vma->vm_start; } else { address = -EFAULT; } return address; } /* * Then at what user virtual address will none of the range be found in vma? * Assumes that vma_address() already returned a good starting address. */ static inline unsigned long vma_address_end(struct page_vma_mapped_walk *pvmw) { struct vm_area_struct *vma = pvmw->vma; pgoff_t pgoff; unsigned long address; /* Common case, plus ->pgoff is invalid for KSM */ if (pvmw->nr_pages == 1) return pvmw->address + PAGE_SIZE; pgoff = pvmw->pgoff + pvmw->nr_pages; address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); /* Check for address beyond vma (or wrapped through 0?) */ if (address < vma->vm_start || address > vma->vm_end) address = vma->vm_end; return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, struct file *fpin) { int flags = vmf->flags; if (fpin) return fpin; /* * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or * anything, so we only pin the file and drop the mmap_lock if only * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt. */ if (fault_flag_allow_retry_first(flags) && !(flags & FAULT_FLAG_RETRY_NOWAIT)) { fpin = get_file(vmf->vma->vm_file); release_fault_lock(vmf); } return fpin; } #else /* !CONFIG_MMU */ static inline void unmap_mapping_folio(struct folio *folio) { } static inline void mlock_new_folio(struct folio *folio) { } static inline bool need_mlock_drain(int cpu) { return false; } static inline void mlock_drain_local(void) { } static inline void mlock_drain_remote(int cpu) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) { } #endif /* !CONFIG_MMU */ /* Memory initialisation debug and verification */ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT DECLARE_STATIC_KEY_TRUE(deferred_pages); bool __init deferred_grow_zone(struct zone *zone, unsigned int order); #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ void init_deferred_page(unsigned long pfn, int nid); enum mminit_level { MMINIT_WARNING, MMINIT_VERIFY, MMINIT_TRACE }; #ifdef CONFIG_DEBUG_MEMORY_INIT extern int mminit_loglevel; #define mminit_dprintk(level, prefix, fmt, arg...) \ do { \ if (level < mminit_loglevel) { \ if (level <= MMINIT_WARNING) \ pr_warn("mminit::" prefix " " fmt, ##arg); \ else \ printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ } \ } while (0) extern void mminit_verify_pageflags_layout(void); extern void mminit_verify_zonelist(void); #else static inline void mminit_dprintk(enum mminit_level level, const char *prefix, const char *fmt, ...) { } static inline void mminit_verify_pageflags_layout(void) { } static inline void mminit_verify_zonelist(void) { } #endif /* CONFIG_DEBUG_MEMORY_INIT */ #define NODE_RECLAIM_NOSCAN -2 #define NODE_RECLAIM_FULL -1 #define NODE_RECLAIM_SOME 0 #define NODE_RECLAIM_SUCCESS 1 #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int); extern int find_next_best_node(int node, nodemask_t *used_node_mask); #else #define node_reclaim_mode 0 static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask, unsigned int order) { return NODE_RECLAIM_NOSCAN; } static inline int find_next_best_node(int node, nodemask_t *used_node_mask) { return NUMA_NO_NODE; } #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); } /* * mm/memory-failure.c */ #ifdef CONFIG_MEMORY_FAILURE int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill); void shake_folio(struct folio *folio); typedef int hwpoison_filter_func_t(struct page *p); void hwpoison_filter_register(hwpoison_filter_func_t *filter); void hwpoison_filter_unregister(void); #define MAGIC_HWPOISON 0x48575053U /* HWPS */ void SetPageHWPoisonTakenOff(struct page *page); void ClearPageHWPoisonTakenOff(struct page *page); bool take_page_off_buddy(struct page *page); bool put_page_back_buddy(struct page *page); struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); void add_to_kill_ksm(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long ksm_addr); unsigned long page_mapped_in_vma(const struct page *page, struct vm_area_struct *vma); #else static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill) { return -EBUSY; } #endif extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); extern void set_pageblock_order(void); unsigned long reclaim_pages(struct list_head *folio_list); unsigned int reclaim_clean_pages_from_list(struct zone *zone, struct list_head *folio_list); /* The ALLOC_WMARK bits are used as an index to zone->watermark */ #define ALLOC_WMARK_MIN WMARK_MIN #define ALLOC_WMARK_LOW WMARK_LOW #define ALLOC_WMARK_HIGH WMARK_HIGH #define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ /* Mask to get the watermark bits */ #define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) /* * Only MMU archs have async oom victim reclaim - aka oom_reaper so we * cannot assume a reduced access to memory reserves is sufficient for * !MMU */ #ifdef CONFIG_MMU #define ALLOC_OOM 0x08 #else #define ALLOC_OOM ALLOC_NO_WATERMARKS #endif #define ALLOC_NON_BLOCK 0x10 /* Caller cannot block. Allow access * to 25% of the min watermark or * 62.5% if __GFP_HIGH is set. */ #define ALLOC_MIN_RESERVE 0x20 /* __GFP_HIGH set. Allow access to 50% * of the min watermark. */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ #define ALLOC_CMA 0x80 /* allow allocations from CMA areas */ #ifdef CONFIG_ZONE_DMA32 #define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */ #else #define ALLOC_NOFRAGMENT 0x0 #endif #define ALLOC_HIGHATOMIC 0x200 /* Allows access to MIGRATE_HIGHATOMIC */ #define ALLOC_TRYLOCK 0x400 /* Only use spin_trylock in allocation path */ #define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */ /* Flags that allow allocations below the min watermark. */ #define ALLOC_RESERVES (ALLOC_NON_BLOCK|ALLOC_MIN_RESERVE|ALLOC_HIGHATOMIC|ALLOC_OOM) enum ttu_flags; struct tlbflush_unmap_batch; /* * only for MM internal work items which do not depend on * any allocations or locks which might depend on allocations */ extern struct workqueue_struct *mm_percpu_wq; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); void try_to_unmap_flush_dirty(void); void flush_tlb_batched_pending(struct mm_struct *mm); #else static inline void try_to_unmap_flush(void) { } static inline void try_to_unmap_flush_dirty(void) { } static inline void flush_tlb_batched_pending(struct mm_struct *mm) { } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; void setup_zone_pageset(struct zone *zone); struct migration_target_control { int nid; /* preferred node id */ nodemask_t *nmask; gfp_t gfp_mask; enum migrate_reason reason; }; /* * mm/filemap.c */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size); /* * mm/vmalloc.c */ #ifdef CONFIG_MMU void __init vmalloc_init(void); int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); unsigned int get_vm_area_page_order(struct vm_struct *vm); #else static inline void vmalloc_init(void) { } static inline int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift) { return -EINVAL; } #endif int __must_check __vmap_pages_range_noflush(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); void vunmap_range_noflush(unsigned long start, unsigned long end); void __vunmap_range_noflush(unsigned long start, unsigned long end); int numa_migrate_check(struct folio *folio, struct vm_fault *vmf, unsigned long addr, int *flags, bool writable, int *last_cpupid); void free_zone_device_folio(struct folio *folio); int migrate_device_coherent_folio(struct folio *folio); struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long shift, unsigned long vm_flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, const void *caller); /* * mm/gup.c */ int __must_check try_grab_folio(struct folio *folio, int refs, unsigned int flags); /* * mm/huge_memory.c */ void touch_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, bool write); void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write); /* * Parses a string with mem suffixes into its order. Useful to parse kernel * parameters. */ static inline int get_order_from_str(const char *size_str, unsigned long valid_orders) { unsigned long size; char *endptr; int order; size = memparse(size_str, &endptr); if (!is_power_of_2(size)) return -EINVAL; order = get_order(size); if (BIT(order) & ~valid_orders) return -EINVAL; return order; } enum { /* mark page accessed */ FOLL_TOUCH = 1 << 16, /* a retry, previous pass started an IO */ FOLL_TRIED = 1 << 17, /* we are working on non-current tsk/mm */ FOLL_REMOTE = 1 << 18, /* pages must be released via unpin_user_page */ FOLL_PIN = 1 << 19, /* gup_fast: prevent fall-back to slow gup */ FOLL_FAST_ONLY = 1 << 20, /* allow unlocking the mmap lock */ FOLL_UNLOCKABLE = 1 << 21, /* VMA lookup+checks compatible with MADV_POPULATE_(READ|WRITE) */ FOLL_MADV_POPULATE = 1 << 22, }; #define INTERNAL_GUP_FLAGS (FOLL_TOUCH | FOLL_TRIED | FOLL_REMOTE | FOLL_PIN | \ FOLL_FAST_ONLY | FOLL_UNLOCKABLE | \ FOLL_MADV_POPULATE) /* * Indicates for which pages that are write-protected in the page table, * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the * GUP pin will remain consistent with the pages mapped into the page tables * of the MM. * * Temporary unmapping of PageAnonExclusive() pages or clearing of * PageAnonExclusive() has to protect against concurrent GUP: * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq * * GUP-fast and KSM or temporary unmapping (swap, migration): see * folio_try_share_anon_rmap_*() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a * PTE-mapped THP. * * If the vma is NULL, we're coming from the GUP-fast path and might have * to fallback to the slow path just to lookup the vma. */ static inline bool gup_must_unshare(struct vm_area_struct *vma, unsigned int flags, struct page *page) { /* * FOLL_WRITE is implicitly handled correctly as the page table entry * has to be writable -- and if it references (part of) an anonymous * folio, that part is required to be marked exclusive. */ if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) return false; /* * Note: PageAnon(page) is stable until the page is actually getting * freed. */ if (!PageAnon(page)) { /* * We only care about R/O long-term pining: R/O short-term * pinning does not have the semantics to observe successive * changes through the process page tables. */ if (!(flags & FOLL_LONGTERM)) return false; /* We really need the vma ... */ if (!vma) return true; /* * ... because we only care about writable private ("COW") * mappings where we have to break COW early. */ return is_cow_mapping(vma->vm_flags); } /* Paired with a memory barrier in folio_try_share_anon_rmap_*(). */ if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_rmb(); /* * Note that KSM pages cannot be exclusive, and consequently, * cannot get pinned. */ return !PageAnonExclusive(page); } extern bool mirrored_kernelcore; bool memblock_has_mirror(void); void memblock_free_all(void); static __always_inline void vma_set_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff) { vma->vm_start = start; vma->vm_end = end; vma->vm_pgoff = pgoff; } static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma) { /* * NOTE: we must check this before VM_SOFTDIRTY on soft-dirty * enablements, because when without soft-dirty being compiled in, * VM_SOFTDIRTY is defined as 0x0, then !(vm_flags & VM_SOFTDIRTY) * will be constantly true. */ if (!IS_ENABLED(CONFIG_MEM_SOFT_DIRTY)) return false; /* * Soft-dirty is kind of special: its tracking is enabled when the * vma flags not set. */ return !(vma->vm_flags & VM_SOFTDIRTY); } static inline bool pmd_needs_soft_dirty_wp(struct vm_area_struct *vma, pmd_t pmd) { return vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd); } static inline bool pte_needs_soft_dirty_wp(struct vm_area_struct *vma, pte_t pte) { return vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte); } void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid); void __meminit __init_page_from_nid(unsigned long pfn, int nid); /* shrinker related functions */ unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority); #ifdef CONFIG_SHRINKER_DEBUG static inline __printf(2, 0) int shrinker_debugfs_name_alloc( struct shrinker *shrinker, const char *fmt, va_list ap) { shrinker->name = kvasprintf_const(GFP_KERNEL, fmt, ap); return shrinker->name ? 0 : -ENOMEM; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { kfree_const(shrinker->name); shrinker->name = NULL; } extern int shrinker_debugfs_add(struct shrinker *shrinker); extern struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id); extern void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id); #else /* CONFIG_SHRINKER_DEBUG */ static inline int shrinker_debugfs_add(struct shrinker *shrinker) { return 0; } static inline int shrinker_debugfs_name_alloc(struct shrinker *shrinker, const char *fmt, va_list ap) { return 0; } static inline void shrinker_debugfs_name_free(struct shrinker *shrinker) { } static inline struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker, int *debugfs_id) { *debugfs_id = -1; return NULL; } static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, int debugfs_id) { } #endif /* CONFIG_SHRINKER_DEBUG */ /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; #define mapping_set_update(xas, mapping) do { \ if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \ xas_set_update(xas, workingset_update_node); \ xas_set_lru(xas, &shadow_nodes); \ } \ } while (0) /* mremap.c */ unsigned long move_page_tables(struct pagetable_move_control *pmc); #ifdef CONFIG_UNACCEPTED_MEMORY void accept_page(struct page *page); #else /* CONFIG_UNACCEPTED_MEMORY */ static inline void accept_page(struct page *page) { } #endif /* CONFIG_UNACCEPTED_MEMORY */ /* pagewalk.c */ int walk_page_range_mm(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private); int walk_page_range_debug(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, pgd_t *pgd, void *private); /* pt_reclaim.c */ bool try_get_and_clear_pmd(struct mm_struct *mm, pmd_t *pmd, pmd_t *pmdval); void free_pte(struct mm_struct *mm, unsigned long addr, struct mmu_gather *tlb, pmd_t pmdval); void try_to_free_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, struct mmu_gather *tlb); #ifdef CONFIG_PT_RECLAIM bool reclaim_pt_is_enabled(unsigned long start, unsigned long end, struct zap_details *details); #else static inline bool reclaim_pt_is_enabled(unsigned long start, unsigned long end, struct zap_details *details) { return false; } #endif /* CONFIG_PT_RECLAIM */ void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm); int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm); #endif /* __MM_INTERNAL_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_HUGETLB_H #define _ASM_GENERIC_HUGETLB_H #include <linux/swap.h> #include <linux/swapops.h> static inline unsigned long huge_pte_write(pte_t pte) { return pte_write(pte); } static inline unsigned long huge_pte_dirty(pte_t pte) { return pte_dirty(pte); } static inline pte_t huge_pte_mkwrite(pte_t pte) { return pte_mkwrite_novma(pte); } #ifndef __HAVE_ARCH_HUGE_PTE_WRPROTECT static inline pte_t huge_pte_wrprotect(pte_t pte) { return pte_wrprotect(pte); } #endif static inline pte_t huge_pte_mkdirty(pte_t pte) { return pte_mkdirty(pte); } static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) { return pte_modify(pte, newprot); } #ifndef __HAVE_ARCH_HUGE_PTE_MKUFFD_WP static inline pte_t huge_pte_mkuffd_wp(pte_t pte) { return huge_pte_wrprotect(pte_mkuffd_wp(pte)); } #endif #ifndef __HAVE_ARCH_HUGE_PTE_CLEAR_UFFD_WP static inline pte_t huge_pte_clear_uffd_wp(pte_t pte) { return pte_clear_uffd_wp(pte); } #endif #ifndef __HAVE_ARCH_HUGE_PTE_UFFD_WP static inline int huge_pte_uffd_wp(pte_t pte) { return pte_uffd_wp(pte); } #endif #ifndef __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) { pte_clear(mm, addr, ptep); } #endif #ifndef __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { set_pte_at(mm, addr, ptep, pte); } #endif #ifndef __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) { return ptep_get_and_clear(mm, addr, ptep); } #endif #ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return ptep_clear_flush(vma, addr, ptep); } #endif #ifndef __HAVE_ARCH_HUGE_PTE_NONE static inline int huge_pte_none(pte_t pte) { return pte_none(pte); } #endif /* Please refer to comments above pte_none_mostly() for the usage */ #ifndef __HAVE_ARCH_HUGE_PTE_NONE_MOSTLY static inline int huge_pte_none_mostly(pte_t pte) { return huge_pte_none(pte) || is_pte_marker(pte); } #endif #ifndef __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { ptep_set_wrprotect(mm, addr, ptep); } #endif #ifndef __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty) { return ptep_set_access_flags(vma, addr, ptep, pte, dirty); } #endif #ifndef __HAVE_ARCH_HUGE_PTEP_GET static inline pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { return ptep_get(ptep); } #endif #ifndef __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED static inline bool gigantic_page_runtime_supported(void) { return IS_ENABLED(CONFIG_ARCH_HAS_GIGANTIC_PAGE); } #endif /* __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED */ #endif /* _ASM_GENERIC_HUGETLB_H */ |
| 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> */ #include <linux/ethtool.h> #include <net/netdev_lock.h> #include "ipvlan.h" static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval, struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan; unsigned int flags; int err; ASSERT_RTNL(); if (port->mode != nval) { list_for_each_entry(ipvlan, &port->ipvlans, pnode) { flags = ipvlan->dev->flags; if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) { err = dev_change_flags(ipvlan->dev, flags | IFF_NOARP, extack); } else { err = dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP, extack); } if (unlikely(err)) goto fail; } if (nval == IPVLAN_MODE_L3S) { /* New mode is L3S */ err = ipvlan_l3s_register(port); if (err) goto fail; } else if (port->mode == IPVLAN_MODE_L3S) { /* Old mode was L3S */ ipvlan_l3s_unregister(port); } port->mode = nval; } return 0; fail: /* Undo the flags changes that have been done so far. */ list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) { flags = ipvlan->dev->flags; if (port->mode == IPVLAN_MODE_L3 || port->mode == IPVLAN_MODE_L3S) dev_change_flags(ipvlan->dev, flags | IFF_NOARP, NULL); else dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP, NULL); } return err; } static int ipvlan_port_create(struct net_device *dev) { struct ipvl_port *port; int err, idx; port = kzalloc(sizeof(struct ipvl_port), GFP_KERNEL); if (!port) return -ENOMEM; write_pnet(&port->pnet, dev_net(dev)); port->dev = dev; port->mode = IPVLAN_MODE_L3; INIT_LIST_HEAD(&port->ipvlans); for (idx = 0; idx < IPVLAN_HASH_SIZE; idx++) INIT_HLIST_HEAD(&port->hlhead[idx]); skb_queue_head_init(&port->backlog); INIT_WORK(&port->wq, ipvlan_process_multicast); ida_init(&port->ida); port->dev_id_start = 1; err = netdev_rx_handler_register(dev, ipvlan_handle_frame, port); if (err) goto err; netdev_hold(dev, &port->dev_tracker, GFP_KERNEL); return 0; err: kfree(port); return err; } static void ipvlan_port_destroy(struct net_device *dev) { struct ipvl_port *port = ipvlan_port_get_rtnl(dev); struct sk_buff *skb; netdev_put(dev, &port->dev_tracker); if (port->mode == IPVLAN_MODE_L3S) ipvlan_l3s_unregister(port); netdev_rx_handler_unregister(dev); cancel_work_sync(&port->wq); while ((skb = __skb_dequeue(&port->backlog)) != NULL) { dev_put(skb->dev); kfree_skb(skb); } ida_destroy(&port->ida); kfree(port); } #define IPVLAN_ALWAYS_ON_OFLOADS \ (NETIF_F_SG | NETIF_F_HW_CSUM | \ NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL) #define IPVLAN_ALWAYS_ON \ (IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_VLAN_CHALLENGED) #define IPVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_ALL_TSO | NETIF_F_GSO_ROBUST | \ NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) /* NETIF_F_GSO_ENCAP_ALL NETIF_F_GSO_SOFTWARE Newly added */ #define IPVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) static int ipvlan_init(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_port *port; int err; dev->state = (dev->state & ~IPVLAN_STATE_MASK) | (phy_dev->state & IPVLAN_STATE_MASK); dev->features = phy_dev->features & IPVLAN_FEATURES; dev->features |= IPVLAN_ALWAYS_ON; dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES; dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS; dev->hw_enc_features |= dev->features; dev->lltx = true; netif_inherit_tso_max(dev, phy_dev); dev->hard_header_len = phy_dev->hard_header_len; netdev_lockdep_set_classes(dev); ipvlan->pcpu_stats = netdev_alloc_pcpu_stats(struct ipvl_pcpu_stats); if (!ipvlan->pcpu_stats) return -ENOMEM; if (!netif_is_ipvlan_port(phy_dev)) { err = ipvlan_port_create(phy_dev); if (err < 0) { free_percpu(ipvlan->pcpu_stats); return err; } } port = ipvlan_port_get_rtnl(phy_dev); port->count += 1; return 0; } static void ipvlan_uninit(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_port *port; free_percpu(ipvlan->pcpu_stats); port = ipvlan_port_get_rtnl(phy_dev); port->count -= 1; if (!port->count) ipvlan_port_destroy(port->dev); } static int ipvlan_open(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr; if (ipvlan->port->mode == IPVLAN_MODE_L3 || ipvlan->port->mode == IPVLAN_MODE_L3S) dev->flags |= IFF_NOARP; else dev->flags &= ~IFF_NOARP; rcu_read_lock(); list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_add(ipvlan, addr); rcu_read_unlock(); return 0; } static int ipvlan_stop(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; struct ipvl_addr *addr; dev_uc_unsync(phy_dev, dev); dev_mc_unsync(phy_dev, dev); rcu_read_lock(); list_for_each_entry_rcu(addr, &ipvlan->addrs, anode) ipvlan_ht_addr_del(addr); rcu_read_unlock(); return 0; } static netdev_tx_t ipvlan_start_xmit(struct sk_buff *skb, struct net_device *dev) { const struct ipvl_dev *ipvlan = netdev_priv(dev); int skblen = skb->len; int ret; ret = ipvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct ipvl_pcpu_stats *pcptr; pcptr = this_cpu_ptr(ipvlan->pcpu_stats); u64_stats_update_begin(&pcptr->syncp); u64_stats_inc(&pcptr->tx_pkts); u64_stats_add(&pcptr->tx_bytes, skblen); u64_stats_update_end(&pcptr->syncp); } else { this_cpu_inc(ipvlan->pcpu_stats->tx_drps); } return ret; } static netdev_features_t ipvlan_fix_features(struct net_device *dev, netdev_features_t features) { struct ipvl_dev *ipvlan = netdev_priv(dev); features |= NETIF_F_ALL_FOR_ALL; features &= (ipvlan->sfeatures | ~IPVLAN_FEATURES); features = netdev_increment_features(ipvlan->phy_dev->features, features, features); features |= IPVLAN_ALWAYS_ON; features &= (IPVLAN_FEATURES | IPVLAN_ALWAYS_ON); return features; } static void ipvlan_change_rx_flags(struct net_device *dev, int change) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; if (change & IFF_ALLMULTI) dev_set_allmulti(phy_dev, dev->flags & IFF_ALLMULTI? 1 : -1); } static void ipvlan_set_multicast_mac_filter(struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) { bitmap_fill(ipvlan->mac_filters, IPVLAN_MAC_FILTER_SIZE); } else { struct netdev_hw_addr *ha; DECLARE_BITMAP(mc_filters, IPVLAN_MAC_FILTER_SIZE); bitmap_zero(mc_filters, IPVLAN_MAC_FILTER_SIZE); netdev_for_each_mc_addr(ha, dev) __set_bit(ipvlan_mac_hash(ha->addr), mc_filters); /* Turn-on broadcast bit irrespective of address family, * since broadcast is deferred to a work-queue, hence no * impact on fast-path processing. */ __set_bit(ipvlan_mac_hash(dev->broadcast), mc_filters); bitmap_copy(ipvlan->mac_filters, mc_filters, IPVLAN_MAC_FILTER_SIZE); } dev_uc_sync(ipvlan->phy_dev, dev); dev_mc_sync(ipvlan->phy_dev, dev); } static void ipvlan_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { struct ipvl_dev *ipvlan = netdev_priv(dev); if (ipvlan->pcpu_stats) { struct ipvl_pcpu_stats *pcptr; u64 rx_pkts, rx_bytes, rx_mcast, tx_pkts, tx_bytes; u32 rx_errs = 0, tx_drps = 0; u32 strt; int idx; for_each_possible_cpu(idx) { pcptr = per_cpu_ptr(ipvlan->pcpu_stats, idx); do { strt = u64_stats_fetch_begin(&pcptr->syncp); rx_pkts = u64_stats_read(&pcptr->rx_pkts); rx_bytes = u64_stats_read(&pcptr->rx_bytes); rx_mcast = u64_stats_read(&pcptr->rx_mcast); tx_pkts = u64_stats_read(&pcptr->tx_pkts); tx_bytes = u64_stats_read(&pcptr->tx_bytes); } while (u64_stats_fetch_retry(&pcptr->syncp, strt)); s->rx_packets += rx_pkts; s->rx_bytes += rx_bytes; s->multicast += rx_mcast; s->tx_packets += tx_pkts; s->tx_bytes += tx_bytes; /* u32 values are updated without syncp protection. */ rx_errs += READ_ONCE(pcptr->rx_errs); tx_drps += READ_ONCE(pcptr->tx_drps); } s->rx_errors = rx_errs; s->rx_dropped = rx_errs; s->tx_dropped = tx_drps; } s->tx_errors = DEV_STATS_READ(dev, tx_errors); } static int ipvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; return vlan_vid_add(phy_dev, proto, vid); } static int ipvlan_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; vlan_vid_del(phy_dev, proto, vid); return 0; } static int ipvlan_get_iflink(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); return READ_ONCE(ipvlan->phy_dev->ifindex); } static const struct net_device_ops ipvlan_netdev_ops = { .ndo_init = ipvlan_init, .ndo_uninit = ipvlan_uninit, .ndo_open = ipvlan_open, .ndo_stop = ipvlan_stop, .ndo_start_xmit = ipvlan_start_xmit, .ndo_fix_features = ipvlan_fix_features, .ndo_change_rx_flags = ipvlan_change_rx_flags, .ndo_set_rx_mode = ipvlan_set_multicast_mac_filter, .ndo_get_stats64 = ipvlan_get_stats64, .ndo_vlan_rx_add_vid = ipvlan_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ipvlan_vlan_rx_kill_vid, .ndo_get_iflink = ipvlan_get_iflink, }; static int ipvlan_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len) { const struct ipvl_dev *ipvlan = netdev_priv(dev); struct net_device *phy_dev = ipvlan->phy_dev; /* TODO Probably use a different field than dev_addr so that the * mac-address on the virtual device is portable and can be carried * while the packets use the mac-addr on the physical device. */ return dev_hard_header(skb, phy_dev, type, daddr, saddr ? : phy_dev->dev_addr, len); } static const struct header_ops ipvlan_header_ops = { .create = ipvlan_hard_header, .parse = eth_header_parse, .cache = eth_header_cache, .cache_update = eth_header_cache_update, .parse_protocol = eth_header_parse_protocol, }; static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev) { ipvlan->dev->mtu = dev->mtu; } static bool netif_is_ipvlan(const struct net_device *dev) { /* both ipvlan and ipvtap devices use the same netdev_ops */ return dev->netdev_ops == &ipvlan_netdev_ops; } static int ipvlan_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { const struct ipvl_dev *ipvlan = netdev_priv(dev); return __ethtool_get_link_ksettings(ipvlan->phy_dev, cmd); } static void ipvlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, IPVLAN_DRV, sizeof(drvinfo->driver)); strscpy(drvinfo->version, IPV_DRV_VER, sizeof(drvinfo->version)); } static u32 ipvlan_ethtool_get_msglevel(struct net_device *dev) { const struct ipvl_dev *ipvlan = netdev_priv(dev); return ipvlan->msg_enable; } static void ipvlan_ethtool_set_msglevel(struct net_device *dev, u32 value) { struct ipvl_dev *ipvlan = netdev_priv(dev); ipvlan->msg_enable = value; } static const struct ethtool_ops ipvlan_ethtool_ops = { .get_link = ethtool_op_get_link, .get_link_ksettings = ipvlan_ethtool_get_link_ksettings, .get_drvinfo = ipvlan_ethtool_get_drvinfo, .get_msglevel = ipvlan_ethtool_get_msglevel, .set_msglevel = ipvlan_ethtool_set_msglevel, }; static int ipvlan_nl_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); int err = 0; if (!data) return 0; if (!ns_capable(dev_net(ipvlan->phy_dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (data[IFLA_IPVLAN_MODE]) { u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]); err = ipvlan_set_port_mode(port, nmode, extack); } if (!err && data[IFLA_IPVLAN_FLAGS]) { u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); if (flags & IPVLAN_F_PRIVATE) ipvlan_mark_private(port); else ipvlan_clear_private(port); if (flags & IPVLAN_F_VEPA) ipvlan_mark_vepa(port); else ipvlan_clear_vepa(port); } return err; } static size_t ipvlan_nl_getsize(const struct net_device *dev) { return (0 + nla_total_size(2) /* IFLA_IPVLAN_MODE */ + nla_total_size(2) /* IFLA_IPVLAN_FLAGS */ ); } static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) return 0; if (data[IFLA_IPVLAN_MODE]) { u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]); if (mode >= IPVLAN_MODE_MAX) return -EINVAL; } if (data[IFLA_IPVLAN_FLAGS]) { u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); /* Only two bits are used at this moment. */ if (flags & ~(IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) return -EINVAL; /* Also both flags can't be active at the same time. */ if ((flags & (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) == (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) return -EINVAL; } return 0; } static int ipvlan_nl_fillinfo(struct sk_buff *skb, const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); int ret = -EINVAL; if (!port) goto err; ret = -EMSGSIZE; if (nla_put_u16(skb, IFLA_IPVLAN_MODE, port->mode)) goto err; if (nla_put_u16(skb, IFLA_IPVLAN_FLAGS, port->flags)) goto err; return 0; err: return ret; } int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct ipvl_dev *ipvlan = netdev_priv(dev); struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct ipvl_port *port; struct net_device *phy_dev; int err; u16 mode = IPVLAN_MODE_L3; if (!tb[IFLA_LINK]) return -EINVAL; phy_dev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK])); if (!phy_dev) return -ENODEV; if (netif_is_ipvlan(phy_dev)) { struct ipvl_dev *tmp = netdev_priv(phy_dev); phy_dev = tmp->phy_dev; if (!ns_capable(dev_net(phy_dev)->user_ns, CAP_NET_ADMIN)) return -EPERM; } else if (!netif_is_ipvlan_port(phy_dev)) { /* Exit early if the underlying link is invalid or busy */ if (phy_dev->type != ARPHRD_ETHER || phy_dev->flags & IFF_LOOPBACK) { netdev_err(phy_dev, "Master is either lo or non-ether device\n"); return -EINVAL; } if (netdev_is_rx_handler_busy(phy_dev)) { netdev_err(phy_dev, "Device is already in use.\n"); return -EBUSY; } } ipvlan->phy_dev = phy_dev; ipvlan->dev = dev; ipvlan->sfeatures = IPVLAN_FEATURES; if (!tb[IFLA_MTU]) ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); spin_lock_init(&ipvlan->addrs_lock); /* TODO Probably put random address here to be presented to the * world but keep using the physical-dev address for the outgoing * packets. */ eth_hw_addr_set(dev, phy_dev->dev_addr); dev->priv_flags |= IFF_NO_RX_HANDLER; err = register_netdevice(dev); if (err < 0) return err; /* ipvlan_init() would have created the port, if required */ port = ipvlan_port_get_rtnl(phy_dev); ipvlan->port = port; /* If the port-id base is at the MAX value, then wrap it around and * begin from 0x1 again. This may be due to a busy system where lots * of slaves are getting created and deleted. */ if (port->dev_id_start == 0xFFFE) port->dev_id_start = 0x1; /* Since L2 address is shared among all IPvlan slaves including * master, use unique 16 bit dev-ids to differentiate among them. * Assign IDs between 0x1 and 0xFFFE (used by the master) to each * slave link [see addrconf_ifid_eui48()]. */ err = ida_alloc_range(&port->ida, port->dev_id_start, 0xFFFD, GFP_KERNEL); if (err < 0) err = ida_alloc_range(&port->ida, 0x1, port->dev_id_start - 1, GFP_KERNEL); if (err < 0) goto unregister_netdev; dev->dev_id = err; /* Increment id-base to the next slot for the future assignment */ port->dev_id_start = err + 1; err = netdev_upper_dev_link(phy_dev, dev, extack); if (err) goto remove_ida; /* Flags are per port and latest update overrides. User has * to be consistent in setting it just like the mode attribute. */ if (data && data[IFLA_IPVLAN_FLAGS]) port->flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); if (data && data[IFLA_IPVLAN_MODE]) mode = nla_get_u16(data[IFLA_IPVLAN_MODE]); err = ipvlan_set_port_mode(port, mode, extack); if (err) goto unlink_netdev; list_add_tail_rcu(&ipvlan->pnode, &port->ipvlans); netif_stacked_transfer_operstate(phy_dev, dev); return 0; unlink_netdev: netdev_upper_dev_unlink(phy_dev, dev); remove_ida: ida_free(&port->ida, dev->dev_id); unregister_netdev: unregister_netdevice(dev); return err; } EXPORT_SYMBOL_GPL(ipvlan_link_new); void ipvlan_link_delete(struct net_device *dev, struct list_head *head) { struct ipvl_dev *ipvlan = netdev_priv(dev); struct ipvl_addr *addr, *next; spin_lock_bh(&ipvlan->addrs_lock); list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) { ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); kfree_rcu(addr, rcu); } spin_unlock_bh(&ipvlan->addrs_lock); ida_free(&ipvlan->port->ida, dev->dev_id); list_del_rcu(&ipvlan->pnode); unregister_netdevice_queue(dev, head); netdev_upper_dev_unlink(ipvlan->phy_dev, dev); } EXPORT_SYMBOL_GPL(ipvlan_link_delete); void ipvlan_link_setup(struct net_device *dev) { ether_setup(dev); dev->max_mtu = ETH_MAX_MTU; dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING); dev->priv_flags |= IFF_UNICAST_FLT | IFF_NO_QUEUE; dev->netdev_ops = &ipvlan_netdev_ops; dev->needs_free_netdev = true; dev->header_ops = &ipvlan_header_ops; dev->ethtool_ops = &ipvlan_ethtool_ops; } EXPORT_SYMBOL_GPL(ipvlan_link_setup); static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] = { [IFLA_IPVLAN_MODE] = { .type = NLA_U16 }, [IFLA_IPVLAN_FLAGS] = { .type = NLA_U16 }, }; static struct net *ipvlan_get_link_net(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); return dev_net(ipvlan->phy_dev); } static struct rtnl_link_ops ipvlan_link_ops = { .kind = "ipvlan", .priv_size = sizeof(struct ipvl_dev), .setup = ipvlan_link_setup, .newlink = ipvlan_link_new, .dellink = ipvlan_link_delete, .get_link_net = ipvlan_get_link_net, }; int ipvlan_link_register(struct rtnl_link_ops *ops) { ops->get_size = ipvlan_nl_getsize; ops->policy = ipvlan_nl_policy; ops->validate = ipvlan_nl_validate; ops->fill_info = ipvlan_nl_fillinfo; ops->changelink = ipvlan_nl_changelink; ops->maxtype = IFLA_IPVLAN_MAX; return rtnl_link_register(ops); } EXPORT_SYMBOL_GPL(ipvlan_link_register); static int ipvlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(ptr); struct netdev_notifier_pre_changeaddr_info *prechaddr_info; struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct ipvl_dev *ipvlan, *next; struct ipvl_port *port; LIST_HEAD(lst_kill); int err; if (!netif_is_ipvlan_port(dev)) return NOTIFY_DONE; port = ipvlan_port_get_rtnl(dev); switch (event) { case NETDEV_UP: case NETDEV_DOWN: case NETDEV_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) netif_stacked_transfer_operstate(ipvlan->phy_dev, ipvlan->dev); break; case NETDEV_REGISTER: { struct net *oldnet, *newnet = dev_net(dev); oldnet = read_pnet(&port->pnet); if (net_eq(newnet, oldnet)) break; write_pnet(&port->pnet, newnet); if (port->mode == IPVLAN_MODE_L3S) ipvlan_migrate_l3s_hook(oldnet, newnet); break; } case NETDEV_UNREGISTER: if (dev->reg_state != NETREG_UNREGISTERING) break; list_for_each_entry_safe(ipvlan, next, &port->ipvlans, pnode) ipvlan->dev->rtnl_link_ops->dellink(ipvlan->dev, &lst_kill); unregister_netdevice_many(&lst_kill); break; case NETDEV_FEAT_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { netif_inherit_tso_max(ipvlan->dev, dev); netdev_update_features(ipvlan->dev); } break; case NETDEV_CHANGEMTU: list_for_each_entry(ipvlan, &port->ipvlans, pnode) ipvlan_adjust_mtu(ipvlan, dev); break; case NETDEV_PRE_CHANGEADDR: prechaddr_info = ptr; list_for_each_entry(ipvlan, &port->ipvlans, pnode) { err = netif_pre_changeaddr_notify(ipvlan->dev, prechaddr_info->dev_addr, extack); if (err) return notifier_from_errno(err); } break; case NETDEV_CHANGEADDR: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { eth_hw_addr_set(ipvlan->dev, dev->dev_addr); call_netdevice_notifiers(NETDEV_CHANGEADDR, ipvlan->dev); } break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: case NETDEV_RESEND_IGMP: list_for_each_entry(ipvlan, &port->ipvlans, pnode) call_netdevice_notifiers(event, ipvlan->dev); } return NOTIFY_DONE; } /* the caller must held the addrs lock */ static int ipvlan_add_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; addr = kzalloc(sizeof(struct ipvl_addr), GFP_ATOMIC); if (!addr) return -ENOMEM; addr->master = ipvlan; if (!is_v6) { memcpy(&addr->ip4addr, iaddr, sizeof(struct in_addr)); addr->atype = IPVL_IPV4; #if IS_ENABLED(CONFIG_IPV6) } else { memcpy(&addr->ip6addr, iaddr, sizeof(struct in6_addr)); addr->atype = IPVL_IPV6; #endif } list_add_tail_rcu(&addr->anode, &ipvlan->addrs); /* If the interface is not up, the address will be added to the hash * list by ipvlan_open. */ if (netif_running(ipvlan->dev)) ipvlan_ht_addr_add(ipvlan, addr); return 0; } static void ipvlan_del_addr(struct ipvl_dev *ipvlan, void *iaddr, bool is_v6) { struct ipvl_addr *addr; spin_lock_bh(&ipvlan->addrs_lock); addr = ipvlan_find_addr(ipvlan, iaddr, is_v6); if (!addr) { spin_unlock_bh(&ipvlan->addrs_lock); return; } ipvlan_ht_addr_del(addr); list_del_rcu(&addr->anode); spin_unlock_bh(&ipvlan->addrs_lock); kfree_rcu(addr, rcu); } static bool ipvlan_is_valid_dev(const struct net_device *dev) { struct ipvl_dev *ipvlan = netdev_priv(dev); if (!netif_is_ipvlan(dev)) return false; if (!ipvlan || !ipvlan->port) return false; return true; } #if IS_ENABLED(CONFIG_IPV6) static int ipvlan_add_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { int ret = -EINVAL; spin_lock_bh(&ipvlan->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip6_addr, true)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv6=%pI6c addr for %s intf\n", ip6_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip6_addr, true); spin_unlock_bh(&ipvlan->addrs_lock); return ret; } static void ipvlan_del_addr6(struct ipvl_dev *ipvlan, struct in6_addr *ip6_addr) { return ipvlan_del_addr(ipvlan, ip6_addr, true); } static int ipvlan_addr6_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct inet6_ifaddr *if6 = (struct inet6_ifaddr *)ptr; struct net_device *dev = (struct net_device *)if6->idev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (ipvlan_add_addr6(ipvlan, &if6->addr)) return NOTIFY_BAD; break; case NETDEV_DOWN: ipvlan_del_addr6(ipvlan, &if6->addr); break; } return NOTIFY_OK; } static int ipvlan_addr6_validator_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct in6_validator_info *i6vi = (struct in6_validator_info *)ptr; struct net_device *dev = (struct net_device *)i6vi->i6vi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (ipvlan_addr_busy(ipvlan->port, &i6vi->i6vi_addr, true)) { NL_SET_ERR_MSG(i6vi->extack, "Address already assigned to an ipvlan device"); return notifier_from_errno(-EADDRINUSE); } break; } return NOTIFY_OK; } #endif static int ipvlan_add_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { int ret = -EINVAL; spin_lock_bh(&ipvlan->addrs_lock); if (ipvlan_addr_busy(ipvlan->port, ip4_addr, false)) netif_err(ipvlan, ifup, ipvlan->dev, "Failed to add IPv4=%pI4 on %s intf.\n", ip4_addr, ipvlan->dev->name); else ret = ipvlan_add_addr(ipvlan, ip4_addr, false); spin_unlock_bh(&ipvlan->addrs_lock); return ret; } static void ipvlan_del_addr4(struct ipvl_dev *ipvlan, struct in_addr *ip4_addr) { return ipvlan_del_addr(ipvlan, ip4_addr, false); } static int ipvlan_addr4_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct in_ifaddr *if4 = (struct in_ifaddr *)ptr; struct net_device *dev = (struct net_device *)if4->ifa_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); struct in_addr ip4_addr; if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: ip4_addr.s_addr = if4->ifa_address; if (ipvlan_add_addr4(ipvlan, &ip4_addr)) return NOTIFY_BAD; break; case NETDEV_DOWN: ip4_addr.s_addr = if4->ifa_address; ipvlan_del_addr4(ipvlan, &ip4_addr); break; } return NOTIFY_OK; } static int ipvlan_addr4_validator_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct in_validator_info *ivi = (struct in_validator_info *)ptr; struct net_device *dev = (struct net_device *)ivi->ivi_dev->dev; struct ipvl_dev *ipvlan = netdev_priv(dev); if (!ipvlan_is_valid_dev(dev)) return NOTIFY_DONE; switch (event) { case NETDEV_UP: if (ipvlan_addr_busy(ipvlan->port, &ivi->ivi_addr, false)) { NL_SET_ERR_MSG(ivi->extack, "Address already assigned to an ipvlan device"); return notifier_from_errno(-EADDRINUSE); } break; } return NOTIFY_OK; } static struct notifier_block ipvlan_addr4_notifier_block __read_mostly = { .notifier_call = ipvlan_addr4_event, }; static struct notifier_block ipvlan_addr4_vtor_notifier_block __read_mostly = { .notifier_call = ipvlan_addr4_validator_event, }; static struct notifier_block ipvlan_notifier_block __read_mostly = { .notifier_call = ipvlan_device_event, }; #if IS_ENABLED(CONFIG_IPV6) static struct notifier_block ipvlan_addr6_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_event, }; static struct notifier_block ipvlan_addr6_vtor_notifier_block __read_mostly = { .notifier_call = ipvlan_addr6_validator_event, }; #endif static int __init ipvlan_init_module(void) { int err; ipvlan_init_secret(); register_netdevice_notifier(&ipvlan_notifier_block); #if IS_ENABLED(CONFIG_IPV6) register_inet6addr_notifier(&ipvlan_addr6_notifier_block); register_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); #endif register_inetaddr_notifier(&ipvlan_addr4_notifier_block); register_inetaddr_validator_notifier(&ipvlan_addr4_vtor_notifier_block); err = ipvlan_l3s_init(); if (err < 0) goto error; err = ipvlan_link_register(&ipvlan_link_ops); if (err < 0) { ipvlan_l3s_cleanup(); goto error; } return 0; error: unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( &ipvlan_addr4_vtor_notifier_block); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); unregister_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); #endif unregister_netdevice_notifier(&ipvlan_notifier_block); return err; } static void __exit ipvlan_cleanup_module(void) { rtnl_link_unregister(&ipvlan_link_ops); ipvlan_l3s_cleanup(); unregister_netdevice_notifier(&ipvlan_notifier_block); unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( &ipvlan_addr4_vtor_notifier_block); #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&ipvlan_addr6_notifier_block); unregister_inet6addr_validator_notifier( &ipvlan_addr6_vtor_notifier_block); #endif } module_init(ipvlan_init_module); module_exit(ipvlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>"); MODULE_DESCRIPTION("Driver for L3 (IPv6/IPv4) based VLANs"); MODULE_ALIAS_RTNL_LINK("ipvlan"); MODULE_IMPORT_NS("NETDEV_INTERNAL"); |
| 274 273 274 274 139 139 273 273 273 | 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 | /* 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_free_vmas() * * tlb_free_vmas() marks the start of unlinking of one or more vmas * and freeing page-tables. * * - 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_size() * - __tlb_remove_folio_pages() / __tlb_remove_page_size() * - __tlb_remove_folio_pages_size() * * __tlb_remove_folio_pages_size() is the basic primitive that queues pages * for freeing. It 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_size(), * however, instead of removing a single page, assume PAGE_SIZE and remove * the given number of consecutive pages that are all part of the * same (large) folio. * * - 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 ptdesc *ptdesc = (struct ptdesc *)table; pagetable_dtor(ptdesc); tlb_remove_page(tlb, ptdesc_page(ptdesc)); } #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); /* * Track if there's at least one VM_PFNMAP/VM_MIXEDMAP vma * in the tracked range, see tlb_free_vmas(). */ 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 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, struct ptdesc *pt) { tlb_remove_table(tlb, 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 || IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS)) return; /* * Do a TLB flush and reset the range at VMA boundaries; this avoids * the ranges growing with the unused space between consecutive VMAs, * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on * this. */ tlb_flush_mmu_tlbonly(tlb); } static inline void tlb_free_vmas(struct mmu_gather *tlb) { 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. * * Specifically() there is a race between munmap() and * unmap_mapping_range(), where munmap() will unlink the VMA, such * that unmap_mapping_range() will no longer observe the VMA and * no-op, without observing the TLBI, returning prematurely. * * So if we're about to unlink such a VMA, and we have pending * TLBI for such a vma, flush things now. */ if (tlb->vma_pfn) 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 4 4 270 31 271 31 45 53 91 50 35 50 37 50 50 4 41 45 18 13 4 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGETLB_H #define _LINUX_HUGETLB_H #include <linux/mm.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/fs.h> #include <linux/hugetlb_inline.h> #include <linux/cgroup.h> #include <linux/page_ref.h> #include <linux/list.h> #include <linux/kref.h> #include <linux/pgtable.h> #include <linux/gfp.h> #include <linux/userfaultfd_k.h> #include <linux/nodemask.h> struct ctl_table; struct user_struct; struct mmu_gather; struct node; void free_huge_folio(struct folio *folio); #ifdef CONFIG_HUGETLB_PAGE #include <linux/pagemap.h> #include <linux/shm.h> #include <asm/tlbflush.h> /* * For HugeTLB page, there are more metadata to save in the struct page. But * the head struct page cannot meet our needs, so we have to abuse other tail * struct page to store the metadata. */ #define __NR_USED_SUBPAGE 3 struct hugepage_subpool { spinlock_t lock; long count; long max_hpages; /* Maximum huge pages or -1 if no maximum. */ long used_hpages; /* Used count against maximum, includes */ /* both allocated and reserved pages. */ struct hstate *hstate; long min_hpages; /* Minimum huge pages or -1 if no minimum. */ long rsv_hpages; /* Pages reserved against global pool to */ /* satisfy minimum size. */ }; struct resv_map { struct kref refs; spinlock_t lock; struct list_head regions; long adds_in_progress; struct list_head region_cache; long region_cache_count; struct rw_semaphore rw_sema; #ifdef CONFIG_CGROUP_HUGETLB /* * On private mappings, the counter to uncharge reservations is stored * here. If these fields are 0, then either the mapping is shared, or * cgroup accounting is disabled for this resv_map. */ struct page_counter *reservation_counter; unsigned long pages_per_hpage; struct cgroup_subsys_state *css; #endif }; /* * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. * * The region data structures are embedded into a resv_map and protected * by a resv_map's lock. The set of regions within the resv_map represent * reservations for huge pages, or huge pages that have already been * instantiated within the map. The from and to elements are huge page * indices into the associated mapping. from indicates the starting index * of the region. to represents the first index past the end of the region. * * For example, a file region structure with from == 0 and to == 4 represents * four huge pages in a mapping. It is important to note that the to element * represents the first element past the end of the region. This is used in * arithmetic as 4(to) - 0(from) = 4 huge pages in the region. * * Interval notation of the form [from, to) will be used to indicate that * the endpoint from is inclusive and to is exclusive. */ struct file_region { struct list_head link; long from; long to; #ifdef CONFIG_CGROUP_HUGETLB /* * On shared mappings, each reserved region appears as a struct * file_region in resv_map. These fields hold the info needed to * uncharge each reservation. */ struct page_counter *reservation_counter; struct cgroup_subsys_state *css; #endif }; struct hugetlb_vma_lock { struct kref refs; struct rw_semaphore rw_sema; struct vm_area_struct *vma; }; extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); extern spinlock_t hugetlb_lock; extern int hugetlb_max_hstate __read_mostly; #define for_each_hstate(h) \ for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++) struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages); void hugepage_put_subpool(struct hugepage_subpool *spool); void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *, struct vm_area_struct *); void unmap_hugepage_range(struct vm_area_struct *, unsigned long start, unsigned long end, struct folio *, zap_flags_t); void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct folio *, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo_node(int nid); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop); #endif /* CONFIG_USERFAULTFD */ long hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list); int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void folio_putback_hugetlb(struct folio *folio); void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud); bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address); struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio); extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages[MAX_NUMNODES]; void hugetlb_bootmem_alloc(void); bool hugetlb_bootmem_allocated(void); extern nodemask_t hugetlb_bootmem_nodes; void hugetlb_bootmem_set_nodes(void); /* arch callbacks */ #ifndef CONFIG_HIGHPTE /* * pte_offset_huge() and pte_alloc_huge() are helpers for those architectures * which may go down to the lowest PTE level in their huge_pte_offset() and * huge_pte_alloc(): to avoid reliance on pte_offset_map() without pte_unmap(). */ static inline pte_t *pte_offset_huge(pmd_t *pmd, unsigned long address) { return pte_offset_kernel(pmd, address); } static inline pte_t *pte_alloc_huge(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { return pte_alloc(mm, pmd) ? NULL : pte_offset_huge(pmd, address); } #endif pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); /* * huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE. * Returns the pte_t* if found, or NULL if the address is not mapped. * * IMPORTANT: we should normally not directly call this function, instead * this is only a common interface to implement arch-specific * walker. Please use hugetlb_walk() instead, because that will attempt to * verify the locking for you. * * Since this function will walk all the pgtable pages (including not only * high-level pgtable page, but also PUD entry that can be unshared * concurrently for VM_SHARED), the caller of this function should be * responsible of its thread safety. One can follow this rule: * * (1) For private mappings: pmd unsharing is not possible, so holding the * mmap_lock for either read or write is sufficient. Most callers * already hold the mmap_lock, so normally, no special action is * required. * * (2) For shared mappings: pmd unsharing is possible (so the PUD-ranged * pgtable page can go away from under us! It can be done by a pmd * unshare with a follow up munmap() on the other process), then we * need either: * * (2.1) hugetlb vma lock read or write held, to make sure pmd unshare * won't happen upon the range (it also makes sure the pte_t we * read is the right and stable one), or, * * (2.2) hugetlb mapping i_mmap_rwsem lock held read or write, to make * sure even if unshare happened the racy unmap() will wait until * i_mmap_rwsem is released. * * Option (2.1) is the safest, which guarantees pte stability from pmd * sharing pov, until the vma lock released. Option (2.2) doesn't protect * a concurrent pmd unshare, but it makes sure the pgtable page is safe to * access. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); extern void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *begin, unsigned long *end); extern void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details); static inline void hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_begin(vma, start, end); } static inline void hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_end(vma, details); } void hugetlb_vma_lock_read(struct vm_area_struct *vma); void hugetlb_vma_unlock_read(struct vm_area_struct *vma); void hugetlb_vma_lock_write(struct vm_area_struct *vma); void hugetlb_vma_unlock_write(struct vm_area_struct *vma); int hugetlb_vma_trylock_write(struct vm_area_struct *vma); void hugetlb_vma_assert_locked(struct vm_area_struct *vma); void hugetlb_vma_lock_release(struct kref *kref); long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); void fixup_hugetlb_reservations(struct vm_area_struct *vma); void hugetlb_split(struct vm_area_struct *vma, unsigned long addr); #else /* !CONFIG_HUGETLB_PAGE */ static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma) { } static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { } static inline unsigned long hugetlb_total_pages(void) { return 0; } static inline struct address_space *hugetlb_folio_mapping_lock_write( struct folio *folio) { return NULL; } static inline int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_begin( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_end( struct vm_area_struct *vma, struct zap_details *details) { } static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { BUG(); return 0; } static inline int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { BUG(); return 0; } static inline void hugetlb_report_meminfo(struct seq_file *m) { } static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid) { return 0; } static inline void hugetlb_show_meminfo_node(int nid) { } static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { } static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { return 1; } static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { } static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } #ifdef CONFIG_USERFAULTFD static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { BUG(); return 0; } #endif /* CONFIG_USERFAULTFD */ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { return NULL; } static inline bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list) { return false; } static inline int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { return 0; } static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { return 0; } static inline void folio_putback_hugetlb(struct folio *folio) { } static inline void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { } static inline long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { return 0; } static inline void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct folio *folio, zap_flags_t zap_flags) { BUG(); } static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { BUG(); return 0; } static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) { } static inline void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) {} #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write static inline int pgd_write(pgd_t pgd) { BUG(); return 0; } #endif #define HUGETLB_ANON_FILE "anon_hugepage" enum { /* * The file will be used as an shm file so shmfs accounting rules * apply */ HUGETLB_SHMFS_INODE = 1, /* * The file is being created on the internal vfs mount and shmfs * accounting rules do not apply */ HUGETLB_ANONHUGE_INODE = 2, }; #ifdef CONFIG_HUGETLBFS struct hugetlbfs_sb_info { long max_inodes; /* inodes allowed */ long free_inodes; /* inodes free */ spinlock_t stat_lock; struct hstate *hstate; struct hugepage_subpool *spool; kuid_t uid; kgid_t gid; umode_t mode; }; static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) { return sb->s_fs_info; } struct hugetlbfs_inode_info { struct inode vfs_inode; unsigned int seals; }; static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) { return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, int creat_flags, int page_size_log); static inline bool is_file_hugepages(const struct file *file) { return file->f_op->fop_flags & FOP_HUGE_PAGES; } static inline struct hstate *hstate_inode(struct inode *i) { return HUGETLBFS_SB(i->i_sb)->hstate; } #else /* !CONFIG_HUGETLBFS */ #define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); } static inline struct hstate *hstate_inode(struct inode *i) { return NULL; } #endif /* !CONFIG_HUGETLBFS */ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); /* * huegtlb page specific state flags. These flags are located in page.private * of the hugetlb head page. Functions created via the below macros should be * used to manipulate these flags. * * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at * allocation time. Cleared when page is fully instantiated. Free * routine checks flag to restore a reservation on error paths. * Synchronization: Examined or modified by code that knows it has * the only reference to page. i.e. After allocation but before use * or when the page is being freed. * HPG_migratable - Set after a newly allocated page is added to the page * cache and/or page tables. Indicates the page is a candidate for * migration. * Synchronization: Initially set after new page allocation with no * locking. When examined and modified during migration processing * (isolate, migrate, putback) the hugetlb_lock is held. * HPG_temporary - Set on a page that is temporarily allocated from the buddy * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. * Synchronization: Can be set after huge page allocation from buddy when * code knows it has only reference. All other examinations and * modifications require hugetlb_lock. * HPG_freed - Set when page is on the free lists. * Synchronization: hugetlb_lock held for examination and modification. * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. * HPG_raw_hwp_unreliable - Set when the hugetlb page has a hwpoison sub-page * that is not tracked by raw_hwp_page list. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, HPG_freed, HPG_vmemmap_optimized, HPG_raw_hwp_unreliable, HPG_cma, __NR_HPAGEFLAGS, }; /* * Macros to create test, set and clear function definitions for * hugetlb specific page flags. */ #ifdef CONFIG_HUGETLB_PAGE #define TESTHPAGEFLAG(uname, flname) \ static __always_inline \ bool folio_test_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ return test_bit(HPG_##flname, private); \ } #define SETHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_set_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ set_bit(HPG_##flname, private); \ } #define CLEARHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_clear_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ clear_bit(HPG_##flname, private); \ } #else #define TESTHPAGEFLAG(uname, flname) \ static inline bool \ folio_test_hugetlb_##flname(struct folio *folio) \ { return 0; } #define SETHPAGEFLAG(uname, flname) \ static inline void \ folio_set_hugetlb_##flname(struct folio *folio) \ { } #define CLEARHPAGEFLAG(uname, flname) \ static inline void \ folio_clear_hugetlb_##flname(struct folio *folio) \ { } #endif #define HPAGEFLAG(uname, flname) \ TESTHPAGEFLAG(uname, flname) \ SETHPAGEFLAG(uname, flname) \ CLEARHPAGEFLAG(uname, flname) \ /* * Create functions associated with hugetlb page flags */ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) HPAGEFLAG(Cma, cma) #ifdef CONFIG_HUGETLB_PAGE #define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { struct mutex resize_lock; struct lock_class_key resize_key; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; unsigned int demote_order; unsigned long mask; unsigned long max_huge_pages; unsigned long nr_huge_pages; unsigned long free_huge_pages; unsigned long resv_huge_pages; unsigned long surplus_huge_pages; unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; char name[HSTATE_NAME_LEN]; }; struct cma; struct huge_bootmem_page { struct list_head list; struct hstate *hstate; unsigned long flags; struct cma *cma; }; #define HUGE_BOOTMEM_HVO 0x0001 #define HUGE_BOOTMEM_ZONES_VALID 0x0002 #define HUGE_BOOTMEM_CMA 0x0004 bool hugetlb_bootmem_page_zones_valid(int nid, struct huge_bootmem_page *m); int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list); int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn); void wait_for_freed_hugetlb_folios(void); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback); struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio); /* arch callback */ int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); int __init alloc_bootmem_huge_page(struct hstate *h, int nid); bool __init hugetlb_node_alloc_supported(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); #ifndef HUGE_MAX_HSTATE #define HUGE_MAX_HSTATE 1 #endif extern struct hstate hstates[HUGE_MAX_HSTATE]; extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) static inline struct hugepage_subpool *subpool_inode(struct inode *inode) { return HUGETLBFS_SB(inode->i_sb)->spool; } static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return folio->_hugetlb_subpool; } static inline void hugetlb_set_folio_subpool(struct folio *folio, struct hugepage_subpool *subpool) { folio->_hugetlb_subpool = subpool; } static inline struct hstate *hstate_file(struct file *f) { return hstate_inode(file_inode(f)); } static inline struct hstate *hstate_sizelog(int page_size_log) { if (!page_size_log) return &default_hstate; if (page_size_log < BITS_PER_LONG) return size_to_hstate(1UL << page_size_log); return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return hstate_file(vma->vm_file); } static inline unsigned long huge_page_size(const struct hstate *h) { return (unsigned long)PAGE_SIZE << h->order; } extern unsigned long vma_kernel_pagesize(struct vm_area_struct *vma); extern unsigned long vma_mmu_pagesize(struct vm_area_struct *vma); static inline unsigned long huge_page_mask(struct hstate *h) { return h->mask; } static inline unsigned int huge_page_order(struct hstate *h) { return h->order; } static inline unsigned huge_page_shift(struct hstate *h) { return h->order + PAGE_SHIFT; } static inline bool order_is_gigantic(unsigned int order) { return order > MAX_PAGE_ORDER; } static inline bool hstate_is_gigantic(struct hstate *h) { return order_is_gigantic(huge_page_order(h)); } static inline unsigned int pages_per_huge_page(const struct hstate *h) { return 1 << h->order; } static inline unsigned int blocks_per_huge_page(struct hstate *h) { return huge_page_size(h) / 512; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return filemap_lock_folio(mapping, idx << huge_page_order(h)); } #include <asm/hugetlb.h> #ifndef is_hugepage_only_range static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } #define is_hugepage_only_range is_hugepage_only_range #endif #ifndef arch_clear_hugetlb_flags static inline void arch_clear_hugetlb_flags(struct folio *folio) { } #define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #endif #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { return pte_mkhuge(entry); } #endif #ifndef arch_has_huge_bootmem_alloc /* * Some architectures do their own bootmem allocation, so they can't use * early CMA allocation. */ static inline bool arch_has_huge_bootmem_alloc(void) { return false; } #endif static inline struct hstate *folio_hstate(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); return size_to_hstate(folio_size(folio)); } static inline unsigned hstate_index_to_shift(unsigned index) { return hstates[index].order + PAGE_SHIFT; } static inline int hstate_index(struct hstate *h) { return h - hstates; } int dissolve_free_hugetlb_folio(struct folio *folio); int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_FAILURE extern void folio_clear_hugetlb_hwpoison(struct folio *folio); #else static inline void folio_clear_hugetlb_hwpoison(struct folio *folio) { } #endif #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION #ifndef arch_hugetlb_migration_supported static inline bool arch_hugetlb_migration_supported(struct hstate *h) { if ((huge_page_shift(h) == PMD_SHIFT) || (huge_page_shift(h) == PUD_SHIFT) || (huge_page_shift(h) == PGDIR_SHIFT)) return true; else return false; } #endif #else static inline bool arch_hugetlb_migration_supported(struct hstate *h) { return false; } #endif static inline bool hugepage_migration_supported(struct hstate *h) { return arch_hugetlb_migration_supported(h); } /* * Movability check is different as compared to migration check. * It determines whether or not a huge page should be placed on * movable zone or not. Movability of any huge page should be * required only if huge page size is supported for migration. * There won't be any reason for the huge page to be movable if * it is not migratable to start with. Also the size of the huge * page should be large enough to be placed under a movable zone * and still feasible enough to be migratable. Just the presence * in movable zone does not make the migration feasible. * * So even though large huge page sizes like the gigantic ones * are migratable they should not be movable because its not * feasible to migrate them from movable zone. */ static inline bool hugepage_movable_supported(struct hstate *h) { if (!hugepage_migration_supported(h)) return false; if (hstate_is_gigantic(h)) return false; return true; } /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { gfp_t gfp = __GFP_COMP | __GFP_NOWARN; gfp |= hugepage_movable_supported(h) ? GFP_HIGHUSER_MOVABLE : GFP_HIGHUSER; return gfp; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { gfp_t modified_mask = htlb_alloc_mask(h); /* Some callers might want to enforce node */ modified_mask |= (gfp_mask & __GFP_THISNODE); modified_mask |= (gfp_mask & __GFP_NOWARN); return modified_mask; } static inline bool htlb_allow_alloc_fallback(int reason) { bool allowed_fallback = false; /* * Note: the memory offline, memory failure and migration syscalls will * be allowed to fallback to other nodes due to lack of a better chioce, * that might break the per-node hugetlb pool. While other cases will * set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool. */ switch (reason) { case MR_MEMORY_HOTPLUG: case MR_MEMORY_FAILURE: case MR_SYSCALL: case MR_MEMPOLICY_MBIND: allowed_fallback = true; break; default: break; } return allowed_fallback; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { const unsigned long size = huge_page_size(h); VM_WARN_ON(size == PAGE_SIZE); /* * hugetlb must use the exact same PT locks as core-mm page table * walkers would. When modifying a PTE table, hugetlb must take the * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD * PT lock etc. * * The expectation is that any hugetlb folio smaller than a PMD is * always mapped into a single PTE table and that any hugetlb folio * smaller than a PUD (but at least as big as a PMD) is always mapped * into a single PMD table. * * If that does not hold for an architecture, then that architecture * must disable split PT locks such that all *_lockptr() functions * will give us the same result: the per-MM PT lock. * * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() * and core-mm would use pmd_lockptr(). However, in such configurations * split PMD locks are disabled -- they don't make sense on a single * PGDIR page table -- and the end result is the same. */ if (size >= PUD_SIZE) return pud_lockptr(mm, (pud_t *) pte); else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ return ptep_lockptr(mm, pte); } #ifndef hugepages_supported /* * Some platform decide whether they support huge pages at boot * time. Some of them, such as powerpc, set HPAGE_SHIFT to 0 * when there is no such support */ #define hugepages_supported() (HPAGE_SHIFT != 0) #endif void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm); static inline void hugetlb_count_init(struct mm_struct *mm) { atomic_long_set(&mm->hugetlb_usage, 0); } static inline void hugetlb_count_add(long l, struct mm_struct *mm) { atomic_long_add(l, &mm->hugetlb_usage); } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { atomic_long_sub(l, &mm->hugetlb_usage); } #ifndef huge_ptep_modify_prot_start #define huge_ptep_modify_prot_start huge_ptep_modify_prot_start static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { unsigned long psize = huge_page_size(hstate_vma(vma)); return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize); } #endif #ifndef huge_ptep_modify_prot_commit #define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { unsigned long psize = huge_page_size(hstate_vma(vma)); set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } #endif #ifdef CONFIG_NUMA void hugetlb_register_node(struct node *node); void hugetlb_unregister_node(struct node *node); #endif /* * Check if a given raw @page in a hugepage is HWPOISON. */ bool is_raw_hwpoison_page_in_hugepage(struct page *page); static inline unsigned long huge_page_mask_align(struct file *file) { return PAGE_MASK & ~huge_page_mask(hstate_file(file)); } #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; static inline unsigned long huge_page_mask_align(struct file *file) { return 0; } static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return NULL; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return NULL; } static inline int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list) { return -ENOMEM; } static inline int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; } static inline void wait_for_freed_hugetlb_folios(void) { } static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner) { return NULL; } static inline struct folio * alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { return NULL; } static inline struct folio * alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { return NULL; } static inline int __alloc_bootmem_huge_page(struct hstate *h) { return 0; } static inline struct hstate *hstate_file(struct file *f) { return NULL; } static inline struct hstate *hstate_sizelog(int page_size_log) { return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return NULL; } static inline struct hstate *folio_hstate(struct folio *folio) { return NULL; } static inline struct hstate *size_to_hstate(unsigned long size) { return NULL; } static inline unsigned long huge_page_size(struct hstate *h) { return PAGE_SIZE; } static inline unsigned long huge_page_mask(struct hstate *h) { return PAGE_MASK; } static inline unsigned long vma_kernel_pagesize(struct vm_area_struct *vma) { return PAGE_SIZE; } static inline unsigned long vma_mmu_pagesize(struct vm_area_struct *vma) { return PAGE_SIZE; } static inline unsigned int huge_page_order(struct hstate *h) { return 0; } static inline unsigned int huge_page_shift(struct hstate *h) { return PAGE_SHIFT; } static inline bool hstate_is_gigantic(struct hstate *h) { return false; } static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; } static inline unsigned hstate_index_to_shift(unsigned index) { return 0; } static inline int hstate_index(struct hstate *h) { return 0; } static inline int dissolve_free_hugetlb_folio(struct folio *folio) { return 0; } static inline int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; } static inline bool hugepage_migration_supported(struct hstate *h) { return false; } static inline bool hugepage_movable_supported(struct hstate *h) { return false; } static inline gfp_t htlb_alloc_mask(struct hstate *h) { return 0; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { return 0; } static inline bool htlb_allow_alloc_fallback(int reason) { return false; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { return &mm->page_table_lock; } static inline void hugetlb_count_init(struct mm_struct *mm) { } static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) { } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { #ifdef CONFIG_MMU return ptep_get(ptep); #else return *ptep; #endif } static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { } static inline void hugetlb_register_node(struct node *node) { } static inline void hugetlb_unregister_node(struct node *node) { } static inline bool hugetlbfs_pagecache_present( struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return false; } static inline void hugetlb_bootmem_alloc(void) { } static inline bool hugetlb_bootmem_allocated(void) { return false; } #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) { spinlock_t *ptl; ptl = huge_pte_lockptr(h, mm, pte); spin_lock(ptl); return ptl; } #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) extern void __init hugetlb_cma_reserve(int order); #else static inline __init void hugetlb_cma_reserve(int order) { } #endif #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared(pte_t *pte) { return page_count(virt_to_page(pte)) > 1; } #else static inline bool hugetlb_pmd_shared(pte_t *pte) { return false; } #endif bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE /* * ARCHes with special requirements for evicting HUGETLB backing TLB entries can * implement this. */ #define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #endif static inline bool __vma_shareable_lock(struct vm_area_struct *vma) { return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; } bool __vma_private_lock(struct vm_area_struct *vma); /* * Safe version of huge_pte_offset() to check the locks. See comments * above huge_pte_offset(). */ static inline pte_t * hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { #if defined(CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING) && defined(CONFIG_LOCKDEP) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; /* * If pmd sharing possible, locking needed to safely walk the * hugetlb pgtables. More information can be found at the comment * above huge_pte_offset() in the same file. * * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP. */ if (__vma_shareable_lock(vma)) WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) && !lockdep_is_held( &vma->vm_file->f_mapping->i_mmap_rwsem)); #endif return huge_pte_offset(vma->vm_mm, addr, sz); } #endif /* _LINUX_HUGETLB_H */ |
| 4 4 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 | // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* Authors: Bernard Metzler <bmt@zurich.ibm.com> */ /* Copyright (c) 2008-2019, IBM Corporation */ #include <linux/init.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <net/net_namespace.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> #include <linux/list.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/dma-mapping.h> #include <net/addrconf.h> #include <rdma/ib_verbs.h> #include <rdma/ib_user_verbs.h> #include <rdma/rdma_netlink.h> #include <linux/kthread.h> #include "siw.h" #include "siw_verbs.h" MODULE_AUTHOR("Bernard Metzler"); MODULE_DESCRIPTION("Software iWARP Driver"); MODULE_LICENSE("Dual BSD/GPL"); /* transmit from user buffer, if possible */ const bool zcopy_tx = true; /* Restrict usage of GSO, if hardware peer iwarp is unable to process * large packets. try_gso = true lets siw try to use local GSO, * if peer agrees. Not using GSO severly limits siw maximum tx bandwidth. */ const bool try_gso; /* Attach siw also with loopback devices */ const bool loopback_enabled = true; /* We try to negotiate CRC on, if true */ const bool mpa_crc_required; /* MPA CRC on/off enforced */ const bool mpa_crc_strict; /* Control TCP_NODELAY socket option */ const bool siw_tcp_nagle; /* Select MPA version to be used during connection setup */ u_char mpa_version = MPA_REVISION_2; /* Selects MPA P2P mode (additional handshake during connection * setup, if true. */ const bool peer_to_peer; struct task_struct *siw_tx_thread[NR_CPUS]; static int siw_device_register(struct siw_device *sdev, const char *name) { struct ib_device *base_dev = &sdev->base_dev; static int dev_id = 1; int rv; sdev->vendor_part_id = dev_id++; rv = ib_register_device(base_dev, name, NULL); if (rv) { pr_warn("siw: device registration error %d\n", rv); return rv; } siw_dbg(base_dev, "HWaddr=%pM\n", sdev->raw_gid); return 0; } static void siw_device_cleanup(struct ib_device *base_dev) { struct siw_device *sdev = to_siw_dev(base_dev); xa_destroy(&sdev->qp_xa); xa_destroy(&sdev->mem_xa); } static int siw_dev_qualified(struct net_device *netdev) { /* * Additional hardware support can be added here * (e.g. ARPHRD_FDDI, ARPHRD_ATM, ...) - see * <linux/if_arp.h> for type identifiers. */ if (netdev->type == ARPHRD_ETHER || netdev->type == ARPHRD_IEEE802 || netdev->type == ARPHRD_NONE || (netdev->type == ARPHRD_LOOPBACK && loopback_enabled)) return 1; return 0; } static DEFINE_PER_CPU(atomic_t, siw_use_cnt); static struct { struct cpumask **tx_valid_cpus; int num_nodes; } siw_cpu_info; static void siw_destroy_cpulist(int number) { int i = 0; while (i < number) kfree(siw_cpu_info.tx_valid_cpus[i++]); kfree(siw_cpu_info.tx_valid_cpus); siw_cpu_info.tx_valid_cpus = NULL; } static int siw_init_cpulist(void) { int i, num_nodes = nr_node_ids; memset(siw_tx_thread, 0, sizeof(siw_tx_thread)); siw_cpu_info.num_nodes = num_nodes; siw_cpu_info.tx_valid_cpus = kcalloc(num_nodes, sizeof(struct cpumask *), GFP_KERNEL); if (!siw_cpu_info.tx_valid_cpus) { siw_cpu_info.num_nodes = 0; return -ENOMEM; } for (i = 0; i < siw_cpu_info.num_nodes; i++) { siw_cpu_info.tx_valid_cpus[i] = kzalloc(sizeof(struct cpumask), GFP_KERNEL); if (!siw_cpu_info.tx_valid_cpus[i]) goto out_err; cpumask_clear(siw_cpu_info.tx_valid_cpus[i]); } for_each_possible_cpu(i) cpumask_set_cpu(i, siw_cpu_info.tx_valid_cpus[cpu_to_node(i)]); return 0; out_err: siw_cpu_info.num_nodes = 0; siw_destroy_cpulist(i); return -ENOMEM; } /* * Choose CPU with least number of active QP's from NUMA node of * TX interface. */ int siw_get_tx_cpu(struct siw_device *sdev) { const struct cpumask *tx_cpumask; int i, num_cpus, cpu, min_use, node = sdev->numa_node, tx_cpu = -1; if (node < 0) tx_cpumask = cpu_online_mask; else tx_cpumask = siw_cpu_info.tx_valid_cpus[node]; num_cpus = cpumask_weight(tx_cpumask); if (!num_cpus) { /* no CPU on this NUMA node */ tx_cpumask = cpu_online_mask; num_cpus = cpumask_weight(tx_cpumask); } if (!num_cpus) goto out; cpu = cpumask_first(tx_cpumask); for (i = 0, min_use = SIW_MAX_QP; i < num_cpus; i++, cpu = cpumask_next(cpu, tx_cpumask)) { int usage; /* Skip any cores which have no TX thread */ if (!siw_tx_thread[cpu]) continue; usage = atomic_read(&per_cpu(siw_use_cnt, cpu)); if (usage <= min_use) { tx_cpu = cpu; min_use = usage; } } siw_dbg(&sdev->base_dev, "tx cpu %d, node %d, %d qp's\n", tx_cpu, node, min_use); out: if (tx_cpu >= 0) atomic_inc(&per_cpu(siw_use_cnt, tx_cpu)); else pr_warn("siw: no tx cpu found\n"); return tx_cpu; } void siw_put_tx_cpu(int cpu) { atomic_dec(&per_cpu(siw_use_cnt, cpu)); } static struct ib_qp *siw_get_base_qp(struct ib_device *base_dev, int id) { struct siw_qp *qp = siw_qp_id2obj(to_siw_dev(base_dev), id); if (qp) { /* * siw_qp_id2obj() increments object reference count */ siw_qp_put(qp); return &qp->base_qp; } return NULL; } static const struct ib_device_ops siw_device_ops = { .owner = THIS_MODULE, .uverbs_abi_ver = SIW_ABI_VERSION, .driver_id = RDMA_DRIVER_SIW, .alloc_mr = siw_alloc_mr, .alloc_pd = siw_alloc_pd, .alloc_ucontext = siw_alloc_ucontext, .create_cq = siw_create_cq, .create_qp = siw_create_qp, .create_srq = siw_create_srq, .dealloc_driver = siw_device_cleanup, .dealloc_pd = siw_dealloc_pd, .dealloc_ucontext = siw_dealloc_ucontext, .dereg_mr = siw_dereg_mr, .destroy_cq = siw_destroy_cq, .destroy_qp = siw_destroy_qp, .destroy_srq = siw_destroy_srq, .get_dma_mr = siw_get_dma_mr, .get_port_immutable = siw_get_port_immutable, .iw_accept = siw_accept, .iw_add_ref = siw_qp_get_ref, .iw_connect = siw_connect, .iw_create_listen = siw_create_listen, .iw_destroy_listen = siw_destroy_listen, .iw_get_qp = siw_get_base_qp, .iw_reject = siw_reject, .iw_rem_ref = siw_qp_put_ref, .map_mr_sg = siw_map_mr_sg, .mmap = siw_mmap, .mmap_free = siw_mmap_free, .modify_qp = siw_verbs_modify_qp, .modify_srq = siw_modify_srq, .poll_cq = siw_poll_cq, .post_recv = siw_post_receive, .post_send = siw_post_send, .post_srq_recv = siw_post_srq_recv, .query_device = siw_query_device, .query_gid = siw_query_gid, .query_port = siw_query_port, .query_qp = siw_query_qp, .query_srq = siw_query_srq, .req_notify_cq = siw_req_notify_cq, .reg_user_mr = siw_reg_user_mr, INIT_RDMA_OBJ_SIZE(ib_cq, siw_cq, base_cq), INIT_RDMA_OBJ_SIZE(ib_pd, siw_pd, base_pd), INIT_RDMA_OBJ_SIZE(ib_qp, siw_qp, base_qp), INIT_RDMA_OBJ_SIZE(ib_srq, siw_srq, base_srq), INIT_RDMA_OBJ_SIZE(ib_ucontext, siw_ucontext, base_ucontext), }; static struct siw_device *siw_device_create(struct net_device *netdev) { struct siw_device *sdev = NULL; struct ib_device *base_dev; int rv; sdev = ib_alloc_device(siw_device, base_dev); if (!sdev) return NULL; base_dev = &sdev->base_dev; if (netdev->addr_len) { memcpy(sdev->raw_gid, netdev->dev_addr, min_t(unsigned int, netdev->addr_len, ETH_ALEN)); } else { /* * This device does not have a HW address, but * connection mangagement requires a unique gid. */ eth_random_addr(sdev->raw_gid); } addrconf_addr_eui48((u8 *)&base_dev->node_guid, sdev->raw_gid); base_dev->uverbs_cmd_mask |= BIT_ULL(IB_USER_VERBS_CMD_POST_SEND); base_dev->node_type = RDMA_NODE_RNIC; memcpy(base_dev->node_desc, SIW_NODE_DESC_COMMON, sizeof(SIW_NODE_DESC_COMMON)); /* * Current model (one-to-one device association): * One Softiwarp device per net_device or, equivalently, * per physical port. */ base_dev->phys_port_cnt = 1; base_dev->num_comp_vectors = num_possible_cpus(); xa_init_flags(&sdev->qp_xa, XA_FLAGS_ALLOC1); xa_init_flags(&sdev->mem_xa, XA_FLAGS_ALLOC1); ib_set_device_ops(base_dev, &siw_device_ops); rv = ib_device_set_netdev(base_dev, netdev, 1); if (rv) goto error; memcpy(base_dev->iw_ifname, netdev->name, sizeof(base_dev->iw_ifname)); /* Disable TCP port mapping */ base_dev->iw_driver_flags = IW_F_NO_PORT_MAP; sdev->attrs.max_qp = SIW_MAX_QP; sdev->attrs.max_qp_wr = SIW_MAX_QP_WR; sdev->attrs.max_ord = SIW_MAX_ORD_QP; sdev->attrs.max_ird = SIW_MAX_IRD_QP; sdev->attrs.max_sge = SIW_MAX_SGE; sdev->attrs.max_sge_rd = SIW_MAX_SGE_RD; sdev->attrs.max_cq = SIW_MAX_CQ; sdev->attrs.max_cqe = SIW_MAX_CQE; sdev->attrs.max_mr = SIW_MAX_MR; sdev->attrs.max_pd = SIW_MAX_PD; sdev->attrs.max_mw = SIW_MAX_MW; sdev->attrs.max_srq = SIW_MAX_SRQ; sdev->attrs.max_srq_wr = SIW_MAX_SRQ_WR; sdev->attrs.max_srq_sge = SIW_MAX_SGE; INIT_LIST_HEAD(&sdev->cep_list); INIT_LIST_HEAD(&sdev->qp_list); atomic_set(&sdev->num_ctx, 0); atomic_set(&sdev->num_srq, 0); atomic_set(&sdev->num_qp, 0); atomic_set(&sdev->num_cq, 0); atomic_set(&sdev->num_mr, 0); atomic_set(&sdev->num_pd, 0); sdev->numa_node = dev_to_node(&netdev->dev); spin_lock_init(&sdev->lock); return sdev; error: ib_dealloc_device(base_dev); return NULL; } static int siw_netdev_event(struct notifier_block *nb, unsigned long event, void *arg) { struct net_device *netdev = netdev_notifier_info_to_dev(arg); struct ib_device *base_dev; struct siw_device *sdev; dev_dbg(&netdev->dev, "siw: event %lu\n", event); base_dev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_SIW); if (!base_dev) return NOTIFY_OK; sdev = to_siw_dev(base_dev); switch (event) { case NETDEV_REGISTER: /* * Device registration now handled only by * rdma netlink commands. So it shall be impossible * to end up here with a valid siw device. */ siw_dbg(base_dev, "unexpected NETDEV_REGISTER event\n"); break; case NETDEV_UNREGISTER: ib_unregister_device_queued(&sdev->base_dev); break; case NETDEV_CHANGEADDR: siw_port_event(sdev, 1, IB_EVENT_LID_CHANGE); break; /* * All other events are not handled */ default: break; } ib_device_put(&sdev->base_dev); return NOTIFY_OK; } static struct notifier_block siw_netdev_nb = { .notifier_call = siw_netdev_event, }; static int siw_newlink(const char *basedev_name, struct net_device *netdev) { struct ib_device *base_dev; struct siw_device *sdev = NULL; int rv = -ENOMEM; if (!siw_dev_qualified(netdev)) return -EINVAL; base_dev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_SIW); if (base_dev) { ib_device_put(base_dev); return -EEXIST; } sdev = siw_device_create(netdev); if (sdev) { dev_dbg(&netdev->dev, "siw: new device\n"); ib_mark_name_assigned_by_user(&sdev->base_dev); rv = siw_device_register(sdev, basedev_name); if (rv) ib_dealloc_device(&sdev->base_dev); } return rv; } static struct rdma_link_ops siw_link_ops = { .type = "siw", .newlink = siw_newlink, }; /* * siw_init_module - Initialize Softiwarp module and register with netdev * subsystem. */ static __init int siw_init_module(void) { int rv; if (SENDPAGE_THRESH < SIW_MAX_INLINE) { pr_info("siw: sendpage threshold too small: %u\n", (int)SENDPAGE_THRESH); rv = -EINVAL; goto out_error; } rv = siw_init_cpulist(); if (rv) goto out_error; rv = siw_cm_init(); if (rv) goto out_error; if (!siw_create_tx_threads()) { pr_info("siw: Could not start any TX thread\n"); rv = -ENOMEM; goto out_error; } rv = register_netdevice_notifier(&siw_netdev_nb); if (rv) goto out_error; rdma_link_register(&siw_link_ops); pr_info("SoftiWARP attached\n"); return 0; out_error: siw_stop_tx_threads(); pr_info("SoftIWARP attach failed. Error: %d\n", rv); siw_cm_exit(); siw_destroy_cpulist(siw_cpu_info.num_nodes); return rv; } static void __exit siw_exit_module(void) { siw_stop_tx_threads(); unregister_netdevice_notifier(&siw_netdev_nb); rdma_link_unregister(&siw_link_ops); ib_unregister_driver(RDMA_DRIVER_SIW); siw_cm_exit(); siw_destroy_cpulist(siw_cpu_info.num_nodes); pr_info("SoftiWARP detached\n"); } module_init(siw_init_module); module_exit(siw_exit_module); MODULE_ALIAS_RDMA_LINK("siw"); |
| 4 4 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright 2011-2014 Autronica Fire and Security AS * * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * * include file for HSR and PRP. */ #ifndef __HSR_SLAVE_H #define __HSR_SLAVE_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include "hsr_main.h" int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, enum hsr_port_type pt, struct netlink_ext_ack *extack); void hsr_del_port(struct hsr_port *port); bool hsr_port_exists(const struct net_device *dev); static inline struct hsr_port *hsr_port_get_rtnl(const struct net_device *dev) { ASSERT_RTNL(); return hsr_port_exists(dev) ? rtnl_dereference(dev->rx_handler_data) : NULL; } static inline struct hsr_port *hsr_port_get_rcu(const struct net_device *dev) { return hsr_port_exists(dev) ? rcu_dereference(dev->rx_handler_data) : NULL; } bool hsr_invalid_dan_ingress_frame(__be16 protocol); #endif /* __HSR_SLAVE_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 | // 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; 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; filep = anon_inode_getfile_fmode("[vfio-device]", &vfio_device_fops, df, O_RDWR, FMODE_PREAD | FMODE_PWRITE); if (IS_ERR(filep)) { ret = PTR_ERR(filep); goto err_close_device; } /* * 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(); } |
| 271 272 272 272 | 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 | /* 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 |
| 66 66 4 62 4 66 65 66 66 | 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 | // 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/kstack_erase.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 <linux/unwind_deferred.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> /* For dup_mmap(). */ #include "../mm/internal.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); } #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]); /* * Allocated stacks are cached and later reused by new threads, so memcg * accounting is performed by the code assigning/releasing stacks to tasks. * We need a zeroed memory without __GFP_ACCOUNT. */ #define GFP_VMAP_STACK (GFP_KERNEL | __GFP_ZERO) 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_area) { 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_area)) 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); struct vm_struct *vm_area = vm_stack->stack_vm_area; if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) return; vfree(vm_area->addr); } 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_stack_areas = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_area = cached_vm_stack_areas[i]; if (!vm_area) continue; vfree(vm_area->addr); cached_vm_stack_areas[i] = NULL; } return 0; } static int memcg_charge_kernel_stack(struct vm_struct *vm_area) { int i; int ret; int nr_charged = 0; BUG_ON(vm_area->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { ret = memcg_kmem_charge_page(vm_area->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_area->pages[i], 0); return ret; } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct vm_struct *vm_area; void *stack; int i; for (i = 0; i < NR_CACHED_STACKS; i++) { vm_area = this_cpu_xchg(cached_stacks[i], NULL); if (!vm_area) continue; if (memcg_charge_kernel_stack(vm_area)) { vfree(vm_area->addr); return -ENOMEM; } /* Reset stack metadata. */ kasan_unpoison_range(vm_area->addr, THREAD_SIZE); stack = kasan_reset_tag(vm_area->addr); /* Clear stale pointers from reused stack. */ memset(stack, 0, THREAD_SIZE); tsk->stack_vm_area = vm_area; tsk->stack = stack; return 0; } stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_VMAP_STACK, node, __builtin_return_address(0)); if (!stack) return -ENOMEM; vm_area = find_vm_area(stack); if (memcg_charge_kernel_stack(vm_area)) { 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_area; 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 */ /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ #if THREAD_SIZE >= PAGE_SIZE 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; } #else /* !(THREAD_SIZE >= PAGE_SIZE) */ 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 */ #endif /* 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 mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; static void account_kernel_stack(struct task_struct *tsk, int account) { if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm_area = task_stack_vm_area(tsk); int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm_area->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_area; int i; vm_area = task_stack_vm_area(tsk); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm_area->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); 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 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 #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ #ifdef CONFIG_MM_ID static DEFINE_IDA(mm_ida); static inline int mm_alloc_id(struct mm_struct *mm) { int ret; ret = ida_alloc_range(&mm_ida, MM_ID_MIN, MM_ID_MAX, GFP_KERNEL); if (ret < 0) return ret; mm->mm_id = ret; return 0; } static inline void mm_free_id(struct mm_struct *mm) { const mm_id_t id = mm->mm_id; mm->mm_id = MM_ID_DUMMY; if (id == MM_ID_DUMMY) return; if (WARN_ON_ONCE(id < MM_ID_MIN || id > MM_ID_MAX)) return; ida_free(&mm_ida, id); } #else /* !CONFIG_MM_ID */ static inline int mm_alloc_id(struct mm_struct *mm) { return 0; } static inline void mm_free_id(struct mm_struct *mm) {} #endif /* CONFIG_MM_ID */ 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 Comm:%s Pid:%d\n", mm, resident_page_types[i], x, current->comm, task_pid_nr(current)); } } 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 where it can be remotely checked without a * lock, to filter out false-positives in the cpumask. * - After mm_users or mm_count reaches zero, switching away from the * mm could clear mm_cpumask to reduce some IPIs, perhaps together * with some batching or delaying of the final IPIs. * - A delayed freeing and RCU-like quiescing sequence based on mm * switching to avoid IPIs completely. */ on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1); if (IS_ENABLED(CONFIG_DEBUG_VM_SHOOT_LAZIES)) on_each_cpu(do_check_lazy_tlb, (void *)mm, 1); } /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); /* Ensure no CPUs are using this as their lazy tlb mm */ cleanup_lazy_tlbs(mm); WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); mm_free_id(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); mm_pasid_drop(mm); mm_destroy_cid(mm); percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; mm = container_of(work, struct mm_struct, async_put_work); __mmdrop(mm); } static void mmdrop_async(struct mm_struct *mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) { INIT_WORK(&mm->async_put_work, mmdrop_async_fn); schedule_work(&mm->async_put_work); } } static inline void free_signal_struct(struct signal_struct *sig) { taskstats_tgid_free(sig); sched_autogroup_exit(sig); /* * __mmdrop is not safe to call from softirq context on x86 due to * pgd_dtor so postpone it to the async context */ if (sig->oom_mm) mmdrop_async(sig->oom_mm); kmem_cache_free(signal_cachep, sig); } static inline void put_signal_struct(struct signal_struct *sig) { if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); unwind_task_free(tsk); sched_ext_free(tsk); io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); sched_core_free(tsk); free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); void __put_task_struct_rcu_cb(struct rcu_head *rhp) { struct task_struct *task = container_of(rhp, struct task_struct, rcu); __put_task_struct(task); } EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb); void __init __weak arch_task_cache_init(void) { } /* * set_max_threads */ static void __init set_max_threads(unsigned int max_threads_suggested) { u64 threads; unsigned long nr_pages = memblock_estimated_nr_free_pages(); /* * The number of threads shall be limited such that the thread * structures may only consume a small part of the available memory. */ if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64) threads = MAX_THREADS; else threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE, (u64) THREAD_SIZE * 8UL); if (threads > max_threads_suggested) threads = max_threads_suggested; max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT /* Initialized by the architecture: */ int arch_task_struct_size __read_mostly; #endif static void __init task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ arch_thread_struct_whitelist(offset, size); /* * Handle zero-sized whitelist or empty thread_struct, otherwise * adjust offset to position of thread_struct in task_struct. */ if (unlikely(*size == 0)) *offset = 0; else *offset += offsetof(struct task_struct, thread); } void __init fork_init(void) { int i; #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN 0 #endif int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); unsigned long useroffset, usersize; /* create a slab on which task_structs can be allocated */ task_struct_whitelist(&useroffset, &usersize); task_struct_cachep = kmem_cache_create_usercopy("task_struct", arch_task_struct_size, align, SLAB_PANIC|SLAB_ACCOUNT, useroffset, usersize, NULL); /* do the arch specific task caches init */ arch_task_cache_init(); set_max_threads(MAX_THREADS); init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", NULL, free_vm_stack_cache); #endif scs_init(); lockdep_init_task(&init_task); uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; return 0; } void set_task_stack_end_magic(struct task_struct *tsk) { unsigned long *stackend; stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ } static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; int err; if (node == NUMA_NO_NODE) node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; err = arch_dup_task_struct(tsk, orig); if (err) goto free_tsk; err = alloc_thread_stack_node(tsk, node); if (err) goto free_tsk; #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif account_kernel_stack(tsk, 1); err = scs_prepare(tsk, node); if (err) goto free_stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under * the sighand lock in case orig has changed between now and * then. Until then, filter must be NULL to avoid messing up * the usage counts on the error path calling free_task. */ tsk->seccomp.filter = NULL; #endif setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); clear_syscall_work_syscall_user_dispatch(tsk); #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif if (orig->cpus_ptr == &orig->cpus_mask) tsk->cpus_ptr = &tsk->cpus_mask; dup_user_cpus_ptr(tsk, orig, node); /* * One for the user space visible state that goes away when reaped. * One for the scheduler. */ refcount_set(&tsk->rcu_users, 2); /* One for the rcu users */ refcount_set(&tsk->usage, 1); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; tsk->worker_private = NULL; kcov_task_init(tsk); kmsan_task_create(tsk); kmap_local_fork(tsk); #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif #ifdef CONFIG_BLK_CGROUP tsk->throttle_disk = NULL; tsk->use_memdelay = 0; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID tsk->pasid_activated = 0; #endif #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT tsk->reported_split_lock = 0; #endif #ifdef CONFIG_SCHED_MM_CID tsk->mm_cid = -1; tsk->last_mm_cid = -1; tsk->mm_cid_active = 0; tsk->migrate_from_cpu = -1; #endif return tsk; free_stack: exit_task_stack_account(tsk); free_thread_stack(tsk); free_tsk: free_task_struct(tsk); return NULL; } __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; static int __init coredump_filter_setup(char *s) { default_dump_filter = (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & MMF_DUMP_FILTER_MASK; return 1; } __setup("coredump_filter=", coredump_filter_setup); #include <linux/init_task.h> static void mm_init_aio(struct mm_struct *mm) { #ifdef CONFIG_AIO spin_lock_init(&mm->ioctx_lock); mm->ioctx_table = NULL; #endif } static __always_inline void mm_clear_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG if (mm->owner == p) WRITE_ONCE(mm->owner, NULL); #endif } static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG mm->owner = p; #endif } static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES mm->uprobes_state.xol_area = NULL; arch_uprobe_init_state(mm); #endif } static void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); mm_lock_seqcount_init(mm); #ifdef CONFIG_PER_VMA_LOCK rcuwait_init(&mm->vma_writer_wait); #endif } static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { mt_init_flags(&mm->mm_mt, MM_MT_FLAGS); mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock); atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); mm_pasid_init(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); mm_flags_clear_all(mm); if (current->mm) { unsigned long flags = __mm_flags_get_word(current->mm); __mm_flags_set_word(mm, mmf_init_legacy_flags(flags)); mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { __mm_flags_set_word(mm, default_dump_filter); mm->def_flags = 0; } if (futex_mm_init(mm)) goto fail_mm_init; if (mm_alloc_pgd(mm)) goto fail_nopgd; if (mm_alloc_id(mm)) goto fail_noid; if (init_new_context(p, mm)) goto fail_nocontext; if (mm_alloc_cid(mm, p)) goto fail_cid; if (percpu_counter_init_many(mm->rss_stat, 0, GFP_KERNEL_ACCOUNT, NR_MM_COUNTERS)) goto fail_pcpu; mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); return mm; fail_pcpu: mm_destroy_cid(mm); fail_cid: destroy_context(mm); fail_nocontext: mm_free_id(mm); fail_noid: mm_free_pgd(mm); fail_nopgd: futex_hash_free(mm); fail_mm_init: free_mm(mm); return NULL; } /* * Allocate and initialize an mm_struct. */ struct mm_struct *mm_alloc(void) { struct mm_struct *mm; mm = allocate_mm(); if (!mm) return NULL; memset(mm, 0, sizeof(*mm)); return mm_init(mm, current, current_user_ns()); } EXPORT_SYMBOL_IF_KUNIT(mm_alloc); static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); mm_put_huge_zero_folio(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); futex_hash_free(mm); mmdrop(mm); } /* * Decrement the use count and release all resources for an mm. */ void mmput(struct mm_struct *mm) { might_sleep(); if (atomic_dec_and_test(&mm->mm_users)) __mmput(mm); } EXPORT_SYMBOL_GPL(mmput); #if defined(CONFIG_MMU) || defined(CONFIG_FUTEX_PRIVATE_HASH) static void mmput_async_fn(struct work_struct *work) { struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); __mmput(mm); } void mmput_async(struct mm_struct *mm) { if (atomic_dec_and_test(&mm->mm_users)) { INIT_WORK(&mm->async_put_work, mmput_async_fn); schedule_work(&mm->async_put_work); } } EXPORT_SYMBOL_GPL(mmput_async); #endif /** * set_mm_exe_file - change a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve it happens before * the new mm is made visible to anyone. * * Can only fail if new_exe_file != NULL. */ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct file *old_exe_file; /* * It is safe to dereference the exe_file without RCU as * this function is only called if nobody else can access * this mm -- see comment above for justification. */ old_exe_file = rcu_dereference_raw(mm->exe_file); if (new_exe_file) { /* * We expect the caller (i.e., sys_execve) to already denied * write access, so this is unlikely to fail. */ if (unlikely(exe_file_deny_write_access(new_exe_file))) return -EACCES; get_file(new_exe_file); } rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) { exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * replace_mm_exe_file - replace a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE). */ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct vm_area_struct *vma; struct file *old_exe_file; int ret = 0; /* Forbid mm->exe_file change if old file still mapped. */ old_exe_file = get_mm_exe_file(mm); if (old_exe_file) { VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, &old_exe_file->f_path)) { ret = -EBUSY; break; } } mmap_read_unlock(mm); fput(old_exe_file); if (ret) return ret; } ret = exe_file_deny_write_access(new_exe_file); if (ret) return -EACCES; get_file(new_exe_file); /* set the new file */ mmap_write_lock(mm); old_exe_file = rcu_dereference_raw(mm->exe_file); rcu_assign_pointer(mm->exe_file, new_exe_file); mmap_write_unlock(mm); if (old_exe_file) { exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * get_mm_exe_file - acquire a reference to the mm's executable file * @mm: The mm of interest. * * Returns %NULL if mm has no associated executable file. * User must release file via fput(). */ struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; rcu_read_lock(); exe_file = get_file_rcu(&mm->exe_file); rcu_read_unlock(); return exe_file; } /** * get_task_exe_file - acquire a reference to the task's executable file * @task: The task. * * Returns %NULL if task's mm (if any) has no associated executable file or * this is a kernel thread with borrowed mm (see the comment above get_task_mm). * User must release file via fput(). */ struct file *get_task_exe_file(struct task_struct *task) { struct file *exe_file = NULL; struct mm_struct *mm; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) exe_file = get_mm_exe_file(mm); task_unlock(task); return exe_file; } /** * get_task_mm - acquire a reference to the task's mm * @task: The task. * * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning * this kernel workthread has transiently adopted a user mm with use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. */ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) mmget(mm); task_unlock(task); return mm; } EXPORT_SYMBOL_GPL(get_task_mm); static bool may_access_mm(struct mm_struct *mm, struct task_struct *task, unsigned int mode) { if (mm == current->mm) return true; if (ptrace_may_access(task, mode)) return true; if ((mode & PTRACE_MODE_READ) && perfmon_capable()) return true; return false; } struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) { struct mm_struct *mm; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return ERR_PTR(err); mm = get_task_mm(task); if (!mm) { mm = ERR_PTR(-ESRCH); } else if (!may_access_mm(mm, task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } up_read(&task->signal->exec_update_lock); return mm; } static void complete_vfork_done(struct task_struct *tsk) { struct completion *vfork; task_lock(tsk); vfork = tsk->vfork_done; if (likely(vfork)) { tsk->vfork_done = NULL; complete(vfork); } task_unlock(tsk); } static int wait_for_vfork_done(struct task_struct *child, struct completion *vfork) { unsigned int state = TASK_KILLABLE|TASK_FREEZABLE; int killed; cgroup_enter_frozen(); killed = wait_for_completion_state(vfork, state); cgroup_leave_frozen(false); if (killed) { task_lock(child); child->vfork_done = NULL; task_unlock(child); } put_task_struct(child); return killed; } /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. * * mm_release is called after a mm_struct has been removed * from the current process. * * This difference is important for error handling, when we * only half set up a mm_struct for a new process and need to restore * the old one. Because we mmput the new mm_struct before * restoring the old one. . . * Eric Biederman 10 January 1998 */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { uprobe_free_utask(tsk); /* Get rid of any cached register state */ deactivate_mm(tsk, mm); /* * Signal userspace if we're not exiting with a core dump * because we want to leave the value intact for debugging * purposes. */ if (tsk->clear_child_tid) { if (atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ put_user(0, tsk->clear_child_tid); do_futex(tsk->clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0, 0); } tsk->clear_child_tid = NULL; } /* * All done, finally we can wake up parent and return this mm to him. * Also kthread_stop() uses this completion for synchronization. */ if (tsk->vfork_done) complete_vfork_done(tsk); } void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exit_release(tsk); mm_release(tsk, mm); } void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exec_release(tsk); mm_release(tsk, mm); } /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. * @oldmm: the mm to duplicate. * * Allocates a new mm structure and duplicates the provided @oldmm structure * content into it. * * Return: the duplicated mm or NULL on failure. */ static struct mm_struct *dup_mm(struct task_struct *tsk, struct mm_struct *oldmm) { struct mm_struct *mm; int err; mm = allocate_mm(); if (!mm) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; uprobe_start_dup_mmap(); err = dup_mmap(mm, oldmm); if (err) goto free_pt; uprobe_end_dup_mmap(); mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; return mm; free_pt: /* don't put binfmt in mmput, we haven't got module yet */ mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); if (err) uprobe_end_dup_mmap(); fail_nomem: return NULL; } static int copy_mm(u64 clone_flags, struct task_struct *tsk) { struct mm_struct *mm, *oldmm; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; #ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; tsk->last_switch_time = 0; #endif tsk->mm = NULL; tsk->active_mm = NULL; /* * Are we cloning a kernel thread? * * We need to steal a active VM for that.. */ oldmm = current->mm; if (!oldmm) return 0; if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; } else { mm = dup_mm(tsk, current->mm); if (!mm) return -ENOMEM; } tsk->mm = mm; tsk->active_mm = mm; sched_mm_cid_fork(tsk); return 0; } static int copy_fs(u64 clone_flags, struct task_struct *tsk) { struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ read_seqlock_excl(&fs->seq); /* "users" and "in_exec" locked for check_unsafe_exec() */ if (fs->in_exec) { read_sequnlock_excl(&fs->seq); return -EAGAIN; } fs->users++; read_sequnlock_excl(&fs->seq); return 0; } tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; } static int copy_files(u64 clone_flags, struct task_struct *tsk, int no_files) { struct files_struct *oldf, *newf; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) return 0; if (no_files) { tsk->files = NULL; return 0; } if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); return 0; } newf = dup_fd(oldf, NULL); if (IS_ERR(newf)) return PTR_ERR(newf); tsk->files = newf; return 0; } static int copy_sighand(u64 clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); /* Reset all signal handler not set to SIG_IGN to SIG_DFL. */ if (clone_flags & CLONE_CLEAR_SIGHAND) flush_signal_handlers(tsk, 0); return 0; } void __cleanup_sighand(struct sighand_struct *sighand) { if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it * without an RCU grace period, see __lock_task_sighand(). */ kmem_cache_free(sighand_cachep, sighand); } } /* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; unsigned long cpu_limit; cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); posix_cputimers_group_init(pct, cpu_limit); } static int copy_signal(u64 clone_flags, struct task_struct *tsk) { struct signal_struct *sig; if (clone_flags & CLONE_THREAD) return 0; sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; sig->nr_threads = 1; sig->quick_threads = 1; atomic_set(&sig->live, 1); refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head); init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_HLIST_HEAD(&sig->multiprocess); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS INIT_HLIST_HEAD(&sig->posix_timers); INIT_HLIST_HEAD(&sig->ignored_posix_timers); hrtimer_setup(&sig->real_timer, it_real_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL); #endif task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); tty_audit_fork(sig); sched_autogroup_fork(sig); #ifdef CONFIG_CGROUPS init_rwsem(&sig->cgroup_threadgroup_rwsem); #endif sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); init_rwsem(&sig->exec_update_lock); return 0; } static void copy_seccomp(struct task_struct *p) { #ifdef CONFIG_SECCOMP /* * Must be called with sighand->lock held, which is common to * all threads in the group. Holding cred_guard_mutex is not * needed because this new task is not yet running and cannot * be racing exec. */ assert_spin_locked(¤t->sighand->siglock); /* Ref-count the new filter user, and assign it. */ get_seccomp_filter(current); p->seccomp = current->seccomp; /* * Explicitly enable no_new_privs here in case it got set * between the task_struct being duplicated and holding the * sighand lock. The seccomp state and nnp must be in sync. */ if (task_no_new_privs(current)) task_set_no_new_privs(p); /* * If the parent gained a seccomp mode after copying thread * flags and between before we held the sighand lock, we have * to manually enable the seccomp thread flag here. */ if (p->seccomp.mode != SECCOMP_MODE_DISABLED) set_task_syscall_work(p, SECCOMP); #endif } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; return task_pid_vnr(current); } static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES p->pi_waiters = RB_ROOT_CACHED; p->pi_top_task = NULL; p->pi_blocked_on = NULL; #endif } static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); } static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { if (type == PIDTYPE_PID) task->thread_pid = pid; else task->signal->pids[type] = pid; } static inline void rcu_copy_process(struct task_struct *p) { #ifdef CONFIG_PREEMPT_RCU p->rcu_read_lock_nesting = 0; p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; INIT_LIST_HEAD(&p->rcu_node_entry); #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; INIT_LIST_HEAD(&p->rcu_tasks_exit_list); #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; p->trc_reader_special.s = 0; INIT_LIST_HEAD(&p->trc_holdout_list); INIT_LIST_HEAD(&p->trc_blkd_node); #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } /** * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @ret_file: return the new pidfs file * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper verifies that @pid is still in use, without PIDFD_THREAD the * task identified by @pid must be a thread-group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file) { struct file *pidfs_file; /* * PIDFD_STALE is only allowed to be passed if the caller knows * that @pid is already registered in pidfs and thus * PIDFD_INFO_EXIT information is guaranteed to be available. */ if (!(flags & PIDFD_STALE)) { /* * While holding the pidfd waitqueue lock removing the * task linkage for the thread-group leader pid * (PIDTYPE_TGID) isn't possible. Thus, if there's still * task linkage for PIDTYPE_PID not having thread-group * leader linkage for the pid means it wasn't a * thread-group leader in the first place. */ guard(spinlock_irq)(&pid->wait_pidfd.lock); /* Task has already been reaped. */ if (!pid_has_task(pid, PIDTYPE_PID)) return -ESRCH; /* * If this struct pid isn't used as a thread-group * leader but the caller requested to create a * thread-group leader pidfd then report ENOENT. */ if (!(flags & PIDFD_THREAD) && !pid_has_task(pid, PIDTYPE_TGID)) return -ENOENT; } CLASS(get_unused_fd, pidfd)(O_CLOEXEC); if (pidfd < 0) return pidfd; pidfs_file = pidfs_alloc_file(pid, flags | O_RDWR); if (IS_ERR(pidfs_file)) return PTR_ERR(pidfs_file); *ret_file = pidfs_file; return take_fd(pidfd); } static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); free_task(tsk); } static __always_inline void delayed_free_task(struct task_struct *tsk) { if (IS_ENABLED(CONFIG_MEMCG)) call_rcu(&tsk->rcu, __delayed_free_task); else free_task(tsk); } static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) { /* Skip if kernel thread */ if (!tsk->mm) return; /* Skip if spawning a thread or using vfork */ if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) return; /* We need to synchronize with __set_oom_adj */ mutex_lock(&oom_adj_mutex); mm_flags_set(MMF_MULTIPROCESS, tsk->mm); /* Update the values in case they were changed after copy_signal */ tsk->signal->oom_score_adj = current->signal->oom_score_adj; tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_unlock(&oom_adj_mutex); } #ifdef CONFIG_RV static void rv_task_fork(struct task_struct *p) { memset(&p->rv, 0, sizeof(p->rv)); } #else #define rv_task_fork(p) do {} while (0) #endif static bool need_futex_hash_allocate_default(u64 clone_flags) { if ((clone_flags & (CLONE_THREAD | CLONE_VM)) != (CLONE_THREAD | CLONE_VM)) return false; return true; } /* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ __latent_entropy struct task_struct *copy_process( struct pid *pid, int trace, int node, struct kernel_clone_args *args) { int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; const u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); /* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. */ if (clone_flags & CLONE_DETACHED) return ERR_PTR(-EINVAL); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; if (args->user_worker) { /* * Mark us a user worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } if (args->io_thread) p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; retval = -EAGAIN; if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ retval = -EAGAIN; if (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY); p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0; #endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE; #endif #ifdef CONFIG_IO_URING p->io_uring = NULL; #endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0; #endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); tick_dep_init_task(p); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); if (args->kthread) { if (!set_kthread_struct(p)) goto bad_fork_cleanup_delayacct; } #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_delayacct; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0; #endif p->pagefault_disabled = 0; lockdep_init_task(p); p->blocked_on = NULL; /* not blocked yet */ #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(p->bpf_storage, NULL); p->bpf_ctx = NULL; #endif unwind_task_init(p); /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p, clone_flags); if (retval) goto bad_fork_sched_cancel_fork; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p, args->no_files); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(p, args); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0; /* * Note that no task has been attached to @pid yet indicate * that via CLONE_PIDFD. */ retval = pidfd_prepare(pid, flags | PIDFD_STALE, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; #endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_task_syscall_work(p, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(p, SYSCALL_EMU); #endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; p->task_works = NULL; clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; #endif #ifdef CONFIG_RETHOOK p->rethooks.first = NULL; #endif /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * Now that the cgroups are pinned, re-clone the parent cgroup and put * the new task on the correct runqueue. All this *before* the task * becomes visible. * * This isn't part of ->can_fork() because while the re-cloning is * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ retval = sched_cgroup_fork(p, args); if (retval) goto bad_fork_cancel_cgroup; /* * Allocate a default futex hash for the user process once the first * thread spawns. */ if (need_futex_hash_allocate_default(clone_flags)) { retval = futex_hash_allocate_default(); if (retval) goto bad_fork_cancel_cgroup; /* * If we fail beyond this point we don't free the allocated * futex hash map. We assume that another thread will be created * and makes use of it. The hash map will be freed once the main * thread terminates. */ } /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); sched_core_fork(p); spin_lock(¤t->sighand->siglock); rv_task_fork(p); rseq_fork(p, clone_flags); /* Don't start children in a dying pid namespace */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_core_free; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_core_free; } /* No more failure paths after this point. */ /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) { ns_of_pid(pid)->child_reaper = p; p->signal->flags |= SIGNAL_UNKILLABLE; } p->signal->shared_pending.signal = delayed.signal; p->signal->tty = tty_kref_get(current->signal->tty); /* * Inherit has_child_subreaper flag under the same * tasklist_lock with adding child to the process tree * for propagate_has_child_subreaper optimization. */ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || p->real_parent->signal->is_child_subreaper; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_TGID); attach_pid(p, PIDTYPE_PGID); attach_pid(p, PIDTYPE_SID); __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; current->signal->quick_threads++; atomic_inc(¤t->signal->live); refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); nr_threads++; } total_forks++; hlist_del_init(&delayed.node); spin_unlock(¤t->sighand->siglock); syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); if (pidfile) fd_install(pidfd, pidfile); proc_fork_connector(p); sched_post_fork(p); cgroup_post_fork(p, args); perf_event_fork(p); trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); user_events_fork(p, clone_flags); copy_oom_score_adj(clone_flags, p); return p; bad_fork_core_free: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); bad_fork_cancel_cgroup: cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { fput(pidfile); put_unused_fd(pidfd); } bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: exit_thread(p); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { mm_clear_owner(p->mm, p); mmput(p->mm); } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); bad_fork_sched_cancel_fork: sched_cancel_fork(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); #endif bad_fork_cleanup_delayacct: delayacct_tsk_free(p); bad_fork_cleanup_count: dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); exit_task_stack_account(p); put_task_stack(p); delayed_free_task(p); fork_out: spin_lock_irq(¤t->sighand->siglock); hlist_del_init(&delayed.node); spin_unlock_irq(¤t->sighand->siglock); return ERR_PTR(retval); } static inline void init_idle_pids(struct task_struct *idle) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */ init_task_pid(idle, type, &init_struct_pid); } } static int idle_dummy(void *dummy) { /* This function is never called */ return 0; } struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, .fn = &idle_dummy, .fn_arg = NULL, .kthread = 1, .idle = 1, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); if (!IS_ERR(task)) { init_idle_pids(task); init_idle(task, cpu); } return task; } /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. * The returned task is inactive, and the caller must fire it up through * wake_up_new_task(p). All signals are blocked in the created task. */ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) { unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| CLONE_IO|CLONE_VM|CLONE_UNTRACED; struct kernel_clone_args args = { .flags = flags, .fn = fn, .fn_arg = arg, .io_thread = 1, .user_worker = 1, }; return copy_process(NULL, 0, node, &args); } /* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. * * args->exit_signal is expected to be checked for sanity by the caller. */ pid_t kernel_clone(struct kernel_clone_args *args) { u64 clone_flags = args->flags; struct completion vfork; struct pid *pid; struct task_struct *p; int trace = 0; pid_t nr; /* * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate * field in struct clone_args and it still doesn't make sense to have * them both point at the same memory location. Performing this check * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ if ((clone_flags & CLONE_PIDFD) && (clone_flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; /* * Determine whether and which event to report to ptracer. When * called from kernel_thread or CLONE_UNTRACED is explicitly * requested, no event is reported; otherwise, report if the event * for the type of forking is enabled. */ if (!(clone_flags & CLONE_UNTRACED)) { if (clone_flags & CLONE_VFORK) trace = PTRACE_EVENT_VFORK; else if (args->exit_signal != SIGCHLD) trace = PTRACE_EVENT_CLONE; else trace = PTRACE_EVENT_FORK; if (likely(!ptrace_event_enabled(current, trace))) trace = 0; } p = copy_process(NULL, trace, NUMA_NO_NODE, args); add_latent_entropy(); if (IS_ERR(p)) return PTR_ERR(p); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, args->parent_tid); if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); get_task_struct(p); } if (IS_ENABLED(CONFIG_LRU_GEN_WALKS_MMU) && !(clone_flags & CLONE_VM)) { /* lock the task to synchronize with memcg migration */ task_lock(p); lru_gen_add_mm(p->mm); task_unlock(p); } wake_up_new_task(p); /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } put_pid(pid); return nr; } /* * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, unsigned long flags) { struct kernel_clone_args args = { .flags = ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (flags & CSIGNAL), .fn = fn, .fn_arg = arg, .name = name, .kthread = 1, }; return kernel_clone(&args); } /* * Create a user mode thread. */ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (flags & CSIGNAL), .fn = fn, .fn_arg = arg, }; return kernel_clone(&args); } #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) { #ifdef CONFIG_MMU struct kernel_clone_args args = { .exit_signal = SIGCHLD, }; return kernel_clone(&args); #else /* can not support in nommu mode */ return -EINVAL; #endif } #endif #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { struct kernel_clone_args args = { .flags = CLONE_VFORK | CLONE_VM, .exit_signal = SIGCHLD, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE #ifdef CONFIG_CLONE_BACKWARDS SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, unsigned long, tls, int __user *, child_tidptr) #elif defined(CONFIG_CLONE_BACKWARDS2) SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #elif defined(CONFIG_CLONE_BACKWARDS3) SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, int, stack_size, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #endif { struct kernel_clone_args args = { .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; return kernel_clone(&args); } #endif static noinline int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) { int err; struct clone_args args; pid_t *kset_tid = kargs->set_tid; BUILD_BUG_ON(offsetofend(struct clone_args, tls) != CLONE_ARGS_SIZE_VER0); BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) != CLONE_ARGS_SIZE_VER1); BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != CLONE_ARGS_SIZE_VER2); BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (err) return err; if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL)) return -EINVAL; if (unlikely(!args.set_tid && args.set_tid_size > 0)) return -EINVAL; if (unlikely(args.set_tid && args.set_tid_size == 0)) return -EINVAL; /* * Verify that higher 32bits of exit_signal are unset and that * it is a valid signal */ if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || !valid_signal(args.exit_signal))) return -EINVAL; if ((args.flags & CLONE_INTO_CGROUP) && (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2)) return -EINVAL; *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), .child_tid = u64_to_user_ptr(args.child_tid), .parent_tid = u64_to_user_ptr(args.parent_tid), .exit_signal = args.exit_signal, .stack = args.stack, .stack_size = args.stack_size, .tls = args.tls, .set_tid_size = args.set_tid_size, .cgroup = args.cgroup, }; if (args.set_tid && copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid), (kargs->set_tid_size * sizeof(pid_t)))) return -EFAULT; kargs->set_tid = kset_tid; return 0; } /** * clone3_stack_valid - check and prepare stack * @kargs: kernel clone args * * Verify that the stack arguments userspace gave us are sane. * In addition, set the stack direction for userspace since it's easy for us to * determine. */ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) { if (kargs->stack == 0) { if (kargs->stack_size > 0) return false; } else { if (kargs->stack_size == 0) return false; if (!access_ok((void __user *)kargs->stack, kargs->stack_size)) return false; #if !defined(CONFIG_STACK_GROWSUP) kargs->stack += kargs->stack_size; #endif } return true; } static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP)) return false; /* * - make the CLONE_DETACHED bit reusable for clone3 * - make the CSIGNAL bits reusable for clone3 */ if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME)))) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) return false; if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) && kargs->exit_signal) return false; if (!clone3_stack_valid(kargs)) return false; return true; } /** * sys_clone3 - create a new process with specific properties * @uargs: argument structure * @size: size of @uargs * * clone3() is the extensible successor to clone()/clone2(). * It takes a struct as argument that is versioned by its size. * * Return: On success, a positive PID for the child process. * On error, a negative errno number. */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; struct kernel_clone_args kargs; pid_t set_tid[MAX_PID_NS_LEVEL]; #ifdef __ARCH_BROKEN_SYS_CLONE3 #warning clone3() entry point is missing, please fix return -ENOSYS; #endif kargs.set_tid = set_tid; err = copy_clone_args_from_user(&kargs, uargs, size); if (err) return err; if (!clone3_args_valid(&kargs)) return -EINVAL; return kernel_clone(&kargs); } void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data) { struct task_struct *leader, *parent, *child; int res; read_lock(&tasklist_lock); leader = top = top->group_leader; down: for_each_thread(leader, parent) { list_for_each_entry(child, &parent->children, sibling) { res = visitor(child, data); if (res) { if (res < 0) goto out; leader = child; goto down; } up: ; } } if (leader != top) { child = leader; parent = child->real_parent; leader = parent->group_leader; goto up; } out: read_unlock(&tasklist_lock); } #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; spin_lock_init(&sighand->siglock); init_waitqueue_head(&sighand->signalfd_wqh); } void __init mm_cache_init(void) { unsigned int mm_size; /* * The mm_cpumask is located at the end of mm_struct, and is * dynamically sized based on the maximum CPU number this system * can have, taking hotplug into account (nr_cpu_ids). */ mm_size = sizeof(struct mm_struct) + cpumask_size() + mm_cid_size(); mm_cachep = kmem_cache_create_usercopy("mm_struct", mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), NULL); } void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); mmap_init(); nsproxy_cache_init(); } /* * Check constraints on flags passed to the unshare system call. */ static int check_unshare_flags(unsigned long unshare_flags) { if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing * to unshare. Note that unsharing the address space or the * signal handlers also need to unshare the signal queues (aka * CLONE_THREAD). */ if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) { if (!thread_group_empty(current)) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { if (!current_is_single_threaded()) return -EINVAL; } return 0; } /* * Unshare the filesystem structure if it is being shared */ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; if (!(unshare_flags & CLONE_FS) || !fs) return 0; /* don't need lock here; in the worst case we'll do useless copy */ if (fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); if (!*new_fsp) return -ENOMEM; return 0; } /* * Unshare file descriptor table if it is being shared */ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) { struct files_struct *fd = current->files; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { fd = dup_fd(fd, NULL); if (IS_ERR(fd)) return PTR_ERR(fd); *new_fdp = fd; } return 0; } /* * unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* * functions used by kernel_clone() cannot be used here directly * because they modify an inactive task_struct that is being * constructed. Here we are modifying the current, active, * task_struct. */ int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *new_fd = NULL; struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; int err; /* * If unsharing a user namespace must also unshare the thread group * and unshare the filesystem root and working directories. */ if (unshare_flags & CLONE_NEWUSER) unshare_flags |= CLONE_THREAD | CLONE_FS; /* * If unsharing vm, must also unshare signal handlers. */ if (unshare_flags & CLONE_VM) unshare_flags |= CLONE_SIGHAND; /* * If unsharing a signal handlers, must also unshare the signal queues. */ if (unshare_flags & CLONE_SIGHAND) unshare_flags |= CLONE_THREAD; /* * If unsharing namespace, must also unshare filesystem information. */ if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; /* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; err = unshare_fs(unshare_flags, &new_fs); if (err) goto bad_unshare_out; err = unshare_fd(unshare_flags, &new_fd); if (err) goto bad_unshare_cleanup_fs; err = unshare_userns(unshare_flags, &new_cred); if (err) goto bad_unshare_cleanup_fd; err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_cred, new_fs); if (err) goto bad_unshare_cleanup_cred; if (new_cred) { err = set_cred_ucounts(new_cred); if (err) goto bad_unshare_cleanup_cred; } if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). */ exit_sem(current); } if (unshare_flags & CLONE_NEWIPC) { /* Orphan segments in old ns (see sem above). */ exit_shm(current); shm_init_task(current); } if (new_nsproxy) switch_task_namespaces(current, new_nsproxy); task_lock(current); if (new_fs) { fs = current->fs; read_seqlock_excl(&fs->seq); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; read_sequnlock_excl(&fs->seq); } if (new_fd) swap(current->files, new_fd); task_unlock(current); if (new_cred) { /* Install the new user namespace */ commit_creds(new_cred); new_cred = NULL; } } perf_event_namespaces(current); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); bad_unshare_cleanup_fs: if (new_fs) free_fs_struct(new_fs); bad_unshare_out: return err; } SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { return ksys_unshare(unshare_flags); } /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to * the exec layer of the kernel. */ int unshare_files(void) { struct task_struct *task = current; struct files_struct *old, *copy = NULL; int error; error = unshare_fd(CLONE_FILES, ©); if (error || !copy) return error; old = task->files; task_lock(task); task->files = copy; task_unlock(task); put_files_struct(old); return 0; } static int sysctl_max_threads(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int ret; int threads = max_threads; int min = 1; int max = MAX_THREADS; t = *table; t.data = &threads; t.extra1 = &min; t.extra2 = &max; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || !write) return ret; max_threads = threads; return 0; } static const struct ctl_table fork_sysctl_table[] = { { .procname = "threads-max", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = sysctl_max_threads, }, }; static int __init init_fork_sysctl(void) { register_sysctl_init("kernel", fork_sysctl_table); return 0; } subsys_initcall(init_fork_sysctl); |
| 1 14 13 13 14 14 14 13 14 14 14 10 1 1 1 1 14 | 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 | // 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) { struct flow_dissector_key_ports_range *key_ports_range = NULL; struct flow_dissector_key_ports *key_ports = NULL; __be32 ports; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) key_ports_range = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE, target_container); if (!key_ports && !key_ports_range) return; ports = skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen); if (key_ports) key_ports->ports = ports; if (key_ports_range) key_ports_range->tp.ports = ports; } 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_range *key_ports_range = NULL; 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); key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) { key_ports_range = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE, target_container); key_ports_range->tp.src = flow_keys->sport; key_ports_range->tp.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); rcu_read_lock(); if (skb) { if (!net) { if (skb->dev) net = dev_net_rcu(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; 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) { __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); return result == BPF_OK; } } } 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); |
| 300 | 1 2 3 4 5 6 7 8 9 10 11 12 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012-2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <asm/kvm_hyp.h> void __kvm_timer_set_cntvoff(u64 cntvoff) { write_sysreg(cntvoff, cntvoff_el2); } |
| 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * NETLINK Netlink attributes * * Authors: Thomas Graf <tgraf@suug.ch> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/jiffies.h> #include <linux/nospec.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/types.h> #include <net/netlink.h> /* For these data types, attribute length should be exactly the given * size. However, to maintain compatibility with broken commands, if the * attribute length does not match the expected size a warning is emitted * to the user that the command is sending invalid data and needs to be fixed. */ static const u8 nla_attr_len[NLA_TYPE_MAX+1] = { [NLA_U8] = sizeof(u8), [NLA_U16] = sizeof(u16), [NLA_U32] = sizeof(u32), [NLA_U64] = sizeof(u64), [NLA_S8] = sizeof(s8), [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), [NLA_BE16] = sizeof(__be16), [NLA_BE32] = sizeof(__be32), }; static const u8 nla_attr_minlen[NLA_TYPE_MAX+1] = { [NLA_U8] = sizeof(u8), [NLA_U16] = sizeof(u16), [NLA_U32] = sizeof(u32), [NLA_U64] = sizeof(u64), [NLA_MSECS] = sizeof(u64), [NLA_NESTED] = NLA_HDRLEN, [NLA_S8] = sizeof(s8), [NLA_S16] = sizeof(s16), [NLA_S32] = sizeof(s32), [NLA_S64] = sizeof(s64), [NLA_BE16] = sizeof(__be16), [NLA_BE32] = sizeof(__be32), }; /* * Nested policies might refer back to the original * policy in some cases, and userspace could try to * abuse that and recurse by nesting in the right * ways. Limit recursion to avoid this problem. */ #define MAX_POLICY_RECURSION_DEPTH 10 static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, struct nlattr **tb, unsigned int depth); static int validate_nla_bitfield32(const struct nlattr *nla, const u32 valid_flags_mask) { const struct nla_bitfield32 *bf = nla_data(nla); if (!valid_flags_mask) return -EINVAL; /*disallow invalid bit selector */ if (bf->selector & ~valid_flags_mask) return -EINVAL; /*disallow invalid bit values */ if (bf->value & ~valid_flags_mask) return -EINVAL; /*disallow valid bit values that are not selected*/ if (bf->value & ~bf->selector) return -EINVAL; return 0; } static int nla_validate_array(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack, unsigned int validate, unsigned int depth) { const struct nlattr *entry; int rem; nla_for_each_attr(entry, head, len, rem) { int ret; if (nla_len(entry) == 0) continue; if (nla_len(entry) < NLA_HDRLEN) { NL_SET_ERR_MSG_ATTR_POL(extack, entry, policy, "Array element too short"); return -ERANGE; } ret = __nla_validate_parse(nla_data(entry), nla_len(entry), maxtype, policy, validate, extack, NULL, depth + 1); if (ret < 0) return ret; } return 0; } void nla_get_range_unsigned(const struct nla_policy *pt, struct netlink_range_validation *range) { WARN_ON_ONCE(pt->validation_type != NLA_VALIDATE_RANGE_PTR && (pt->min < 0 || pt->max < 0)); range->min = 0; switch (pt->type) { case NLA_U8: range->max = U8_MAX; break; case NLA_U16: case NLA_BE16: case NLA_BINARY: range->max = U16_MAX; break; case NLA_U32: case NLA_BE32: range->max = U32_MAX; break; case NLA_U64: case NLA_UINT: case NLA_MSECS: range->max = U64_MAX; break; default: WARN_ON_ONCE(1); return; } switch (pt->validation_type) { case NLA_VALIDATE_RANGE: case NLA_VALIDATE_RANGE_WARN_TOO_LONG: range->min = pt->min; range->max = pt->max; break; case NLA_VALIDATE_RANGE_PTR: *range = *pt->range; break; case NLA_VALIDATE_MIN: range->min = pt->min; break; case NLA_VALIDATE_MAX: range->max = pt->max; break; default: break; } } static int nla_validate_range_unsigned(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack, unsigned int validate) { struct netlink_range_validation range; u64 value; switch (pt->type) { case NLA_U8: value = nla_get_u8(nla); break; case NLA_U16: value = nla_get_u16(nla); break; case NLA_U32: value = nla_get_u32(nla); break; case NLA_U64: value = nla_get_u64(nla); break; case NLA_UINT: value = nla_get_uint(nla); break; case NLA_MSECS: value = nla_get_u64(nla); break; case NLA_BINARY: value = nla_len(nla); break; case NLA_BE16: value = ntohs(nla_get_be16(nla)); break; case NLA_BE32: value = ntohl(nla_get_be32(nla)); break; default: return -EINVAL; } nla_get_range_unsigned(pt, &range); if (pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG && pt->type == NLA_BINARY && value > range.max) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, pt->type); if (validate & NL_VALIDATE_STRICT_ATTRS) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } /* this assumes min <= max (don't validate against min) */ return 0; } if (value < range.min || value > range.max) { bool binary = pt->type == NLA_BINARY; if (binary) NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "binary attribute size out of range"); else NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "integer out of range"); return -ERANGE; } return 0; } void nla_get_range_signed(const struct nla_policy *pt, struct netlink_range_validation_signed *range) { switch (pt->type) { case NLA_S8: range->min = S8_MIN; range->max = S8_MAX; break; case NLA_S16: range->min = S16_MIN; range->max = S16_MAX; break; case NLA_S32: range->min = S32_MIN; range->max = S32_MAX; break; case NLA_S64: case NLA_SINT: range->min = S64_MIN; range->max = S64_MAX; break; default: WARN_ON_ONCE(1); return; } switch (pt->validation_type) { case NLA_VALIDATE_RANGE: range->min = pt->min; range->max = pt->max; break; case NLA_VALIDATE_RANGE_PTR: *range = *pt->range_signed; break; case NLA_VALIDATE_MIN: range->min = pt->min; break; case NLA_VALIDATE_MAX: range->max = pt->max; break; default: break; } } static int nla_validate_int_range_signed(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack) { struct netlink_range_validation_signed range; s64 value; switch (pt->type) { case NLA_S8: value = nla_get_s8(nla); break; case NLA_S16: value = nla_get_s16(nla); break; case NLA_S32: value = nla_get_s32(nla); break; case NLA_S64: value = nla_get_s64(nla); break; case NLA_SINT: value = nla_get_sint(nla); break; default: return -EINVAL; } nla_get_range_signed(pt, &range); if (value < range.min || value > range.max) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "integer out of range"); return -ERANGE; } return 0; } static int nla_validate_int_range(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack, unsigned int validate) { switch (pt->type) { case NLA_U8: case NLA_U16: case NLA_U32: case NLA_U64: case NLA_UINT: case NLA_MSECS: case NLA_BINARY: case NLA_BE16: case NLA_BE32: return nla_validate_range_unsigned(pt, nla, extack, validate); case NLA_S8: case NLA_S16: case NLA_S32: case NLA_S64: case NLA_SINT: return nla_validate_int_range_signed(pt, nla, extack); default: WARN_ON(1); return -EINVAL; } } static int nla_validate_mask(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack) { u64 value; switch (pt->type) { case NLA_U8: value = nla_get_u8(nla); break; case NLA_U16: value = nla_get_u16(nla); break; case NLA_U32: value = nla_get_u32(nla); break; case NLA_U64: value = nla_get_u64(nla); break; case NLA_UINT: value = nla_get_uint(nla); break; case NLA_BE16: value = ntohs(nla_get_be16(nla)); break; case NLA_BE32: value = ntohl(nla_get_be32(nla)); break; default: return -EINVAL; } if (value & ~(u64)pt->mask) { NL_SET_ERR_MSG_ATTR(extack, nla, "reserved bit set"); return -EINVAL; } return 0; } static int validate_nla(const struct nlattr *nla, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, unsigned int depth) { u16 strict_start_type = policy[0].strict_start_type; const struct nla_policy *pt; int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla); int err = -ERANGE; if (strict_start_type && type >= strict_start_type) validate |= NL_VALIDATE_STRICT; if (type <= 0 || type > maxtype) return 0; type = array_index_nospec(type, maxtype + 1); pt = &policy[type]; BUG_ON(pt->type > NLA_TYPE_MAX); if (nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, type); if (validate & NL_VALIDATE_STRICT_ATTRS) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } } if (validate & NL_VALIDATE_NESTED) { if ((pt->type == NLA_NESTED || pt->type == NLA_NESTED_ARRAY) && !(nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "NLA_F_NESTED is missing"); return -EINVAL; } if (pt->type != NLA_NESTED && pt->type != NLA_NESTED_ARRAY && pt->type != NLA_UNSPEC && (nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "NLA_F_NESTED not expected"); return -EINVAL; } } switch (pt->type) { case NLA_REJECT: if (extack && pt->reject_message) { NL_SET_BAD_ATTR(extack, nla); extack->_msg = pt->reject_message; return -EINVAL; } err = -EINVAL; goto out_err; case NLA_FLAG: if (attrlen > 0) goto out_err; break; case NLA_SINT: case NLA_UINT: if (attrlen != sizeof(u32) && attrlen != sizeof(u64)) { NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "invalid attribute length"); return -EINVAL; } break; case NLA_BITFIELD32: if (attrlen != sizeof(struct nla_bitfield32)) goto out_err; err = validate_nla_bitfield32(nla, pt->bitfield32_valid); if (err) goto out_err; break; case NLA_NUL_STRING: if (pt->len) minlen = min_t(int, attrlen, pt->len + 1); else minlen = attrlen; if (!minlen || memchr(nla_data(nla), '\0', minlen) == NULL) { err = -EINVAL; goto out_err; } fallthrough; case NLA_STRING: if (attrlen < 1) goto out_err; if (pt->len) { char *buf = nla_data(nla); if (buf[attrlen - 1] == '\0') attrlen--; if (attrlen > pt->len) goto out_err; } break; case NLA_BINARY: if (pt->len && attrlen > pt->len) goto out_err; break; case NLA_NESTED: /* a nested attributes is allowed to be empty; if its not, * it must have a size of at least NLA_HDRLEN. */ if (attrlen == 0) break; if (attrlen < NLA_HDRLEN) goto out_err; if (pt->nested_policy) { err = __nla_validate_parse(nla_data(nla), nla_len(nla), pt->len, pt->nested_policy, validate, extack, NULL, depth + 1); if (err < 0) { /* * return directly to preserve the inner * error message/attribute pointer */ return err; } } break; case NLA_NESTED_ARRAY: /* a nested array attribute is allowed to be empty; if its not, * it must have a size of at least NLA_HDRLEN. */ if (attrlen == 0) break; if (attrlen < NLA_HDRLEN) goto out_err; if (pt->nested_policy) { int err; err = nla_validate_array(nla_data(nla), nla_len(nla), pt->len, pt->nested_policy, extack, validate, depth); if (err < 0) { /* * return directly to preserve the inner * error message/attribute pointer */ return err; } } break; case NLA_UNSPEC: if (validate & NL_VALIDATE_UNSPEC) { NL_SET_ERR_MSG_ATTR(extack, nla, "Unsupported attribute"); return -EINVAL; } if (attrlen < pt->len) goto out_err; break; default: if (pt->len) minlen = pt->len; else minlen = nla_attr_minlen[pt->type]; if (attrlen < minlen) goto out_err; } /* further validation */ switch (pt->validation_type) { case NLA_VALIDATE_NONE: /* nothing to do */ break; case NLA_VALIDATE_RANGE_PTR: case NLA_VALIDATE_RANGE: case NLA_VALIDATE_RANGE_WARN_TOO_LONG: case NLA_VALIDATE_MIN: case NLA_VALIDATE_MAX: err = nla_validate_int_range(pt, nla, extack, validate); if (err) return err; break; case NLA_VALIDATE_MASK: err = nla_validate_mask(pt, nla, extack); if (err) return err; break; case NLA_VALIDATE_FUNCTION: if (pt->validate) { err = pt->validate(nla, extack); if (err) return err; } break; } return 0; out_err: NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, "Attribute failed policy validation"); return err; } static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack, struct nlattr **tb, unsigned int depth) { const struct nlattr *nla; int rem; if (depth >= MAX_POLICY_RECURSION_DEPTH) { NL_SET_ERR_MSG(extack, "allowed policy recursion depth exceeded"); return -EINVAL; } if (tb) memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); nla_for_each_attr(nla, head, len, rem) { u16 type = nla_type(nla); if (type == 0 || type > maxtype) { if (validate & NL_VALIDATE_MAXTYPE) { NL_SET_ERR_MSG_ATTR(extack, nla, "Unknown attribute type"); return -EINVAL; } continue; } type = array_index_nospec(type, maxtype + 1); if (policy) { int err = validate_nla(nla, maxtype, policy, validate, extack, depth); if (err < 0) return err; } if (tb) tb[type] = (struct nlattr *)nla; } if (unlikely(rem > 0)) { pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n", rem, current->comm); NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes"); if (validate & NL_VALIDATE_TRAILING) return -EINVAL; } return 0; } /** * __nla_validate - Validate a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation depends on the validate flags passed, see * &enum netlink_validation for more details on that. * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ int __nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate_parse(head, len, maxtype, policy, validate, extack, NULL, 0); } EXPORT_SYMBOL(__nla_validate); /** * nla_policy_len - Determine the max. length of a policy * @p: policy to use * @n: number of policies * * Determines the max. length of the policy. It is currently used * to allocated Netlink buffers roughly the size of the actual * message. * * Returns 0 on success or a negative error code. */ int nla_policy_len(const struct nla_policy *p, int n) { int i, len = 0; for (i = 0; i < n; i++, p++) { if (p->len) len += nla_total_size(p->len); else if (nla_attr_len[p->type]) len += nla_total_size(nla_attr_len[p->type]); else if (nla_attr_minlen[p->type]) len += nla_total_size(nla_attr_minlen[p->type]); } return len; } EXPORT_SYMBOL(nla_policy_len); /** * __nla_parse - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @validate: validation strictness * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. * Validation is controlled by the @validate parameter. * * Returns 0 on success or a negative error code. */ int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate_parse(head, len, maxtype, policy, validate, extack, tb, 0); } EXPORT_SYMBOL(__nla_parse); /** * nla_find - Find a specific attribute in a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @attrtype: type of attribute to look for * * Returns the first attribute in the stream matching the specified type. */ struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype) { const struct nlattr *nla; int rem; nla_for_each_attr(nla, head, len, rem) if (nla_type(nla) == attrtype) return (struct nlattr *)nla; return NULL; } EXPORT_SYMBOL(nla_find); /** * nla_strscpy - Copy string attribute payload into a sized buffer * @dst: Where to copy the string to. * @nla: Attribute to copy the string from. * @dstsize: Size of destination buffer. * * Copies at most dstsize - 1 bytes into the destination buffer. * Unlike strscpy() the destination buffer is always padded out. * * Return: * * srclen - Returns @nla length (not including the trailing %NUL). * * -E2BIG - If @dstsize is 0 or greater than U16_MAX or @nla length greater * than @dstsize. */ ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize) { size_t srclen = nla_len(nla); char *src = nla_data(nla); ssize_t ret; size_t len; if (dstsize == 0 || WARN_ON_ONCE(dstsize > U16_MAX)) return -E2BIG; if (srclen > 0 && src[srclen - 1] == '\0') srclen--; if (srclen >= dstsize) { len = dstsize - 1; ret = -E2BIG; } else { len = srclen; ret = len; } memcpy(dst, src, len); /* Zero pad end of dst. */ memset(dst + len, 0, dstsize - len); return ret; } EXPORT_SYMBOL(nla_strscpy); /** * nla_strdup - Copy string attribute payload into a newly allocated buffer * @nla: attribute to copy the string from * @flags: the type of memory to allocate (see kmalloc). * * Returns a pointer to the allocated buffer or NULL on error. */ char *nla_strdup(const struct nlattr *nla, gfp_t flags) { size_t srclen = nla_len(nla); char *src = nla_data(nla), *dst; if (srclen > 0 && src[srclen - 1] == '\0') srclen--; dst = kmalloc(srclen + 1, flags); if (dst != NULL) { memcpy(dst, src, srclen); dst[srclen] = '\0'; } return dst; } EXPORT_SYMBOL(nla_strdup); /** * nla_memcpy - Copy a netlink attribute into another memory area * @dest: where to copy to memcpy * @src: netlink attribute to copy from * @count: size of the destination area * * Note: The number of bytes copied is limited by the length of * attribute's payload. memcpy * * Returns the number of bytes copied. */ int nla_memcpy(void *dest, const struct nlattr *src, int count) { int minlen = min_t(int, count, nla_len(src)); memcpy(dest, nla_data(src), minlen); if (count > minlen) memset(dest + minlen, 0, count - minlen); return minlen; } EXPORT_SYMBOL(nla_memcpy); /** * nla_memcmp - Compare an attribute with sized memory area * @nla: netlink attribute * @data: memory area * @size: size of memory area */ int nla_memcmp(const struct nlattr *nla, const void *data, size_t size) { int d = nla_len(nla) - size; if (d == 0) d = memcmp(nla_data(nla), data, size); return d; } EXPORT_SYMBOL(nla_memcmp); /** * nla_strcmp - Compare a string attribute against a string * @nla: netlink string attribute * @str: another string */ int nla_strcmp(const struct nlattr *nla, const char *str) { int len = strlen(str); char *buf = nla_data(nla); int attrlen = nla_len(nla); int d; while (attrlen > 0 && buf[attrlen - 1] == '\0') attrlen--; d = attrlen - len; if (d == 0) d = memcmp(nla_data(nla), str, len); return d; } EXPORT_SYMBOL(nla_strcmp); #ifdef CONFIG_NET /** * __nla_reserve - reserve room for attribute on the skb * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) { struct nlattr *nla; nla = skb_put(skb, nla_total_size(attrlen)); nla->nla_type = attrtype; nla->nla_len = nla_attr_size(attrlen); memset((unsigned char *) nla + nla->nla_len, 0, nla_padlen(attrlen)); return nla; } EXPORT_SYMBOL(__nla_reserve); /** * __nla_reserve_64bit - reserve room for attribute on the skb and align it * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * @padattr: attribute type for the padding * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. It also ensure that this * attribute will have a 64-bit aligned nla_data() area. * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr) { nla_align_64bit(skb, padattr); return __nla_reserve(skb, attrtype, attrlen); } EXPORT_SYMBOL(__nla_reserve_64bit); /** * __nla_reserve_nohdr - reserve room for attribute without header * @skb: socket buffer to reserve room on * @attrlen: length of attribute payload * * Reserves room for attribute payload without a header. * * The caller is responsible to ensure that the skb provides enough * tailroom for the payload. */ void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen) { return skb_put_zero(skb, NLA_ALIGN(attrlen)); } EXPORT_SYMBOL(__nla_reserve_nohdr); /** * nla_reserve - reserve room for attribute on the skb * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute header and payload. */ struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) return NULL; return __nla_reserve(skb, attrtype, attrlen); } EXPORT_SYMBOL(nla_reserve); /** * nla_reserve_64bit - reserve room for attribute on the skb and align it * @skb: socket buffer to reserve room on * @attrtype: attribute type * @attrlen: length of attribute payload * @padattr: attribute type for the padding * * Adds a netlink attribute header to a socket buffer and reserves * room for the payload but does not copy it. It also ensure that this * attribute will have a 64-bit aligned nla_data() area. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute header and payload. */ struct nlattr *nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr) { size_t len; if (nla_need_padding_for_64bit(skb)) len = nla_total_size_64bit(attrlen); else len = nla_total_size(attrlen); if (unlikely(skb_tailroom(skb) < len)) return NULL; return __nla_reserve_64bit(skb, attrtype, attrlen, padattr); } EXPORT_SYMBOL(nla_reserve_64bit); /** * nla_reserve_nohdr - reserve room for attribute without header * @skb: socket buffer to reserve room on * @attrlen: length of attribute payload * * Reserves room for attribute payload without a header. * * Returns NULL if the tailroom of the skb is insufficient to store * the attribute payload. */ void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return NULL; return __nla_reserve_nohdr(skb, attrlen); } EXPORT_SYMBOL(nla_reserve_nohdr); /** * __nla_put - Add a netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { struct nlattr *nla; nla = __nla_reserve(skb, attrtype, attrlen); memcpy(nla_data(nla), data, attrlen); } EXPORT_SYMBOL(__nla_put); /** * __nla_put_64bit - Add a netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * @padattr: attribute type for the padding * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute header and payload. */ void __nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr) { struct nlattr *nla; nla = __nla_reserve_64bit(skb, attrtype, attrlen, padattr); memcpy(nla_data(nla), data, attrlen); } EXPORT_SYMBOL(__nla_put_64bit); /** * __nla_put_nohdr - Add a netlink attribute without header * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * The caller is responsible to ensure that the skb provides enough * tailroom for the attribute payload. */ void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { void *start; start = __nla_reserve_nohdr(skb, attrlen); memcpy(start, data, attrlen); } EXPORT_SYMBOL(__nla_put_nohdr); /** * nla_put - Add a netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) return -EMSGSIZE; __nla_put(skb, attrtype, attrlen, data); return 0; } EXPORT_SYMBOL(nla_put); /** * nla_put_64bit - Add a netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @attrlen: length of attribute payload * @data: head of attribute payload * @padattr: attribute type for the padding * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr) { size_t len; if (nla_need_padding_for_64bit(skb)) len = nla_total_size_64bit(attrlen); else len = nla_total_size(attrlen); if (unlikely(skb_tailroom(skb) < len)) return -EMSGSIZE; __nla_put_64bit(skb, attrtype, attrlen, data, padattr); return 0; } EXPORT_SYMBOL(nla_put_64bit); /** * nla_put_nohdr - Add a netlink attribute without header * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return -EMSGSIZE; __nla_put_nohdr(skb, attrlen, data); return 0; } EXPORT_SYMBOL(nla_put_nohdr); /** * nla_append - Add a netlink attribute without header or padding * @skb: socket buffer to add attribute to * @attrlen: length of attribute payload * @data: head of attribute payload * * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_append(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) return -EMSGSIZE; skb_put_data(skb, data, attrlen); return 0; } EXPORT_SYMBOL(nla_append); #endif |
| 4 4 4 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kdebug.h> #include <linux/kprobes.h> #include <linux/export.h> #include <linux/notifier.h> #include <linux/rcupdate.h> #include <linux/vmalloc.h> #define CREATE_TRACE_POINTS #include <trace/events/notifier.h> /* * Notifier chain core routines. The exported routines below * are layered on top of these, with appropriate locking added. */ static int notifier_chain_register(struct notifier_block **nl, struct notifier_block *n, bool unique_priority) { while ((*nl) != NULL) { if (unlikely((*nl) == n)) { WARN(1, "notifier callback %ps already registered", n->notifier_call); return -EEXIST; } if (n->priority > (*nl)->priority) break; if (n->priority == (*nl)->priority && unique_priority) return -EBUSY; nl = &((*nl)->next); } n->next = *nl; rcu_assign_pointer(*nl, n); trace_notifier_register((void *)n->notifier_call); return 0; } static int notifier_chain_unregister(struct notifier_block **nl, struct notifier_block *n) { while ((*nl) != NULL) { if ((*nl) == n) { rcu_assign_pointer(*nl, n->next); trace_notifier_unregister((void *)n->notifier_call); return 0; } nl = &((*nl)->next); } return -ENOENT; } /** * notifier_call_chain - Informs the registered notifiers about an event. * @nl: Pointer to head of the blocking notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * @nr_to_call: Number of notifier functions to be called. Don't care * value of this parameter is -1. * @nr_calls: Records the number of notifications sent. Don't care * value of this field is NULL. * Return: notifier_call_chain returns the value returned by the * last notifier function called. */ static int notifier_call_chain(struct notifier_block **nl, unsigned long val, void *v, int nr_to_call, int *nr_calls) { int ret = NOTIFY_DONE; struct notifier_block *nb, *next_nb; nb = rcu_dereference_raw(*nl); while (nb && nr_to_call) { next_nb = rcu_dereference_raw(nb->next); #ifdef CONFIG_DEBUG_NOTIFIERS if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) { WARN(1, "Invalid notifier called!"); nb = next_nb; continue; } #endif trace_notifier_run((void *)nb->notifier_call); ret = nb->notifier_call(nb, val, v); if (nr_calls) (*nr_calls)++; if (ret & NOTIFY_STOP_MASK) break; nb = next_nb; nr_to_call--; } return ret; } NOKPROBE_SYMBOL(notifier_call_chain); /** * notifier_call_chain_robust - Inform the registered notifiers about an event * and rollback on error. * @nl: Pointer to head of the blocking notifier chain * @val_up: Value passed unmodified to the notifier function * @val_down: Value passed unmodified to the notifier function when recovering * from an error on @val_up * @v: Pointer passed unmodified to the notifier function * * NOTE: It is important the @nl chain doesn't change between the two * invocations of notifier_call_chain() such that we visit the * exact same notifier callbacks; this rules out any RCU usage. * * Return: the return value of the @val_up call. */ static int notifier_call_chain_robust(struct notifier_block **nl, unsigned long val_up, unsigned long val_down, void *v) { int ret, nr = 0; ret = notifier_call_chain(nl, val_up, v, -1, &nr); if (ret & NOTIFY_STOP_MASK) notifier_call_chain(nl, val_down, v, nr-1, NULL); return ret; } /* * Atomic notifier chain routines. Registration and unregistration * use a spinlock, and call_chain is synchronized by RCU (no locks). */ /** * atomic_notifier_chain_register - Add notifier to an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: New entry in notifier chain * * Adds a notifier to an atomic notifier chain. * * Returns 0 on success, %-EEXIST on error. */ int atomic_notifier_chain_register(struct atomic_notifier_head *nh, struct notifier_block *n) { unsigned long flags; int ret; spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_register(&nh->head, n, false); spin_unlock_irqrestore(&nh->lock, flags); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_register); /** * atomic_notifier_chain_register_unique_prio - Add notifier to an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: New entry in notifier chain * * Adds a notifier to an atomic notifier chain if there is no other * notifier registered using the same priority. * * Returns 0 on success, %-EEXIST or %-EBUSY on error. */ int atomic_notifier_chain_register_unique_prio(struct atomic_notifier_head *nh, struct notifier_block *n) { unsigned long flags; int ret; spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_register(&nh->head, n, true); spin_unlock_irqrestore(&nh->lock, flags); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_register_unique_prio); /** * atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from an atomic notifier chain. * * Returns zero on success or %-ENOENT on failure. */ int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *n) { unsigned long flags; int ret; spin_lock_irqsave(&nh->lock, flags); ret = notifier_chain_unregister(&nh->head, n); spin_unlock_irqrestore(&nh->lock, flags); synchronize_rcu(); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister); /** * atomic_notifier_call_chain - Call functions in an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in an atomic context, so they must not block. * This routine uses RCU to synchronize with changes to the chain. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then atomic_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int atomic_notifier_call_chain(struct atomic_notifier_head *nh, unsigned long val, void *v) { int ret; rcu_read_lock(); ret = notifier_call_chain(&nh->head, val, v, -1, NULL); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_call_chain); NOKPROBE_SYMBOL(atomic_notifier_call_chain); /** * atomic_notifier_call_chain_is_empty - Check whether notifier chain is empty * @nh: Pointer to head of the atomic notifier chain * * Checks whether notifier chain is empty. * * Returns true is notifier chain is empty, false otherwise. */ bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh) { return !rcu_access_pointer(nh->head); } /* * Blocking notifier chain routines. All access to the chain is * synchronized by an rwsem. */ static int __blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *n, bool unique_priority) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call down_write(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_register(&nh->head, n, unique_priority); down_write(&nh->rwsem); ret = notifier_chain_register(&nh->head, n, unique_priority); up_write(&nh->rwsem); return ret; } /** * blocking_notifier_chain_register - Add notifier to a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: New entry in notifier chain * * Adds a notifier to a blocking notifier chain. * Must be called in process context. * * Returns 0 on success, %-EEXIST on error. */ int blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *n) { return __blocking_notifier_chain_register(nh, n, false); } EXPORT_SYMBOL_GPL(blocking_notifier_chain_register); /** * blocking_notifier_chain_register_unique_prio - Add notifier to a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: New entry in notifier chain * * Adds a notifier to an blocking notifier chain if there is no other * notifier registered using the same priority. * * Returns 0 on success, %-EEXIST or %-EBUSY on error. */ int blocking_notifier_chain_register_unique_prio(struct blocking_notifier_head *nh, struct notifier_block *n) { return __blocking_notifier_chain_register(nh, n, true); } EXPORT_SYMBOL_GPL(blocking_notifier_chain_register_unique_prio); /** * blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from a blocking notifier chain. * Must be called from process context. * * Returns zero on success or %-ENOENT on failure. */ int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, struct notifier_block *n) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call down_write(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_unregister(&nh->head, n); down_write(&nh->rwsem); ret = notifier_chain_unregister(&nh->head, n); up_write(&nh->rwsem); return ret; } EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister); int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v) { int ret = NOTIFY_DONE; /* * We check the head outside the lock, but if this access is * racy then it does not matter what the result of the test * is, we re-check the list after having taken the lock anyway: */ if (rcu_access_pointer(nh->head)) { down_read(&nh->rwsem); ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v); up_read(&nh->rwsem); } return ret; } EXPORT_SYMBOL_GPL(blocking_notifier_call_chain_robust); /** * blocking_notifier_call_chain - Call functions in a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in a process context, so they are allowed to block. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then blocking_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int blocking_notifier_call_chain(struct blocking_notifier_head *nh, unsigned long val, void *v) { int ret = NOTIFY_DONE; /* * We check the head outside the lock, but if this access is * racy then it does not matter what the result of the test * is, we re-check the list after having taken the lock anyway: */ if (rcu_access_pointer(nh->head)) { down_read(&nh->rwsem); ret = notifier_call_chain(&nh->head, val, v, -1, NULL); up_read(&nh->rwsem); } return ret; } EXPORT_SYMBOL_GPL(blocking_notifier_call_chain); /* * Raw notifier chain routines. There is no protection; * the caller must provide it. Use at your own risk! */ /** * raw_notifier_chain_register - Add notifier to a raw notifier chain * @nh: Pointer to head of the raw notifier chain * @n: New entry in notifier chain * * Adds a notifier to a raw notifier chain. * All locking must be provided by the caller. * * Returns 0 on success, %-EEXIST on error. */ int raw_notifier_chain_register(struct raw_notifier_head *nh, struct notifier_block *n) { return notifier_chain_register(&nh->head, n, false); } EXPORT_SYMBOL_GPL(raw_notifier_chain_register); /** * raw_notifier_chain_unregister - Remove notifier from a raw notifier chain * @nh: Pointer to head of the raw notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from a raw notifier chain. * All locking must be provided by the caller. * * Returns zero on success or %-ENOENT on failure. */ int raw_notifier_chain_unregister(struct raw_notifier_head *nh, struct notifier_block *n) { return notifier_chain_unregister(&nh->head, n); } EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister); int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v) { return notifier_call_chain_robust(&nh->head, val_up, val_down, v); } EXPORT_SYMBOL_GPL(raw_notifier_call_chain_robust); /** * raw_notifier_call_chain - Call functions in a raw notifier chain * @nh: Pointer to head of the raw notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in an undefined context. * All locking must be provided by the caller. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then raw_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int raw_notifier_call_chain(struct raw_notifier_head *nh, unsigned long val, void *v) { return notifier_call_chain(&nh->head, val, v, -1, NULL); } EXPORT_SYMBOL_GPL(raw_notifier_call_chain); /* * SRCU notifier chain routines. Registration and unregistration * use a mutex, and call_chain is synchronized by SRCU (no locks). */ /** * srcu_notifier_chain_register - Add notifier to an SRCU notifier chain * @nh: Pointer to head of the SRCU notifier chain * @n: New entry in notifier chain * * Adds a notifier to an SRCU notifier chain. * Must be called in process context. * * Returns 0 on success, %-EEXIST on error. */ int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *n) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call mutex_lock(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_register(&nh->head, n, false); mutex_lock(&nh->mutex); ret = notifier_chain_register(&nh->head, n, false); mutex_unlock(&nh->mutex); return ret; } EXPORT_SYMBOL_GPL(srcu_notifier_chain_register); /** * srcu_notifier_chain_unregister - Remove notifier from an SRCU notifier chain * @nh: Pointer to head of the SRCU notifier chain * @n: Entry to remove from notifier chain * * Removes a notifier from an SRCU notifier chain. * Must be called from process context. * * Returns zero on success or %-ENOENT on failure. */ int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, struct notifier_block *n) { int ret; /* * This code gets used during boot-up, when task switching is * not yet working and interrupts must remain disabled. At * such times we must not call mutex_lock(). */ if (unlikely(system_state == SYSTEM_BOOTING)) return notifier_chain_unregister(&nh->head, n); mutex_lock(&nh->mutex); ret = notifier_chain_unregister(&nh->head, n); mutex_unlock(&nh->mutex); synchronize_srcu(&nh->srcu); return ret; } EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister); /** * srcu_notifier_call_chain - Call functions in an SRCU notifier chain * @nh: Pointer to head of the SRCU notifier chain * @val: Value passed unmodified to notifier function * @v: Pointer passed unmodified to notifier function * * Calls each function in a notifier chain in turn. The functions * run in a process context, so they are allowed to block. * * If the return value of the notifier can be and'ed * with %NOTIFY_STOP_MASK then srcu_notifier_call_chain() * will return immediately, with the return value of * the notifier function which halted execution. * Otherwise the return value is the return value * of the last notifier function called. */ int srcu_notifier_call_chain(struct srcu_notifier_head *nh, unsigned long val, void *v) { int ret; int idx; idx = srcu_read_lock(&nh->srcu); ret = notifier_call_chain(&nh->head, val, v, -1, NULL); srcu_read_unlock(&nh->srcu, idx); return ret; } EXPORT_SYMBOL_GPL(srcu_notifier_call_chain); /** * srcu_init_notifier_head - Initialize an SRCU notifier head * @nh: Pointer to head of the srcu notifier chain * * Unlike other sorts of notifier heads, SRCU notifier heads require * dynamic initialization. Be sure to call this routine before * calling any of the other SRCU notifier routines for this head. * * If an SRCU notifier head is deallocated, it must first be cleaned * up by calling srcu_cleanup_notifier_head(). Otherwise the head's * per-cpu data (used by the SRCU mechanism) will leak. */ void srcu_init_notifier_head(struct srcu_notifier_head *nh) { mutex_init(&nh->mutex); if (init_srcu_struct(&nh->srcu) < 0) BUG(); nh->head = NULL; } EXPORT_SYMBOL_GPL(srcu_init_notifier_head); static ATOMIC_NOTIFIER_HEAD(die_chain); int notrace notify_die(enum die_val val, const char *str, struct pt_regs *regs, long err, int trap, int sig) { struct die_args args = { .regs = regs, .str = str, .err = err, .trapnr = trap, .signr = sig, }; RCU_LOCKDEP_WARN(!rcu_is_watching(), "notify_die called but RCU thinks we're quiescent"); return atomic_notifier_call_chain(&die_chain, val, &args); } NOKPROBE_SYMBOL(notify_die); int register_die_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&die_chain, nb); } EXPORT_SYMBOL_GPL(register_die_notifier); int unregister_die_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&die_chain, nb); } EXPORT_SYMBOL_GPL(unregister_die_notifier); |
| 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2007 Patrick McHardy <kaber@trash.net> * * The code this is based on carried the following copyright notice: * --- * (C) Copyright 2001-2006 * Alex Zeffertt, Cambridge Broadband Ltd, ajz@cambridgebroadband.com * Re-worked by Ben Greear <greearb@candelatech.com> * --- */ #include <linux/kernel.h> #include <linux/types.h> #include <linux/module.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/rculist.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/net_tstamp.h> #include <linux/ethtool.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/if_link.h> #include <linux/if_macvlan.h> #include <linux/hash.h> #include <linux/workqueue.h> #include <net/netdev_lock.h> #include <net/rtnetlink.h> #include <net/xfrm.h> #include <linux/netpoll.h> #include <linux/phy.h> #define MACVLAN_HASH_BITS 8 #define MACVLAN_HASH_SIZE (1<<MACVLAN_HASH_BITS) #define MACVLAN_DEFAULT_BC_QUEUE_LEN 1000 #define MACVLAN_F_PASSTHRU 1 #define MACVLAN_F_ADDRCHANGE 2 struct macvlan_port { struct net_device *dev; struct hlist_head vlan_hash[MACVLAN_HASH_SIZE]; struct list_head vlans; struct sk_buff_head bc_queue; struct work_struct bc_work; u32 bc_queue_len_used; int bc_cutoff; u32 flags; int count; struct hlist_head vlan_source_hash[MACVLAN_HASH_SIZE]; DECLARE_BITMAP(bc_filter, MACVLAN_MC_FILTER_SZ); DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ); unsigned char perm_addr[ETH_ALEN]; }; struct macvlan_source_entry { struct hlist_node hlist; struct macvlan_dev *vlan; unsigned char addr[6+2] __aligned(sizeof(u16)); struct rcu_head rcu; }; struct macvlan_skb_cb { const struct macvlan_dev *src; }; #define MACVLAN_SKB_CB(__skb) ((struct macvlan_skb_cb *)&((__skb)->cb[0])) static void macvlan_port_destroy(struct net_device *dev); static void update_port_bc_queue_len(struct macvlan_port *port); static inline bool macvlan_passthru(const struct macvlan_port *port) { return port->flags & MACVLAN_F_PASSTHRU; } static inline void macvlan_set_passthru(struct macvlan_port *port) { port->flags |= MACVLAN_F_PASSTHRU; } static inline bool macvlan_addr_change(const struct macvlan_port *port) { return port->flags & MACVLAN_F_ADDRCHANGE; } static inline void macvlan_set_addr_change(struct macvlan_port *port) { port->flags |= MACVLAN_F_ADDRCHANGE; } static inline void macvlan_clear_addr_change(struct macvlan_port *port) { port->flags &= ~MACVLAN_F_ADDRCHANGE; } /* Hash Ethernet address */ static u32 macvlan_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, MACVLAN_HASH_BITS); } static struct macvlan_port *macvlan_port_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->rx_handler_data); } static struct macvlan_port *macvlan_port_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->rx_handler_data); } static struct macvlan_dev *macvlan_hash_lookup(const struct macvlan_port *port, const unsigned char *addr) { struct macvlan_dev *vlan; u32 idx = macvlan_eth_hash(addr); hlist_for_each_entry_rcu(vlan, &port->vlan_hash[idx], hlist, lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(vlan->dev->dev_addr, addr)) return vlan; } return NULL; } static struct macvlan_source_entry *macvlan_hash_lookup_source( const struct macvlan_dev *vlan, const unsigned char *addr) { struct macvlan_source_entry *entry; u32 idx = macvlan_eth_hash(addr); struct hlist_head *h = &vlan->port->vlan_source_hash[idx]; hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (ether_addr_equal_64bits(entry->addr, addr) && entry->vlan == vlan) return entry; } return NULL; } static int macvlan_hash_add_source(struct macvlan_dev *vlan, const unsigned char *addr) { struct macvlan_port *port = vlan->port; struct macvlan_source_entry *entry; struct hlist_head *h; entry = macvlan_hash_lookup_source(vlan, addr); if (entry) return 0; entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) return -ENOMEM; ether_addr_copy(entry->addr, addr); entry->vlan = vlan; h = &port->vlan_source_hash[macvlan_eth_hash(addr)]; hlist_add_head_rcu(&entry->hlist, h); vlan->macaddr_count++; return 0; } static void macvlan_hash_add(struct macvlan_dev *vlan) { struct macvlan_port *port = vlan->port; const unsigned char *addr = vlan->dev->dev_addr; u32 idx = macvlan_eth_hash(addr); hlist_add_head_rcu(&vlan->hlist, &port->vlan_hash[idx]); } static void macvlan_hash_del_source(struct macvlan_source_entry *entry) { hlist_del_rcu(&entry->hlist); kfree_rcu(entry, rcu); } static void macvlan_hash_del(struct macvlan_dev *vlan, bool sync) { hlist_del_rcu(&vlan->hlist); if (sync) synchronize_rcu(); } static void macvlan_hash_change_addr(struct macvlan_dev *vlan, const unsigned char *addr) { macvlan_hash_del(vlan, true); /* Now that we are unhashed it is safe to change the device * address without confusing packet delivery. */ eth_hw_addr_set(vlan->dev, addr); macvlan_hash_add(vlan); } static bool macvlan_addr_busy(const struct macvlan_port *port, const unsigned char *addr) { /* Test to see if the specified address is * currently in use by the underlying device or * another macvlan. */ if (!macvlan_passthru(port) && !macvlan_addr_change(port) && ether_addr_equal_64bits(port->dev->dev_addr, addr)) return true; if (macvlan_hash_lookup(port, addr)) return true; return false; } static int macvlan_broadcast_one(struct sk_buff *skb, const struct macvlan_dev *vlan, const struct ethhdr *eth, bool local) { struct net_device *dev = vlan->dev; if (local) return __dev_forward_skb(dev, skb); skb->dev = dev; if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_MULTICAST; return 0; } static u32 macvlan_hash_mix(const struct macvlan_dev *vlan) { return (u32)(((unsigned long)vlan) >> L1_CACHE_SHIFT); } static unsigned int mc_hash(const struct macvlan_dev *vlan, const unsigned char *addr) { u32 val = get_unaligned((u32 *)(addr + 2)); val ^= macvlan_hash_mix(vlan); return hash_32(val, MACVLAN_MC_FILTER_BITS); } static void macvlan_broadcast(struct sk_buff *skb, const struct macvlan_port *port, struct net_device *src, enum macvlan_mode mode) { const struct ethhdr *eth = eth_hdr(skb); const struct macvlan_dev *vlan; struct sk_buff *nskb; unsigned int i; int err; unsigned int hash; if (skb->protocol == htons(ETH_P_PAUSE)) return; hash_for_each_rcu(port->vlan_hash, i, vlan, hlist) { if (vlan->dev == src || !(vlan->mode & mode)) continue; hash = mc_hash(vlan, eth->h_dest); if (!test_bit(hash, vlan->mc_filter)) continue; err = NET_RX_DROP; nskb = skb_clone(skb, GFP_ATOMIC); if (likely(nskb)) err = macvlan_broadcast_one(nskb, vlan, eth, mode == MACVLAN_MODE_BRIDGE) ?: netif_rx(nskb); macvlan_count_rx(vlan, skb->len + ETH_HLEN, err == NET_RX_SUCCESS, true); } } static void macvlan_multicast_rx(const struct macvlan_port *port, const struct macvlan_dev *src, struct sk_buff *skb) { if (!src) /* frame comes from an external address */ macvlan_broadcast(skb, port, NULL, MACVLAN_MODE_PRIVATE | MACVLAN_MODE_VEPA | MACVLAN_MODE_PASSTHRU| MACVLAN_MODE_BRIDGE); else if (src->mode == MACVLAN_MODE_VEPA) /* flood to everyone except source */ macvlan_broadcast(skb, port, src->dev, MACVLAN_MODE_VEPA | MACVLAN_MODE_BRIDGE); else /* * flood only to VEPA ports, bridge ports * already saw the frame on the way out. */ macvlan_broadcast(skb, port, src->dev, MACVLAN_MODE_VEPA); } static void macvlan_process_broadcast(struct work_struct *w) { struct macvlan_port *port = container_of(w, struct macvlan_port, bc_work); struct sk_buff *skb; struct sk_buff_head list; __skb_queue_head_init(&list); spin_lock_bh(&port->bc_queue.lock); skb_queue_splice_tail_init(&port->bc_queue, &list); spin_unlock_bh(&port->bc_queue.lock); while ((skb = __skb_dequeue(&list))) { const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src; rcu_read_lock(); macvlan_multicast_rx(port, src, skb); rcu_read_unlock(); if (src) dev_put(src->dev); consume_skb(skb); cond_resched(); } } static void macvlan_broadcast_enqueue(struct macvlan_port *port, const struct macvlan_dev *src, struct sk_buff *skb) { struct sk_buff *nskb; int err = -ENOMEM; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) goto err; MACVLAN_SKB_CB(nskb)->src = src; spin_lock(&port->bc_queue.lock); if (skb_queue_len(&port->bc_queue) < port->bc_queue_len_used) { if (src) dev_hold(src->dev); __skb_queue_tail(&port->bc_queue, nskb); err = 0; } spin_unlock(&port->bc_queue.lock); queue_work(system_dfl_wq, &port->bc_work); if (err) goto free_nskb; return; free_nskb: kfree_skb(nskb); err: dev_core_stats_rx_dropped_inc(skb->dev); } static void macvlan_flush_sources(struct macvlan_port *port, struct macvlan_dev *vlan) { struct macvlan_source_entry *entry; struct hlist_node *next; int i; hash_for_each_safe(port->vlan_source_hash, i, next, entry, hlist) if (entry->vlan == vlan) macvlan_hash_del_source(entry); vlan->macaddr_count = 0; } static void macvlan_forward_source_one(struct sk_buff *skb, struct macvlan_dev *vlan) { struct sk_buff *nskb; struct net_device *dev; int len; int ret; dev = vlan->dev; if (unlikely(!(dev->flags & IFF_UP))) return; nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return; len = nskb->len + ETH_HLEN; nskb->dev = dev; if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, dev->dev_addr)) nskb->pkt_type = PACKET_HOST; ret = __netif_rx(nskb); macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); } static bool macvlan_forward_source(struct sk_buff *skb, struct macvlan_port *port, const unsigned char *addr) { struct macvlan_source_entry *entry; u32 idx = macvlan_eth_hash(addr); struct hlist_head *h = &port->vlan_source_hash[idx]; bool consume = false; hlist_for_each_entry_rcu(entry, h, hlist) { if (ether_addr_equal_64bits(entry->addr, addr)) { if (entry->vlan->flags & MACVLAN_FLAG_NODST) consume = true; macvlan_forward_source_one(skb, entry->vlan); } } return consume; } /* called under rcu_read_lock() from netif_receive_skb */ static rx_handler_result_t macvlan_handle_frame(struct sk_buff **pskb) { struct macvlan_port *port; struct sk_buff *skb = *pskb; const struct ethhdr *eth = eth_hdr(skb); const struct macvlan_dev *vlan; const struct macvlan_dev *src; struct net_device *dev; unsigned int len = 0; int ret; rx_handler_result_t handle_res; /* Packets from dev_loopback_xmit() do not have L2 header, bail out */ if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; port = macvlan_port_get_rcu(skb->dev); if (is_multicast_ether_addr(eth->h_dest)) { unsigned int hash; skb = ip_check_defrag(dev_net(skb->dev), skb, IP_DEFRAG_MACVLAN); if (!skb) return RX_HANDLER_CONSUMED; *pskb = skb; eth = eth_hdr(skb); if (macvlan_forward_source(skb, port, eth->h_source)) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } src = macvlan_hash_lookup(port, eth->h_source); if (src && src->mode != MACVLAN_MODE_VEPA && src->mode != MACVLAN_MODE_BRIDGE) { /* forward to original port. */ vlan = src; ret = macvlan_broadcast_one(skb, vlan, eth, 0) ?: __netif_rx(skb); handle_res = RX_HANDLER_CONSUMED; goto out; } hash = mc_hash(NULL, eth->h_dest); if (test_bit(hash, port->bc_filter)) macvlan_broadcast_enqueue(port, src, skb); else if (test_bit(hash, port->mc_filter)) macvlan_multicast_rx(port, src, skb); return RX_HANDLER_PASS; } if (macvlan_forward_source(skb, port, eth->h_source)) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } if (macvlan_passthru(port)) vlan = list_first_or_null_rcu(&port->vlans, struct macvlan_dev, list); else vlan = macvlan_hash_lookup(port, eth->h_dest); if (!vlan || vlan->mode == MACVLAN_MODE_SOURCE) return RX_HANDLER_PASS; dev = vlan->dev; if (unlikely(!(dev->flags & IFF_UP))) { kfree_skb(skb); return RX_HANDLER_CONSUMED; } len = skb->len + ETH_HLEN; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) { ret = NET_RX_DROP; handle_res = RX_HANDLER_CONSUMED; goto out; } *pskb = skb; skb->dev = dev; skb->pkt_type = PACKET_HOST; ret = NET_RX_SUCCESS; handle_res = RX_HANDLER_ANOTHER; out: macvlan_count_rx(vlan, len, ret == NET_RX_SUCCESS, false); return handle_res; } static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) { const struct macvlan_dev *vlan = netdev_priv(dev); const struct macvlan_port *port = vlan->port; const struct macvlan_dev *dest; if (vlan->mode == MACVLAN_MODE_BRIDGE) { const struct ethhdr *eth = skb_eth_hdr(skb); /* send to other bridge ports directly */ if (is_multicast_ether_addr(eth->h_dest)) { skb_reset_mac_header(skb); macvlan_broadcast(skb, port, dev, MACVLAN_MODE_BRIDGE); goto xmit_world; } dest = macvlan_hash_lookup(port, eth->h_dest); if (dest && dest->mode == MACVLAN_MODE_BRIDGE) { /* send to lowerdev first for its network taps */ dev_forward_skb(vlan->lowerdev, skb); return NET_XMIT_SUCCESS; } } xmit_world: skb->dev = vlan->lowerdev; return dev_queue_xmit_accel(skb, netdev_get_sb_channel(dev) ? dev : NULL); } static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER return netpoll_send_skb(vlan->netpoll, skb); #else BUG(); return NETDEV_TX_OK; #endif } static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); unsigned int len = skb->len; int ret; if (unlikely(netpoll_tx_running(dev))) return macvlan_netpoll_send_skb(vlan, skb); ret = macvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct vlan_pcpu_stats *pcpu_stats; pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); u64_stats_inc(&pcpu_stats->tx_packets); u64_stats_add(&pcpu_stats->tx_bytes, len); u64_stats_update_end(&pcpu_stats->syncp); } else { this_cpu_inc(vlan->pcpu_stats->tx_dropped); } return ret; } static int macvlan_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len) { const struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; return dev_hard_header(skb, lowerdev, type, daddr, saddr ? : dev->dev_addr, len); } static const struct header_ops macvlan_hard_header_ops = { .create = macvlan_hard_header, .parse = eth_header_parse, .cache = eth_header_cache, .cache_update = eth_header_cache_update, .parse_protocol = eth_header_parse_protocol, }; static int macvlan_open(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; int err; if (macvlan_passthru(vlan->port)) { if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) { err = dev_set_promiscuity(lowerdev, 1); if (err < 0) goto out; } goto hash_add; } err = -EADDRINUSE; if (macvlan_addr_busy(vlan->port, dev->dev_addr)) goto out; /* Attempt to populate accel_priv which is used to offload the L2 * forwarding requests for unicast packets. */ if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) vlan->accel_priv = lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev); /* If earlier attempt to offload failed, or accel_priv is not * populated we must add the unicast address to the lower device. */ if (IS_ERR_OR_NULL(vlan->accel_priv)) { vlan->accel_priv = NULL; err = dev_uc_add(lowerdev, dev->dev_addr); if (err < 0) goto out; } if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(lowerdev, 1); if (err < 0) goto del_unicast; } if (dev->flags & IFF_PROMISC) { err = dev_set_promiscuity(lowerdev, 1); if (err < 0) goto clear_multi; } hash_add: macvlan_hash_add(vlan); return 0; clear_multi: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); del_unicast: if (vlan->accel_priv) { lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, vlan->accel_priv); vlan->accel_priv = NULL; } else { dev_uc_del(lowerdev, dev->dev_addr); } out: return err; } static int macvlan_stop(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; if (vlan->accel_priv) { lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, vlan->accel_priv); vlan->accel_priv = NULL; } dev_uc_unsync(lowerdev, dev); dev_mc_unsync(lowerdev, dev); if (macvlan_passthru(vlan->port)) { if (!(vlan->flags & MACVLAN_FLAG_NOPROMISC)) dev_set_promiscuity(lowerdev, -1); goto hash_del; } if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); if (dev->flags & IFF_PROMISC) dev_set_promiscuity(lowerdev, -1); dev_uc_del(lowerdev, dev->dev_addr); hash_del: macvlan_hash_del(vlan, !dev->dismantle); return 0; } static int macvlan_sync_address(struct net_device *dev, const unsigned char *addr) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; struct macvlan_port *port = vlan->port; int err; if (!(dev->flags & IFF_UP)) { /* Just copy in the new address */ eth_hw_addr_set(dev, addr); } else { /* Rehash and update the device filters */ if (macvlan_addr_busy(vlan->port, addr)) return -EADDRINUSE; if (!macvlan_passthru(port)) { err = dev_uc_add(lowerdev, addr); if (err) return err; dev_uc_del(lowerdev, dev->dev_addr); } macvlan_hash_change_addr(vlan, addr); } if (macvlan_passthru(port) && !macvlan_addr_change(port)) { /* Since addr_change isn't set, we are here due to lower * device change. Save the lower-dev address so we can * restore it later. */ ether_addr_copy(vlan->port->perm_addr, lowerdev->dev_addr); } macvlan_clear_addr_change(port); return 0; } static int macvlan_set_mac_address(struct net_device *dev, void *p) { struct macvlan_dev *vlan = netdev_priv(dev); struct sockaddr_storage *addr = p; if (!is_valid_ether_addr(addr->__data)) return -EADDRNOTAVAIL; /* If the addresses are the same, this is a no-op */ if (ether_addr_equal(dev->dev_addr, addr->__data)) return 0; if (vlan->mode == MACVLAN_MODE_PASSTHRU) { macvlan_set_addr_change(vlan->port); return dev_set_mac_address(vlan->lowerdev, addr, NULL); } if (macvlan_addr_busy(vlan->port, addr->__data)) return -EADDRINUSE; return macvlan_sync_address(dev, addr->__data); } static void macvlan_change_rx_flags(struct net_device *dev, int change) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; if (dev->flags & IFF_UP) { if (change & IFF_ALLMULTI) dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1); if (!macvlan_passthru(vlan->port) && change & IFF_PROMISC) dev_set_promiscuity(lowerdev, dev->flags & IFF_PROMISC ? 1 : -1); } } static void macvlan_compute_filter(unsigned long *mc_filter, struct net_device *dev, struct macvlan_dev *vlan, int cutoff) { if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) { bitmap_fill(mc_filter, MACVLAN_MC_FILTER_SZ); } else { DECLARE_BITMAP(filter, MACVLAN_MC_FILTER_SZ); struct netdev_hw_addr *ha; bitmap_zero(filter, MACVLAN_MC_FILTER_SZ); netdev_for_each_mc_addr(ha, dev) { if (!vlan && ha->synced <= cutoff) continue; __set_bit(mc_hash(vlan, ha->addr), filter); } __set_bit(mc_hash(vlan, dev->broadcast), filter); bitmap_copy(mc_filter, filter, MACVLAN_MC_FILTER_SZ); } } static void macvlan_recompute_bc_filter(struct macvlan_dev *vlan) { if (vlan->port->bc_cutoff < 0) { bitmap_zero(vlan->port->bc_filter, MACVLAN_MC_FILTER_SZ); return; } macvlan_compute_filter(vlan->port->bc_filter, vlan->lowerdev, NULL, vlan->port->bc_cutoff); } static void macvlan_set_mac_lists(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); macvlan_compute_filter(vlan->mc_filter, dev, vlan, 0); dev_uc_sync(vlan->lowerdev, dev); dev_mc_sync(vlan->lowerdev, dev); /* This is slightly inaccurate as we're including the subscription * list of vlan->lowerdev too. * * Bug alert: This only works if everyone has the same broadcast * address as lowerdev. As soon as someone changes theirs this * will break. * * However, this is already broken as when you change your broadcast * address we don't get called. * * The solution is to maintain a list of broadcast addresses like * we do for uc/mc, if you care. */ macvlan_compute_filter(vlan->port->mc_filter, vlan->lowerdev, NULL, 0); macvlan_recompute_bc_filter(vlan); } static void update_port_bc_cutoff(struct macvlan_dev *vlan, int cutoff) { if (vlan->port->bc_cutoff == cutoff) return; vlan->port->bc_cutoff = cutoff; macvlan_recompute_bc_filter(vlan); } static int macvlan_change_mtu(struct net_device *dev, int new_mtu) { struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->lowerdev->mtu < new_mtu) return -EINVAL; WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int macvlan_hwtstamp_get(struct net_device *dev, struct kernel_hwtstamp_config *cfg) { struct net_device *real_dev = macvlan_dev_real_dev(dev); return generic_hwtstamp_get_lower(real_dev, cfg); } static int macvlan_hwtstamp_set(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { struct net_device *real_dev = macvlan_dev_real_dev(dev); if (!net_eq(dev_net(dev), &init_net)) return -EOPNOTSUPP; return generic_hwtstamp_set_lower(real_dev, cfg, extack); } /* * macvlan network devices have devices nesting below it and are a special * "super class" of normal network devices; split their locks off into a * separate class since they always nest. */ static struct lock_class_key macvlan_netdev_addr_lock_key; #define ALWAYS_ON_OFFLOADS \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \ NETIF_F_GSO_ROBUST | NETIF_F_GSO_ENCAP_ALL) #define ALWAYS_ON_FEATURES ALWAYS_ON_OFFLOADS #define MACVLAN_FEATURES \ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_TSO | NETIF_F_LRO | \ NETIF_F_TSO_ECN | NETIF_F_TSO6 | NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) #define MACVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) static void macvlan_set_lockdep_class(struct net_device *dev) { netdev_lockdep_set_classes(dev); lockdep_set_class(&dev->addr_list_lock, &macvlan_netdev_addr_lock_key); } static int macvlan_init(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; struct macvlan_port *port = vlan->port; dev->state = (dev->state & ~MACVLAN_STATE_MASK) | (lowerdev->state & MACVLAN_STATE_MASK); dev->features = lowerdev->features & MACVLAN_FEATURES; dev->features |= ALWAYS_ON_FEATURES; dev->hw_features |= NETIF_F_LRO; dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; dev->vlan_features |= ALWAYS_ON_OFFLOADS; dev->hw_enc_features |= dev->features; dev->lltx = true; netif_inherit_tso_max(dev, lowerdev); dev->hard_header_len = lowerdev->hard_header_len; macvlan_set_lockdep_class(dev); vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->pcpu_stats) return -ENOMEM; port->count += 1; /* Get macvlan's reference to lowerdev */ netdev_hold(lowerdev, &vlan->dev_tracker, GFP_KERNEL); return 0; } static void macvlan_uninit(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port = vlan->port; free_percpu(vlan->pcpu_stats); macvlan_flush_sources(port, vlan); port->count -= 1; if (!port->count) macvlan_port_destroy(port->dev); } static void macvlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->pcpu_stats) { struct vlan_pcpu_stats *p; u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes; u32 rx_errors = 0, tx_dropped = 0; unsigned int start; int i; for_each_possible_cpu(i) { p = per_cpu_ptr(vlan->pcpu_stats, i); do { start = u64_stats_fetch_begin(&p->syncp); rx_packets = u64_stats_read(&p->rx_packets); rx_bytes = u64_stats_read(&p->rx_bytes); rx_multicast = u64_stats_read(&p->rx_multicast); tx_packets = u64_stats_read(&p->tx_packets); tx_bytes = u64_stats_read(&p->tx_bytes); } while (u64_stats_fetch_retry(&p->syncp, start)); stats->rx_packets += rx_packets; stats->rx_bytes += rx_bytes; stats->multicast += rx_multicast; stats->tx_packets += tx_packets; stats->tx_bytes += tx_bytes; /* rx_errors & tx_dropped are u32, updated * without syncp protection. */ rx_errors += READ_ONCE(p->rx_errors); tx_dropped += READ_ONCE(p->tx_dropped); } stats->rx_errors = rx_errors; stats->rx_dropped = rx_errors; stats->tx_dropped = tx_dropped; } } static int macvlan_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; return vlan_vid_add(lowerdev, proto, vid); } static int macvlan_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; vlan_vid_del(lowerdev, proto, vid); return 0; } static int macvlan_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 macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; /* Support unicast filter only on passthru devices. * Multicast filter should be allowed on all devices. */ if (!macvlan_passthru(vlan->port) && is_unicast_ether_addr(addr)) return -EOPNOTSUPP; if (flags & NLM_F_REPLACE) return -EOPNOTSUPP; if (is_unicast_ether_addr(addr)) err = dev_uc_add_excl(dev, addr); else if (is_multicast_ether_addr(addr)) err = dev_mc_add_excl(dev, addr); return err; } static int macvlan_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, bool *notified, struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; /* Support unicast filter only on passthru devices. * Multicast filter should be allowed on all devices. */ if (!macvlan_passthru(vlan->port) && is_unicast_ether_addr(addr)) return -EOPNOTSUPP; if (is_unicast_ether_addr(addr)) err = dev_uc_del(dev, addr); else if (is_multicast_ether_addr(addr)) err = dev_mc_del(dev, addr); return err; } static void macvlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, "macvlan", sizeof(drvinfo->driver)); strscpy(drvinfo->version, "0.1", sizeof(drvinfo->version)); } static int macvlan_ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { const struct macvlan_dev *vlan = netdev_priv(dev); return __ethtool_get_link_ksettings(vlan->lowerdev, cmd); } static int macvlan_ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) { struct net_device *real_dev = macvlan_dev_real_dev(dev); return ethtool_get_ts_info_by_layer(real_dev, info); } static netdev_features_t macvlan_fix_features(struct net_device *dev, netdev_features_t features) { struct macvlan_dev *vlan = netdev_priv(dev); netdev_features_t lowerdev_features = vlan->lowerdev->features; netdev_features_t mask; features |= NETIF_F_ALL_FOR_ALL; features &= (vlan->set_features | ~MACVLAN_FEATURES); mask = features; lowerdev_features &= (features | ~NETIF_F_LRO); features = netdev_increment_features(lowerdev_features, features, mask); features |= ALWAYS_ON_FEATURES; features &= (ALWAYS_ON_FEATURES | MACVLAN_FEATURES); return features; } #ifdef CONFIG_NET_POLL_CONTROLLER static void macvlan_dev_poll_controller(struct net_device *dev) { return; } static int macvlan_dev_netpoll_setup(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *real_dev = vlan->lowerdev; struct netpoll *netpoll; int err; netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); err = -ENOMEM; if (!netpoll) goto out; err = __netpoll_setup(netpoll, real_dev); if (err) { kfree(netpoll); goto out; } vlan->netpoll = netpoll; out: return err; } static void macvlan_dev_netpoll_cleanup(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct netpoll *netpoll = vlan->netpoll; if (!netpoll) return; vlan->netpoll = NULL; __netpoll_free(netpoll); } #endif /* CONFIG_NET_POLL_CONTROLLER */ static int macvlan_dev_get_iflink(const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); return READ_ONCE(vlan->lowerdev->ifindex); } static const struct ethtool_ops macvlan_ethtool_ops = { .get_link = ethtool_op_get_link, .get_link_ksettings = macvlan_ethtool_get_link_ksettings, .get_drvinfo = macvlan_ethtool_get_drvinfo, .get_ts_info = macvlan_ethtool_get_ts_info, }; static const struct net_device_ops macvlan_netdev_ops = { .ndo_init = macvlan_init, .ndo_uninit = macvlan_uninit, .ndo_open = macvlan_open, .ndo_stop = macvlan_stop, .ndo_start_xmit = macvlan_start_xmit, .ndo_change_mtu = macvlan_change_mtu, .ndo_fix_features = macvlan_fix_features, .ndo_change_rx_flags = macvlan_change_rx_flags, .ndo_set_mac_address = macvlan_set_mac_address, .ndo_set_rx_mode = macvlan_set_mac_lists, .ndo_get_stats64 = macvlan_dev_get_stats64, .ndo_validate_addr = eth_validate_addr, .ndo_vlan_rx_add_vid = macvlan_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = macvlan_vlan_rx_kill_vid, .ndo_fdb_add = macvlan_fdb_add, .ndo_fdb_del = macvlan_fdb_del, .ndo_fdb_dump = ndo_dflt_fdb_dump, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = macvlan_dev_poll_controller, .ndo_netpoll_setup = macvlan_dev_netpoll_setup, .ndo_netpoll_cleanup = macvlan_dev_netpoll_cleanup, #endif .ndo_get_iflink = macvlan_dev_get_iflink, .ndo_features_check = passthru_features_check, .ndo_hwtstamp_get = macvlan_hwtstamp_get, .ndo_hwtstamp_set = macvlan_hwtstamp_set, }; static void macvlan_dev_free(struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); /* Get rid of the macvlan's reference to lowerdev */ netdev_put(vlan->lowerdev, &vlan->dev_tracker); } void macvlan_common_setup(struct net_device *dev) { ether_setup(dev); /* ether_setup() has set dev->min_mtu to ETH_MIN_MTU. */ dev->max_mtu = ETH_MAX_MTU; dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); dev->priv_flags |= IFF_UNICAST_FLT; dev->change_proto_down = true; dev->netdev_ops = &macvlan_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = macvlan_dev_free; dev->header_ops = &macvlan_hard_header_ops; dev->ethtool_ops = &macvlan_ethtool_ops; } EXPORT_SYMBOL_GPL(macvlan_common_setup); static void macvlan_setup(struct net_device *dev) { macvlan_common_setup(dev); dev->priv_flags |= IFF_NO_QUEUE; } static int macvlan_port_create(struct net_device *dev) { struct macvlan_port *port; unsigned int i; int err; if (dev->type != ARPHRD_ETHER || dev->flags & IFF_LOOPBACK) return -EINVAL; if (netdev_is_rx_handler_busy(dev)) return -EBUSY; port = kzalloc(sizeof(*port), GFP_KERNEL); if (port == NULL) return -ENOMEM; port->dev = dev; ether_addr_copy(port->perm_addr, dev->dev_addr); INIT_LIST_HEAD(&port->vlans); for (i = 0; i < MACVLAN_HASH_SIZE; i++) INIT_HLIST_HEAD(&port->vlan_hash[i]); for (i = 0; i < MACVLAN_HASH_SIZE; i++) INIT_HLIST_HEAD(&port->vlan_source_hash[i]); port->bc_queue_len_used = 0; port->bc_cutoff = 1; skb_queue_head_init(&port->bc_queue); INIT_WORK(&port->bc_work, macvlan_process_broadcast); err = netdev_rx_handler_register(dev, macvlan_handle_frame, port); if (err) kfree(port); else dev->priv_flags |= IFF_MACVLAN_PORT; return err; } static void macvlan_port_destroy(struct net_device *dev) { struct macvlan_port *port = macvlan_port_get_rtnl(dev); struct sk_buff *skb; dev->priv_flags &= ~IFF_MACVLAN_PORT; netdev_rx_handler_unregister(dev); /* After this point, no packet can schedule bc_work anymore, * but we need to cancel it and purge left skbs if any. */ cancel_work_sync(&port->bc_work); while ((skb = __skb_dequeue(&port->bc_queue))) { const struct macvlan_dev *src = MACVLAN_SKB_CB(skb)->src; if (src) dev_put(src->dev); kfree_skb(skb); } /* If the lower device address has been changed by passthru * macvlan, put it back. */ if (macvlan_passthru(port) && !ether_addr_equal(port->dev->dev_addr, port->perm_addr)) { struct sockaddr_storage ss; ss.ss_family = port->dev->type; memcpy(&ss.__data, port->perm_addr, port->dev->addr_len); dev_set_mac_address(port->dev, &ss, NULL); } kfree(port); } static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct nlattr *nla, *head; int rem, len; if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) return 0; if (data[IFLA_MACVLAN_FLAGS] && nla_get_u16(data[IFLA_MACVLAN_FLAGS]) & ~(MACVLAN_FLAG_NOPROMISC | MACVLAN_FLAG_NODST)) return -EINVAL; if (data[IFLA_MACVLAN_MODE]) { switch (nla_get_u32(data[IFLA_MACVLAN_MODE])) { case MACVLAN_MODE_PRIVATE: case MACVLAN_MODE_VEPA: case MACVLAN_MODE_BRIDGE: case MACVLAN_MODE_PASSTHRU: case MACVLAN_MODE_SOURCE: break; default: return -EINVAL; } } if (data[IFLA_MACVLAN_MACADDR_MODE]) { switch (nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE])) { case MACVLAN_MACADDR_ADD: case MACVLAN_MACADDR_DEL: case MACVLAN_MACADDR_FLUSH: case MACVLAN_MACADDR_SET: break; default: return -EINVAL; } } if (data[IFLA_MACVLAN_MACADDR]) { if (nla_len(data[IFLA_MACVLAN_MACADDR]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(data[IFLA_MACVLAN_MACADDR]))) return -EADDRNOTAVAIL; } if (data[IFLA_MACVLAN_MACADDR_DATA]) { head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]); len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); nla_for_each_attr(nla, head, len, rem) { if (nla_type(nla) != IFLA_MACVLAN_MACADDR || nla_len(nla) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(nla))) return -EADDRNOTAVAIL; } } if (data[IFLA_MACVLAN_MACADDR_COUNT]) return -EINVAL; return 0; } /* * reconfigure list of remote source mac address * (only for macvlan devices in source mode) * Note regarding alignment: all netlink data is aligned to 4 Byte, which * suffices for both ether_addr_copy and ether_addr_equal_64bits usage. */ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode, struct nlattr *data[]) { char *addr = NULL; int ret, rem, len; struct nlattr *nla, *head; struct macvlan_source_entry *entry; if (data[IFLA_MACVLAN_MACADDR]) addr = nla_data(data[IFLA_MACVLAN_MACADDR]); if (mode == MACVLAN_MACADDR_ADD) { if (!addr) return -EINVAL; return macvlan_hash_add_source(vlan, addr); } else if (mode == MACVLAN_MACADDR_DEL) { if (!addr) return -EINVAL; entry = macvlan_hash_lookup_source(vlan, addr); if (entry) { macvlan_hash_del_source(entry); vlan->macaddr_count--; } } else if (mode == MACVLAN_MACADDR_FLUSH) { macvlan_flush_sources(vlan->port, vlan); } else if (mode == MACVLAN_MACADDR_SET) { macvlan_flush_sources(vlan->port, vlan); if (addr) { ret = macvlan_hash_add_source(vlan, addr); if (ret) return ret; } if (!data[IFLA_MACVLAN_MACADDR_DATA]) return 0; head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]); len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); nla_for_each_attr(nla, head, len, rem) { addr = nla_data(nla); ret = macvlan_hash_add_source(vlan, addr); if (ret) return ret; } } else { return -EINVAL; } return 0; } int macvlan_common_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *link_net = rtnl_newlink_link_net(params); struct macvlan_dev *vlan = netdev_priv(dev); struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct net_device *lowerdev; struct macvlan_port *port; bool create = false; int macmode; int err; if (!tb[IFLA_LINK]) return -EINVAL; lowerdev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK])); if (lowerdev == NULL) return -ENODEV; /* When creating macvlans or macvtaps on top of other macvlans - use * the real device as the lowerdev. */ if (netif_is_macvlan(lowerdev)) lowerdev = macvlan_dev_real_dev(lowerdev); if (!tb[IFLA_MTU]) dev->mtu = lowerdev->mtu; else if (dev->mtu > lowerdev->mtu) return -EINVAL; /* MTU range: 68 - lowerdev->max_mtu */ dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = lowerdev->max_mtu; if (!tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); if (!netif_is_macvlan_port(lowerdev)) { err = macvlan_port_create(lowerdev); if (err < 0) return err; create = true; } port = macvlan_port_get_rtnl(lowerdev); /* Only 1 macvlan device can be created in passthru mode */ if (macvlan_passthru(port)) { /* The macvlan port must be not created this time, * still goto destroy_macvlan_port for readability. */ err = -EINVAL; goto destroy_macvlan_port; } vlan->lowerdev = lowerdev; vlan->dev = dev; vlan->port = port; vlan->set_features = MACVLAN_FEATURES; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) vlan->mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); if (data && data[IFLA_MACVLAN_FLAGS]) vlan->flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]); if (vlan->mode == MACVLAN_MODE_PASSTHRU) { if (port->count) { err = -EINVAL; goto destroy_macvlan_port; } macvlan_set_passthru(port); eth_hw_addr_inherit(dev, lowerdev); } if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { if (vlan->mode != MACVLAN_MODE_SOURCE) { err = -EINVAL; goto destroy_macvlan_port; } macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]); err = macvlan_changelink_sources(vlan, macmode, data); if (err) goto destroy_macvlan_port; } vlan->bc_queue_len_req = MACVLAN_DEFAULT_BC_QUEUE_LEN; if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]); if (data && data[IFLA_MACVLAN_BC_CUTOFF]) update_port_bc_cutoff( vlan, nla_get_s32(data[IFLA_MACVLAN_BC_CUTOFF])); err = register_netdevice(dev); if (err < 0) goto destroy_macvlan_port; dev->priv_flags |= IFF_MACVLAN; err = netdev_upper_dev_link(lowerdev, dev, extack); if (err) goto unregister_netdev; list_add_tail_rcu(&vlan->list, &port->vlans); update_port_bc_queue_len(vlan->port); netif_stacked_transfer_operstate(lowerdev, dev); linkwatch_fire_event(dev); return 0; unregister_netdev: /* macvlan_uninit would free the macvlan port */ unregister_netdevice(dev); return err; destroy_macvlan_port: /* the macvlan port may be freed by macvlan_uninit when fail to register. * so we destroy the macvlan port only when it's valid. */ if (create && macvlan_port_get_rtnl(lowerdev)) { macvlan_flush_sources(port, vlan); macvlan_port_destroy(port->dev); } return err; } EXPORT_SYMBOL_GPL(macvlan_common_newlink); static int macvlan_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { return macvlan_common_newlink(dev, params, extack); } void macvlan_dellink(struct net_device *dev, struct list_head *head) { struct macvlan_dev *vlan = netdev_priv(dev); if (vlan->mode == MACVLAN_MODE_SOURCE) macvlan_flush_sources(vlan->port, vlan); list_del_rcu(&vlan->list); update_port_bc_queue_len(vlan->port); unregister_netdevice_queue(dev, head); netdev_upper_dev_unlink(vlan->lowerdev, dev); } EXPORT_SYMBOL_GPL(macvlan_dellink); static int macvlan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macvlan_dev *vlan = netdev_priv(dev); enum macvlan_mode mode; bool set_mode = false; enum macvlan_macaddr_mode macmode; int ret; /* Validate mode, but don't set yet: setting flags may fail. */ if (data && data[IFLA_MACVLAN_MODE]) { set_mode = true; mode = nla_get_u32(data[IFLA_MACVLAN_MODE]); /* Passthrough mode can't be set or cleared dynamically */ if ((mode == MACVLAN_MODE_PASSTHRU) != (vlan->mode == MACVLAN_MODE_PASSTHRU)) return -EINVAL; if (vlan->mode == MACVLAN_MODE_SOURCE && vlan->mode != mode) macvlan_flush_sources(vlan->port, vlan); } if (data && data[IFLA_MACVLAN_FLAGS]) { __u16 flags = nla_get_u16(data[IFLA_MACVLAN_FLAGS]); bool promisc = (flags ^ vlan->flags) & MACVLAN_FLAG_NOPROMISC; if (macvlan_passthru(vlan->port) && promisc) { int err; if (flags & MACVLAN_FLAG_NOPROMISC) err = dev_set_promiscuity(vlan->lowerdev, -1); else err = dev_set_promiscuity(vlan->lowerdev, 1); if (err < 0) return err; } vlan->flags = flags; } if (data && data[IFLA_MACVLAN_BC_QUEUE_LEN]) { vlan->bc_queue_len_req = nla_get_u32(data[IFLA_MACVLAN_BC_QUEUE_LEN]); update_port_bc_queue_len(vlan->port); } if (data && data[IFLA_MACVLAN_BC_CUTOFF]) update_port_bc_cutoff( vlan, nla_get_s32(data[IFLA_MACVLAN_BC_CUTOFF])); if (set_mode) vlan->mode = mode; if (data && data[IFLA_MACVLAN_MACADDR_MODE]) { if (vlan->mode != MACVLAN_MODE_SOURCE) return -EINVAL; macmode = nla_get_u32(data[IFLA_MACVLAN_MACADDR_MODE]); ret = macvlan_changelink_sources(vlan, macmode, data); if (ret) return ret; } return 0; } static size_t macvlan_get_size_mac(const struct macvlan_dev *vlan) { if (vlan->macaddr_count == 0) return 0; return nla_total_size(0) /* IFLA_MACVLAN_MACADDR_DATA */ + vlan->macaddr_count * nla_total_size(sizeof(u8) * ETH_ALEN); } static size_t macvlan_get_size(const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); return (0 + nla_total_size(4) /* IFLA_MACVLAN_MODE */ + nla_total_size(2) /* IFLA_MACVLAN_FLAGS */ + nla_total_size(4) /* IFLA_MACVLAN_MACADDR_COUNT */ + macvlan_get_size_mac(vlan) /* IFLA_MACVLAN_MACADDR */ + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN */ + nla_total_size(4) /* IFLA_MACVLAN_BC_QUEUE_LEN_USED */ ); } static int macvlan_fill_info_macaddr(struct sk_buff *skb, const struct macvlan_dev *vlan, const int i) { struct hlist_head *h = &vlan->port->vlan_source_hash[i]; struct macvlan_source_entry *entry; hlist_for_each_entry_rcu(entry, h, hlist, lockdep_rtnl_is_held()) { if (entry->vlan != vlan) continue; if (nla_put(skb, IFLA_MACVLAN_MACADDR, ETH_ALEN, entry->addr)) return 1; } return 0; } static int macvlan_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct macvlan_dev *vlan = netdev_priv(dev); struct macvlan_port *port = vlan->port; int i; struct nlattr *nest; if (nla_put_u32(skb, IFLA_MACVLAN_MODE, vlan->mode)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_MACVLAN_FLAGS, vlan->flags)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_MACVLAN_MACADDR_COUNT, vlan->macaddr_count)) goto nla_put_failure; if (vlan->macaddr_count > 0) { nest = nla_nest_start_noflag(skb, IFLA_MACVLAN_MACADDR_DATA); if (nest == NULL) goto nla_put_failure; for (i = 0; i < MACVLAN_HASH_SIZE; i++) { if (macvlan_fill_info_macaddr(skb, vlan, i)) goto nla_put_failure; } nla_nest_end(skb, nest); } if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN, vlan->bc_queue_len_req)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_MACVLAN_BC_QUEUE_LEN_USED, port->bc_queue_len_used)) goto nla_put_failure; if (port->bc_cutoff != 1 && nla_put_s32(skb, IFLA_MACVLAN_BC_CUTOFF, port->bc_cutoff)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy macvlan_policy[IFLA_MACVLAN_MAX + 1] = { [IFLA_MACVLAN_MODE] = { .type = NLA_U32 }, [IFLA_MACVLAN_FLAGS] = { .type = NLA_U16 }, [IFLA_MACVLAN_MACADDR_MODE] = { .type = NLA_U32 }, [IFLA_MACVLAN_MACADDR] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN }, [IFLA_MACVLAN_MACADDR_DATA] = { .type = NLA_NESTED }, [IFLA_MACVLAN_MACADDR_COUNT] = { .type = NLA_U32 }, [IFLA_MACVLAN_BC_QUEUE_LEN] = { .type = NLA_U32 }, [IFLA_MACVLAN_BC_QUEUE_LEN_USED] = { .type = NLA_REJECT }, [IFLA_MACVLAN_BC_CUTOFF] = { .type = NLA_S32 }, }; int macvlan_link_register(struct rtnl_link_ops *ops) { /* common fields */ ops->validate = macvlan_validate; ops->maxtype = IFLA_MACVLAN_MAX; ops->policy = macvlan_policy; ops->changelink = macvlan_changelink; ops->get_size = macvlan_get_size; ops->fill_info = macvlan_fill_info; return rtnl_link_register(ops); }; EXPORT_SYMBOL_GPL(macvlan_link_register); static struct net *macvlan_get_link_net(const struct net_device *dev) { return dev_net(macvlan_dev_real_dev(dev)); } static struct rtnl_link_ops macvlan_link_ops = { .kind = "macvlan", .setup = macvlan_setup, .newlink = macvlan_newlink, .dellink = macvlan_dellink, .get_link_net = macvlan_get_link_net, .priv_size = sizeof(struct macvlan_dev), }; static void update_port_bc_queue_len(struct macvlan_port *port) { u32 max_bc_queue_len_req = 0; struct macvlan_dev *vlan; list_for_each_entry(vlan, &port->vlans, list) { if (vlan->bc_queue_len_req > max_bc_queue_len_req) max_bc_queue_len_req = vlan->bc_queue_len_req; } port->bc_queue_len_used = max_bc_queue_len_req; } static int macvlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvlan_dev *vlan, *next; struct macvlan_port *port; LIST_HEAD(list_kill); if (!netif_is_macvlan_port(dev)) return NOTIFY_DONE; port = macvlan_port_get_rtnl(dev); switch (event) { case NETDEV_UP: case NETDEV_DOWN: case NETDEV_CHANGE: list_for_each_entry(vlan, &port->vlans, list) netif_stacked_transfer_operstate(vlan->lowerdev, vlan->dev); break; case NETDEV_FEAT_CHANGE: list_for_each_entry(vlan, &port->vlans, list) { netif_inherit_tso_max(vlan->dev, dev); netdev_update_features(vlan->dev); } break; case NETDEV_CHANGEMTU: list_for_each_entry(vlan, &port->vlans, list) { if (vlan->dev->mtu <= dev->mtu) continue; dev_set_mtu(vlan->dev, dev->mtu); } break; case NETDEV_CHANGEADDR: if (!macvlan_passthru(port)) return NOTIFY_DONE; vlan = list_first_entry_or_null(&port->vlans, struct macvlan_dev, list); if (vlan && macvlan_sync_address(vlan->dev, dev->dev_addr)) return NOTIFY_BAD; break; case NETDEV_UNREGISTER: /* twiddle thumbs on netns device moves */ if (dev->reg_state != NETREG_UNREGISTERING) break; list_for_each_entry_safe(vlan, next, &port->vlans, list) vlan->dev->rtnl_link_ops->dellink(vlan->dev, &list_kill); unregister_netdevice_many(&list_kill); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: case NETDEV_RESEND_IGMP: /* Propagate to all vlans */ list_for_each_entry(vlan, &port->vlans, list) call_netdevice_notifiers(event, vlan->dev); } return NOTIFY_DONE; } static struct notifier_block macvlan_notifier_block __read_mostly = { .notifier_call = macvlan_device_event, }; static int __init macvlan_init_module(void) { int err; register_netdevice_notifier(&macvlan_notifier_block); err = macvlan_link_register(&macvlan_link_ops); if (err < 0) goto err1; return 0; err1: unregister_netdevice_notifier(&macvlan_notifier_block); return err; } static void __exit macvlan_cleanup_module(void) { rtnl_link_unregister(&macvlan_link_ops); unregister_netdevice_notifier(&macvlan_notifier_block); } module_init(macvlan_init_module); module_exit(macvlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Driver for MAC address based VLANs"); MODULE_ALIAS_RTNL_LINK("macvlan"); |
| 16 2 19 14 18 64 65 10 55 28 3 31 168 38 19 19 19 64 64 37 86 77 31 39 50 64 64 65 65 65 65 65 64 65 41 41 41 41 41 30 31 31 41 41 41 41 3 6 6 4 2 4 2 3 3 4 2 6 6 6 6 6 4 2 38 38 38 38 38 38 38 83 65 65 50 10 39 40 40 65 64 65 65 65 65 65 68 68 68 65 64 9 1 9 9 65 65 65 65 55 10 55 55 55 55 55 58 59 58 3 55 70 70 70 70 65 4 4 22 4 4 4 83 64 19 83 83 83 83 83 83 10 10 10 10 10 9 9 10 10 10 10 10 10 1 10 14 14 14 14 14 5 5 5 14 19 13 13 2 4 19 19 19 14 83 38 38 38 64 64 64 64 64 | 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 | /* * Resizable virtual memory filesystem for Linux. * * Copyright (C) 2000 Linus Torvalds. * 2000 Transmeta Corp. * 2000-2001 Christoph Rohland * 2000-2001 SAP AG * 2002 Red Hat Inc. * Copyright (C) 2002-2011 Hugh Dickins. * Copyright (C) 2011 Google Inc. * Copyright (C) 2002-2005 VERITAS Software Corporation. * Copyright (C) 2004 Andi Kleen, SuSE Labs * * Extended attribute support for tmpfs: * Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net> * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com> * * tiny-shmem: * Copyright (c) 2004, 2008 Matt Mackall <mpm@selenic.com> * * This file is released under the GPL. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/vfs.h> #include <linux/mount.h> #include <linux/ramfs.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/fileattr.h> #include <linux/mm.h> #include <linux/random.h> #include <linux/sched/signal.h> #include <linux/export.h> #include <linux/shmem_fs.h> #include <linux/swap.h> #include <linux/uio.h> #include <linux/hugetlb.h> #include <linux/fs_parser.h> #include <linux/swapfile.h> #include <linux/iversion.h> #include <linux/unicode.h> #include "swap.h" static struct vfsmount *shm_mnt __ro_after_init; #ifdef CONFIG_SHMEM /* * This virtual memory filesystem is heavily based on the ramfs. It * extends ramfs by the ability to use swap and honor resource limits * which makes it a completely usable filesystem. */ #include <linux/xattr.h> #include <linux/exportfs.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/mman.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #include <linux/pagevec.h> #include <linux/percpu_counter.h> #include <linux/falloc.h> #include <linux/splice.h> #include <linux/security.h> #include <linux/swapops.h> #include <linux/mempolicy.h> #include <linux/namei.h> #include <linux/ctype.h> #include <linux/migrate.h> #include <linux/highmem.h> #include <linux/seq_file.h> #include <linux/magic.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <uapi/linux/memfd.h> #include <linux/rmap.h> #include <linux/uuid.h> #include <linux/quotaops.h> #include <linux/rcupdate_wait.h> #include <linux/uaccess.h> #include "internal.h" #define VM_ACCT(size) (PAGE_ALIGN(size) >> PAGE_SHIFT) /* Pretend that each entry is of this size in directory's i_size */ #define BOGO_DIRENT_SIZE 20 /* Pretend that one inode + its dentry occupy this much memory */ #define BOGO_INODE_SIZE 1024 /* Symlink up to this size is kmalloc'ed instead of using a swappable page */ #define SHORT_SYMLINK_LEN 128 /* * shmem_fallocate communicates with shmem_fault or shmem_writeout via * inode->i_private (with i_rwsem making sure that it has only one user at * a time): we would prefer not to enlarge the shmem inode just for that. */ struct shmem_falloc { wait_queue_head_t *waitq; /* faults into hole wait for punch to end */ pgoff_t start; /* start of range currently being fallocated */ pgoff_t next; /* the next page offset to be fallocated */ pgoff_t nr_falloced; /* how many new pages have been fallocated */ pgoff_t nr_unswapped; /* how often writeout refused to swap out */ }; struct shmem_options { unsigned long long blocks; unsigned long long inodes; struct mempolicy *mpol; kuid_t uid; kgid_t gid; umode_t mode; bool full_inums; int huge; int seen; bool noswap; unsigned short quota_types; struct shmem_quota_limits qlimits; #if IS_ENABLED(CONFIG_UNICODE) struct unicode_map *encoding; bool strict_encoding; #endif #define SHMEM_SEEN_BLOCKS 1 #define SHMEM_SEEN_INODES 2 #define SHMEM_SEEN_HUGE 4 #define SHMEM_SEEN_INUMS 8 #define SHMEM_SEEN_NOSWAP 16 #define SHMEM_SEEN_QUOTA 32 }; #ifdef CONFIG_TRANSPARENT_HUGEPAGE static unsigned long huge_shmem_orders_always __read_mostly; static unsigned long huge_shmem_orders_madvise __read_mostly; static unsigned long huge_shmem_orders_inherit __read_mostly; static unsigned long huge_shmem_orders_within_size __read_mostly; static bool shmem_orders_configured __initdata; #endif #ifdef CONFIG_TMPFS static unsigned long shmem_default_max_blocks(void) { return totalram_pages() / 2; } static unsigned long shmem_default_max_inodes(void) { unsigned long nr_pages = totalram_pages(); return min3(nr_pages - totalhigh_pages(), nr_pages / 2, ULONG_MAX / BOGO_INODE_SIZE); } #endif static int shmem_swapin_folio(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, vm_fault_t *fault_type); static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) { return sb->s_fs_info; } /* * shmem_file_setup pre-accounts the whole fixed size of a VM object, * for shared memory and for shared anonymous (/dev/zero) mappings * (unless MAP_NORESERVE and sysctl_overcommit_memory <= 1), * consistent with the pre-accounting of private mappings ... */ static inline int shmem_acct_size(unsigned long flags, loff_t size) { return (flags & VM_NORESERVE) ? 0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(size)); } static inline void shmem_unacct_size(unsigned long flags, loff_t size) { if (!(flags & VM_NORESERVE)) vm_unacct_memory(VM_ACCT(size)); } static inline int shmem_reacct_size(unsigned long flags, loff_t oldsize, loff_t newsize) { if (!(flags & VM_NORESERVE)) { if (VM_ACCT(newsize) > VM_ACCT(oldsize)) return security_vm_enough_memory_mm(current->mm, VM_ACCT(newsize) - VM_ACCT(oldsize)); else if (VM_ACCT(newsize) < VM_ACCT(oldsize)) vm_unacct_memory(VM_ACCT(oldsize) - VM_ACCT(newsize)); } return 0; } /* * ... whereas tmpfs objects are accounted incrementally as * pages are allocated, in order to allow large sparse files. * shmem_get_folio reports shmem_acct_blocks failure as -ENOSPC not -ENOMEM, * so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM. */ static inline int shmem_acct_blocks(unsigned long flags, long pages) { if (!(flags & VM_NORESERVE)) return 0; return security_vm_enough_memory_mm(current->mm, pages * VM_ACCT(PAGE_SIZE)); } static inline void shmem_unacct_blocks(unsigned long flags, long pages) { if (flags & VM_NORESERVE) vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE)); } static int shmem_inode_acct_blocks(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); int err = -ENOSPC; if (shmem_acct_blocks(info->flags, pages)) return err; might_sleep(); /* when quotas */ if (sbinfo->max_blocks) { if (!percpu_counter_limited_add(&sbinfo->used_blocks, sbinfo->max_blocks, pages)) goto unacct; err = dquot_alloc_block_nodirty(inode, pages); if (err) { percpu_counter_sub(&sbinfo->used_blocks, pages); goto unacct; } } else { err = dquot_alloc_block_nodirty(inode, pages); if (err) goto unacct; } return 0; unacct: shmem_unacct_blocks(info->flags, pages); return err; } static void shmem_inode_unacct_blocks(struct inode *inode, long pages) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); might_sleep(); /* when quotas */ dquot_free_block_nodirty(inode, pages); if (sbinfo->max_blocks) percpu_counter_sub(&sbinfo->used_blocks, pages); shmem_unacct_blocks(info->flags, pages); } static const struct super_operations shmem_ops; static const struct address_space_operations shmem_aops; static const struct file_operations shmem_file_operations; static const struct inode_operations shmem_inode_operations; static const struct inode_operations shmem_dir_inode_operations; static const struct inode_operations shmem_special_inode_operations; static const struct vm_operations_struct shmem_vm_ops; static const struct vm_operations_struct shmem_anon_vm_ops; static struct file_system_type shmem_fs_type; bool shmem_mapping(const struct address_space *mapping) { return mapping->a_ops == &shmem_aops; } EXPORT_SYMBOL_GPL(shmem_mapping); bool vma_is_anon_shmem(const struct vm_area_struct *vma) { return vma->vm_ops == &shmem_anon_vm_ops; } bool vma_is_shmem(const struct vm_area_struct *vma) { return vma_is_anon_shmem(vma) || vma->vm_ops == &shmem_vm_ops; } static LIST_HEAD(shmem_swaplist); static DEFINE_SPINLOCK(shmem_swaplist_lock); #ifdef CONFIG_TMPFS_QUOTA static int shmem_enable_quotas(struct super_block *sb, unsigned short quota_types) { int type, err = 0; sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY; for (type = 0; type < SHMEM_MAXQUOTAS; type++) { if (!(quota_types & (1 << type))) continue; err = dquot_load_quota_sb(sb, type, QFMT_SHMEM, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); if (err) goto out_err; } return 0; out_err: pr_warn("tmpfs: failed to enable quota tracking (type=%d, err=%d)\n", type, err); for (type--; type >= 0; type--) dquot_quota_off(sb, type); return err; } static void shmem_disable_quotas(struct super_block *sb) { int type; for (type = 0; type < SHMEM_MAXQUOTAS; type++) dquot_quota_off(sb, type); } static struct dquot __rcu **shmem_get_dquots(struct inode *inode) { return SHMEM_I(inode)->i_dquot; } #endif /* CONFIG_TMPFS_QUOTA */ /* * shmem_reserve_inode() performs bookkeeping to reserve a shmem inode, and * produces a novel ino for the newly allocated inode. * * It may also be called when making a hard link to permit the space needed by * each dentry. However, in that case, no new inode number is needed since that * internally draws from another pool of inode numbers (currently global * get_next_ino()). This case is indicated by passing NULL as inop. */ #define SHMEM_INO_BATCH 1024 static int shmem_reserve_inode(struct super_block *sb, ino_t *inop) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); ino_t ino; if (!(sb->s_flags & SB_KERNMOUNT)) { raw_spin_lock(&sbinfo->stat_lock); if (sbinfo->max_inodes) { if (sbinfo->free_ispace < BOGO_INODE_SIZE) { raw_spin_unlock(&sbinfo->stat_lock); return -ENOSPC; } sbinfo->free_ispace -= BOGO_INODE_SIZE; } if (inop) { ino = sbinfo->next_ino++; if (unlikely(is_zero_ino(ino))) ino = sbinfo->next_ino++; if (unlikely(!sbinfo->full_inums && ino > UINT_MAX)) { /* * Emulate get_next_ino uint wraparound for * compatibility */ if (IS_ENABLED(CONFIG_64BIT)) pr_warn("%s: inode number overflow on device %d, consider using inode64 mount option\n", __func__, MINOR(sb->s_dev)); sbinfo->next_ino = 1; ino = sbinfo->next_ino++; } *inop = ino; } raw_spin_unlock(&sbinfo->stat_lock); } else if (inop) { /* * __shmem_file_setup, one of our callers, is lock-free: it * doesn't hold stat_lock in shmem_reserve_inode since * max_inodes is always 0, and is called from potentially * unknown contexts. As such, use a per-cpu batched allocator * which doesn't require the per-sb stat_lock unless we are at * the batch boundary. * * We don't need to worry about inode{32,64} since SB_KERNMOUNT * shmem mounts are not exposed to userspace, so we don't need * to worry about things like glibc compatibility. */ ino_t *next_ino; next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu()); ino = *next_ino; if (unlikely(ino % SHMEM_INO_BATCH == 0)) { raw_spin_lock(&sbinfo->stat_lock); ino = sbinfo->next_ino; sbinfo->next_ino += SHMEM_INO_BATCH; raw_spin_unlock(&sbinfo->stat_lock); if (unlikely(is_zero_ino(ino))) ino++; } *inop = ino; *next_ino = ++ino; put_cpu(); } return 0; } static void shmem_free_inode(struct super_block *sb, size_t freed_ispace) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (sbinfo->max_inodes) { raw_spin_lock(&sbinfo->stat_lock); sbinfo->free_ispace += BOGO_INODE_SIZE + freed_ispace; raw_spin_unlock(&sbinfo->stat_lock); } } /** * shmem_recalc_inode - recalculate the block usage of an inode * @inode: inode to recalc * @alloced: the change in number of pages allocated to inode * @swapped: the change in number of pages swapped from inode * * We have to calculate the free blocks since the mm can drop * undirtied hole pages behind our back. * * But normally info->alloced == inode->i_mapping->nrpages + info->swapped * So mm freed is info->alloced - (inode->i_mapping->nrpages + info->swapped) * * Return: true if swapped was incremented from 0, for shmem_writeout(). */ static bool shmem_recalc_inode(struct inode *inode, long alloced, long swapped) { struct shmem_inode_info *info = SHMEM_I(inode); bool first_swapped = false; long freed; spin_lock(&info->lock); info->alloced += alloced; info->swapped += swapped; freed = info->alloced - info->swapped - READ_ONCE(inode->i_mapping->nrpages); /* * Special case: whereas normally shmem_recalc_inode() is called * after i_mapping->nrpages has already been adjusted (up or down), * shmem_writeout() has to raise swapped before nrpages is lowered - * to stop a racing shmem_recalc_inode() from thinking that a page has * been freed. Compensate here, to avoid the need for a followup call. */ if (swapped > 0) { if (info->swapped == swapped) first_swapped = true; freed += swapped; } if (freed > 0) info->alloced -= freed; spin_unlock(&info->lock); /* The quota case may block */ if (freed > 0) shmem_inode_unacct_blocks(inode, freed); return first_swapped; } bool shmem_charge(struct inode *inode, long pages) { struct address_space *mapping = inode->i_mapping; if (shmem_inode_acct_blocks(inode, pages)) return false; /* nrpages adjustment first, then shmem_recalc_inode() when balanced */ xa_lock_irq(&mapping->i_pages); mapping->nrpages += pages; xa_unlock_irq(&mapping->i_pages); shmem_recalc_inode(inode, pages, 0); return true; } void shmem_uncharge(struct inode *inode, long pages) { /* pages argument is currently unused: keep it to help debugging */ /* nrpages adjustment done by __filemap_remove_folio() or caller */ shmem_recalc_inode(inode, 0, 0); } /* * Replace item expected in xarray by a new item, while holding xa_lock. */ static int shmem_replace_entry(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { XA_STATE(xas, &mapping->i_pages, index); void *item; VM_BUG_ON(!expected); VM_BUG_ON(!replacement); item = xas_load(&xas); if (item != expected) return -ENOENT; xas_store(&xas, replacement); return 0; } /* * Sometimes, before we decide whether to proceed or to fail, we must check * that an entry was not already brought back or split by a racing thread. * * Checking folio is not enough: by the time a swapcache folio is locked, it * might be reused, and again be swapcache, using the same swap as before. * Returns the swap entry's order if it still presents, else returns -1. */ static int shmem_confirm_swap(struct address_space *mapping, pgoff_t index, swp_entry_t swap) { XA_STATE(xas, &mapping->i_pages, index); int ret = -1; void *entry; rcu_read_lock(); do { entry = xas_load(&xas); if (entry == swp_to_radix_entry(swap)) ret = xas_get_order(&xas); } while (xas_retry(&xas, entry)); rcu_read_unlock(); return ret; } /* * Definitions for "huge tmpfs": tmpfs mounted with the huge= option * * SHMEM_HUGE_NEVER: * disables huge pages for the mount; * SHMEM_HUGE_ALWAYS: * enables huge pages for the mount; * SHMEM_HUGE_WITHIN_SIZE: * only allocate huge pages if the page will be fully within i_size, * also respect madvise() hints; * SHMEM_HUGE_ADVISE: * only allocate huge pages if requested with madvise(); */ #define SHMEM_HUGE_NEVER 0 #define SHMEM_HUGE_ALWAYS 1 #define SHMEM_HUGE_WITHIN_SIZE 2 #define SHMEM_HUGE_ADVISE 3 /* * Special values. * Only can be set via /sys/kernel/mm/transparent_hugepage/shmem_enabled: * * SHMEM_HUGE_DENY: * disables huge on shm_mnt and all mounts, for emergency use; * SHMEM_HUGE_FORCE: * enables huge on shm_mnt and all mounts, w/o needing option, for testing; * */ #define SHMEM_HUGE_DENY (-1) #define SHMEM_HUGE_FORCE (-2) #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* ifdef here to avoid bloating shmem.o when not necessary */ static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER; static int tmpfs_huge __read_mostly = SHMEM_HUGE_NEVER; static unsigned int shmem_get_orders_within_size(struct inode *inode, unsigned long within_size_orders, pgoff_t index, loff_t write_end) { pgoff_t aligned_index; unsigned long order; loff_t i_size; order = highest_order(within_size_orders); while (within_size_orders) { aligned_index = round_up(index + 1, 1 << order); i_size = max(write_end, i_size_read(inode)); i_size = round_up(i_size, PAGE_SIZE); if (i_size >> PAGE_SHIFT >= aligned_index) return within_size_orders; order = next_order(&within_size_orders, order); } return 0; } static unsigned int shmem_huge_global_enabled(struct inode *inode, pgoff_t index, loff_t write_end, bool shmem_huge_force, struct vm_area_struct *vma, vm_flags_t vm_flags) { unsigned int maybe_pmd_order = HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER ? 0 : BIT(HPAGE_PMD_ORDER); unsigned long within_size_orders; if (!S_ISREG(inode->i_mode)) return 0; if (shmem_huge == SHMEM_HUGE_DENY) return 0; if (shmem_huge_force || shmem_huge == SHMEM_HUGE_FORCE) return maybe_pmd_order; /* * The huge order allocation for anon shmem is controlled through * the mTHP interface, so we still use PMD-sized huge order to * check whether global control is enabled. * * For tmpfs mmap()'s huge order, we still use PMD-sized order to * allocate huge pages due to lack of a write size hint. * * For tmpfs with 'huge=always' or 'huge=within_size' mount option, * we will always try PMD-sized order first. If that failed, it will * fall back to small large folios. */ switch (SHMEM_SB(inode->i_sb)->huge) { case SHMEM_HUGE_ALWAYS: if (vma) return maybe_pmd_order; return THP_ORDERS_ALL_FILE_DEFAULT; case SHMEM_HUGE_WITHIN_SIZE: if (vma) within_size_orders = maybe_pmd_order; else within_size_orders = THP_ORDERS_ALL_FILE_DEFAULT; within_size_orders = shmem_get_orders_within_size(inode, within_size_orders, index, write_end); if (within_size_orders > 0) return within_size_orders; fallthrough; case SHMEM_HUGE_ADVISE: if (vm_flags & VM_HUGEPAGE) return maybe_pmd_order; fallthrough; default: return 0; } } static int shmem_parse_huge(const char *str) { int huge; if (!str) return -EINVAL; if (!strcmp(str, "never")) huge = SHMEM_HUGE_NEVER; else if (!strcmp(str, "always")) huge = SHMEM_HUGE_ALWAYS; else if (!strcmp(str, "within_size")) huge = SHMEM_HUGE_WITHIN_SIZE; else if (!strcmp(str, "advise")) huge = SHMEM_HUGE_ADVISE; else if (!strcmp(str, "deny")) huge = SHMEM_HUGE_DENY; else if (!strcmp(str, "force")) huge = SHMEM_HUGE_FORCE; else return -EINVAL; if (!has_transparent_hugepage() && huge != SHMEM_HUGE_NEVER && huge != SHMEM_HUGE_DENY) return -EINVAL; /* Do not override huge allocation policy with non-PMD sized mTHP */ if (huge == SHMEM_HUGE_FORCE && huge_shmem_orders_inherit != BIT(HPAGE_PMD_ORDER)) return -EINVAL; return huge; } #if defined(CONFIG_SYSFS) || defined(CONFIG_TMPFS) static const char *shmem_format_huge(int huge) { switch (huge) { case SHMEM_HUGE_NEVER: return "never"; case SHMEM_HUGE_ALWAYS: return "always"; case SHMEM_HUGE_WITHIN_SIZE: return "within_size"; case SHMEM_HUGE_ADVISE: return "advise"; case SHMEM_HUGE_DENY: return "deny"; case SHMEM_HUGE_FORCE: return "force"; default: VM_BUG_ON(1); return "bad_val"; } } #endif static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_free) { LIST_HEAD(list), *pos, *next; struct inode *inode; struct shmem_inode_info *info; struct folio *folio; unsigned long batch = sc ? sc->nr_to_scan : 128; unsigned long split = 0, freed = 0; if (list_empty(&sbinfo->shrinklist)) return SHRINK_STOP; spin_lock(&sbinfo->shrinklist_lock); list_for_each_safe(pos, next, &sbinfo->shrinklist) { info = list_entry(pos, struct shmem_inode_info, shrinklist); /* pin the inode */ inode = igrab(&info->vfs_inode); /* inode is about to be evicted */ if (!inode) { list_del_init(&info->shrinklist); goto next; } list_move(&info->shrinklist, &list); next: sbinfo->shrinklist_len--; if (!--batch) break; } spin_unlock(&sbinfo->shrinklist_lock); list_for_each_safe(pos, next, &list) { pgoff_t next, end; loff_t i_size; int ret; info = list_entry(pos, struct shmem_inode_info, shrinklist); inode = &info->vfs_inode; if (nr_to_free && freed >= nr_to_free) goto move_back; i_size = i_size_read(inode); folio = filemap_get_entry(inode->i_mapping, i_size / PAGE_SIZE); if (!folio || xa_is_value(folio)) goto drop; /* No large folio at the end of the file: nothing to split */ if (!folio_test_large(folio)) { folio_put(folio); goto drop; } /* Check if there is anything to gain from splitting */ next = folio_next_index(folio); end = shmem_fallocend(inode, DIV_ROUND_UP(i_size, PAGE_SIZE)); if (end <= folio->index || end >= next) { folio_put(folio); goto drop; } /* * Move the inode on the list back to shrinklist if we failed * to lock the page at this time. * * Waiting for the lock may lead to deadlock in the * reclaim path. */ if (!folio_trylock(folio)) { folio_put(folio); goto move_back; } ret = split_folio(folio); folio_unlock(folio); folio_put(folio); /* If split failed move the inode on the list back to shrinklist */ if (ret) goto move_back; freed += next - end; split++; drop: list_del_init(&info->shrinklist); goto put; move_back: /* * Make sure the inode is either on the global list or deleted * from any local list before iput() since it could be deleted * in another thread once we put the inode (then the local list * is corrupted). */ spin_lock(&sbinfo->shrinklist_lock); list_move(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; spin_unlock(&sbinfo->shrinklist_lock); put: iput(inode); } return split; } static long shmem_unused_huge_scan(struct super_block *sb, struct shrink_control *sc) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); if (!READ_ONCE(sbinfo->shrinklist_len)) return SHRINK_STOP; return shmem_unused_huge_shrink(sbinfo, sc, 0); } static long shmem_unused_huge_count(struct super_block *sb, struct shrink_control *sc) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); return READ_ONCE(sbinfo->shrinklist_len); } #else /* !CONFIG_TRANSPARENT_HUGEPAGE */ #define shmem_huge SHMEM_HUGE_DENY static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_free) { return 0; } static unsigned int shmem_huge_global_enabled(struct inode *inode, pgoff_t index, loff_t write_end, bool shmem_huge_force, struct vm_area_struct *vma, vm_flags_t vm_flags) { return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static void shmem_update_stats(struct folio *folio, int nr_pages) { if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr_pages); __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr_pages); __lruvec_stat_mod_folio(folio, NR_SHMEM, nr_pages); } /* * Somewhat like filemap_add_folio, but error if expected item has gone. */ static int shmem_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t index, void *expected, gfp_t gfp) { XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio)); unsigned long nr = folio_nr_pages(folio); swp_entry_t iter, swap; void *entry; VM_BUG_ON_FOLIO(index != round_down(index, nr), folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_swapbacked(folio), folio); folio_ref_add(folio, nr); folio->mapping = mapping; folio->index = index; gfp &= GFP_RECLAIM_MASK; folio_throttle_swaprate(folio, gfp); swap = radix_to_swp_entry(expected); do { iter = swap; xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { /* * The range must either be empty, or filled with * expected swap entries. Shmem swap entries are never * partially freed without split of both entry and * folio, so there shouldn't be any holes. */ if (!expected || entry != swp_to_radix_entry(iter)) { xas_set_err(&xas, -EEXIST); goto unlock; } iter.val += 1 << xas_get_order(&xas); } if (expected && iter.val - nr != swap.val) { xas_set_err(&xas, -EEXIST); goto unlock; } xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; shmem_update_stats(folio, nr); mapping->nrpages += nr; unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); if (xas_error(&xas)) { folio->mapping = NULL; folio_ref_sub(folio, nr); return xas_error(&xas); } return 0; } /* * Somewhat like filemap_remove_folio, but substitutes swap for @folio. */ static void shmem_delete_from_page_cache(struct folio *folio, void *radswap) { struct address_space *mapping = folio->mapping; long nr = folio_nr_pages(folio); int error; xa_lock_irq(&mapping->i_pages); error = shmem_replace_entry(mapping, folio->index, folio, radswap); folio->mapping = NULL; mapping->nrpages -= nr; shmem_update_stats(folio, -nr); xa_unlock_irq(&mapping->i_pages); folio_put_refs(folio, nr); BUG_ON(error); } /* * Remove swap entry from page cache, free the swap and its page cache. Returns * the number of pages being freed. 0 means entry not found in XArray (0 pages * being freed). */ static long shmem_free_swap(struct address_space *mapping, pgoff_t index, void *radswap) { int order = xa_get_order(&mapping->i_pages, index); void *old; old = xa_cmpxchg_irq(&mapping->i_pages, index, radswap, NULL, 0); if (old != radswap) return 0; free_swap_and_cache_nr(radix_to_swp_entry(radswap), 1 << order); return 1 << order; } /* * Determine (in bytes) how many of the shmem object's pages mapped by the * given offsets are swapped out. * * This is safe to call without i_rwsem or the i_pages lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); struct folio *folio; unsigned long swapped = 0; unsigned long max = end - 1; rcu_read_lock(); xas_for_each(&xas, folio, max) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) swapped += 1 << xas_get_order(&xas); if (xas.xa_index == max) break; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); return swapped << PAGE_SHIFT; } /* * Determine (in bytes) how many of the shmem object's pages mapped by the * given vma is swapped out. * * This is safe to call without i_rwsem or the i_pages lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ unsigned long shmem_swap_usage(struct vm_area_struct *vma) { struct inode *inode = file_inode(vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); struct address_space *mapping = inode->i_mapping; unsigned long swapped; /* Be careful as we don't hold info->lock */ swapped = READ_ONCE(info->swapped); /* * The easier cases are when the shmem object has nothing in swap, or * the vma maps it whole. Then we can simply use the stats that we * already track. */ if (!swapped) return 0; if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size) return swapped << PAGE_SHIFT; /* Here comes the more involved part */ return shmem_partial_swap_usage(mapping, vma->vm_pgoff, vma->vm_pgoff + vma_pages(vma)); } /* * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. */ void shmem_unlock_mapping(struct address_space *mapping) { struct folio_batch fbatch; pgoff_t index = 0; folio_batch_init(&fbatch); /* * Minor point, but we might as well stop if someone else SHM_LOCKs it. */ while (!mapping_unevictable(mapping) && filemap_get_folios(mapping, &index, ~0UL, &fbatch)) { check_move_unevictable_folios(&fbatch); folio_batch_release(&fbatch); cond_resched(); } } static struct folio *shmem_get_partial_folio(struct inode *inode, pgoff_t index) { struct folio *folio; /* * At first avoid shmem_get_folio(,,,SGP_READ): that fails * beyond i_size, and reports fallocated folios as holes. */ folio = filemap_get_entry(inode->i_mapping, index); if (!folio) return folio; if (!xa_is_value(folio)) { folio_lock(folio); if (folio->mapping == inode->i_mapping) return folio; /* The folio has been swapped out */ folio_unlock(folio); folio_put(folio); } /* * But read a folio back from swap if any of it is within i_size * (although in some cases this is just a waste of time). */ folio = NULL; shmem_get_folio(inode, index, 0, &folio, SGP_READ); return folio; } /* * Remove range of pages and swap entries from page cache, and free them. * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate. */ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, bool unfalloc) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; pgoff_t end = (lend + 1) >> PAGE_SHIFT; struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; struct folio *folio; bool same_folio; long nr_swaps_freed = 0; pgoff_t index; int i; if (lend == -1) end = -1; /* unsigned, so actually very big */ if (info->fallocend > start && info->fallocend <= end && !unfalloc) info->fallocend = start; folio_batch_init(&fbatch); index = start; while (index < end && find_lock_entries(mapping, &index, end - 1, &fbatch, indices)) { for (i = 0; i < folio_batch_count(&fbatch); i++) { folio = fbatch.folios[i]; if (xa_is_value(folio)) { if (unfalloc) continue; nr_swaps_freed += shmem_free_swap(mapping, indices[i], folio); continue; } if (!unfalloc || !folio_test_uptodate(folio)) truncate_inode_folio(mapping, folio); folio_unlock(folio); } folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); cond_resched(); } /* * When undoing a failed fallocate, we want none of the partial folio * zeroing and splitting below, but shall want to truncate the whole * folio when !uptodate indicates that it was added by this fallocate, * even when [lstart, lend] covers only a part of the folio. */ if (unfalloc) goto whole_folios; same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT); folio = shmem_get_partial_folio(inode, lstart >> PAGE_SHIFT); if (folio) { same_folio = lend < folio_pos(folio) + folio_size(folio); folio_mark_dirty(folio); if (!truncate_inode_partial_folio(folio, lstart, lend)) { start = folio_next_index(folio); if (same_folio) end = folio->index; } folio_unlock(folio); folio_put(folio); folio = NULL; } if (!same_folio) folio = shmem_get_partial_folio(inode, lend >> PAGE_SHIFT); if (folio) { folio_mark_dirty(folio); if (!truncate_inode_partial_folio(folio, lstart, lend)) end = folio->index; folio_unlock(folio); folio_put(folio); } whole_folios: index = start; while (index < end) { cond_resched(); if (!find_get_entries(mapping, &index, end - 1, &fbatch, indices)) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) break; /* But if truncating, restart to make sure all gone */ index = start; continue; } for (i = 0; i < folio_batch_count(&fbatch); i++) { folio = fbatch.folios[i]; if (xa_is_value(folio)) { long swaps_freed; if (unfalloc) continue; swaps_freed = shmem_free_swap(mapping, indices[i], folio); if (!swaps_freed) { /* Swap was replaced by page: retry */ index = indices[i]; break; } nr_swaps_freed += swaps_freed; continue; } folio_lock(folio); if (!unfalloc || !folio_test_uptodate(folio)) { if (folio_mapping(folio) != mapping) { /* Page was replaced by swap: retry */ folio_unlock(folio); index = indices[i]; break; } VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); if (!folio_test_large(folio)) { truncate_inode_folio(mapping, folio); } else if (truncate_inode_partial_folio(folio, lstart, lend)) { /* * If we split a page, reset the loop so * that we pick up the new sub pages. * Otherwise the THP was entirely * dropped or the target range was * zeroed, so just continue the loop as * is. */ if (!folio_test_large(folio)) { folio_unlock(folio); index = start; break; } } } folio_unlock(folio); } folio_batch_remove_exceptionals(&fbatch); folio_batch_release(&fbatch); } shmem_recalc_inode(inode, 0, -nr_swaps_freed); } void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { shmem_undo_range(inode, lstart, lend, false); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); inode_inc_iversion(inode); } EXPORT_SYMBOL_GPL(shmem_truncate_range); static int shmem_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = path->dentry->d_inode; struct shmem_inode_info *info = SHMEM_I(inode); if (info->alloced - info->swapped != inode->i_mapping->nrpages) shmem_recalc_inode(inode, 0, 0); if (info->fsflags & FS_APPEND_FL) stat->attributes |= STATX_ATTR_APPEND; if (info->fsflags & FS_IMMUTABLE_FL) stat->attributes |= STATX_ATTR_IMMUTABLE; if (info->fsflags & FS_NODUMP_FL) stat->attributes |= STATX_ATTR_NODUMP; stat->attributes_mask |= (STATX_ATTR_APPEND | STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); generic_fillattr(idmap, request_mask, inode, stat); if (shmem_huge_global_enabled(inode, 0, 0, false, NULL, 0)) stat->blksize = HPAGE_PMD_SIZE; if (request_mask & STATX_BTIME) { stat->result_mask |= STATX_BTIME; stat->btime.tv_sec = info->i_crtime.tv_sec; stat->btime.tv_nsec = info->i_crtime.tv_nsec; } return 0; } static int shmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct shmem_inode_info *info = SHMEM_I(inode); int error; bool update_mtime = false; bool update_ctime = true; error = setattr_prepare(idmap, dentry, attr); if (error) return error; if ((info->seals & F_SEAL_EXEC) && (attr->ia_valid & ATTR_MODE)) { if ((inode->i_mode ^ attr->ia_mode) & 0111) { return -EPERM; } } if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { loff_t oldsize = inode->i_size; loff_t newsize = attr->ia_size; /* protected by i_rwsem */ if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) || (newsize > oldsize && (info->seals & F_SEAL_GROW))) return -EPERM; if (newsize != oldsize) { error = shmem_reacct_size(SHMEM_I(inode)->flags, oldsize, newsize); if (error) return error; i_size_write(inode, newsize); update_mtime = true; } else { update_ctime = false; } if (newsize <= oldsize) { loff_t holebegin = round_up(newsize, PAGE_SIZE); if (oldsize > holebegin) unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); if (info->alloced) shmem_truncate_range(inode, newsize, (loff_t)-1); /* unmap again to remove racily COWed private pages */ if (oldsize > holebegin) unmap_mapping_range(inode->i_mapping, holebegin, 0, 1); } } if (is_quota_modification(idmap, inode, attr)) { error = dquot_initialize(inode); if (error) return error; } /* Transfer quota accounting */ if (i_uid_needs_update(idmap, attr, inode) || i_gid_needs_update(idmap, attr, inode)) { error = dquot_transfer(idmap, inode, attr); if (error) return error; } setattr_copy(idmap, inode, attr); if (attr->ia_valid & ATTR_MODE) error = posix_acl_chmod(idmap, dentry, inode->i_mode); if (!error && update_ctime) { inode_set_ctime_current(inode); if (update_mtime) inode_set_mtime_to_ts(inode, inode_get_ctime(inode)); inode_inc_iversion(inode); } return error; } static void shmem_evict_inode(struct inode *inode) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); size_t freed = 0; if (shmem_mapping(inode->i_mapping)) { shmem_unacct_size(info->flags, inode->i_size); inode->i_size = 0; mapping_set_exiting(inode->i_mapping); shmem_truncate_range(inode, 0, (loff_t)-1); if (!list_empty(&info->shrinklist)) { spin_lock(&sbinfo->shrinklist_lock); if (!list_empty(&info->shrinklist)) { list_del_init(&info->shrinklist); sbinfo->shrinklist_len--; } spin_unlock(&sbinfo->shrinklist_lock); } while (!list_empty(&info->swaplist)) { /* Wait while shmem_unuse() is scanning this inode... */ wait_var_event(&info->stop_eviction, !atomic_read(&info->stop_eviction)); spin_lock(&shmem_swaplist_lock); /* ...but beware of the race if we peeked too early */ if (!atomic_read(&info->stop_eviction)) list_del_init(&info->swaplist); spin_unlock(&shmem_swaplist_lock); } } simple_xattrs_free(&info->xattrs, sbinfo->max_inodes ? &freed : NULL); shmem_free_inode(inode->i_sb, freed); WARN_ON(inode->i_blocks); clear_inode(inode); #ifdef CONFIG_TMPFS_QUOTA dquot_free_inode(inode); dquot_drop(inode); #endif } static unsigned int shmem_find_swap_entries(struct address_space *mapping, pgoff_t start, struct folio_batch *fbatch, pgoff_t *indices, unsigned int type) { XA_STATE(xas, &mapping->i_pages, start); struct folio *folio; swp_entry_t entry; rcu_read_lock(); xas_for_each(&xas, folio, ULONG_MAX) { if (xas_retry(&xas, folio)) continue; if (!xa_is_value(folio)) continue; entry = radix_to_swp_entry(folio); /* * swapin error entries can be found in the mapping. But they're * deliberately ignored here as we've done everything we can do. */ if (swp_type(entry) != type) continue; indices[folio_batch_count(fbatch)] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); return folio_batch_count(fbatch); } /* * Move the swapped pages for an inode to page cache. Returns the count * of pages swapped in, or the error in case of failure. */ static int shmem_unuse_swap_entries(struct inode *inode, struct folio_batch *fbatch, pgoff_t *indices) { int i = 0; int ret = 0; int error = 0; struct address_space *mapping = inode->i_mapping; for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; error = shmem_swapin_folio(inode, indices[i], &folio, SGP_CACHE, mapping_gfp_mask(mapping), NULL, NULL); if (error == 0) { folio_unlock(folio); folio_put(folio); ret++; } if (error == -ENOMEM) break; error = 0; } return error ? error : ret; } /* * If swap found in inode, free it and move page from swapcache to filecache. */ static int shmem_unuse_inode(struct inode *inode, unsigned int type) { struct address_space *mapping = inode->i_mapping; pgoff_t start = 0; struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; int ret = 0; do { folio_batch_init(&fbatch); if (!shmem_find_swap_entries(mapping, start, &fbatch, indices, type)) { ret = 0; break; } ret = shmem_unuse_swap_entries(inode, &fbatch, indices); if (ret < 0) break; start = indices[folio_batch_count(&fbatch) - 1]; } while (true); return ret; } /* * Read all the shared memory data that resides in the swap * device 'type' back into memory, so the swap device can be * unused. */ int shmem_unuse(unsigned int type) { struct shmem_inode_info *info, *next; int error = 0; if (list_empty(&shmem_swaplist)) return 0; spin_lock(&shmem_swaplist_lock); start_over: list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) { if (!info->swapped) { list_del_init(&info->swaplist); continue; } /* * Drop the swaplist mutex while searching the inode for swap; * but before doing so, make sure shmem_evict_inode() will not * remove placeholder inode from swaplist, nor let it be freed * (igrab() would protect from unlink, but not from unmount). */ atomic_inc(&info->stop_eviction); spin_unlock(&shmem_swaplist_lock); error = shmem_unuse_inode(&info->vfs_inode, type); cond_resched(); spin_lock(&shmem_swaplist_lock); if (atomic_dec_and_test(&info->stop_eviction)) wake_up_var(&info->stop_eviction); if (error) break; if (list_empty(&info->swaplist)) goto start_over; next = list_next_entry(info, swaplist); if (!info->swapped) list_del_init(&info->swaplist); } spin_unlock(&shmem_swaplist_lock); return error; } /** * shmem_writeout - Write the folio to swap * @folio: The folio to write * @plug: swap plug * @folio_list: list to put back folios on split * * Move the folio from the page cache to the swap cache. */ int shmem_writeout(struct folio *folio, struct swap_iocb **plug, struct list_head *folio_list) { struct address_space *mapping = folio->mapping; struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); pgoff_t index; int nr_pages; bool split = false; if ((info->flags & VM_LOCKED) || sbinfo->noswap) goto redirty; if (!total_swap_pages) goto redirty; /* * If CONFIG_THP_SWAP is not enabled, the large folio should be * split when swapping. * * And shrinkage of pages beyond i_size does not split swap, so * swapout of a large folio crossing i_size needs to split too * (unless fallocate has been used to preallocate beyond EOF). */ if (folio_test_large(folio)) { index = shmem_fallocend(inode, DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE)); if ((index > folio->index && index < folio_next_index(folio)) || !IS_ENABLED(CONFIG_THP_SWAP)) split = true; } if (split) { try_split: /* Ensure the subpages are still dirty */ folio_test_set_dirty(folio); if (split_folio_to_list(folio, folio_list)) goto redirty; folio_clear_dirty(folio); } index = folio->index; nr_pages = folio_nr_pages(folio); /* * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC * value into swapfile.c, the only way we can correctly account for a * fallocated folio arriving here is now to initialize it and write it. * * That's okay for a folio already fallocated earlier, but if we have * not yet completed the fallocation, then (a) we want to keep track * of this folio in case we have to undo it, and (b) it may not be a * good idea to continue anyway, once we're pushing into swap. So * reactivate the folio, and let shmem_fallocate() quit when too many. */ if (!folio_test_uptodate(folio)) { if (inode->i_private) { struct shmem_falloc *shmem_falloc; spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) shmem_falloc->nr_unswapped += nr_pages; else shmem_falloc = NULL; spin_unlock(&inode->i_lock); if (shmem_falloc) goto redirty; } folio_zero_range(folio, 0, folio_size(folio)); flush_dcache_folio(folio); folio_mark_uptodate(folio); } if (!folio_alloc_swap(folio, __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN)) { bool first_swapped = shmem_recalc_inode(inode, 0, nr_pages); int error; /* * Add inode to shmem_unuse()'s list of swapped-out inodes, * if it's not already there. Do it now before the folio is * removed from page cache, when its pagelock no longer * protects the inode from eviction. And do it now, after * we've incremented swapped, because shmem_unuse() will * prune a !swapped inode from the swaplist. */ if (first_swapped) { spin_lock(&shmem_swaplist_lock); if (list_empty(&info->swaplist)) list_add(&info->swaplist, &shmem_swaplist); spin_unlock(&shmem_swaplist_lock); } swap_shmem_alloc(folio->swap, nr_pages); shmem_delete_from_page_cache(folio, swp_to_radix_entry(folio->swap)); BUG_ON(folio_mapped(folio)); error = swap_writeout(folio, plug); if (error != AOP_WRITEPAGE_ACTIVATE) { /* folio has been unlocked */ return error; } /* * The intention here is to avoid holding on to the swap when * zswap was unable to compress and unable to writeback; but * it will be appropriate if other reactivate cases are added. */ error = shmem_add_to_page_cache(folio, mapping, index, swp_to_radix_entry(folio->swap), __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); /* Swap entry might be erased by racing shmem_free_swap() */ if (!error) { shmem_recalc_inode(inode, 0, -nr_pages); swap_free_nr(folio->swap, nr_pages); } /* * The swap_cache_del_folio() below could be left for * shrink_folio_list()'s folio_free_swap() to dispose of; * but I'm a little nervous about letting this folio out of * shmem_writeout() in a hybrid half-tmpfs-half-swap state * e.g. folio_mapping(folio) might give an unexpected answer. */ swap_cache_del_folio(folio); goto redirty; } if (nr_pages > 1) goto try_split; redirty: folio_mark_dirty(folio); return AOP_WRITEPAGE_ACTIVATE; /* Return with folio locked */ } EXPORT_SYMBOL_GPL(shmem_writeout); #if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS) static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { char buffer[64]; if (!mpol || mpol->mode == MPOL_DEFAULT) return; /* show nothing */ mpol_to_str(buffer, sizeof(buffer), mpol); seq_printf(seq, ",mpol=%s", buffer); } static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { struct mempolicy *mpol = NULL; if (sbinfo->mpol) { raw_spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */ mpol = sbinfo->mpol; mpol_get(mpol); raw_spin_unlock(&sbinfo->stat_lock); } return mpol; } #else /* !CONFIG_NUMA || !CONFIG_TMPFS */ static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol) { } static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo) { return NULL; } #endif /* CONFIG_NUMA && CONFIG_TMPFS */ static struct mempolicy *shmem_get_pgoff_policy(struct shmem_inode_info *info, pgoff_t index, unsigned int order, pgoff_t *ilx); static struct folio *shmem_swapin_cluster(swp_entry_t swap, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct mempolicy *mpol; pgoff_t ilx; struct folio *folio; mpol = shmem_get_pgoff_policy(info, index, 0, &ilx); folio = swap_cluster_readahead(swap, gfp, mpol, ilx); mpol_cond_put(mpol); return folio; } /* * Make sure huge_gfp is always more limited than limit_gfp. * Some of the flags set permissions, while others set limitations. */ static gfp_t limit_gfp_mask(gfp_t huge_gfp, gfp_t limit_gfp) { gfp_t allowflags = __GFP_IO | __GFP_FS | __GFP_RECLAIM; gfp_t denyflags = __GFP_NOWARN | __GFP_NORETRY; gfp_t zoneflags = limit_gfp & GFP_ZONEMASK; gfp_t result = huge_gfp & ~(allowflags | GFP_ZONEMASK); /* Allow allocations only from the originally specified zones. */ result |= zoneflags; /* * Minimize the result gfp by taking the union with the deny flags, * and the intersection of the allow flags. */ result |= (limit_gfp & denyflags); result |= (huge_gfp & limit_gfp) & allowflags; return result; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE bool shmem_hpage_pmd_enabled(void) { if (shmem_huge == SHMEM_HUGE_DENY) return false; if (test_bit(HPAGE_PMD_ORDER, &huge_shmem_orders_always)) return true; if (test_bit(HPAGE_PMD_ORDER, &huge_shmem_orders_madvise)) return true; if (test_bit(HPAGE_PMD_ORDER, &huge_shmem_orders_within_size)) return true; if (test_bit(HPAGE_PMD_ORDER, &huge_shmem_orders_inherit) && shmem_huge != SHMEM_HUGE_NEVER) return true; return false; } 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) { unsigned long mask = READ_ONCE(huge_shmem_orders_always); unsigned long within_size_orders = READ_ONCE(huge_shmem_orders_within_size); vm_flags_t vm_flags = vma ? vma->vm_flags : 0; unsigned int global_orders; if (thp_disabled_by_hw() || (vma && vma_thp_disabled(vma, vm_flags, shmem_huge_force))) return 0; global_orders = shmem_huge_global_enabled(inode, index, write_end, shmem_huge_force, vma, vm_flags); /* Tmpfs huge pages allocation */ if (!vma || !vma_is_anon_shmem(vma)) return global_orders; /* * Following the 'deny' semantics of the top level, force the huge * option off from all mounts. */ if (shmem_huge == SHMEM_HUGE_DENY) return 0; /* * Only allow inherit orders if the top-level value is 'force', which * means non-PMD sized THP can not override 'huge' mount option now. */ if (shmem_huge == SHMEM_HUGE_FORCE) return READ_ONCE(huge_shmem_orders_inherit); /* Allow mTHP that will be fully within i_size. */ mask |= shmem_get_orders_within_size(inode, within_size_orders, index, 0); if (vm_flags & VM_HUGEPAGE) mask |= READ_ONCE(huge_shmem_orders_madvise); if (global_orders > 0) mask |= READ_ONCE(huge_shmem_orders_inherit); return THP_ORDERS_ALL_FILE_DEFAULT & mask; } static unsigned long shmem_suitable_orders(struct inode *inode, struct vm_fault *vmf, struct address_space *mapping, pgoff_t index, unsigned long orders) { struct vm_area_struct *vma = vmf ? vmf->vma : NULL; pgoff_t aligned_index; unsigned long pages; int order; if (vma) { orders = thp_vma_suitable_orders(vma, vmf->address, orders); if (!orders) return 0; } /* Find the highest order that can add into the page cache */ order = highest_order(orders); while (orders) { pages = 1UL << order; aligned_index = round_down(index, pages); /* * Check for conflict before waiting on a huge allocation. * Conflict might be that a huge page has just been allocated * and added to page cache by a racing thread, or that there * is already at least one small page in the huge extent. * Be careful to retry when appropriate, but not forever! * Elsewhere -EEXIST would be the right code, but not here. */ if (!xa_find(&mapping->i_pages, &aligned_index, aligned_index + pages - 1, XA_PRESENT)) break; order = next_order(&orders, order); } return orders; } #else static unsigned long shmem_suitable_orders(struct inode *inode, struct vm_fault *vmf, struct address_space *mapping, pgoff_t index, unsigned long orders) { return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static struct folio *shmem_alloc_folio(gfp_t gfp, int order, struct shmem_inode_info *info, pgoff_t index) { struct mempolicy *mpol; pgoff_t ilx; struct folio *folio; mpol = shmem_get_pgoff_policy(info, index, order, &ilx); folio = folio_alloc_mpol(gfp, order, mpol, ilx, numa_node_id()); mpol_cond_put(mpol); return folio; } static struct folio *shmem_alloc_and_add_folio(struct vm_fault *vmf, gfp_t gfp, struct inode *inode, pgoff_t index, struct mm_struct *fault_mm, unsigned long orders) { struct address_space *mapping = inode->i_mapping; struct shmem_inode_info *info = SHMEM_I(inode); unsigned long suitable_orders = 0; struct folio *folio = NULL; long pages; int error, order; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) orders = 0; if (orders > 0) { suitable_orders = shmem_suitable_orders(inode, vmf, mapping, index, orders); order = highest_order(suitable_orders); while (suitable_orders) { pages = 1UL << order; index = round_down(index, pages); folio = shmem_alloc_folio(gfp, order, info, index); if (folio) goto allocated; if (pages == HPAGE_PMD_NR) count_vm_event(THP_FILE_FALLBACK); count_mthp_stat(order, MTHP_STAT_SHMEM_FALLBACK); order = next_order(&suitable_orders, order); } } else { pages = 1; folio = shmem_alloc_folio(gfp, 0, info, index); } if (!folio) return ERR_PTR(-ENOMEM); allocated: __folio_set_locked(folio); __folio_set_swapbacked(folio); gfp &= GFP_RECLAIM_MASK; error = mem_cgroup_charge(folio, fault_mm, gfp); if (error) { if (xa_find(&mapping->i_pages, &index, index + pages - 1, XA_PRESENT)) { error = -EEXIST; } else if (pages > 1) { if (pages == HPAGE_PMD_NR) { count_vm_event(THP_FILE_FALLBACK); count_vm_event(THP_FILE_FALLBACK_CHARGE); } count_mthp_stat(folio_order(folio), MTHP_STAT_SHMEM_FALLBACK); count_mthp_stat(folio_order(folio), MTHP_STAT_SHMEM_FALLBACK_CHARGE); } goto unlock; } error = shmem_add_to_page_cache(folio, mapping, index, NULL, gfp); if (error) goto unlock; error = shmem_inode_acct_blocks(inode, pages); if (error) { struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); long freed; /* * Try to reclaim some space by splitting a few * large folios beyond i_size on the filesystem. */ shmem_unused_huge_shrink(sbinfo, NULL, pages); /* * And do a shmem_recalc_inode() to account for freed pages: * except our folio is there in cache, so not quite balanced. */ spin_lock(&info->lock); freed = pages + info->alloced - info->swapped - READ_ONCE(mapping->nrpages); if (freed > 0) info->alloced -= freed; spin_unlock(&info->lock); if (freed > 0) shmem_inode_unacct_blocks(inode, freed); error = shmem_inode_acct_blocks(inode, pages); if (error) { filemap_remove_folio(folio); goto unlock; } } shmem_recalc_inode(inode, pages, 0); folio_add_lru(folio); return folio; unlock: folio_unlock(folio); folio_put(folio); return ERR_PTR(error); } static struct folio *shmem_swap_alloc_folio(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, swp_entry_t entry, int order, gfp_t gfp) { struct shmem_inode_info *info = SHMEM_I(inode); int nr_pages = 1 << order; struct folio *new; gfp_t alloc_gfp; void *shadow; /* * We have arrived here because our zones are constrained, so don't * limit chance of success with further cpuset and node constraints. */ gfp &= ~GFP_CONSTRAINT_MASK; alloc_gfp = gfp; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (WARN_ON_ONCE(order)) return ERR_PTR(-EINVAL); } else if (order) { /* * If uffd is active for the vma, we need per-page fault * fidelity to maintain the uffd semantics, then fallback * to swapin order-0 folio, as well as for zswap case. * Any existing sub folio in the swap cache also blocks * mTHP swapin. */ if ((vma && unlikely(userfaultfd_armed(vma))) || !zswap_never_enabled() || non_swapcache_batch(entry, nr_pages) != nr_pages) goto fallback; alloc_gfp = limit_gfp_mask(vma_thp_gfp_mask(vma), gfp); } retry: new = shmem_alloc_folio(alloc_gfp, order, info, index); if (!new) { new = ERR_PTR(-ENOMEM); goto fallback; } if (mem_cgroup_swapin_charge_folio(new, vma ? vma->vm_mm : NULL, alloc_gfp, entry)) { folio_put(new); new = ERR_PTR(-ENOMEM); goto fallback; } /* * Prevent parallel swapin from proceeding with the swap cache flag. * * Of course there is another possible concurrent scenario as well, * that is to say, the swap cache flag of a large folio has already * been set by swapcache_prepare(), while another thread may have * already split the large swap entry stored in the shmem mapping. * In this case, shmem_add_to_page_cache() will help identify the * concurrent swapin and return -EEXIST. */ if (swapcache_prepare(entry, nr_pages)) { folio_put(new); new = ERR_PTR(-EEXIST); /* Try smaller folio to avoid cache conflict */ goto fallback; } __folio_set_locked(new); __folio_set_swapbacked(new); new->swap = entry; memcg1_swapin(entry, nr_pages); shadow = swap_cache_get_shadow(entry); if (shadow) workingset_refault(new, shadow); folio_add_lru(new); swap_read_folio(new, NULL); return new; fallback: /* Order 0 swapin failed, nothing to fallback to, abort */ if (!order) return new; entry.val += index - round_down(index, nr_pages); alloc_gfp = gfp; nr_pages = 1; order = 0; goto retry; } /* * When a page is moved from swapcache to shmem filecache (either by the * usual swapin of shmem_get_folio_gfp(), or by the less common swapoff of * shmem_unuse_inode()), it may have been read in earlier from swap, in * ignorance of the mapping it belongs to. If that mapping has special * constraints (like the gma500 GEM driver, which requires RAM below 4GB), * we may need to copy to a suitable page before moving to filecache. * * In a future release, this may well be extended to respect cpuset and * NUMA mempolicy, and applied also to anonymous pages in do_swap_page(); * but for now it is a simple matter of zone. */ static bool shmem_should_replace_folio(struct folio *folio, gfp_t gfp) { return folio_zonenum(folio) > gfp_zone(gfp); } static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index, struct vm_area_struct *vma) { struct swap_cluster_info *ci; struct folio *new, *old = *foliop; swp_entry_t entry = old->swap; int nr_pages = folio_nr_pages(old); int error = 0; /* * We have arrived here because our zones are constrained, so don't * limit chance of success by further cpuset and node constraints. */ gfp &= ~GFP_CONSTRAINT_MASK; #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (nr_pages > 1) { gfp_t huge_gfp = vma_thp_gfp_mask(vma); gfp = limit_gfp_mask(huge_gfp, gfp); } #endif new = shmem_alloc_folio(gfp, folio_order(old), info, index); if (!new) return -ENOMEM; folio_ref_add(new, nr_pages); folio_copy(new, old); flush_dcache_folio(new); __folio_set_locked(new); __folio_set_swapbacked(new); folio_mark_uptodate(new); new->swap = entry; folio_set_swapcache(new); ci = swap_cluster_get_and_lock_irq(old); __swap_cache_replace_folio(ci, old, new); mem_cgroup_replace_folio(old, new); shmem_update_stats(new, nr_pages); shmem_update_stats(old, -nr_pages); swap_cluster_unlock_irq(ci); folio_add_lru(new); *foliop = new; folio_clear_swapcache(old); old->private = NULL; folio_unlock(old); /* * The old folio are removed from swap cache, drop the 'nr_pages' * reference, as well as one temporary reference getting from swap * cache. */ folio_put_refs(old, nr_pages + 1); return error; } static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index, struct folio *folio, swp_entry_t swap, bool skip_swapcache) { struct address_space *mapping = inode->i_mapping; swp_entry_t swapin_error; void *old; int nr_pages; swapin_error = make_poisoned_swp_entry(); old = xa_cmpxchg_irq(&mapping->i_pages, index, swp_to_radix_entry(swap), swp_to_radix_entry(swapin_error), 0); if (old != swp_to_radix_entry(swap)) return; nr_pages = folio_nr_pages(folio); folio_wait_writeback(folio); if (!skip_swapcache) swap_cache_del_folio(folio); /* * Don't treat swapin error folio as alloced. Otherwise inode->i_blocks * won't be 0 when inode is released and thus trigger WARN_ON(i_blocks) * in shmem_evict_inode(). */ shmem_recalc_inode(inode, -nr_pages, -nr_pages); swap_free_nr(swap, nr_pages); } static int shmem_split_large_entry(struct inode *inode, pgoff_t index, swp_entry_t swap, gfp_t gfp) { struct address_space *mapping = inode->i_mapping; XA_STATE_ORDER(xas, &mapping->i_pages, index, 0); int split_order = 0; int i; /* Convert user data gfp flags to xarray node gfp flags */ gfp &= GFP_RECLAIM_MASK; for (;;) { void *old = NULL; int cur_order; pgoff_t swap_index; xas_lock_irq(&xas); old = xas_load(&xas); if (!xa_is_value(old) || swp_to_radix_entry(swap) != old) { xas_set_err(&xas, -EEXIST); goto unlock; } cur_order = xas_get_order(&xas); if (!cur_order) goto unlock; /* Try to split large swap entry in pagecache */ swap_index = round_down(index, 1 << cur_order); split_order = xas_try_split_min_order(cur_order); while (cur_order > 0) { pgoff_t aligned_index = round_down(index, 1 << cur_order); pgoff_t swap_offset = aligned_index - swap_index; xas_set_order(&xas, index, split_order); xas_try_split(&xas, old, cur_order); if (xas_error(&xas)) goto unlock; /* * Re-set the swap entry after splitting, and the swap * offset of the original large entry must be continuous. */ for (i = 0; i < 1 << cur_order; i += (1 << split_order)) { swp_entry_t tmp; tmp = swp_entry(swp_type(swap), swp_offset(swap) + swap_offset + i); __xa_store(&mapping->i_pages, aligned_index + i, swp_to_radix_entry(tmp), 0); } cur_order = split_order; split_order = xas_try_split_min_order(split_order); } unlock: xas_unlock_irq(&xas); if (!xas_nomem(&xas, gfp)) break; } if (xas_error(&xas)) return xas_error(&xas); return 0; } /* * Swap in the folio pointed to by *foliop. * Caller has to make sure that *foliop contains a valid swapped folio. * Returns 0 and the folio in foliop if success. On failure, returns the * error code and NULL in *foliop. */ static int shmem_swapin_folio(struct inode *inode, pgoff_t index, struct folio **foliop, enum sgp_type sgp, gfp_t gfp, struct vm_area_struct *vma, vm_fault_t *fault_type) { struct address_space *mapping = inode->i_mapping; struct mm_struct *fault_mm = vma ? vma->vm_mm : NULL; struct shmem_inode_info *info = SHMEM_I(inode); swp_entry_t swap, index_entry; struct swap_info_struct *si; struct folio *folio = NULL; bool skip_swapcache = false; int error, nr_pages, order; pgoff_t offset; VM_BUG_ON(!*foliop || !xa_is_value(*foliop)); index_entry = radix_to_swp_entry(*foliop); swap = index_entry; *foliop = NULL; if (is_poisoned_swp_entry(index_entry)) return -EIO; si = get_swap_device(index_entry); order = shmem_confirm_swap(mapping, index, index_entry); if (unlikely(!si)) { if (order < 0) return -EEXIST; else return -EINVAL; } if (unlikely(order < 0)) { put_swap_device(si); return -EEXIST; } /* index may point to the middle of a large entry, get the sub entry */ if (order) { offset = index - round_down(index, 1 << order); swap = swp_entry(swp_type(swap), swp_offset(swap) + offset); } /* Look it up and read it in.. */ folio = swap_cache_get_folio(swap); if (!folio) { if (data_race(si->flags & SWP_SYNCHRONOUS_IO)) { /* Direct swapin skipping swap cache & readahead */ folio = shmem_swap_alloc_folio(inode, vma, index, index_entry, order, gfp); if (IS_ERR(folio)) { error = PTR_ERR(folio); folio = NULL; goto failed; } skip_swapcache = true; } else { /* Cached swapin only supports order 0 folio */ folio = shmem_swapin_cluster(swap, gfp, info, index); if (!folio) { error = -ENOMEM; goto failed; } } if (fault_type) { *fault_type |= VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); count_memcg_event_mm(fault_mm, PGMAJFAULT); } } else { swap_update_readahead(folio, NULL, 0); } if (order > folio_order(folio)) { /* * Swapin may get smaller folios due to various reasons: * It may fallback to order 0 due to memory pressure or race, * swap readahead may swap in order 0 folios into swapcache * asynchronously, while the shmem mapping can still stores * large swap entries. In such cases, we should split the * large swap entry to prevent possible data corruption. */ error = shmem_split_large_entry(inode, index, index_entry, gfp); if (error) goto failed_nolock; } /* * If the folio is large, round down swap and index by folio size. * No matter what race occurs, the swap layer ensures we either get * a valid folio that has its swap entry aligned by size, or a * temporarily invalid one which we'll abort very soon and retry. * * shmem_add_to_page_cache ensures the whole range contains expected * entries and prevents any corruption, so any race split is fine * too, it will succeed as long as the entries are still there. */ nr_pages = folio_nr_pages(folio); if (nr_pages > 1) { swap.val = round_down(swap.val, nr_pages); index = round_down(index, nr_pages); } /* * We have to do this with the folio locked to prevent races. * The shmem_confirm_swap below only checks if the first swap * entry matches the folio, that's enough to ensure the folio * is not used outside of shmem, as shmem swap entries * and swap cache folios are never partially freed. */ folio_lock(folio); if ((!skip_swapcache && !folio_test_swapcache(folio)) || shmem_confirm_swap(mapping, index, swap) < 0 || folio->swap.val != swap.val) { error = -EEXIST; goto unlock; } if (!folio_test_uptodate(folio)) { error = -EIO; goto failed; } folio_wait_writeback(folio); /* * Some architectures may have to restore extra metadata to the * folio after reading from swap. */ arch_swap_restore(folio_swap(swap, folio), folio); if (shmem_should_replace_folio(folio, gfp)) { error = shmem_replace_folio(&folio, gfp, info, index, vma); if (error) goto failed; } error = shmem_add_to_page_cache(folio, mapping, index, swp_to_radix_entry(swap), gfp); if (error) goto failed; shmem_recalc_inode(inode, 0, -nr_pages); if (sgp == SGP_WRITE) folio_mark_accessed(folio); if (skip_swapcache) { folio->swap.val = 0; swapcache_clear(si, swap, nr_pages); } else { swap_cache_del_folio(folio); } folio_mark_dirty(folio); swap_free_nr(swap, nr_pages); put_swap_device(si); *foliop = folio; return 0; failed: if (shmem_confirm_swap(mapping, index, swap) < 0) error = -EEXIST; if (error == -EIO) shmem_set_folio_swapin_error(inode, index, folio, swap, skip_swapcache); unlock: if (folio) folio_unlock(folio); failed_nolock: if (skip_swapcache) swapcache_clear(si, folio->swap, folio_nr_pages(folio)); if (folio) folio_put(folio); put_swap_device(si); return error; } /* * shmem_get_folio_gfp - find page in cache, or get from swap, or allocate * * If we allocate a new one we do not mark it dirty. That's up to the * vm. If we swap it in we mark it dirty since we also free the swap * entry since a page cannot live in both the swap and page cache. * * vmf and fault_type are only supplied by shmem_fault: otherwise they are NULL. */ static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index, loff_t write_end, struct folio **foliop, enum sgp_type sgp, gfp_t gfp, struct vm_fault *vmf, vm_fault_t *fault_type) { struct vm_area_struct *vma = vmf ? vmf->vma : NULL; struct mm_struct *fault_mm; struct folio *folio; int error; bool alloced; unsigned long orders = 0; if (WARN_ON_ONCE(!shmem_mapping(inode->i_mapping))) return -EINVAL; if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT)) return -EFBIG; repeat: if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) return -EINVAL; alloced = false; fault_mm = vma ? vma->vm_mm : NULL; folio = filemap_get_entry(inode->i_mapping, index); if (folio && vma && userfaultfd_minor(vma)) { if (!xa_is_value(folio)) folio_put(folio); *fault_type = handle_userfault(vmf, VM_UFFD_MINOR); return 0; } if (xa_is_value(folio)) { error = shmem_swapin_folio(inode, index, &folio, sgp, gfp, vma, fault_type); if (error == -EEXIST) goto repeat; *foliop = folio; return error; } if (folio) { folio_lock(folio); /* Has the folio been truncated or swapped out? */ if (unlikely(folio->mapping != inode->i_mapping)) { folio_unlock(folio); folio_put(folio); goto repeat; } if (sgp == SGP_WRITE) folio_mark_accessed(folio); if (folio_test_uptodate(folio)) goto out; /* fallocated folio */ if (sgp != SGP_READ) goto clear; folio_unlock(folio); folio_put(folio); } /* * SGP_READ: succeed on hole, with NULL folio, letting caller zero. * SGP_NOALLOC: fail on hole, with NULL folio, letting caller fail. */ *foliop = NULL; if (sgp == SGP_READ) return 0; if (sgp == SGP_NOALLOC) return -ENOENT; /* * Fast cache lookup and swap lookup did not find it: allocate. */ if (vma && userfaultfd_missing(vma)) { *fault_type = handle_userfault(vmf, VM_UFFD_MISSING); return 0; } /* Find hugepage orders that are allowed for anonymous shmem and tmpfs. */ orders = shmem_allowable_huge_orders(inode, vma, index, write_end, false); if (orders > 0) { gfp_t huge_gfp; huge_gfp = vma_thp_gfp_mask(vma); huge_gfp = limit_gfp_mask(huge_gfp, gfp); folio = shmem_alloc_and_add_folio(vmf, huge_gfp, inode, index, fault_mm, orders); if (!IS_ERR(folio)) { if (folio_test_pmd_mappable(folio)) count_vm_event(THP_FILE_ALLOC); count_mthp_stat(folio_order(folio), MTHP_STAT_SHMEM_ALLOC); goto alloced; } if (PTR_ERR(folio) == -EEXIST) goto repeat; } folio = shmem_alloc_and_add_folio(vmf, gfp, inode, index, fault_mm, 0); if (IS_ERR(folio)) { error = PTR_ERR(folio); if (error == -EEXIST) goto repeat; folio = NULL; goto unlock; } alloced: alloced = true; if (folio_test_large(folio) && DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE) < folio_next_index(folio)) { struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); struct shmem_inode_info *info = SHMEM_I(inode); /* * Part of the large folio is beyond i_size: subject * to shrink under memory pressure. */ spin_lock(&sbinfo->shrinklist_lock); /* * _careful to defend against unlocked access to * ->shrink_list in shmem_unused_huge_shrink() */ if (list_empty_careful(&info->shrinklist)) { list_add_tail(&info->shrinklist, &sbinfo->shrinklist); sbinfo->shrinklist_len++; } spin_unlock(&sbinfo->shrinklist_lock); } if (sgp == SGP_WRITE) folio_set_referenced(folio); /* * Let SGP_FALLOC use the SGP_WRITE optimization on a new folio. */ if (sgp == SGP_FALLOC) sgp = SGP_WRITE; clear: /* * Let SGP_WRITE caller clear ends if write does not fill folio; * but SGP_FALLOC on a folio fallocated earlier must initialize * it now, lest undo on failure cancel our earlier guarantee. */ if (sgp != SGP_WRITE && !folio_test_uptodate(folio)) { long i, n = folio_nr_pages(folio); for (i = 0; i < n; i++) clear_highpage(folio_page(folio, i)); flush_dcache_folio(folio); folio_mark_uptodate(folio); } /* Perhaps the file has been truncated since we checked */ if (sgp <= SGP_CACHE && ((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) { error = -EINVAL; goto unlock; } out: *foliop = folio; return 0; /* * Error recovery. */ unlock: if (alloced) filemap_remove_folio(folio); shmem_recalc_inode(inode, 0, 0); if (folio) { folio_unlock(folio); folio_put(folio); } return error; } /** * shmem_get_folio - find, and lock a shmem folio. * @inode: inode to search * @index: the page index. * @write_end: end of a write, could extend inode size * @foliop: pointer to the folio if found * @sgp: SGP_* flags to control behavior * * Looks up the page cache entry at @inode & @index. If a folio is * present, it is returned locked with an increased refcount. * * If the caller modifies data in the folio, it must call folio_mark_dirty() * before unlocking the folio to ensure that the folio is not reclaimed. * There is no need to reserve space before calling folio_mark_dirty(). * * When no folio is found, the behavior depends on @sgp: * - for SGP_READ, *@foliop is %NULL and 0 is returned * - for SGP_NOALLOC, *@foliop is %NULL and -ENOENT is returned * - for all other flags a new folio is allocated, inserted into the * page cache and returned locked in @foliop. * * Context: May sleep. * Return: 0 if successful, else a negative error code. */ int shmem_get_folio(struct inode *inode, pgoff_t index, loff_t write_end, struct folio **foliop, enum sgp_type sgp) { return shmem_get_folio_gfp(inode, index, write_end, foliop, sgp, mapping_gfp_mask(inode->i_mapping), NULL, NULL); } EXPORT_SYMBOL_GPL(shmem_get_folio); /* * This is like autoremove_wake_function, but it removes the wait queue * entry unconditionally - even if something else had already woken the * target. */ static int synchronous_wake_function(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key) { int ret = default_wake_function(wait, mode, sync, key); list_del_init(&wait->entry); return ret; } /* * Trinity finds that probing a hole which tmpfs is punching can * prevent the hole-punch from ever completing: which in turn * locks writers out with its hold on i_rwsem. So refrain from * faulting pages into the hole while it's being punched. Although * shmem_undo_range() does remove the additions, it may be unable to * keep up, as each new page needs its own unmap_mapping_range() call, * and the i_mmap tree grows ever slower to scan if new vmas are added. * * It does not matter if we sometimes reach this check just before the * hole-punch begins, so that one fault then races with the punch: * we just need to make racing faults a rare case. * * The implementation below would be much simpler if we just used a * standard mutex or completion: but we cannot take i_rwsem in fault, * and bloating every shmem inode for this unlikely case would be sad. */ static vm_fault_t shmem_falloc_wait(struct vm_fault *vmf, struct inode *inode) { struct shmem_falloc *shmem_falloc; struct file *fpin = NULL; vm_fault_t ret = 0; spin_lock(&inode->i_lock); shmem_falloc = inode->i_private; if (shmem_falloc && shmem_falloc->waitq && vmf->pgoff >= shmem_falloc->start && vmf->pgoff < shmem_falloc->next) { wait_queue_head_t *shmem_falloc_waitq; DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function); ret = VM_FAULT_NOPAGE; fpin = maybe_unlock_mmap_for_io(vmf, NULL); shmem_falloc_waitq = shmem_falloc->waitq; prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); schedule(); /* * shmem_falloc_waitq points into the shmem_fallocate() * stack of the hole-punching task: shmem_falloc_waitq * is usually invalid by the time we reach here, but * finish_wait() does not dereference it in that case; * though i_lock needed lest racing with wake_up_all(). */ spin_lock(&inode->i_lock); finish_wait(shmem_falloc_waitq, &shmem_fault_wait); } spin_unlock(&inode->i_lock); if (fpin) { fput(fpin); ret = VM_FAULT_RETRY; } return ret; } static vm_fault_t shmem_fault(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); gfp_t gfp = mapping_gfp_mask(inode->i_mapping); struct folio *folio = NULL; vm_fault_t ret = 0; int err; /* * Trinity finds that probing a hole which tmpfs is punching can * prevent the hole-punch from ever completing: noted in i_private. */ if (unlikely(inode->i_private)) { ret = shmem_falloc_wait(vmf, inode); if (ret) return ret; } WARN_ON_ONCE(vmf->page != NULL); err = shmem_get_folio_gfp(inode, vmf->pgoff, 0, &folio, SGP_CACHE, gfp, vmf, &ret); if (err) return vmf_error(err); if (folio) { vmf->page = folio_file_page(folio, vmf->pgoff); ret |= VM_FAULT_LOCKED; } return ret; } unsigned long shmem_get_unmapped_area(struct file *file, unsigned long uaddr, unsigned long len, unsigned long pgoff, unsigned long flags) { unsigned long addr; unsigned long offset; unsigned long inflated_len; unsigned long inflated_addr; unsigned long inflated_offset; unsigned long hpage_size; if (len > TASK_SIZE) return -ENOMEM; addr = mm_get_unmapped_area(current->mm, file, uaddr, len, pgoff, flags); if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return addr; if (IS_ERR_VALUE(addr)) return addr; if (addr & ~PAGE_MASK) return addr; if (addr > TASK_SIZE - len) return addr; if (shmem_huge == SHMEM_HUGE_DENY) return addr; if (flags & MAP_FIXED) return addr; /* * Our priority is to support MAP_SHARED mapped hugely; * and support MAP_PRIVATE mapped hugely too, until it is COWed. * But if caller specified an address hint and we allocated area there * successfully, respect that as before. */ if (uaddr == addr) return addr; hpage_size = HPAGE_PMD_SIZE; if (shmem_huge != SHMEM_HUGE_FORCE) { struct super_block *sb; unsigned long __maybe_unused hpage_orders; int order = 0; if (file) { VM_BUG_ON(file->f_op != &shmem_file_operations); sb = file_inode(file)->i_sb; } else { /* * Called directly from mm/mmap.c, or drivers/char/mem.c * for "/dev/zero", to create a shared anonymous object. */ if (IS_ERR(shm_mnt)) return addr; sb = shm_mnt->mnt_sb; /* * Find the highest mTHP order used for anonymous shmem to * provide a suitable alignment address. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE hpage_orders = READ_ONCE(huge_shmem_orders_always); hpage_orders |= READ_ONCE(huge_shmem_orders_within_size); hpage_orders |= READ_ONCE(huge_shmem_orders_madvise); if (SHMEM_SB(sb)->huge != SHMEM_HUGE_NEVER) hpage_orders |= READ_ONCE(huge_shmem_orders_inherit); if (hpage_orders > 0) { order = highest_order(hpage_orders); hpage_size = PAGE_SIZE << order; } #endif } if (SHMEM_SB(sb)->huge == SHMEM_HUGE_NEVER && !order) return addr; } if (len < hpage_size) return addr; offset = (pgoff << PAGE_SHIFT) & (hpage_size - 1); if (offset && offset + len < 2 * hpage_size) return addr; if ((addr & (hpage_size - 1)) == offset) return addr; inflated_len = len + hpage_size - PAGE_SIZE; if (inflated_len > TASK_SIZE) return addr; if (inflated_len < len) return addr; inflated_addr = mm_get_unmapped_area(current->mm, NULL, uaddr, inflated_len, 0, flags); if (IS_ERR_VALUE(inflated_addr)) return addr; if (inflated_addr & ~PAGE_MASK) return addr; inflated_offset = inflated_addr & (hpage_size - 1); inflated_addr += offset - inflated_offset; if (inflated_offset > offset) inflated_addr += hpage_size; if (inflated_addr > TASK_SIZE - len) return addr; return inflated_addr; } #ifdef CONFIG_NUMA static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol) { struct inode *inode = file_inode(vma->vm_file); return mpol_set_shared_policy(&SHMEM_I(inode)->policy, vma, mpol); } static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx) { struct inode *inode = file_inode(vma->vm_file); pgoff_t index; /* * Bias interleave by inode number to distribute better across nodes; * but this interface is independent of which page order is used, so * supplies only that bias, letting caller apply the offset (adjusted * by page order, as in shmem_get_pgoff_policy() and get_vma_policy()). */ *ilx = inode->i_ino; index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; return mpol_shared_policy_lookup(&SHMEM_I(inode)->policy, index); } static struct mempolicy *shmem_get_pgoff_policy(struct shmem_inode_info *info, pgoff_t index, unsigned int order, pgoff_t *ilx) { struct mempolicy *mpol; /* Bias interleave by inode number to distribute better across nodes */ *ilx = info->vfs_inode.i_ino + (index >> order); mpol = mpol_shared_policy_lookup(&info->policy, index); return mpol ? mpol : get_task_policy(current); } #else static struct mempolicy *shmem_get_pgoff_policy(struct shmem_inode_info *info, pgoff_t index, unsigned int order, pgoff_t *ilx) { *ilx = 0; return NULL; } #endif /* CONFIG_NUMA */ int shmem_lock(struct file *file, int lock, struct ucounts *ucounts) { struct inode *inode = file_inode(file); struct shmem_inode_info *info = SHMEM_I(inode); int retval = -ENOMEM; /* * What serializes the accesses to info->flags? * ipc_lock_object() when called from shmctl_do_lock(), * no serialization needed when called from shm_destroy(). */ if (lock && !(info->flags & VM_LOCKED)) { if (!user_shm_lock(inode->i_size, ucounts)) goto out_nomem; info->flags |= VM_LOCKED; mapping_set_unevictable(file->f_mapping); } if (!lock && (info->flags & VM_LOCKED) && ucounts) { user_shm_unlock(inode->i_size, ucounts); info->flags &= ~VM_LOCKED; mapping_clear_unevictable(file->f_mapping); } retval = 0; out_nomem: return retval; } static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); file_accessed(file); /* This is anonymous shared memory if it is unlinked at the time of mmap */ if (inode->i_nlink) vma->vm_ops = &shmem_vm_ops; else vma->vm_ops = &shmem_anon_vm_ops; return 0; } static int shmem_file_open(struct inode *inode, struct file *file) { file->f_mode |= FMODE_CAN_ODIRECT; return generic_file_open(inode, file); } #ifdef CONFIG_TMPFS_XATTR static int shmem_initxattrs(struct inode *, const struct xattr *, void *); #if IS_ENABLED(CONFIG_UNICODE) /* * shmem_inode_casefold_flags - Deal with casefold file attribute flag * * The casefold file attribute needs some special checks. I can just be added to * an empty dir, and can't be removed from a non-empty dir. */ static int shmem_inode_casefold_flags(struct inode *inode, unsigned int fsflags, struct dentry *dentry, unsigned int *i_flags) { unsigned int old = inode->i_flags; struct super_block *sb = inode->i_sb; if (fsflags & FS_CASEFOLD_FL) { if (!(old & S_CASEFOLD)) { if (!sb->s_encoding) return -EOPNOTSUPP; if (!S_ISDIR(inode->i_mode)) return -ENOTDIR; if (dentry && !simple_empty(dentry)) return -ENOTEMPTY; } *i_flags = *i_flags | S_CASEFOLD; } else if (old & S_CASEFOLD) { if (dentry && !simple_empty(dentry)) return -ENOTEMPTY; } return 0; } #else static int shmem_inode_casefold_flags(struct inode *inode, unsigned int fsflags, struct dentry *dentry, unsigned int *i_flags) { if (fsflags & FS_CASEFOLD_FL) return -EOPNOTSUPP; return 0; } #endif /* * chattr's fsflags are unrelated to extended attributes, * but tmpfs has chosen to enable them under the same config option. */ static int shmem_set_inode_flags(struct inode *inode, unsigned int fsflags, struct dentry *dentry) { unsigned int i_flags = 0; int ret; ret = shmem_inode_casefold_flags(inode, fsflags, dentry, &i_flags); if (ret) return ret; if (fsflags & FS_NOATIME_FL) i_flags |= S_NOATIME; if (fsflags & FS_APPEND_FL) i_flags |= S_APPEND; if (fsflags & FS_IMMUTABLE_FL) i_flags |= S_IMMUTABLE; /* * But FS_NODUMP_FL does not require any action in i_flags. */ inode_set_flags(inode, i_flags, S_NOATIME | S_APPEND | S_IMMUTABLE | S_CASEFOLD); return 0; } #else static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags, struct dentry *dentry) { } #define shmem_initxattrs NULL #endif static struct offset_ctx *shmem_get_offset_ctx(struct inode *inode) { return &SHMEM_I(inode)->dir_offsets; } static struct inode *__shmem_get_inode(struct mnt_idmap *idmap, struct super_block *sb, struct inode *dir, umode_t mode, dev_t dev, unsigned long flags) { struct inode *inode; struct shmem_inode_info *info; struct shmem_sb_info *sbinfo = SHMEM_SB(sb); ino_t ino; int err; err = shmem_reserve_inode(sb, &ino); if (err) return ERR_PTR(err); inode = new_inode(sb); if (!inode) { shmem_free_inode(sb, 0); return ERR_PTR(-ENOSPC); } inode->i_ino = ino; inode_init_owner(idmap, inode, dir, mode); inode->i_blocks = 0; simple_inode_init_ts(inode); inode->i_generation = get_random_u32(); info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); atomic_set(&info->stop_eviction, 0); info->seals = F_SEAL_SEAL; info->flags = flags & VM_NORESERVE; info->i_crtime = inode_get_mtime(inode); info->fsflags = (dir == NULL) ? 0 : SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED; if (info->fsflags) shmem_set_inode_flags(inode, info->fsflags, NULL); INIT_LIST_HEAD(&info->shrinklist); INIT_LIST_HEAD(&info->swaplist); simple_xattrs_init(&info->xattrs); cache_no_acl(inode); if (sbinfo->noswap) mapping_set_unevictable(inode->i_mapping); /* Don't consider 'deny' for emergencies and 'force' for testing */ if (sbinfo->huge) mapping_set_large_folios(inode->i_mapping); switch (mode & S_IFMT) { default: inode->i_op = &shmem_special_inode_operations; init_special_inode(inode, mode, dev); break; case S_IFREG: inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_inode_operations; inode->i_fop = &shmem_file_operations; mpol_shared_policy_init(&info->policy, shmem_get_sbmpol(sbinfo)); break; case S_IFDIR: inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ inode->i_size = 2 * BOGO_DIRENT_SIZE; inode->i_op = &shmem_dir_inode_operations; inode->i_fop = &simple_offset_dir_operations; simple_offset_init(shmem_get_offset_ctx(inode)); break; case S_IFLNK: /* * Must not load anything in the rbtree, * mpol_free_shared_policy will not be called. */ mpol_shared_policy_init(&info->policy, NULL); break; } lockdep_annotate_inode_mutex_key(inode); return inode; } #ifdef CONFIG_TMPFS_QUOTA static struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block *sb, struct inode *dir, umode_t mode, dev_t dev, unsigned long flags) { int err; struct inode *inode; inode = __shmem_get_inode(idmap, sb, dir, mode, dev, flags); if (IS_ERR(inode)) return inode; err = dquot_initialize(inode); if (err) goto errout; err = dquot_alloc_inode(inode); if (err) { dquot_drop(inode); goto errout; } return inode; errout: inode->i_flags |= S_NOQUOTA; iput(inode); return ERR_PTR(err); } #else static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block *sb, struct inode *dir, umode_t mode, dev_t dev, unsigned long flags) { return __shmem_get_inode(idmap, sb, dir, mode, dev, flags); } #endif /* CONFIG_TMPFS_QUOTA */ #ifdef CONFIG_USERFAULTFD 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) { struct inode *inode = file_inode(dst_vma->vm_file); struct shmem_inode_info *info = SHMEM_I(inode); struct address_space *mapping = inode->i_mapping; gfp_t gfp = mapping_gfp_mask(mapping); pgoff_t pgoff = linear_page_index(dst_vma, dst_addr); void *page_kaddr; struct folio *folio; int ret; pgoff_t max_off; if (shmem_inode_acct_blocks(inode, 1)) { /* * We may have got a page, returned -ENOENT triggering a retry, * and now we find ourselves with -ENOMEM. Release the page, to * avoid a BUG_ON in our caller. */ if (unlikely(*foliop)) { folio_put(*foliop); *foliop = NULL; } return -ENOMEM; } if (!*foliop) { ret = -ENOMEM; folio = shmem_alloc_folio(gfp, 0, info, pgoff); if (!folio) goto out_unacct_blocks; if (uffd_flags_mode_is(flags, MFILL_ATOMIC_COPY)) { page_kaddr = kmap_local_folio(folio, 0); /* * The read mmap_lock is held here. Despite the * mmap_lock being read recursive a deadlock is still * possible if a writer has taken a lock. For example: * * process A thread 1 takes read lock on own mmap_lock * process A thread 2 calls mmap, blocks taking write lock * process B thread 1 takes page fault, read lock on own mmap lock * process B thread 2 calls mmap, blocks taking write lock * process A thread 1 blocks taking read lock on process B * process B thread 1 blocks taking read lock on process A * * Disable page faults to prevent potential deadlock * and retry the copy outside the mmap_lock. */ pagefault_disable(); ret = copy_from_user(page_kaddr, (const void __user *)src_addr, PAGE_SIZE); pagefault_enable(); kunmap_local(page_kaddr); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { *foliop = folio; ret = -ENOENT; /* don't free the page */ goto out_unacct_blocks; } flush_dcache_folio(folio); } else { /* ZEROPAGE */ clear_user_highpage(&folio->page, dst_addr); } } else { folio = *foliop; VM_BUG_ON_FOLIO(folio_test_large(folio), folio); *foliop = NULL; } VM_BUG_ON(folio_test_locked(folio)); VM_BUG_ON(folio_test_swapbacked(folio)); __folio_set_locked(folio); __folio_set_swapbacked(folio); __folio_mark_uptodate(folio); ret = -EFAULT; max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(pgoff >= max_off)) goto out_release; ret = mem_cgroup_charge(folio, dst_vma->vm_mm, gfp); if (ret) goto out_release; ret = shmem_add_to_page_cache(folio, mapping, pgoff, NULL, gfp); if (ret) goto out_release; ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr, &folio->page, true, flags); if (ret) goto out_delete_from_cache; shmem_recalc_inode(inode, 1, 0); folio_unlock(folio); return 0; out_delete_from_cache: filemap_remove_folio(folio); out_release: folio_unlock(folio); folio_put(folio); out_unacct_blocks: shmem_inode_unacct_blocks(inode, 1); return ret; } #endif /* CONFIG_USERFAULTFD */ #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; static int shmem_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t index = pos >> PAGE_SHIFT; struct folio *folio; int ret = 0; /* i_rwsem is held by caller */ if (unlikely(info->seals & (F_SEAL_GROW | F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))) { if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) return -EPERM; if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size) return -EPERM; } ret = shmem_get_folio(inode, index, pos + len, &folio, SGP_WRITE); if (ret) return ret; if (folio_contain_hwpoisoned_page(folio)) { folio_unlock(folio); folio_put(folio); return -EIO; } *foliop = folio; return 0; } static int shmem_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; if (pos + copied > inode->i_size) i_size_write(inode, pos + copied); if (!folio_test_uptodate(folio)) { if (copied < folio_size(folio)) { size_t from = offset_in_folio(folio, pos); folio_zero_segments(folio, 0, from, from + copied, folio_size(folio)); } folio_mark_uptodate(folio); } folio_mark_dirty(folio); folio_unlock(folio); folio_put(folio); return copied; } static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; pgoff_t index; unsigned long offset; int error = 0; ssize_t retval = 0; for (;;) { struct folio *folio = NULL; struct page *page = NULL; unsigned long nr, ret; loff_t end_offset, i_size = i_size_read(inode); bool fallback_page_copy = false; size_t fsize; if (unlikely(iocb->ki_pos >= i_size)) break; index = iocb->ki_pos >> PAGE_SHIFT; error = shmem_get_folio(inode, index, 0, &folio, SGP_READ); if (error) { if (error == -EINVAL) error = 0; break; } if (folio) { folio_unlock(folio); page = folio_file_page(folio, index); if (PageHWPoison(page)) { folio_put(folio); error = -EIO; break; } if (folio_test_large(folio) && folio_test_has_hwpoisoned(folio)) fallback_page_copy = true; } /* * We must evaluate after, since reads (unlike writes) * are called without i_rwsem protection against truncate */ i_size = i_size_read(inode); if (unlikely(iocb->ki_pos >= i_size)) { if (folio) folio_put(folio); break; } end_offset = min_t(loff_t, i_size, iocb->ki_pos + to->count); if (folio && likely(!fallback_page_copy)) fsize = folio_size(folio); else fsize = PAGE_SIZE; offset = iocb->ki_pos & (fsize - 1); nr = min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset); if (folio) { /* * If users can be writing to this page using arbitrary * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ if (mapping_writably_mapped(mapping)) { if (likely(!fallback_page_copy)) flush_dcache_folio(folio); else flush_dcache_page(page); } /* * Mark the folio accessed if we read the beginning. */ if (!offset) folio_mark_accessed(folio); /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... */ if (likely(!fallback_page_copy)) ret = copy_folio_to_iter(folio, offset, nr, to); else ret = copy_page_to_iter(page, offset, nr, to); folio_put(folio); } else if (user_backed_iter(to)) { /* * Copy to user tends to be so well optimized, but * clear_user() not so much, that it is noticeably * faster to copy the zero page instead of clearing. */ ret = copy_page_to_iter(ZERO_PAGE(0), offset, nr, to); } else { /* * But submitting the same page twice in a row to * splice() - or others? - can result in confusion: * so don't attempt that optimization on pipes etc. */ ret = iov_iter_zero(nr, to); } retval += ret; iocb->ki_pos += ret; if (!iov_iter_count(to)) break; if (ret < nr) { error = -EFAULT; break; } cond_resched(); } file_accessed(file); return retval ? retval : error; } static ssize_t shmem_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret <= 0) goto unlock; ret = file_remove_privs(file); if (ret) goto unlock; ret = file_update_time(file); if (ret) goto unlock; ret = generic_perform_write(iocb, from); unlock: inode_unlock(inode); return ret; } static bool zero_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return true; } static void zero_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { } static bool zero_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return false; } static const struct pipe_buf_operations zero_pipe_buf_ops = { .release = zero_pipe_buf_release, .try_steal = zero_pipe_buf_try_steal, .get = zero_pipe_buf_get, }; static size_t splice_zeropage_into_pipe(struct pipe_inode_info *pipe, loff_t fpos, size_t size) { size_t offset = fpos & ~PAGE_MASK; size = min_t(size_t, size, PAGE_SIZE - offset); if (!pipe_is_full(pipe)) { struct pipe_buffer *buf = pipe_head_buf(pipe); *buf = (struct pipe_buffer) { .ops = &zero_pipe_buf_ops, .page = ZERO_PAGE(0), .offset = offset, .len = size, }; pipe->head++; } return size; } static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct inode *inode = file_inode(in); struct address_space *mapping = inode->i_mapping; struct folio *folio = NULL; size_t total_spliced = 0, used, npages, n, part; loff_t isize; int error = 0; /* Work out how much data we can actually add into the pipe */ used = pipe_buf_usage(pipe); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); do { bool fallback_page_splice = false; struct page *page = NULL; pgoff_t index; size_t size; if (*ppos >= i_size_read(inode)) break; index = *ppos >> PAGE_SHIFT; error = shmem_get_folio(inode, index, 0, &folio, SGP_READ); if (error) { if (error == -EINVAL) error = 0; break; } if (folio) { folio_unlock(folio); page = folio_file_page(folio, index); if (PageHWPoison(page)) { error = -EIO; break; } if (folio_test_large(folio) && folio_test_has_hwpoisoned(folio)) fallback_page_splice = true; } /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); if (unlikely(*ppos >= isize)) break; /* * Fallback to PAGE_SIZE splice if the large folio has hwpoisoned * pages. */ size = len; if (unlikely(fallback_page_splice)) { size_t offset = *ppos & ~PAGE_MASK; size = umin(size, PAGE_SIZE - offset); } part = min_t(loff_t, isize - *ppos, size); if (folio) { /* * If users can be writing to this page using arbitrary * virtual addresses, take care about potential aliasing * before reading the page on the kernel side. */ if (mapping_writably_mapped(mapping)) { if (likely(!fallback_page_splice)) flush_dcache_folio(folio); else flush_dcache_page(page); } folio_mark_accessed(folio); /* * Ok, we have the page, and it's up-to-date, so we can * now splice it into the pipe. */ n = splice_folio_into_pipe(pipe, folio, *ppos, part); folio_put(folio); folio = NULL; } else { n = splice_zeropage_into_pipe(pipe, *ppos, part); } if (!n) break; len -= n; total_spliced += n; *ppos += n; in->f_ra.prev_pos = *ppos; if (pipe_is_full(pipe)) break; cond_resched(); } while (len); if (folio) folio_put(folio); file_accessed(in); return total_spliced ? total_spliced : error; } static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) { struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; if (whence != SEEK_DATA && whence != SEEK_HOLE) return generic_file_llseek_size(file, offset, whence, MAX_LFS_FILESIZE, i_size_read(inode)); if (offset < 0) return -ENXIO; inode_lock(inode); /* We're holding i_rwsem so we can access i_size directly */ offset = mapping_seek_hole_data(mapping, offset, inode->i_size, whence); if (offset >= 0) offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE); inode_unlock(inode); return offset; } static long shmem_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_falloc shmem_falloc; pgoff_t start, index, end, undo_fallocend; int error; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; inode_lock(inode); if (mode & FALLOC_FL_PUNCH_HOLE) { struct address_space *mapping = file->f_mapping; loff_t unmap_start = round_up(offset, PAGE_SIZE); loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1; DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq); /* protected by i_rwsem */ if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { error = -EPERM; goto out; } shmem_falloc.waitq = &shmem_falloc_waitq; shmem_falloc.start = (u64)unmap_start >> PAGE_SHIFT; shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT; spin_lock(&inode->i_lock); inode->i_private = &shmem_falloc; spin_unlock(&inode->i_lock); if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); shmem_truncate_range(inode, offset, offset + len - 1); /* No need to unmap again: hole-punching leaves COWed pages */ spin_lock(&inode->i_lock); inode->i_private = NULL; wake_up_all(&shmem_falloc_waitq); WARN_ON_ONCE(!list_empty(&shmem_falloc_waitq.head)); spin_unlock(&inode->i_lock); error = 0; goto out; } /* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */ error = inode_newsize_ok(inode, offset + len); if (error) goto out; if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) { error = -EPERM; goto out; } start = offset >> PAGE_SHIFT; end = (offset + len + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Try to avoid a swapstorm if len is impossible to satisfy */ if (sbinfo->max_blocks && end - start > sbinfo->max_blocks) { error = -ENOSPC; goto out; } shmem_falloc.waitq = NULL; shmem_falloc.start = start; shmem_falloc.next = start; shmem_falloc.nr_falloced = 0; shmem_falloc.nr_unswapped = 0; spin_lock(&inode->i_lock); inode->i_private = &shmem_falloc; spin_unlock(&inode->i_lock); /* * info->fallocend is only relevant when huge pages might be * involved: to prevent split_huge_page() freeing fallocated * pages when FALLOC_FL_KEEP_SIZE committed beyond i_size. */ undo_fallocend = info->fallocend; if (info->fallocend < end) info->fallocend = end; for (index = start; index < end; ) { struct folio *folio; /* * Check for fatal signal so that we abort early in OOM * situations. We don't want to abort in case of non-fatal * signals as large fallocate can take noticeable time and * e.g. periodic timers may result in fallocate constantly * restarting. */ if (fatal_signal_pending(current)) error = -EINTR; else if (shmem_falloc.nr_unswapped > shmem_falloc.nr_falloced) error = -ENOMEM; else error = shmem_get_folio(inode, index, offset + len, &folio, SGP_FALLOC); if (error) { info->fallocend = undo_fallocend; /* Remove the !uptodate folios we added */ if (index > start) { shmem_undo_range(inode, (loff_t)start << PAGE_SHIFT, ((loff_t)index << PAGE_SHIFT) - 1, true); } goto undone; } /* * Here is a more important optimization than it appears: * a second SGP_FALLOC on the same large folio will clear it, * making it uptodate and un-undoable if we fail later. */ index = folio_next_index(folio); /* Beware 32-bit wraparound */ if (!index) index--; /* * Inform shmem_writeout() how far we have reached. * No need for lock or barrier: we have the page lock. */ if (!folio_test_uptodate(folio)) shmem_falloc.nr_falloced += index - shmem_falloc.next; shmem_falloc.next = index; /* * If !uptodate, leave it that way so that freeable folios * can be recognized if we need to rollback on error later. * But mark it dirty so that memory pressure will swap rather * than free the folios we are allocating (and SGP_CACHE folios * might still be clean: we now need to mark those dirty too). */ folio_mark_dirty(folio); folio_unlock(folio); folio_put(folio); cond_resched(); } if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); undone: spin_lock(&inode->i_lock); inode->i_private = NULL; spin_unlock(&inode->i_lock); out: if (!error) file_modified(file); inode_unlock(inode); return error; } static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) { struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb); buf->f_type = TMPFS_MAGIC; buf->f_bsize = PAGE_SIZE; buf->f_namelen = NAME_MAX; if (sbinfo->max_blocks) { buf->f_blocks = sbinfo->max_blocks; buf->f_bavail = buf->f_bfree = sbinfo->max_blocks - percpu_counter_sum(&sbinfo->used_blocks); } if (sbinfo->max_inodes) { buf->f_files = sbinfo->max_inodes; buf->f_ffree = sbinfo->free_ispace / BOGO_INODE_SIZE; } /* else leave those fields 0 like simple_statfs */ buf->f_fsid = uuid_to_fsid(dentry->d_sb->s_uuid.b); return 0; } /* * File creation. Allocate an inode, and we're done.. */ static int shmem_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { struct inode *inode; int error; if (!generic_ci_validate_strict_name(dir, &dentry->d_name)) return -EINVAL; inode = shmem_get_inode(idmap, dir->i_sb, dir, mode, dev, VM_NORESERVE); if (IS_ERR(inode)) return PTR_ERR(inode); error = simple_acl_create(dir, inode); if (error) goto out_iput; error = security_inode_init_security(inode, dir, &dentry->d_name, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) goto out_iput; error = simple_offset_add(shmem_get_offset_ctx(dir), dentry); if (error) goto out_iput; dir->i_size += BOGO_DIRENT_SIZE; inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); inode_inc_iversion(dir); if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir)) d_add(dentry, inode); else d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ return error; out_iput: iput(inode); return error; } static int shmem_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct inode *inode; int error; inode = shmem_get_inode(idmap, dir->i_sb, dir, mode, 0, VM_NORESERVE); if (IS_ERR(inode)) { error = PTR_ERR(inode); goto err_out; } error = security_inode_init_security(inode, dir, NULL, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) goto out_iput; error = simple_acl_create(dir, inode); if (error) goto out_iput; d_tmpfile(file, inode); err_out: return finish_open_simple(file, error); out_iput: iput(inode); return error; } static struct dentry *shmem_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int error; error = shmem_mknod(idmap, dir, dentry, mode | S_IFDIR, 0); if (error) return ERR_PTR(error); inc_nlink(dir); return NULL; } static int shmem_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return shmem_mknod(idmap, dir, dentry, mode | S_IFREG, 0); } /* * Link a file.. */ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); int ret = 0; /* * No ordinary (disk based) filesystem counts links as inodes; * but each new link needs a new dentry, pinning lowmem, and * tmpfs dentries cannot be pruned until they are unlinked. * But if an O_TMPFILE file is linked into the tmpfs, the * first link must skip that, to get the accounting right. */ if (inode->i_nlink) { ret = shmem_reserve_inode(inode->i_sb, NULL); if (ret) goto out; } ret = simple_offset_add(shmem_get_offset_ctx(dir), dentry); if (ret) { if (inode->i_nlink) shmem_free_inode(inode->i_sb, 0); goto out; } dir->i_size += BOGO_DIRENT_SIZE; inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); inode_inc_iversion(dir); inc_nlink(inode); ihold(inode); /* New dentry reference */ dget(dentry); /* Extra pinning count for the created dentry */ if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir)) d_add(dentry, inode); else d_instantiate(dentry, inode); out: return ret; } static int shmem_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) shmem_free_inode(inode->i_sb, 0); simple_offset_remove(shmem_get_offset_ctx(dir), dentry); dir->i_size -= BOGO_DIRENT_SIZE; inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); inode_inc_iversion(dir); drop_nlink(inode); dput(dentry); /* Undo the count from "create" - does all the work */ /* * For now, VFS can't deal with case-insensitive negative dentries, so * we invalidate them */ if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir)) d_invalidate(dentry); return 0; } static int shmem_rmdir(struct inode *dir, struct dentry *dentry) { if (!simple_empty(dentry)) return -ENOTEMPTY; drop_nlink(d_inode(dentry)); drop_nlink(dir); return shmem_unlink(dir, dentry); } static int shmem_whiteout(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry) { struct dentry *whiteout; int error; whiteout = d_alloc(old_dentry->d_parent, &old_dentry->d_name); if (!whiteout) return -ENOMEM; error = shmem_mknod(idmap, old_dir, whiteout, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); dput(whiteout); if (error) return error; /* * Cheat and hash the whiteout while the old dentry is still in * place, instead of playing games with FS_RENAME_DOES_D_MOVE. * * d_lookup() will consistently find one of them at this point, * not sure which one, but that isn't even important. */ d_rehash(whiteout); return 0; } /* * The VFS layer already does all the dentry stuff for rename, * we just have to decrement the usage count for the target if * it exists so that the VFS layer correctly free's it when it * gets overwritten. */ static int shmem_rename2(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *inode = d_inode(old_dentry); int they_are_dirs = S_ISDIR(inode->i_mode); int error; if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT)) return -EINVAL; if (flags & RENAME_EXCHANGE) return simple_offset_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); if (!simple_empty(new_dentry)) return -ENOTEMPTY; if (flags & RENAME_WHITEOUT) { error = shmem_whiteout(idmap, old_dir, old_dentry); if (error) return error; } error = simple_offset_rename(old_dir, old_dentry, new_dir, new_dentry); if (error) return error; if (d_really_is_positive(new_dentry)) { (void) shmem_unlink(new_dir, new_dentry); if (they_are_dirs) { drop_nlink(d_inode(new_dentry)); drop_nlink(old_dir); } } else if (they_are_dirs) { drop_nlink(old_dir); inc_nlink(new_dir); } old_dir->i_size -= BOGO_DIRENT_SIZE; new_dir->i_size += BOGO_DIRENT_SIZE; simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); inode_inc_iversion(old_dir); inode_inc_iversion(new_dir); return 0; } static int shmem_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { int error; int len; struct inode *inode; struct folio *folio; char *link; len = strlen(symname) + 1; if (len > PAGE_SIZE) return -ENAMETOOLONG; inode = shmem_get_inode(idmap, dir->i_sb, dir, S_IFLNK | 0777, 0, VM_NORESERVE); if (IS_ERR(inode)) return PTR_ERR(inode); error = security_inode_init_security(inode, dir, &dentry->d_name, shmem_initxattrs, NULL); if (error && error != -EOPNOTSUPP) goto out_iput; error = simple_offset_add(shmem_get_offset_ctx(dir), dentry); if (error) goto out_iput; inode->i_size = len-1; if (len <= SHORT_SYMLINK_LEN) { link = kmemdup(symname, len, GFP_KERNEL); if (!link) { error = -ENOMEM; goto out_remove_offset; } inode->i_op = &shmem_short_symlink_operations; inode_set_cached_link(inode, link, len - 1); } else { inode_nohighmem(inode); inode->i_mapping->a_ops = &shmem_aops; error = shmem_get_folio(inode, 0, 0, &folio, SGP_WRITE); if (error) goto out_remove_offset; inode->i_op = &shmem_symlink_inode_operations; memcpy(folio_address(folio), symname, len); folio_mark_uptodate(folio); folio_mark_dirty(folio); folio_unlock(folio); folio_put(folio); } dir->i_size += BOGO_DIRENT_SIZE; inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); inode_inc_iversion(dir); if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir)) d_add(dentry, inode); else d_instantiate(dentry, inode); dget(dentry); return 0; out_remove_offset: simple_offset_remove(shmem_get_offset_ctx(dir), dentry); out_iput: iput(inode); return error; } static void shmem_put_link(void *arg) { folio_mark_accessed(arg); folio_put(arg); } static const char *shmem_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct folio *folio = NULL; int error; if (!dentry) { folio = filemap_get_folio(inode->i_mapping, 0); if (IS_ERR(folio)) return ERR_PTR(-ECHILD); if (PageHWPoison(folio_page(folio, 0)) || !folio_test_uptodate(folio)) { folio_put(folio); return ERR_PTR(-ECHILD); } } else { error = shmem_get_folio(inode, 0, 0, &folio, SGP_READ); if (error) return ERR_PTR(error); if (!folio) return ERR_PTR(-ECHILD); if (PageHWPoison(folio_page(folio, 0))) { folio_unlock(folio); folio_put(folio); return ERR_PTR(-ECHILD); } folio_unlock(folio); } set_delayed_call(done, shmem_put_link, folio); return folio_address(folio); } #ifdef CONFIG_TMPFS_XATTR static int shmem_fileattr_get(struct dentry *dentry, struct file_kattr *fa) { struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); fileattr_fill_flags(fa, info->fsflags & SHMEM_FL_USER_VISIBLE); return 0; } static int shmem_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct file_kattr *fa) { struct inode *inode = d_inode(dentry); struct shmem_inode_info *info = SHMEM_I(inode); int ret, flags; if (fileattr_has_fsx(fa)) return -EOPNOTSUPP; if (fa->flags & ~SHMEM_FL_USER_MODIFIABLE) return -EOPNOTSUPP; flags = (info->fsflags & ~SHMEM_FL_USER_MODIFIABLE) | (fa->flags & SHMEM_FL_USER_MODIFIABLE); ret = shmem_set_inode_flags(inode, flags, dentry); if (ret) return ret; info->fsflags = flags; inode_set_ctime_current(inode); inode_inc_iversion(inode); return 0; } /* * Superblocks without xattr inode operations may get some security.* xattr * support from the LSM "for free". As soon as we have any other xattrs * like ACLs, we also need to implement the security.* handlers at * filesystem level, though. */ /* * Callback for security_inode_init_security() for acquiring xattrs. */ static int shmem_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); const struct xattr *xattr; struct simple_xattr *new_xattr; size_t ispace = 0; size_t len; if (sbinfo->max_inodes) { for (xattr = xattr_array; xattr->name != NULL; xattr++) { ispace += simple_xattr_space(xattr->name, xattr->value_len + XATTR_SECURITY_PREFIX_LEN); } if (ispace) { raw_spin_lock(&sbinfo->stat_lock); if (sbinfo->free_ispace < ispace) ispace = 0; else sbinfo->free_ispace -= ispace; raw_spin_unlock(&sbinfo->stat_lock); if (!ispace) return -ENOSPC; } } for (xattr = xattr_array; xattr->name != NULL; xattr++) { new_xattr = simple_xattr_alloc(xattr->value, xattr->value_len); if (!new_xattr) break; len = strlen(xattr->name) + 1; new_xattr->name = kmalloc(XATTR_SECURITY_PREFIX_LEN + len, GFP_KERNEL_ACCOUNT); if (!new_xattr->name) { kvfree(new_xattr); break; } memcpy(new_xattr->name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); memcpy(new_xattr->name + XATTR_SECURITY_PREFIX_LEN, xattr->name, len); simple_xattr_add(&info->xattrs, new_xattr); } if (xattr->name != NULL) { if (ispace) { raw_spin_lock(&sbinfo->stat_lock); sbinfo->free_ispace += ispace; raw_spin_unlock(&sbinfo->stat_lock); } simple_xattrs_free(&info->xattrs, NULL); return -ENOMEM; } return 0; } static int shmem_xattr_handler_get(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *buffer, size_t size) { struct shmem_inode_info *info = SHMEM_I(inode); name = xattr_full_name(handler, name); return simple_xattr_get(&info->xattrs, name, buffer, size); } static int shmem_xattr_handler_set(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *unused, struct inode *inode, const char *name, const void *value, size_t size, int flags) { struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb); struct simple_xattr *old_xattr; size_t ispace = 0; name = xattr_full_name(handler, name); if (value && sbinfo->max_inodes) { ispace = simple_xattr_space(name, size); raw_spin_lock(&sbinfo->stat_lock); if (sbinfo->free_ispace < ispace) ispace = 0; else sbinfo->free_ispace -= ispace; raw_spin_unlock(&sbinfo->stat_lock); if (!ispace) return -ENOSPC; } old_xattr = simple_xattr_set(&info->xattrs, name, value, size, flags); if (!IS_ERR(old_xattr)) { ispace = 0; if (old_xattr && sbinfo->max_inodes) ispace = simple_xattr_space(old_xattr->name, old_xattr->size); simple_xattr_free(old_xattr); old_xattr = NULL; inode_set_ctime_current(inode); inode_inc_iversion(inode); } if (ispace) { raw_spin_lock(&sbinfo->stat_lock); sbinfo->free_ispace += ispace; raw_spin_unlock(&sbinfo->stat_lock); } return PTR_ERR(old_xattr); } static const struct xattr_handler shmem_security_xattr_handler = { .prefix = XATTR_SECURITY_PREFIX, .get = shmem_xattr_handler_get, .set = shmem_xattr_handler_set, }; static const struct xattr_handler shmem_trusted_xattr_handler = { .prefix = XATTR_TRUSTED_PREFIX, .get = shmem_xattr_handler_get, .set = shmem_xattr_handler_set, }; static const struct xattr_handler shmem_user_xattr_handler = { .prefix = XATTR_USER_PREFIX, .get = shmem_xattr_handler_get, .set = shmem_xattr_handler_set, }; static const struct xattr_handler * const shmem_xattr_handlers[] = { &shmem_security_xattr_handler, &shmem_trusted_xattr_handler, &shmem_user_xattr_handler, NULL }; static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size) { struct shmem_inode_info *info = SHMEM_I(d_inode(dentry)); return simple_xattr_list(d_inode(dentry), &info->xattrs, buffer, size); } #endif /* CONFIG_TMPFS_XATTR */ static const struct inode_operations shmem_short_symlink_operations = { .getattr = shmem_getattr, .setattr = shmem_setattr, .get_link = simple_get_link, #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, #endif }; static const struct inode_operations shmem_symlink_inode_operations = { .getattr = shmem_getattr, .setattr = shmem_setattr, .get_link = shmem_get_link, #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, #endif }; static struct dentry *shmem_get_parent(struct dentry *child) { return ERR_PTR(-ESTALE); } static int shmem_match(struct inode *ino, void *vfh) { __u32 *fh = vfh; __u64 inum = fh[2]; inum = (inum << 32) | fh[1]; return ino->i_ino == inum && fh[0] == ino->i_generation; } /* Find any alias of inode, but prefer a hashed alias */ static struct dentry *shmem_find_alias(struct inode *inode) { struct dentry *alias = d_find_alias(inode); return alias ?: d_find_any_alias(inode); } static struct dentry *shmem_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { struct inode *inode; struct dentry *dentry = NULL; u64 inum; if (fh_len < 3) return NULL; inum = fid->raw[2]; inum = (inum << 32) | fid->raw[1]; inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]), shmem_match, fid->raw); if (inode) { dentry = shmem_find_alias(inode); iput(inode); } return dentry; } static int shmem_encode_fh(struct inode *inode, __u32 *fh, int *len, struct inode *parent) { if (*len < 3) { *len = 3; return FILEID_INVALID; } if (inode_unhashed(inode)) { /* Unfortunately insert_inode_hash is not idempotent, * so as we hash inodes here rather than at creation * time, we need a lock to ensure we only try * to do it once */ static DEFINE_SPINLOCK(lock); spin_lock(&lock); if (inode_unhashed(inode)) __insert_inode_hash(inode, inode->i_ino + inode->i_generation); spin_unlock(&lock); } fh[0] = inode->i_generation; fh[1] = inode->i_ino; fh[2] = ((__u64)inode->i_ino) >> 32; *len = 3; return 1; } static const struct export_operations shmem_export_ops = { .get_parent = shmem_get_parent, .encode_fh = shmem_encode_fh, .fh_to_dentry = shmem_fh_to_dentry, }; enum shmem_param { Opt_gid, Opt_huge, Opt_mode, Opt_mpol, Opt_nr_blocks, Opt_nr_inodes, Opt_size, Opt_uid, Opt_inode32, Opt_inode64, Opt_noswap, Opt_quota, Opt_usrquota, Opt_grpquota, Opt_usrquota_block_hardlimit, Opt_usrquota_inode_hardlimit, Opt_grpquota_block_hardlimit, Opt_grpquota_inode_hardlimit, Opt_casefold_version, Opt_casefold, Opt_strict_encoding, }; static const struct constant_table shmem_param_enums_huge[] = { {"never", SHMEM_HUGE_NEVER }, {"always", SHMEM_HUGE_ALWAYS }, {"within_size", SHMEM_HUGE_WITHIN_SIZE }, {"advise", SHMEM_HUGE_ADVISE }, {} }; const struct fs_parameter_spec shmem_fs_parameters[] = { fsparam_gid ("gid", Opt_gid), fsparam_enum ("huge", Opt_huge, shmem_param_enums_huge), fsparam_u32oct("mode", Opt_mode), fsparam_string("mpol", Opt_mpol), fsparam_string("nr_blocks", Opt_nr_blocks), fsparam_string("nr_inodes", Opt_nr_inodes), fsparam_string("size", Opt_size), fsparam_uid ("uid", Opt_uid), fsparam_flag ("inode32", Opt_inode32), fsparam_flag ("inode64", Opt_inode64), fsparam_flag ("noswap", Opt_noswap), #ifdef CONFIG_TMPFS_QUOTA fsparam_flag ("quota", Opt_quota), fsparam_flag ("usrquota", Opt_usrquota), fsparam_flag ("grpquota", Opt_grpquota), fsparam_string("usrquota_block_hardlimit", Opt_usrquota_block_hardlimit), fsparam_string("usrquota_inode_hardlimit", Opt_usrquota_inode_hardlimit), fsparam_string("grpquota_block_hardlimit", Opt_grpquota_block_hardlimit), fsparam_string("grpquota_inode_hardlimit", Opt_grpquota_inode_hardlimit), #endif fsparam_string("casefold", Opt_casefold_version), fsparam_flag ("casefold", Opt_casefold), fsparam_flag ("strict_encoding", Opt_strict_encoding), {} }; #if IS_ENABLED(CONFIG_UNICODE) static int shmem_parse_opt_casefold(struct fs_context *fc, struct fs_parameter *param, bool latest_version) { struct shmem_options *ctx = fc->fs_private; int version = UTF8_LATEST; struct unicode_map *encoding; char *version_str = param->string + 5; if (!latest_version) { if (strncmp(param->string, "utf8-", 5)) return invalfc(fc, "Only UTF-8 encodings are supported " "in the format: utf8-<version number>"); version = utf8_parse_version(version_str); if (version < 0) return invalfc(fc, "Invalid UTF-8 version: %s", version_str); } encoding = utf8_load(version); if (IS_ERR(encoding)) { return invalfc(fc, "Failed loading UTF-8 version: utf8-%u.%u.%u\n", unicode_major(version), unicode_minor(version), unicode_rev(version)); } pr_info("tmpfs: Using encoding : utf8-%u.%u.%u\n", unicode_major(version), unicode_minor(version), unicode_rev(version)); ctx->encoding = encoding; return 0; } #else static int shmem_parse_opt_casefold(struct fs_context *fc, struct fs_parameter *param, bool latest_version) { return invalfc(fc, "tmpfs: Kernel not built with CONFIG_UNICODE\n"); } #endif static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param) { struct shmem_options *ctx = fc->fs_private; struct fs_parse_result result; unsigned long long size; char *rest; int opt; kuid_t kuid; kgid_t kgid; opt = fs_parse(fc, shmem_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_size: size = memparse(param->string, &rest); if (*rest == '%') { size <<= PAGE_SHIFT; size *= totalram_pages(); do_div(size, 100); rest++; } if (*rest) goto bad_value; ctx->blocks = DIV_ROUND_UP(size, PAGE_SIZE); ctx->seen |= SHMEM_SEEN_BLOCKS; break; case Opt_nr_blocks: ctx->blocks = memparse(param->string, &rest); if (*rest || ctx->blocks > LONG_MAX) goto bad_value; ctx->seen |= SHMEM_SEEN_BLOCKS; break; case Opt_nr_inodes: ctx->inodes = memparse(param->string, &rest); if (*rest || ctx->inodes > ULONG_MAX / BOGO_INODE_SIZE) goto bad_value; ctx->seen |= SHMEM_SEEN_INODES; break; case Opt_mode: ctx->mode = result.uint_32 & 07777; break; case Opt_uid: kuid = result.uid; /* * The requested uid must be representable in the * filesystem's idmapping. */ if (!kuid_has_mapping(fc->user_ns, kuid)) goto bad_value; ctx->uid = kuid; break; case Opt_gid: kgid = result.gid; /* * The requested gid must be representable in the * filesystem's idmapping. */ if (!kgid_has_mapping(fc->user_ns, kgid)) goto bad_value; ctx->gid = kgid; break; case Opt_huge: ctx->huge = result.uint_32; if (ctx->huge != SHMEM_HUGE_NEVER && !(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && has_transparent_hugepage())) goto unsupported_parameter; ctx->seen |= SHMEM_SEEN_HUGE; break; case Opt_mpol: if (IS_ENABLED(CONFIG_NUMA)) { mpol_put(ctx->mpol); ctx->mpol = NULL; if (mpol_parse_str(param->string, &ctx->mpol)) goto bad_value; break; } goto unsupported_parameter; case Opt_inode32: ctx->full_inums = false; ctx->seen |= SHMEM_SEEN_INUMS; break; case Opt_inode64: if (sizeof(ino_t) < 8) { return invalfc(fc, "Cannot use inode64 with <64bit inums in kernel\n"); } ctx->full_inums = true; ctx->seen |= SHMEM_SEEN_INUMS; break; case Opt_noswap: if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN)) { return invalfc(fc, "Turning off swap in unprivileged tmpfs mounts unsupported"); } ctx->noswap = true; ctx->seen |= SHMEM_SEEN_NOSWAP; break; case Opt_quota: if (fc->user_ns != &init_user_ns) return invalfc(fc, "Quotas in unprivileged tmpfs mounts are unsupported"); ctx->seen |= SHMEM_SEEN_QUOTA; ctx->quota_types |= (QTYPE_MASK_USR | QTYPE_MASK_GRP); break; case Opt_usrquota: if (fc->user_ns != &init_user_ns) return invalfc(fc, "Quotas in unprivileged tmpfs mounts are unsupported"); ctx->seen |= SHMEM_SEEN_QUOTA; ctx->quota_types |= QTYPE_MASK_USR; break; case Opt_grpquota: if (fc->user_ns != &init_user_ns) return invalfc(fc, "Quotas in unprivileged tmpfs mounts are unsupported"); ctx->seen |= SHMEM_SEEN_QUOTA; ctx->quota_types |= QTYPE_MASK_GRP; break; case Opt_usrquota_block_hardlimit: size = memparse(param->string, &rest); if (*rest || !size) goto bad_value; if (size > SHMEM_QUOTA_MAX_SPC_LIMIT) return invalfc(fc, "User quota block hardlimit too large."); ctx->qlimits.usrquota_bhardlimit = size; break; case Opt_grpquota_block_hardlimit: size = memparse(param->string, &rest); if (*rest || !size) goto bad_value; if (size > SHMEM_QUOTA_MAX_SPC_LIMIT) return invalfc(fc, "Group quota block hardlimit too large."); ctx->qlimits.grpquota_bhardlimit = size; break; case Opt_usrquota_inode_hardlimit: size = memparse(param->string, &rest); if (*rest || !size) goto bad_value; if (size > SHMEM_QUOTA_MAX_INO_LIMIT) return invalfc(fc, "User quota inode hardlimit too large."); ctx->qlimits.usrquota_ihardlimit = size; break; case Opt_grpquota_inode_hardlimit: size = memparse(param->string, &rest); if (*rest || !size) goto bad_value; if (size > SHMEM_QUOTA_MAX_INO_LIMIT) return invalfc(fc, "Group quota inode hardlimit too large."); ctx->qlimits.grpquota_ihardlimit = size; break; case Opt_casefold_version: return shmem_parse_opt_casefold(fc, param, false); case Opt_casefold: return shmem_parse_opt_casefold(fc, param, true); case Opt_strict_encoding: #if IS_ENABLED(CONFIG_UNICODE) ctx->strict_encoding = true; break; #else return invalfc(fc, "tmpfs: Kernel not built with CONFIG_UNICODE\n"); #endif } return 0; unsupported_parameter: return invalfc(fc, "Unsupported parameter '%s'", param->key); bad_value: return invalfc(fc, "Bad value for '%s'", param->key); } static char *shmem_next_opt(char **s) { char *sbegin = *s; char *p; if (sbegin == NULL) return NULL; /* * NUL-terminate this option: unfortunately, * mount options form a comma-separated list, * but mpol's nodelist may also contain commas. */ for (;;) { p = strchr(*s, ','); if (p == NULL) break; *s = p + 1; if (!isdigit(*(p+1))) { *p = '\0'; return sbegin; } } *s = NULL; return sbegin; } static int shmem_parse_monolithic(struct fs_context *fc, void *data) { return vfs_parse_monolithic_sep(fc, data, shmem_next_opt); } /* * Reconfigure a shmem filesystem. */ static int shmem_reconfigure(struct fs_context *fc) { struct shmem_options *ctx = fc->fs_private; struct shmem_sb_info *sbinfo = SHMEM_SB(fc->root->d_sb); unsigned long used_isp; struct mempolicy *mpol = NULL; const char *err; raw_spin_lock(&sbinfo->stat_lock); used_isp = sbinfo->max_inodes * BOGO_INODE_SIZE - sbinfo->free_ispace; if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) { if (!sbinfo->max_blocks) { err = "Cannot retroactively limit size"; goto out; } if (percpu_counter_compare(&sbinfo->used_blocks, ctx->blocks) > 0) { err = "Too small a size for current use"; goto out; } } if ((ctx->seen & SHMEM_SEEN_INODES) && ctx->inodes) { if (!sbinfo->max_inodes) { err = "Cannot retroactively limit inodes"; goto out; } if (ctx->inodes * BOGO_INODE_SIZE < used_isp) { err = "Too few inodes for current use"; goto out; } } if ((ctx->seen & SHMEM_SEEN_INUMS) && !ctx->full_inums && sbinfo->next_ino > UINT_MAX) { err = "Current inum too high to switch to 32-bit inums"; goto out; } if ((ctx->seen & SHMEM_SEEN_NOSWAP) && ctx->noswap && !sbinfo->noswap) { err = "Cannot disable swap on remount"; goto out; } if (!(ctx->seen & SHMEM_SEEN_NOSWAP) && !ctx->noswap && sbinfo->noswap) { err = "Cannot enable swap on remount if it was disabled on first mount"; goto out; } if (ctx->seen & SHMEM_SEEN_QUOTA && !sb_any_quota_loaded(fc->root->d_sb)) { err = "Cannot enable quota on remount"; goto out; } #ifdef CONFIG_TMPFS_QUOTA #define CHANGED_LIMIT(name) \ (ctx->qlimits.name## hardlimit && \ (ctx->qlimits.name## hardlimit != sbinfo->qlimits.name## hardlimit)) if (CHANGED_LIMIT(usrquota_b) || CHANGED_LIMIT(usrquota_i) || CHANGED_LIMIT(grpquota_b) || CHANGED_LIMIT(grpquota_i)) { err = "Cannot change global quota limit on remount"; goto out; } #endif /* CONFIG_TMPFS_QUOTA */ if (ctx->seen & SHMEM_SEEN_HUGE) sbinfo->huge = ctx->huge; if (ctx->seen & SHMEM_SEEN_INUMS) sbinfo->full_inums = ctx->full_inums; if (ctx->seen & SHMEM_SEEN_BLOCKS) sbinfo->max_blocks = ctx->blocks; if (ctx->seen & SHMEM_SEEN_INODES) { sbinfo->max_inodes = ctx->inodes; sbinfo->free_ispace = ctx->inodes * BOGO_INODE_SIZE - used_isp; } /* * Preserve previous mempolicy unless mpol remount option was specified. */ if (ctx->mpol) { mpol = sbinfo->mpol; sbinfo->mpol = ctx->mpol; /* transfers initial ref */ ctx->mpol = NULL; } if (ctx->noswap) sbinfo->noswap = true; raw_spin_unlock(&sbinfo->stat_lock); mpol_put(mpol); return 0; out: raw_spin_unlock(&sbinfo->stat_lock); return invalfc(fc, "%s", err); } static int shmem_show_options(struct seq_file *seq, struct dentry *root) { struct shmem_sb_info *sbinfo = SHMEM_SB(root->d_sb); struct mempolicy *mpol; if (sbinfo->max_blocks != shmem_default_max_blocks()) seq_printf(seq, ",size=%luk", K(sbinfo->max_blocks)); if (sbinfo->max_inodes != shmem_default_max_inodes()) seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes); if (sbinfo->mode != (0777 | S_ISVTX)) seq_printf(seq, ",mode=%03ho", sbinfo->mode); if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, sbinfo->uid)); if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, sbinfo->gid)); /* * Showing inode{64,32} might be useful even if it's the system default, * since then people don't have to resort to checking both here and * /proc/config.gz to confirm 64-bit inums were successfully applied * (which may not even exist if IKCONFIG_PROC isn't enabled). * * We hide it when inode64 isn't the default and we are using 32-bit * inodes, since that probably just means the feature isn't even under * consideration. * * As such: * * +-----------------+-----------------+ * | TMPFS_INODE64=y | TMPFS_INODE64=n | * +------------------+-----------------+-----------------+ * | full_inums=true | show | show | * | full_inums=false | show | hide | * +------------------+-----------------+-----------------+ * */ if (IS_ENABLED(CONFIG_TMPFS_INODE64) || sbinfo->full_inums) seq_printf(seq, ",inode%d", (sbinfo->full_inums ? 64 : 32)); #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Rightly or wrongly, show huge mount option unmasked by shmem_huge */ if (sbinfo->huge) seq_printf(seq, ",huge=%s", shmem_format_huge(sbinfo->huge)); #endif mpol = shmem_get_sbmpol(sbinfo); shmem_show_mpol(seq, mpol); mpol_put(mpol); if (sbinfo->noswap) seq_printf(seq, ",noswap"); #ifdef CONFIG_TMPFS_QUOTA if (sb_has_quota_active(root->d_sb, USRQUOTA)) seq_printf(seq, ",usrquota"); if (sb_has_quota_active(root->d_sb, GRPQUOTA)) seq_printf(seq, ",grpquota"); if (sbinfo->qlimits.usrquota_bhardlimit) seq_printf(seq, ",usrquota_block_hardlimit=%lld", sbinfo->qlimits.usrquota_bhardlimit); if (sbinfo->qlimits.grpquota_bhardlimit) seq_printf(seq, ",grpquota_block_hardlimit=%lld", sbinfo->qlimits.grpquota_bhardlimit); if (sbinfo->qlimits.usrquota_ihardlimit) seq_printf(seq, ",usrquota_inode_hardlimit=%lld", sbinfo->qlimits.usrquota_ihardlimit); if (sbinfo->qlimits.grpquota_ihardlimit) seq_printf(seq, ",grpquota_inode_hardlimit=%lld", sbinfo->qlimits.grpquota_ihardlimit); #endif return 0; } #endif /* CONFIG_TMPFS */ static void shmem_put_super(struct super_block *sb) { struct shmem_sb_info *sbinfo = SHMEM_SB(sb); #if IS_ENABLED(CONFIG_UNICODE) if (sb->s_encoding) utf8_unload(sb->s_encoding); #endif #ifdef CONFIG_TMPFS_QUOTA shmem_disable_quotas(sb); #endif free_percpu(sbinfo->ino_batch); percpu_counter_destroy(&sbinfo->used_blocks); mpol_put(sbinfo->mpol); kfree(sbinfo); sb->s_fs_info = NULL; } #if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_TMPFS) static const struct dentry_operations shmem_ci_dentry_ops = { .d_hash = generic_ci_d_hash, .d_compare = generic_ci_d_compare, }; #endif static int shmem_fill_super(struct super_block *sb, struct fs_context *fc) { struct shmem_options *ctx = fc->fs_private; struct inode *inode; struct shmem_sb_info *sbinfo; int error = -ENOMEM; /* Round up to L1_CACHE_BYTES to resist false sharing */ sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info), L1_CACHE_BYTES), GFP_KERNEL); if (!sbinfo) return error; sb->s_fs_info = sbinfo; #ifdef CONFIG_TMPFS /* * Per default we only allow half of the physical ram per * tmpfs instance, limiting inodes to one per page of lowmem; * but the internal instance is left unlimited. */ if (!(sb->s_flags & SB_KERNMOUNT)) { if (!(ctx->seen & SHMEM_SEEN_BLOCKS)) ctx->blocks = shmem_default_max_blocks(); if (!(ctx->seen & SHMEM_SEEN_INODES)) ctx->inodes = shmem_default_max_inodes(); if (!(ctx->seen & SHMEM_SEEN_INUMS)) ctx->full_inums = IS_ENABLED(CONFIG_TMPFS_INODE64); sbinfo->noswap = ctx->noswap; } else { sb->s_flags |= SB_NOUSER; } sb->s_export_op = &shmem_export_ops; sb->s_flags |= SB_NOSEC; #if IS_ENABLED(CONFIG_UNICODE) if (!ctx->encoding && ctx->strict_encoding) { pr_err("tmpfs: strict_encoding option without encoding is forbidden\n"); error = -EINVAL; goto failed; } if (ctx->encoding) { sb->s_encoding = ctx->encoding; set_default_d_op(sb, &shmem_ci_dentry_ops); if (ctx->strict_encoding) sb->s_encoding_flags = SB_ENC_STRICT_MODE_FL; } #endif #else sb->s_flags |= SB_NOUSER; #endif /* CONFIG_TMPFS */ sb->s_d_flags |= DCACHE_DONTCACHE; sbinfo->max_blocks = ctx->blocks; sbinfo->max_inodes = ctx->inodes; sbinfo->free_ispace = sbinfo->max_inodes * BOGO_INODE_SIZE; if (sb->s_flags & SB_KERNMOUNT) { sbinfo->ino_batch = alloc_percpu(ino_t); if (!sbinfo->ino_batch) goto failed; } sbinfo->uid = ctx->uid; sbinfo->gid = ctx->gid; sbinfo->full_inums = ctx->full_inums; sbinfo->mode = ctx->mode; #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (ctx->seen & SHMEM_SEEN_HUGE) sbinfo->huge = ctx->huge; else sbinfo->huge = tmpfs_huge; #endif sbinfo->mpol = ctx->mpol; ctx->mpol = NULL; raw_spin_lock_init(&sbinfo->stat_lock); if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL)) goto failed; spin_lock_init(&sbinfo->shrinklist_lock); INIT_LIST_HEAD(&sbinfo->shrinklist); sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = TMPFS_MAGIC; sb->s_op = &shmem_ops; sb->s_time_gran = 1; #ifdef CONFIG_TMPFS_XATTR sb->s_xattr = shmem_xattr_handlers; #endif #ifdef CONFIG_TMPFS_POSIX_ACL sb->s_flags |= SB_POSIXACL; #endif uuid_t uuid; uuid_gen(&uuid); super_set_uuid(sb, uuid.b, sizeof(uuid)); #ifdef CONFIG_TMPFS_QUOTA if (ctx->seen & SHMEM_SEEN_QUOTA) { sb->dq_op = &shmem_quota_operations; sb->s_qcop = &dquot_quotactl_sysfile_ops; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP; /* Copy the default limits from ctx into sbinfo */ memcpy(&sbinfo->qlimits, &ctx->qlimits, sizeof(struct shmem_quota_limits)); if (shmem_enable_quotas(sb, ctx->quota_types)) goto failed; } #endif /* CONFIG_TMPFS_QUOTA */ inode = shmem_get_inode(&nop_mnt_idmap, sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE); if (IS_ERR(inode)) { error = PTR_ERR(inode); goto failed; } inode->i_uid = sbinfo->uid; inode->i_gid = sbinfo->gid; sb->s_root = d_make_root(inode); if (!sb->s_root) goto failed; return 0; failed: shmem_put_super(sb); return error; } static int shmem_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, shmem_fill_super); } static void shmem_free_fc(struct fs_context *fc) { struct shmem_options *ctx = fc->fs_private; if (ctx) { mpol_put(ctx->mpol); kfree(ctx); } } static const struct fs_context_operations shmem_fs_context_ops = { .free = shmem_free_fc, .get_tree = shmem_get_tree, #ifdef CONFIG_TMPFS .parse_monolithic = shmem_parse_monolithic, .parse_param = shmem_parse_one, .reconfigure = shmem_reconfigure, #endif }; static struct kmem_cache *shmem_inode_cachep __ro_after_init; static struct inode *shmem_alloc_inode(struct super_block *sb) { struct shmem_inode_info *info; info = alloc_inode_sb(sb, shmem_inode_cachep, GFP_KERNEL); if (!info) return NULL; return &info->vfs_inode; } static void shmem_free_in_core_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); } static void shmem_destroy_inode(struct inode *inode) { if (S_ISREG(inode->i_mode)) mpol_free_shared_policy(&SHMEM_I(inode)->policy); if (S_ISDIR(inode->i_mode)) simple_offset_destroy(shmem_get_offset_ctx(inode)); } static void shmem_init_inode(void *foo) { struct shmem_inode_info *info = foo; inode_init_once(&info->vfs_inode); } static void __init shmem_init_inodecache(void) { shmem_inode_cachep = kmem_cache_create("shmem_inode_cache", sizeof(struct shmem_inode_info), 0, SLAB_PANIC|SLAB_ACCOUNT, shmem_init_inode); } static void __init shmem_destroy_inodecache(void) { kmem_cache_destroy(shmem_inode_cachep); } /* Keep the page in page cache instead of truncating it */ static int shmem_error_remove_folio(struct address_space *mapping, struct folio *folio) { return 0; } static const struct address_space_operations shmem_aops = { .dirty_folio = noop_dirty_folio, #ifdef CONFIG_TMPFS .write_begin = shmem_write_begin, .write_end = shmem_write_end, #endif #ifdef CONFIG_MIGRATION .migrate_folio = migrate_folio, #endif .error_remove_folio = shmem_error_remove_folio, }; static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, .open = shmem_file_open, .get_unmapped_area = shmem_get_unmapped_area, #ifdef CONFIG_TMPFS .llseek = shmem_file_llseek, .read_iter = shmem_file_read_iter, .write_iter = shmem_file_write_iter, .fsync = noop_fsync, .splice_read = shmem_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = shmem_fallocate, #endif }; static const struct inode_operations shmem_inode_operations = { .getattr = shmem_getattr, .setattr = shmem_setattr, #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, .set_acl = simple_set_acl, .fileattr_get = shmem_fileattr_get, .fileattr_set = shmem_fileattr_set, #endif }; static const struct inode_operations shmem_dir_inode_operations = { #ifdef CONFIG_TMPFS .getattr = shmem_getattr, .create = shmem_create, .lookup = simple_lookup, .link = shmem_link, .unlink = shmem_unlink, .symlink = shmem_symlink, .mkdir = shmem_mkdir, .rmdir = shmem_rmdir, .mknod = shmem_mknod, .rename = shmem_rename2, .tmpfile = shmem_tmpfile, .get_offset_ctx = shmem_get_offset_ctx, #endif #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, .fileattr_get = shmem_fileattr_get, .fileattr_set = shmem_fileattr_set, #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, .set_acl = simple_set_acl, #endif }; static const struct inode_operations shmem_special_inode_operations = { .getattr = shmem_getattr, #ifdef CONFIG_TMPFS_XATTR .listxattr = shmem_listxattr, #endif #ifdef CONFIG_TMPFS_POSIX_ACL .setattr = shmem_setattr, .set_acl = simple_set_acl, #endif }; static const struct super_operations shmem_ops = { .alloc_inode = shmem_alloc_inode, .free_inode = shmem_free_in_core_inode, .destroy_inode = shmem_destroy_inode, #ifdef CONFIG_TMPFS .statfs = shmem_statfs, .show_options = shmem_show_options, #endif #ifdef CONFIG_TMPFS_QUOTA .get_dquots = shmem_get_dquots, #endif .evict_inode = shmem_evict_inode, .drop_inode = inode_just_drop, .put_super = shmem_put_super, #ifdef CONFIG_TRANSPARENT_HUGEPAGE .nr_cached_objects = shmem_unused_huge_count, .free_cached_objects = shmem_unused_huge_scan, #endif }; static const struct vm_operations_struct shmem_vm_ops = { .fault = shmem_fault, .map_pages = filemap_map_pages, #ifdef CONFIG_NUMA .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, #endif }; static const struct vm_operations_struct shmem_anon_vm_ops = { .fault = shmem_fault, .map_pages = filemap_map_pages, #ifdef CONFIG_NUMA .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, #endif }; int shmem_init_fs_context(struct fs_context *fc) { struct shmem_options *ctx; ctx = kzalloc(sizeof(struct shmem_options), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->mode = 0777 | S_ISVTX; ctx->uid = current_fsuid(); ctx->gid = current_fsgid(); #if IS_ENABLED(CONFIG_UNICODE) ctx->encoding = NULL; #endif fc->fs_private = ctx; fc->ops = &shmem_fs_context_ops; #ifdef CONFIG_TMPFS fc->sb_flags |= SB_I_VERSION; #endif return 0; } static struct file_system_type shmem_fs_type = { .owner = THIS_MODULE, .name = "tmpfs", .init_fs_context = shmem_init_fs_context, #ifdef CONFIG_TMPFS .parameters = shmem_fs_parameters, #endif .kill_sb = kill_litter_super, .fs_flags = FS_USERNS_MOUNT | FS_ALLOW_IDMAP | FS_MGTIME, }; #if defined(CONFIG_SYSFS) && defined(CONFIG_TMPFS) #define __INIT_KOBJ_ATTR(_name, _mode, _show, _store) \ { \ .attr = { .name = __stringify(_name), .mode = _mode }, \ .show = _show, \ .store = _store, \ } #define TMPFS_ATTR_W(_name, _store) \ static struct kobj_attribute tmpfs_attr_##_name = \ __INIT_KOBJ_ATTR(_name, 0200, NULL, _store) #define TMPFS_ATTR_RW(_name, _show, _store) \ static struct kobj_attribute tmpfs_attr_##_name = \ __INIT_KOBJ_ATTR(_name, 0644, _show, _store) #define TMPFS_ATTR_RO(_name, _show) \ static struct kobj_attribute tmpfs_attr_##_name = \ __INIT_KOBJ_ATTR(_name, 0444, _show, NULL) #if IS_ENABLED(CONFIG_UNICODE) static ssize_t casefold_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { return sysfs_emit(buf, "supported\n"); } TMPFS_ATTR_RO(casefold, casefold_show); #endif static struct attribute *tmpfs_attributes[] = { #if IS_ENABLED(CONFIG_UNICODE) &tmpfs_attr_casefold.attr, #endif NULL }; static const struct attribute_group tmpfs_attribute_group = { .attrs = tmpfs_attributes, .name = "features" }; static struct kobject *tmpfs_kobj; static int __init tmpfs_sysfs_init(void) { int ret; tmpfs_kobj = kobject_create_and_add("tmpfs", fs_kobj); if (!tmpfs_kobj) return -ENOMEM; ret = sysfs_create_group(tmpfs_kobj, &tmpfs_attribute_group); if (ret) kobject_put(tmpfs_kobj); return ret; } #endif /* CONFIG_SYSFS && CONFIG_TMPFS */ void __init shmem_init(void) { int error; shmem_init_inodecache(); #ifdef CONFIG_TMPFS_QUOTA register_quota_format(&shmem_quota_format); #endif error = register_filesystem(&shmem_fs_type); if (error) { pr_err("Could not register tmpfs\n"); goto out2; } shm_mnt = kern_mount(&shmem_fs_type); if (IS_ERR(shm_mnt)) { error = PTR_ERR(shm_mnt); pr_err("Could not kern_mount tmpfs\n"); goto out1; } #if defined(CONFIG_SYSFS) && defined(CONFIG_TMPFS) error = tmpfs_sysfs_init(); if (error) { pr_err("Could not init tmpfs sysfs\n"); goto out1; } #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (has_transparent_hugepage() && shmem_huge > SHMEM_HUGE_DENY) SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; else shmem_huge = SHMEM_HUGE_NEVER; /* just in case it was patched */ /* * Default to setting PMD-sized THP to inherit the global setting and * disable all other multi-size THPs. */ if (!shmem_orders_configured) huge_shmem_orders_inherit = BIT(HPAGE_PMD_ORDER); #endif return; out1: unregister_filesystem(&shmem_fs_type); out2: #ifdef CONFIG_TMPFS_QUOTA unregister_quota_format(&shmem_quota_format); #endif shmem_destroy_inodecache(); shm_mnt = ERR_PTR(error); } #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS) static ssize_t shmem_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { static const int values[] = { SHMEM_HUGE_ALWAYS, SHMEM_HUGE_WITHIN_SIZE, SHMEM_HUGE_ADVISE, SHMEM_HUGE_NEVER, SHMEM_HUGE_DENY, SHMEM_HUGE_FORCE, }; int len = 0; int i; for (i = 0; i < ARRAY_SIZE(values); i++) { len += sysfs_emit_at(buf, len, shmem_huge == values[i] ? "%s[%s]" : "%s%s", i ? " " : "", shmem_format_huge(values[i])); } len += sysfs_emit_at(buf, len, "\n"); return len; } static ssize_t shmem_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { char tmp[16]; int huge, err; if (count + 1 > sizeof(tmp)) return -EINVAL; memcpy(tmp, buf, count); tmp[count] = '\0'; if (count && tmp[count - 1] == '\n') tmp[count - 1] = '\0'; huge = shmem_parse_huge(tmp); if (huge == -EINVAL) return huge; shmem_huge = huge; if (shmem_huge > SHMEM_HUGE_DENY) SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; err = start_stop_khugepaged(); return err ? err : count; } struct kobj_attribute shmem_enabled_attr = __ATTR_RW(shmem_enabled); static DEFINE_SPINLOCK(huge_shmem_orders_lock); static ssize_t thpsize_shmem_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { int order = to_thpsize(kobj)->order; const char *output; if (test_bit(order, &huge_shmem_orders_always)) output = "[always] inherit within_size advise never"; else if (test_bit(order, &huge_shmem_orders_inherit)) output = "always [inherit] within_size advise never"; else if (test_bit(order, &huge_shmem_orders_within_size)) output = "always inherit [within_size] advise never"; else if (test_bit(order, &huge_shmem_orders_madvise)) output = "always inherit within_size [advise] never"; else output = "always inherit within_size advise [never]"; return sysfs_emit(buf, "%s\n", output); } static ssize_t thpsize_shmem_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int order = to_thpsize(kobj)->order; ssize_t ret = count; if (sysfs_streq(buf, "always")) { spin_lock(&huge_shmem_orders_lock); clear_bit(order, &huge_shmem_orders_inherit); clear_bit(order, &huge_shmem_orders_madvise); clear_bit(order, &huge_shmem_orders_within_size); set_bit(order, &huge_shmem_orders_always); spin_unlock(&huge_shmem_orders_lock); } else if (sysfs_streq(buf, "inherit")) { /* Do not override huge allocation policy with non-PMD sized mTHP */ if (shmem_huge == SHMEM_HUGE_FORCE && order != HPAGE_PMD_ORDER) return -EINVAL; spin_lock(&huge_shmem_orders_lock); clear_bit(order, &huge_shmem_orders_always); clear_bit(order, &huge_shmem_orders_madvise); clear_bit(order, &huge_shmem_orders_within_size); set_bit(order, &huge_shmem_orders_inherit); spin_unlock(&huge_shmem_orders_lock); } else if (sysfs_streq(buf, "within_size")) { spin_lock(&huge_shmem_orders_lock); clear_bit(order, &huge_shmem_orders_always); clear_bit(order, &huge_shmem_orders_inherit); clear_bit(order, &huge_shmem_orders_madvise); set_bit(order, &huge_shmem_orders_within_size); spin_unlock(&huge_shmem_orders_lock); } else if (sysfs_streq(buf, "advise")) { spin_lock(&huge_shmem_orders_lock); clear_bit(order, &huge_shmem_orders_always); clear_bit(order, &huge_shmem_orders_inherit); clear_bit(order, &huge_shmem_orders_within_size); set_bit(order, &huge_shmem_orders_madvise); spin_unlock(&huge_shmem_orders_lock); } else if (sysfs_streq(buf, "never")) { spin_lock(&huge_shmem_orders_lock); clear_bit(order, &huge_shmem_orders_always); clear_bit(order, &huge_shmem_orders_inherit); clear_bit(order, &huge_shmem_orders_within_size); clear_bit(order, &huge_shmem_orders_madvise); spin_unlock(&huge_shmem_orders_lock); } else { ret = -EINVAL; } if (ret > 0) { int err = start_stop_khugepaged(); if (err) ret = err; } return ret; } struct kobj_attribute thpsize_shmem_enabled_attr = __ATTR(shmem_enabled, 0644, thpsize_shmem_enabled_show, thpsize_shmem_enabled_store); #endif /* CONFIG_TRANSPARENT_HUGEPAGE && CONFIG_SYSFS */ #if defined(CONFIG_TRANSPARENT_HUGEPAGE) static int __init setup_transparent_hugepage_shmem(char *str) { int huge; huge = shmem_parse_huge(str); if (huge == -EINVAL) { pr_warn("transparent_hugepage_shmem= cannot parse, ignored\n"); return huge; } shmem_huge = huge; return 1; } __setup("transparent_hugepage_shmem=", setup_transparent_hugepage_shmem); static int __init setup_transparent_hugepage_tmpfs(char *str) { int huge; huge = shmem_parse_huge(str); if (huge < 0) { pr_warn("transparent_hugepage_tmpfs= cannot parse, ignored\n"); return huge; } tmpfs_huge = huge; return 1; } __setup("transparent_hugepage_tmpfs=", setup_transparent_hugepage_tmpfs); static char str_dup[PAGE_SIZE] __initdata; static int __init setup_thp_shmem(char *str) { char *token, *range, *policy, *subtoken; unsigned long always, inherit, madvise, within_size; char *start_size, *end_size; int start, end, nr; char *p; if (!str || strlen(str) + 1 > PAGE_SIZE) goto err; strscpy(str_dup, str); always = huge_shmem_orders_always; inherit = huge_shmem_orders_inherit; madvise = huge_shmem_orders_madvise; within_size = huge_shmem_orders_within_size; p = str_dup; while ((token = strsep(&p, ";")) != NULL) { range = strsep(&token, ":"); policy = token; if (!policy) goto err; while ((subtoken = strsep(&range, ",")) != NULL) { if (strchr(subtoken, '-')) { start_size = strsep(&subtoken, "-"); end_size = subtoken; start = get_order_from_str(start_size, THP_ORDERS_ALL_FILE_DEFAULT); end = get_order_from_str(end_size, THP_ORDERS_ALL_FILE_DEFAULT); } else { start_size = end_size = subtoken; start = end = get_order_from_str(subtoken, THP_ORDERS_ALL_FILE_DEFAULT); } if (start < 0) { pr_err("invalid size %s in thp_shmem boot parameter\n", start_size); goto err; } if (end < 0) { pr_err("invalid size %s in thp_shmem boot parameter\n", end_size); goto err; } if (start > end) goto err; nr = end - start + 1; if (!strcmp(policy, "always")) { bitmap_set(&always, start, nr); bitmap_clear(&inherit, start, nr); bitmap_clear(&madvise, start, nr); bitmap_clear(&within_size, start, nr); } else if (!strcmp(policy, "advise")) { bitmap_set(&madvise, start, nr); bitmap_clear(&inherit, start, nr); bitmap_clear(&always, start, nr); bitmap_clear(&within_size, start, nr); } else if (!strcmp(policy, "inherit")) { bitmap_set(&inherit, start, nr); bitmap_clear(&madvise, start, nr); bitmap_clear(&always, start, nr); bitmap_clear(&within_size, start, nr); } else if (!strcmp(policy, "within_size")) { bitmap_set(&within_size, start, nr); bitmap_clear(&inherit, start, nr); bitmap_clear(&madvise, start, nr); bitmap_clear(&always, start, nr); } else if (!strcmp(policy, "never")) { bitmap_clear(&inherit, start, nr); bitmap_clear(&madvise, start, nr); bitmap_clear(&always, start, nr); bitmap_clear(&within_size, start, nr); } else { pr_err("invalid policy %s in thp_shmem boot parameter\n", policy); goto err; } } } huge_shmem_orders_always = always; huge_shmem_orders_madvise = madvise; huge_shmem_orders_inherit = inherit; huge_shmem_orders_within_size = within_size; shmem_orders_configured = true; return 1; err: pr_warn("thp_shmem=%s: error parsing string, ignoring setting\n", str); return 0; } __setup("thp_shmem=", setup_thp_shmem); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #else /* !CONFIG_SHMEM */ /* * tiny-shmem: simple shmemfs and tmpfs using ramfs code * * This is intended for small system where the benefits of the full * shmem code (swap-backed and resource-limited) are outweighed by * their complexity. On systems without swap this code should be * effectively equivalent, but much lighter weight. */ static struct file_system_type shmem_fs_type = { .name = "tmpfs", .init_fs_context = ramfs_init_fs_context, .parameters = ramfs_fs_parameters, .kill_sb = ramfs_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; void __init shmem_init(void) { BUG_ON(register_filesystem(&shmem_fs_type) != 0); shm_mnt = kern_mount(&shmem_fs_type); BUG_ON(IS_ERR(shm_mnt)); } int shmem_unuse(unsigned int type) { return 0; } int shmem_lock(struct file *file, int lock, struct ucounts *ucounts) { return 0; } void shmem_unlock_mapping(struct address_space *mapping) { } #ifdef CONFIG_MMU unsigned long shmem_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags); } #endif void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { truncate_inode_pages_range(inode->i_mapping, lstart, lend); } EXPORT_SYMBOL_GPL(shmem_truncate_range); #define shmem_vm_ops generic_file_vm_ops #define shmem_anon_vm_ops generic_file_vm_ops #define shmem_file_operations ramfs_file_operations #define shmem_acct_size(flags, size) 0 #define shmem_unacct_size(flags, size) do {} while (0) static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block *sb, struct inode *dir, umode_t mode, dev_t dev, unsigned long flags) { struct inode *inode = ramfs_get_inode(sb, dir, mode, dev); return inode ? inode : ERR_PTR(-ENOSPC); } #endif /* CONFIG_SHMEM */ /* common code */ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, loff_t size, unsigned long flags, unsigned int i_flags) { struct inode *inode; struct file *res; if (IS_ERR(mnt)) return ERR_CAST(mnt); if (size < 0 || size > MAX_LFS_FILESIZE) return ERR_PTR(-EINVAL); if (is_idmapped_mnt(mnt)) return ERR_PTR(-EINVAL); if (shmem_acct_size(flags, size)) return ERR_PTR(-ENOMEM); inode = shmem_get_inode(&nop_mnt_idmap, mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0, flags); if (IS_ERR(inode)) { shmem_unacct_size(flags, size); return ERR_CAST(inode); } inode->i_flags |= i_flags; inode->i_size = size; clear_nlink(inode); /* It is unlinked */ res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size)); if (!IS_ERR(res)) res = alloc_file_pseudo(inode, mnt, name, O_RDWR, &shmem_file_operations); if (IS_ERR(res)) iput(inode); return res; } /** * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be * kernel internal. There will be NO LSM permission checks against the * underlying inode. So users of this interface must do LSM checks at a * higher layer. The users are the big_key and shm implementations. LSM * checks are provided at the key or shm level rather than the inode. * @name: name for dentry (to be seen in /proc/<pid>/maps) * @size: size to be set for the file * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags) { return __shmem_file_setup(shm_mnt, name, size, flags, S_PRIVATE); } EXPORT_SYMBOL_GPL(shmem_kernel_file_setup); /** * shmem_file_setup - get an unlinked file living in tmpfs * @name: name for dentry (to be seen in /proc/<pid>/maps) * @size: size to be set for the file * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags) { return __shmem_file_setup(shm_mnt, name, size, flags, 0); } EXPORT_SYMBOL_GPL(shmem_file_setup); /** * shmem_file_setup_with_mnt - get an unlinked file living in tmpfs * @mnt: the tmpfs mount where the file will be created * @name: name for dentry (to be seen in /proc/<pid>/maps) * @size: size to be set for the file * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size */ struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt, const char *name, loff_t size, unsigned long flags) { return __shmem_file_setup(mnt, name, size, flags, 0); } EXPORT_SYMBOL_GPL(shmem_file_setup_with_mnt); /** * shmem_zero_setup - setup a shared anonymous mapping * @vma: the vma to be mmapped is prepared by do_mmap */ int shmem_zero_setup(struct vm_area_struct *vma) { struct file *file; loff_t size = vma->vm_end - vma->vm_start; /* * Cloning a new file under mmap_lock leads to a lock ordering conflict * between XFS directory reading and selinux: since this file is only * accessible to the user through its mapping, use S_PRIVATE flag to * bypass file security, in the same way as shmem_kernel_file_setup(). */ file = shmem_kernel_file_setup("dev/zero", size, vma->vm_flags); if (IS_ERR(file)) return PTR_ERR(file); if (vma->vm_file) fput(vma->vm_file); vma->vm_file = file; vma->vm_ops = &shmem_anon_vm_ops; return 0; } /** * shmem_read_folio_gfp - read into page cache, using specified page allocation flags. * @mapping: the folio's address_space * @index: the folio index * @gfp: the page allocator flags to use if allocating * * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)", * with any new page allocations done using the specified allocation flags. * But read_cache_page_gfp() uses the ->read_folio() method: which does not * suit tmpfs, since it may have pages in swapcache, and needs to find those * for itself; although drivers/gpu/drm i915 and ttm rely upon this support. * * i915_gem_object_get_pages_gtt() mixes __GFP_NORETRY | __GFP_NOWARN in * with the mapping_gfp_mask(), to avoid OOMing the machine unnecessarily. */ struct folio *shmem_read_folio_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { #ifdef CONFIG_SHMEM struct inode *inode = mapping->host; struct folio *folio; int error; error = shmem_get_folio_gfp(inode, index, i_size_read(inode), &folio, SGP_CACHE, gfp, NULL, NULL); if (error) return ERR_PTR(error); folio_unlock(folio); return folio; #else /* * The tiny !SHMEM case uses ramfs without swap */ return mapping_read_folio_gfp(mapping, index, gfp); #endif } EXPORT_SYMBOL_GPL(shmem_read_folio_gfp); struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { struct folio *folio = shmem_read_folio_gfp(mapping, index, gfp); struct page *page; if (IS_ERR(folio)) return &folio->page; page = folio_file_page(folio, index); if (PageHWPoison(page)) { folio_put(folio); return ERR_PTR(-EIO); } return page; } EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp); |
| 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 | /* 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 folio_is_device_private(const struct folio *folio) { return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && folio_is_zone_device(folio) && folio->pgmap->type == MEMORY_DEVICE_PRIVATE; } static inline bool is_device_private_page(const struct page *page) { return IS_ENABLED(CONFIG_DEVICE_PRIVATE) && folio_is_device_private(page_folio(page)); } static inline bool folio_is_pci_p2pdma(const struct folio *folio) { return IS_ENABLED(CONFIG_PCI_P2PDMA) && folio_is_zone_device(folio) && folio->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA; } static inline bool is_pci_p2pdma_page(const struct page *page) { return IS_ENABLED(CONFIG_PCI_P2PDMA) && folio_is_pci_p2pdma(page_folio(page)); } static inline bool folio_is_device_coherent(const struct folio *folio) { return folio_is_zone_device(folio) && folio->pgmap->type == MEMORY_DEVICE_COHERENT; } static inline bool is_device_coherent_page(const struct page *page) { return folio_is_device_coherent(page_folio(page)); } static inline bool folio_is_fsdax(const struct folio *folio) { return folio_is_zone_device(folio) && folio->pgmap->type == MEMORY_DEVICE_FS_DAX; } static inline bool is_fsdax_page(const struct page *page) { return folio_is_fsdax(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); 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) { 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_ */ |
| 377 300 302 302 104 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #ifndef __ASM_ARM_KVM_ARCH_TIMER_H #define __ASM_ARM_KVM_ARCH_TIMER_H #include <linux/clocksource.h> #include <linux/hrtimer.h> enum kvm_arch_timers { TIMER_PTIMER, TIMER_VTIMER, NR_KVM_EL0_TIMERS, TIMER_HVTIMER = NR_KVM_EL0_TIMERS, TIMER_HPTIMER, NR_KVM_TIMERS }; enum kvm_arch_timer_regs { TIMER_REG_CNT, TIMER_REG_CVAL, TIMER_REG_TVAL, TIMER_REG_CTL, TIMER_REG_VOFF, }; struct arch_timer_offset { /* * If set, pointer to one of the offsets in the kvm's offset * structure. If NULL, assume a zero offset. */ u64 *vm_offset; /* * If set, pointer to one of the offsets in the vcpu's sysreg * array. If NULL, assume a zero offset. */ u64 *vcpu_offset; }; struct arch_timer_vm_data { /* Offset applied to the virtual timer/counter */ u64 voffset; /* Offset applied to the physical timer/counter */ u64 poffset; /* The PPI for each timer, global to the VM */ u8 ppi[NR_KVM_TIMERS]; }; struct arch_timer_context { /* Emulated Timer (may be unused) */ struct hrtimer hrtimer; u64 ns_frac; /* Offset for this counter/timer */ struct arch_timer_offset offset; /* * We have multiple paths which can save/restore the timer state onto * the hardware, so we need some way of keeping track of where the * latest state is. */ bool loaded; /* Output level of the timer IRQ */ struct { bool level; } irq; /* Who am I? */ enum kvm_arch_timers timer_id; /* Duplicated state from arch_timer.c for convenience */ u32 host_timer_irq; }; struct timer_map { struct arch_timer_context *direct_vtimer; struct arch_timer_context *direct_ptimer; struct arch_timer_context *emul_vtimer; struct arch_timer_context *emul_ptimer; }; void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map); struct arch_timer_cpu { struct arch_timer_context timers[NR_KVM_TIMERS]; /* Background timer used when the guest is not running */ struct hrtimer bg_timer; /* Is the timer enabled */ bool enabled; }; int __init kvm_timer_hyp_init(bool has_gic); int kvm_timer_enable(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu); void kvm_timer_sync_nested(struct kvm_vcpu *vcpu); void kvm_timer_sync_user(struct kvm_vcpu *vcpu); bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu); void kvm_timer_update_run(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu); void kvm_timer_init_vm(struct kvm *kvm); int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); u64 kvm_phys_timer_read(void); void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu); void kvm_timer_init_vhe(void); #define vcpu_timer(v) (&(v)->arch.timer_cpu) #define vcpu_get_timer(v,t) (&vcpu_timer(v)->timers[(t)]) #define vcpu_vtimer(v) (&(v)->arch.timer_cpu.timers[TIMER_VTIMER]) #define vcpu_ptimer(v) (&(v)->arch.timer_cpu.timers[TIMER_PTIMER]) #define vcpu_hvtimer(v) (&(v)->arch.timer_cpu.timers[TIMER_HVTIMER]) #define vcpu_hptimer(v) (&(v)->arch.timer_cpu.timers[TIMER_HPTIMER]) #define arch_timer_ctx_index(ctx) ((ctx)->timer_id) #define timer_context_to_vcpu(ctx) container_of((ctx), struct kvm_vcpu, arch.timer_cpu.timers[(ctx)->timer_id]) #define timer_vm_data(ctx) (&(timer_context_to_vcpu(ctx)->kvm->arch.timer_data)) #define timer_irq(ctx) (timer_vm_data(ctx)->ppi[arch_timer_ctx_index(ctx)]) u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timers tmr, enum kvm_arch_timer_regs treg); void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timers tmr, enum kvm_arch_timer_regs treg, u64 val); /* Needed for tracing */ u32 timer_get_ctl(struct arch_timer_context *ctxt); u64 timer_get_cval(struct arch_timer_context *ctxt); /* CPU HP callbacks */ void kvm_timer_cpu_up(void); void kvm_timer_cpu_down(void); /* CNTKCTL_EL1 valid bits as of DDI0487J.a */ #define CNTKCTL_VALID_BITS (BIT(17) | GENMASK_ULL(9, 0)) DECLARE_STATIC_KEY_FALSE(broken_cntvoff_key); static inline bool has_broken_cntvoff(void) { return static_branch_unlikely(&broken_cntvoff_key); } static inline bool has_cntpoff(void) { return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)); } static inline u64 timer_get_offset(struct arch_timer_context *ctxt) { u64 offset = 0; if (!ctxt) return 0; if (ctxt->offset.vm_offset) offset += *ctxt->offset.vm_offset; if (ctxt->offset.vcpu_offset) offset += *ctxt->offset.vcpu_offset; return offset; } static inline void timer_set_offset(struct arch_timer_context *ctxt, u64 offset) { if (!ctxt->offset.vm_offset) { WARN(offset, "timer %d\n", arch_timer_ctx_index(ctxt)); return; } WRITE_ONCE(*ctxt->offset.vm_offset, offset); } #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2008-2012 Novell Inc. * Copyright (c) 2012-2019 Greg Kroah-Hartman <gregkh@linuxfoundation.org> * Copyright (c) 2012-2019 Linux Foundation * * Core driver model functions and structures that should not be * shared outside of the drivers/base/ directory. * */ #include <linux/notifier.h> /** * struct subsys_private - structure to hold the private to the driver core portions of the bus_type/class structure. * * @subsys - the struct kset that defines this subsystem * @devices_kset - the subsystem's 'devices' directory * @interfaces - list of subsystem interfaces associated * @mutex - protect the devices, and interfaces lists. * * @drivers_kset - the list of drivers associated * @klist_devices - the klist to iterate over the @devices_kset * @klist_drivers - the klist to iterate over the @drivers_kset * @bus_notifier - the bus notifier list for anything that cares about things * on this bus. * @bus - pointer back to the struct bus_type that this structure is associated * with. * @dev_root: Default device to use as the parent. * * @glue_dirs - "glue" directory to put in-between the parent device to * avoid namespace conflicts * @class - pointer back to the struct class that this structure is associated * with. * @lock_key: Lock class key for use by the lock validator * * This structure is the one that is the actual kobject allowing struct * bus_type/class to be statically allocated safely. Nothing outside of the * driver core should ever touch these fields. */ struct subsys_private { struct kset subsys; struct kset *devices_kset; struct list_head interfaces; struct mutex mutex; struct kset *drivers_kset; struct klist klist_devices; struct klist klist_drivers; struct blocking_notifier_head bus_notifier; unsigned int drivers_autoprobe:1; const struct bus_type *bus; struct device *dev_root; struct kset glue_dirs; const struct class *class; struct lock_class_key lock_key; }; #define to_subsys_private(obj) container_of_const(obj, struct subsys_private, subsys.kobj) static inline struct subsys_private *subsys_get(struct subsys_private *sp) { if (sp) kset_get(&sp->subsys); return sp; } static inline void subsys_put(struct subsys_private *sp) { if (sp) kset_put(&sp->subsys); } struct subsys_private *bus_to_subsys(const struct bus_type *bus); struct subsys_private *class_to_subsys(const struct class *class); struct driver_private { struct kobject kobj; struct klist klist_devices; struct klist_node knode_bus; struct module_kobject *mkobj; struct device_driver *driver; }; #define to_driver(obj) container_of(obj, struct driver_private, kobj) /** * struct device_private - structure to hold the private to the driver core portions of the device structure. * * @klist_children - klist containing all children of this device * @knode_parent - node in sibling list * @knode_driver - node in driver list * @knode_bus - node in bus list * @knode_class - node in class list * @deferred_probe - entry in deferred_probe_list which is used to retry the * binding of drivers which were unable to get all the resources needed by * the device; typically because it depends on another driver getting * probed first. * @async_driver - pointer to device driver awaiting probe via async_probe * @device - pointer back to the struct device that this structure is * associated with. * @dead - This device is currently either in the process of or has been * removed from the system. Any asynchronous events scheduled for this * device should exit without taking any action. * * Nothing outside of the driver core should ever touch these fields. */ struct device_private { struct klist klist_children; struct klist_node knode_parent; struct klist_node knode_driver; struct klist_node knode_bus; struct klist_node knode_class; struct list_head deferred_probe; const struct device_driver *async_driver; char *deferred_probe_reason; struct device *device; u8 dead:1; }; #define to_device_private_parent(obj) \ container_of(obj, struct device_private, knode_parent) #define to_device_private_driver(obj) \ container_of(obj, struct device_private, knode_driver) #define to_device_private_bus(obj) \ container_of(obj, struct device_private, knode_bus) #define to_device_private_class(obj) \ container_of(obj, struct device_private, knode_class) /* initialisation functions */ int devices_init(void); int buses_init(void); int classes_init(void); int firmware_init(void); #ifdef CONFIG_SYS_HYPERVISOR int hypervisor_init(void); #else static inline int hypervisor_init(void) { return 0; } #endif int platform_bus_init(void); int faux_bus_init(void); void cpu_dev_init(void); void container_dev_init(void); #ifdef CONFIG_AUXILIARY_BUS void auxiliary_bus_init(void); #else static inline void auxiliary_bus_init(void) { } #endif struct kobject *virtual_device_parent(void); int bus_add_device(struct device *dev); void bus_probe_device(struct device *dev); void bus_remove_device(struct device *dev); void bus_notify(struct device *dev, enum bus_notifier_event value); bool bus_is_registered(const struct bus_type *bus); int bus_add_driver(struct device_driver *drv); void bus_remove_driver(struct device_driver *drv); void device_release_driver_internal(struct device *dev, const struct device_driver *drv, struct device *parent); void driver_detach(const struct device_driver *drv); void driver_deferred_probe_del(struct device *dev); void device_set_deferred_probe_reason(const struct device *dev, struct va_format *vaf); static inline int driver_match_device(const struct device_driver *drv, struct device *dev) { return drv->bus->match ? drv->bus->match(dev, drv) : 1; } static inline void dev_sync_state(struct device *dev) { if (dev->bus->sync_state) dev->bus->sync_state(dev); else if (dev->driver && dev->driver->sync_state) dev->driver->sync_state(dev); } int driver_add_groups(const struct device_driver *drv, const struct attribute_group **groups); void driver_remove_groups(const struct device_driver *drv, const struct attribute_group **groups); void device_driver_detach(struct device *dev); static inline void device_set_driver(struct device *dev, const struct device_driver *drv) { /* * Majority (all?) read accesses to dev->driver happens either * while holding device lock or in bus/driver code that is only * invoked when the device is bound to a driver and there is no * concern of the pointer being changed while it is being read. * However when reading device's uevent file we read driver pointer * without taking device lock (so we do not block there for * arbitrary amount of time). We use WRITE_ONCE() here to prevent * tearing so that READ_ONCE() can safely be used in uevent code. */ // FIXME - this cast should not be needed "soon" WRITE_ONCE(dev->driver, (struct device_driver *)drv); } int devres_release_all(struct device *dev); void device_block_probing(void); void device_unblock_probing(void); void deferred_probe_extend_timeout(void); void driver_deferred_probe_trigger(void); const char *device_get_devnode(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid, const char **tmp); /* /sys/devices directory */ extern struct kset *devices_kset; void devices_kset_move_last(struct device *dev); #if defined(CONFIG_MODULES) && defined(CONFIG_SYSFS) int module_add_driver(struct module *mod, const struct device_driver *drv); void module_remove_driver(const struct device_driver *drv); #else static inline int module_add_driver(struct module *mod, struct device_driver *drv) { return 0; } static inline void module_remove_driver(struct device_driver *drv) { } #endif #ifdef CONFIG_DEVTMPFS int devtmpfs_init(void); #else static inline int devtmpfs_init(void) { return 0; } #endif #ifdef CONFIG_BLOCK extern const struct class block_class; static inline bool is_blockdev(struct device *dev) { return dev->class == &block_class; } #else static inline bool is_blockdev(struct device *dev) { return false; } #endif /* Device links support */ int device_links_read_lock(void); void device_links_read_unlock(int idx); int device_links_read_lock_held(void); int device_links_check_suppliers(struct device *dev); void device_links_force_bind(struct device *dev); void device_links_driver_bound(struct device *dev); void device_links_driver_cleanup(struct device *dev); void device_links_no_driver(struct device *dev); bool device_links_busy(struct device *dev); void device_links_unbind_consumers(struct device *dev); bool device_link_flag_is_sync_state_only(u32 flags); void fw_devlink_drivers_done(void); void fw_devlink_probing_done(void); #define dev_for_each_link_to_supplier(__link, __dev) \ list_for_each_entry_srcu(__link, &(__dev)->links.suppliers, c_node, \ device_links_read_lock_held()) #define dev_for_each_link_to_consumer(__link, __dev) \ list_for_each_entry_srcu(__link, &(__dev)->links.consumers, s_node, \ device_links_read_lock_held()) /* device pm support */ void device_pm_move_to_tail(struct device *dev); #ifdef CONFIG_DEVTMPFS int devtmpfs_create_node(struct device *dev); int devtmpfs_delete_node(struct device *dev); #else static inline int devtmpfs_create_node(struct device *dev) { return 0; } static inline int devtmpfs_delete_node(struct device *dev) { return 0; } #endif void software_node_notify(struct device *dev); void software_node_notify_remove(struct device *dev); |
| 1 1 14 14 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef TUN_VNET_H #define TUN_VNET_H /* High bits in flags field are unused. */ #define TUN_VNET_LE 0x80000000 #define TUN_VNET_BE 0x40000000 #define TUN_VNET_TNL_SIZE sizeof(struct virtio_net_hdr_v1_hash_tunnel) static inline bool tun_vnet_legacy_is_little_endian(unsigned int flags) { bool be = IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE) && (flags & TUN_VNET_BE); return !be && virtio_legacy_is_little_endian(); } static inline long tun_get_vnet_be(unsigned int flags, int __user *argp) { int be = !!(flags & TUN_VNET_BE); if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE)) return -EINVAL; if (put_user(be, argp)) return -EFAULT; return 0; } static inline long tun_set_vnet_be(unsigned int *flags, int __user *argp) { int be; if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE)) return -EINVAL; if (get_user(be, argp)) return -EFAULT; if (be) *flags |= TUN_VNET_BE; else *flags &= ~TUN_VNET_BE; return 0; } static inline bool tun_vnet_is_little_endian(unsigned int flags) { return flags & TUN_VNET_LE || tun_vnet_legacy_is_little_endian(flags); } static inline u16 tun_vnet16_to_cpu(unsigned int flags, __virtio16 val) { return __virtio16_to_cpu(tun_vnet_is_little_endian(flags), val); } static inline __virtio16 cpu_to_tun_vnet16(unsigned int flags, u16 val) { return __cpu_to_virtio16(tun_vnet_is_little_endian(flags), val); } static inline long tun_vnet_ioctl(int *vnet_hdr_sz, unsigned int *flags, unsigned int cmd, int __user *sp) { int s; switch (cmd) { case TUNGETVNETHDRSZ: s = *vnet_hdr_sz; if (put_user(s, sp)) return -EFAULT; return 0; case TUNSETVNETHDRSZ: if (get_user(s, sp)) return -EFAULT; if (s < (int)sizeof(struct virtio_net_hdr)) return -EINVAL; *vnet_hdr_sz = s; return 0; case TUNGETVNETLE: s = !!(*flags & TUN_VNET_LE); if (put_user(s, sp)) return -EFAULT; return 0; case TUNSETVNETLE: if (get_user(s, sp)) return -EFAULT; if (s) *flags |= TUN_VNET_LE; else *flags &= ~TUN_VNET_LE; return 0; case TUNGETVNETBE: return tun_get_vnet_be(*flags, sp); case TUNSETVNETBE: return tun_set_vnet_be(flags, sp); default: return -EINVAL; } } static inline unsigned int tun_vnet_parse_size(netdev_features_t features) { if (!(features & NETIF_F_GSO_UDP_TUNNEL)) return sizeof(struct virtio_net_hdr); return TUN_VNET_TNL_SIZE; } static inline int __tun_vnet_hdr_get(int sz, unsigned int flags, netdev_features_t features, struct iov_iter *from, struct virtio_net_hdr *hdr) { unsigned int parsed_size = tun_vnet_parse_size(features); u16 hdr_len; if (iov_iter_count(from) < sz) return -EINVAL; if (!copy_from_iter_full(hdr, parsed_size, from)) return -EFAULT; hdr_len = tun_vnet16_to_cpu(flags, hdr->hdr_len); if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { hdr_len = max(tun_vnet16_to_cpu(flags, hdr->csum_start) + tun_vnet16_to_cpu(flags, hdr->csum_offset) + 2, hdr_len); hdr->hdr_len = cpu_to_tun_vnet16(flags, hdr_len); } if (hdr_len > iov_iter_count(from)) return -EINVAL; iov_iter_advance(from, sz - parsed_size); return hdr_len; } static inline int tun_vnet_hdr_get(int sz, unsigned int flags, struct iov_iter *from, struct virtio_net_hdr *hdr) { return __tun_vnet_hdr_get(sz, flags, 0, from, hdr); } static inline int __tun_vnet_hdr_put(int sz, netdev_features_t features, struct iov_iter *iter, const struct virtio_net_hdr *hdr) { unsigned int parsed_size = tun_vnet_parse_size(features); if (unlikely(iov_iter_count(iter) < sz)) return -EINVAL; if (unlikely(copy_to_iter(hdr, parsed_size, iter) != parsed_size)) return -EFAULT; if (iov_iter_zero(sz - parsed_size, iter) != sz - parsed_size) return -EFAULT; return 0; } static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter, const struct virtio_net_hdr *hdr) { return __tun_vnet_hdr_put(sz, 0, iter, hdr); } static inline int tun_vnet_hdr_to_skb(unsigned int flags, struct sk_buff *skb, const struct virtio_net_hdr *hdr) { return virtio_net_hdr_to_skb(skb, hdr, tun_vnet_is_little_endian(flags)); } /* * Tun is not aware of the negotiated guest features, guess them from the * virtio net hdr size */ static inline netdev_features_t tun_vnet_hdr_guest_features(int vnet_hdr_sz) { if (vnet_hdr_sz >= TUN_VNET_TNL_SIZE) return NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM; return 0; } static inline int tun_vnet_hdr_tnl_to_skb(unsigned int flags, netdev_features_t features, struct sk_buff *skb, const struct virtio_net_hdr_v1_hash_tunnel *hdr) { return virtio_net_hdr_tnl_to_skb(skb, hdr, features & NETIF_F_GSO_UDP_TUNNEL, features & NETIF_F_GSO_UDP_TUNNEL_CSUM, tun_vnet_is_little_endian(flags)); } static inline int tun_vnet_hdr_from_skb(unsigned int flags, const struct net_device *dev, const struct sk_buff *skb, struct virtio_net_hdr *hdr) { int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0; if (virtio_net_hdr_from_skb(skb, hdr, tun_vnet_is_little_endian(flags), true, vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); if (net_ratelimit()) { netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->gso_size), tun_vnet16_to_cpu(flags, hdr->hdr_len)); print_hex_dump(KERN_ERR, "tun: ", DUMP_PREFIX_NONE, 16, 1, skb->head, min(tun_vnet16_to_cpu(flags, hdr->hdr_len), 64), true); } WARN_ON_ONCE(1); return -EINVAL; } return 0; } static inline int tun_vnet_hdr_tnl_from_skb(unsigned int flags, const struct net_device *dev, const struct sk_buff *skb, struct virtio_net_hdr_v1_hash_tunnel *tnl_hdr) { bool has_tnl_offload = !!(dev->features & NETIF_F_GSO_UDP_TUNNEL); int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0; if (virtio_net_hdr_tnl_from_skb(skb, tnl_hdr, has_tnl_offload, tun_vnet_is_little_endian(flags), vlan_hlen)) { struct virtio_net_hdr_v1 *hdr = &tnl_hdr->hash_hdr.hdr; struct skb_shared_info *sinfo = skb_shinfo(skb); if (net_ratelimit()) { int hdr_len = tun_vnet16_to_cpu(flags, hdr->hdr_len); netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->gso_size), tun_vnet16_to_cpu(flags, hdr->hdr_len)); print_hex_dump(KERN_ERR, "tun: ", DUMP_PREFIX_NONE, 16, 1, skb->head, min(hdr_len, 64), true); } WARN_ON_ONCE(1); return -EINVAL; } return 0; } #endif /* TUN_VNET_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 | #ifndef LLC_H #define LLC_H /* * 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/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rculist_nulls.h> #include <linux/hash.h> #include <linux/jhash.h> #include <linux/atomic.h> struct net_device; struct packet_type; struct sk_buff; struct llc_addr { unsigned char lsap; unsigned char mac[IFHWADDRLEN]; }; #define LLC_SAP_STATE_INACTIVE 1 #define LLC_SAP_STATE_ACTIVE 2 #define LLC_SK_DEV_HASH_BITS 6 #define LLC_SK_DEV_HASH_ENTRIES (1<<LLC_SK_DEV_HASH_BITS) #define LLC_SK_LADDR_HASH_BITS 6 #define LLC_SK_LADDR_HASH_ENTRIES (1<<LLC_SK_LADDR_HASH_BITS) /** * struct llc_sap - Defines the SAP component * * @station - station this sap belongs to * @state - sap state * @p_bit - only lowest-order bit used * @f_bit - only lowest-order bit used * @laddr - SAP value in this 'lsap' * @node - entry in station sap_list * @sk_list - LLC sockets this one manages */ struct llc_sap { unsigned char state; unsigned char p_bit; unsigned char f_bit; refcount_t refcnt; int (*rcv_func)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); struct llc_addr laddr; struct list_head node; spinlock_t sk_lock; int sk_count; struct hlist_nulls_head sk_laddr_hash[LLC_SK_LADDR_HASH_ENTRIES]; struct hlist_head sk_dev_hash[LLC_SK_DEV_HASH_ENTRIES]; struct rcu_head rcu; }; static inline struct hlist_head *llc_sk_dev_hash(struct llc_sap *sap, int ifindex) { u32 bucket = hash_32(ifindex, LLC_SK_DEV_HASH_BITS); return &sap->sk_dev_hash[bucket]; } static inline u32 llc_sk_laddr_hashfn(struct llc_sap *sap, const struct llc_addr *laddr) { return hash_32(jhash(laddr->mac, sizeof(laddr->mac), 0), LLC_SK_LADDR_HASH_BITS); } static inline struct hlist_nulls_head *llc_sk_laddr_hash(struct llc_sap *sap, const struct llc_addr *laddr) { return &sap->sk_laddr_hash[llc_sk_laddr_hashfn(sap, laddr)]; } #define LLC_DEST_INVALID 0 /* Invalid LLC PDU type */ #define LLC_DEST_SAP 1 /* Type 1 goes here */ #define LLC_DEST_CONN 2 /* Type 2 goes here */ extern struct list_head llc_sap_list; int llc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); int llc_mac_hdr_init(struct sk_buff *skb, const unsigned char *sa, const unsigned char *da); void llc_add_pack(int type, void (*handler)(struct llc_sap *sap, struct sk_buff *skb)); void llc_remove_pack(int type); void llc_set_station_handler(void (*handler)(struct sk_buff *skb)); struct llc_sap *llc_sap_open(unsigned char lsap, int (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)); static inline void llc_sap_hold(struct llc_sap *sap) { refcount_inc(&sap->refcnt); } static inline bool llc_sap_hold_safe(struct llc_sap *sap) { return refcount_inc_not_zero(&sap->refcnt); } void llc_sap_close(struct llc_sap *sap); static inline void llc_sap_put(struct llc_sap *sap) { if (refcount_dec_and_test(&sap->refcnt)) llc_sap_close(sap); } struct llc_sap *llc_sap_find(unsigned char sap_value); int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, const unsigned char *dmac, unsigned char dsap); void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_station_init(void); void llc_station_exit(void); #ifdef CONFIG_PROC_FS int llc_proc_init(void); void llc_proc_exit(void); #else #define llc_proc_init() (0) #define llc_proc_exit() do { } while(0) #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL int llc_sysctl_init(void); void llc_sysctl_exit(void); extern int sysctl_llc2_ack_timeout; extern int sysctl_llc2_busy_timeout; extern int sysctl_llc2_p_timeout; extern int sysctl_llc2_rej_timeout; #else #define llc_sysctl_init() (0) #define llc_sysctl_exit() do { } while(0) #endif /* CONFIG_SYSCTL */ #endif /* LLC_H */ |
| 4 25 68 64 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 | /* SPDX-License-Identifier: GPL-2.0 */ #if !defined(_TRACE_HANDLE_EXIT_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_HANDLE_EXIT_ARM64_KVM_H #include <linux/tracepoint.h> #include "sys_regs.h" #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm TRACE_EVENT(kvm_wfx_arm64, TP_PROTO(unsigned long vcpu_pc, bool is_wfe), TP_ARGS(vcpu_pc, is_wfe), TP_STRUCT__entry( __field(unsigned long, vcpu_pc) __field(bool, is_wfe) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->is_wfe = is_wfe; ), TP_printk("guest executed wf%c at: 0x%016lx", __entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc) ); TRACE_EVENT(kvm_hvc_arm64, TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm), TP_ARGS(vcpu_pc, r0, imm), TP_STRUCT__entry( __field(unsigned long, vcpu_pc) __field(unsigned long, r0) __field(unsigned long, imm) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->r0 = r0; __entry->imm = imm; ), TP_printk("HVC at 0x%016lx (r0: 0x%016lx, imm: 0x%lx)", __entry->vcpu_pc, __entry->r0, __entry->imm) ); /* * The dreg32 name is a leftover from a distant past. This will really * output a 64bit value... */ TRACE_EVENT(kvm_arm_set_dreg32, TP_PROTO(const char *name, __u64 value), TP_ARGS(name, value), TP_STRUCT__entry( __field(const char *, name) __field(__u64, value) ), TP_fast_assign( __entry->name = name; __entry->value = value; ), TP_printk("%s: 0x%llx", __entry->name, __entry->value) ); TRACE_EVENT(kvm_handle_sys_reg, TP_PROTO(unsigned long hsr), TP_ARGS(hsr), TP_STRUCT__entry( __field(unsigned long, hsr) ), TP_fast_assign( __entry->hsr = hsr; ), TP_printk("HSR 0x%08lx", __entry->hsr) ); TRACE_EVENT(kvm_sys_access, TP_PROTO(unsigned long vcpu_pc, struct sys_reg_params *params, const struct sys_reg_desc *reg), TP_ARGS(vcpu_pc, params, reg), TP_STRUCT__entry( __field(unsigned long, vcpu_pc) __field(bool, is_write) __field(const char *, name) __field(u8, Op0) __field(u8, Op1) __field(u8, CRn) __field(u8, CRm) __field(u8, Op2) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->is_write = params->is_write; __entry->name = reg->name; __entry->Op0 = reg->Op0; __entry->Op0 = reg->Op0; __entry->Op1 = reg->Op1; __entry->CRn = reg->CRn; __entry->CRm = reg->CRm; __entry->Op2 = reg->Op2; ), TP_printk("PC: %lx %s (%d,%d,%d,%d,%d) %s", __entry->vcpu_pc, __entry->name ?: "UNKN", __entry->Op0, __entry->Op1, __entry->CRn, __entry->CRm, __entry->Op2, str_write_read(__entry->is_write)) ); TRACE_EVENT(kvm_set_guest_debug, TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug), TP_ARGS(vcpu, guest_debug), TP_STRUCT__entry( __field(struct kvm_vcpu *, vcpu) __field(__u32, guest_debug) ), TP_fast_assign( __entry->vcpu = vcpu; __entry->guest_debug = guest_debug; ), TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug) ); #endif /* _TRACE_HANDLE_EXIT_ARM64_KVM_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace_handle_exit /* This part must be outside protection */ #include <trace/define_trace.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 | /* 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 **, unsigned long *); /* 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(vm_flags_t vm_flags, const struct inode *inode, struct dax_device *dax_dev) { if (!(vm_flags & VM_SYNC)) return true; if (!IS_DAX(inode)) 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(vm_flags_t vm_flags, const struct inode *inode, struct dax_device *dax_dev) { return !(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); static inline bool dax_page_is_idle(struct page *page) { return page && page_ref_count(page) == 0; } #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 */ #if !IS_ENABLED(CONFIG_FS_DAX) static inline int __must_check dax_break_layout(struct inode *inode, loff_t start, loff_t end, void (cb)(struct inode *)) { return 0; } static inline void dax_break_layout_final(struct inode *inode) { } #endif 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, unsigned long *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, unsigned long *pfnp, int *errp, const struct iomap_ops *ops); vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, unsigned int order, unsigned long pfn); int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); void dax_delete_mapping_range(struct address_space *mapping, loff_t start, loff_t end); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); int __must_check dax_break_layout(struct inode *inode, loff_t start, loff_t end, void (cb)(struct inode *)); static inline int __must_check dax_break_layout_inode(struct inode *inode, void (cb)(struct inode *)) { return dax_break_layout(inode, 0, LLONG_MAX, cb); } void dax_break_layout_final(struct inode *inode); 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 |
| 45 45 192 1 193 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/pgalloc.h * * Copyright (C) 2000-2001 Russell King * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_PGALLOC_H #define __ASM_PGALLOC_H #include <asm/pgtable-hwdef.h> #include <asm/processor.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #define __HAVE_ARCH_PGD_FREE #define __HAVE_ARCH_PUD_FREE #include <asm-generic/pgalloc.h> #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) #if CONFIG_PGTABLE_LEVELS > 2 static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) { set_pud(pudp, __pud(__phys_to_pud_val(pmdp) | prot)); } static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp) { pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_AF; pudval |= (mm == &init_mm) ? PUD_TABLE_UXN : PUD_TABLE_PXN; __pud_populate(pudp, __pa(pmdp), pudval); } #else static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) { BUILD_BUG(); } #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) { if (pgtable_l4_enabled()) set_p4d(p4dp, __p4d(__phys_to_p4d_val(pudp) | prot)); } static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp) { p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_AF; p4dval |= (mm == &init_mm) ? P4D_TABLE_UXN : P4D_TABLE_PXN; __p4d_populate(p4dp, __pa(pudp), p4dval); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) { if (!pgtable_l4_enabled()) return; __pud_free(mm, pud); } #else static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) { BUILD_BUG(); } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #if CONFIG_PGTABLE_LEVELS > 4 static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot) { if (pgtable_l5_enabled()) set_pgd(pgdp, __pgd(__phys_to_pgd_val(p4dp) | prot)); } static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, p4d_t *p4dp) { pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_AF; pgdval |= (mm == &init_mm) ? PGD_TABLE_UXN : PGD_TABLE_PXN; __pgd_populate(pgdp, __pa(p4dp), pgdval); } #else static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot) { BUILD_BUG(); } #endif /* CONFIG_PGTABLE_LEVELS > 4 */ extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp); static inline void __pmd_populate(pmd_t *pmdp, phys_addr_t ptep, pmdval_t prot) { set_pmd(pmdp, __pmd(__phys_to_pmd_val(ptep) | prot)); } /* * Populate the pmdp entry with a pointer to the pte. This pmd is part * of the mm address space. */ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep) { VM_BUG_ON(mm && mm != &init_mm); __pmd_populate(pmdp, __pa(ptep), PMD_TYPE_TABLE | PMD_TABLE_AF | PMD_TABLE_UXN); } static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep) { VM_BUG_ON(mm == &init_mm); __pmd_populate(pmdp, page_to_phys(ptep), PMD_TYPE_TABLE | PMD_TABLE_AF | PMD_TABLE_PXN); } #endif |
| 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, bool daddr_set, bool saddr_set) { 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_set; #ifdef CONFIG_IPV6_SUBTREES np->saddr_cache = saddr_set; #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(dst)->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_rcu(dst)); 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 |
| 38 21 10 7 7 6 3 38 36 38 38 38 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * common LSM auditing functions * * Based on code written for SELinux by : * Stephen Smalley * James Morris <jmorris@redhat.com> * Author : Etienne Basset, <etienne.basset@ensta.org> */ #include <linux/types.h> #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/gfp.h> #include <linux/fs.h> #include <linux/init.h> #include <net/sock.h> #include <linux/un.h> #include <net/af_unix.h> #include <linux/audit.h> #include <linux/ipv6.h> #include <linux/ip.h> #include <net/ip.h> #include <net/ipv6.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/sctp.h> #include <linux/lsm_audit.h> #include <linux/security.h> /** * ipv4_skb_to_auditdata : fill auditdata from skb * @skb : the skb * @ad : the audit data to fill * @proto : the layer 4 protocol * * return 0 on success */ int ipv4_skb_to_auditdata(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int ret = 0; struct iphdr *ih; ih = ip_hdr(skb); ad->u.net->v4info.saddr = ih->saddr; ad->u.net->v4info.daddr = ih->daddr; if (proto) *proto = ih->protocol; /* non initial fragment */ if (ntohs(ih->frag_off) & IP_OFFSET) return 0; switch (ih->protocol) { case IPPROTO_TCP: { struct tcphdr *th = tcp_hdr(skb); ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr *uh = udp_hdr(skb); ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_SCTP: { struct sctphdr *sh = sctp_hdr(skb); ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } default: ret = -EINVAL; } return ret; } #if IS_ENABLED(CONFIG_IPV6) /** * ipv6_skb_to_auditdata : fill auditdata from skb * @skb : the skb * @ad : the audit data to fill * @proto : the layer 4 protocol * * return 0 on success */ int ipv6_skb_to_auditdata(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int offset, ret = 0; struct ipv6hdr *ip6; u8 nexthdr; __be16 frag_off; ip6 = ipv6_hdr(skb); ad->u.net->v6info.saddr = ip6->saddr; ad->u.net->v6info.daddr = ip6->daddr; /* IPv6 can have several extension header before the Transport header * skip them */ offset = skb_network_offset(skb); offset += sizeof(*ip6); nexthdr = ip6->nexthdr; offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset < 0) return 0; if (proto) *proto = nexthdr; switch (nexthdr) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } default: ret = -EINVAL; } return ret; } #endif static inline void print_ipv6_addr(struct audit_buffer *ab, const struct in6_addr *addr, __be16 port, const char *name1, const char *name2) { if (!ipv6_addr_any(addr)) audit_log_format(ab, " %s=%pI6c", name1, addr); if (port) audit_log_format(ab, " %s=%d", name2, ntohs(port)); } static inline void print_ipv4_addr(struct audit_buffer *ab, __be32 addr, __be16 port, const char *name1, const char *name2) { if (addr) audit_log_format(ab, " %s=%pI4", name1, &addr); if (port) audit_log_format(ab, " %s=%d", name2, ntohs(port)); } /** * audit_log_lsm_data - helper to log common LSM audit data * @ab : the audit buffer * @a : common audit data */ void audit_log_lsm_data(struct audit_buffer *ab, const struct common_audit_data *a) { /* * To keep stack sizes in check force programmers to notice if they * start making this union too large! See struct lsm_network_audit * as an example of how to deal with large data. */ BUILD_BUG_ON(sizeof(a->u) > sizeof(void *)*2); switch (a->type) { case LSM_AUDIT_DATA_NONE: return; case LSM_AUDIT_DATA_IPC: audit_log_format(ab, " ipc_key=%d ", a->u.ipc_id); break; case LSM_AUDIT_DATA_CAP: audit_log_format(ab, " capability=%d ", a->u.cap); break; case LSM_AUDIT_DATA_PATH: { struct inode *inode; audit_log_d_path(ab, " path=", &a->u.path); inode = d_backing_inode(a->u.path.dentry); if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } break; } case LSM_AUDIT_DATA_FILE: { struct inode *inode; audit_log_d_path(ab, " path=", &a->u.file->f_path); inode = file_inode(a->u.file); if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } break; } case LSM_AUDIT_DATA_IOCTL_OP: { struct inode *inode; audit_log_d_path(ab, " path=", &a->u.op->path); inode = a->u.op->path.dentry->d_inode; if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } audit_log_format(ab, " ioctlcmd=0x%hx", a->u.op->cmd); break; } case LSM_AUDIT_DATA_DENTRY: { struct inode *inode; audit_log_format(ab, " name="); spin_lock(&a->u.dentry->d_lock); audit_log_untrustedstring(ab, a->u.dentry->d_name.name); spin_unlock(&a->u.dentry->d_lock); inode = d_backing_inode(a->u.dentry); if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } break; } case LSM_AUDIT_DATA_INODE: { struct dentry *dentry; struct inode *inode; rcu_read_lock(); inode = a->u.inode; dentry = d_find_alias_rcu(inode); if (dentry) { audit_log_format(ab, " name="); spin_lock(&dentry->d_lock); audit_log_untrustedstring(ab, dentry->d_name.name); spin_unlock(&dentry->d_lock); } audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); rcu_read_unlock(); break; } case LSM_AUDIT_DATA_TASK: { struct task_struct *tsk = a->u.tsk; if (tsk) { pid_t pid = task_tgid_nr(tsk); if (pid) { char tskcomm[sizeof(tsk->comm)]; audit_log_format(ab, " opid=%d ocomm=", pid); audit_log_untrustedstring(ab, get_task_comm(tskcomm, tsk)); } } break; } case LSM_AUDIT_DATA_NET: if (a->u.net->sk) { const struct sock *sk = a->u.net->sk; const struct unix_sock *u; struct unix_address *addr; int len = 0; char *p = NULL; switch (sk->sk_family) { case AF_INET: { const struct inet_sock *inet = inet_sk(sk); print_ipv4_addr(ab, inet->inet_rcv_saddr, inet->inet_sport, "laddr", "lport"); print_ipv4_addr(ab, inet->inet_daddr, inet->inet_dport, "faddr", "fport"); break; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { const struct inet_sock *inet = inet_sk(sk); print_ipv6_addr(ab, &sk->sk_v6_rcv_saddr, inet->inet_sport, "laddr", "lport"); print_ipv6_addr(ab, &sk->sk_v6_daddr, inet->inet_dport, "faddr", "fport"); break; } #endif case AF_UNIX: u = unix_sk(sk); addr = smp_load_acquire(&u->addr); if (!addr) break; if (u->path.dentry) { audit_log_d_path(ab, " path=", &u->path); break; } len = addr->len-sizeof(short); p = &addr->name->sun_path[0]; audit_log_format(ab, " path="); if (*p) audit_log_untrustedstring(ab, p); else audit_log_n_hex(ab, p, len); break; } } switch (a->u.net->family) { case AF_INET: print_ipv4_addr(ab, a->u.net->v4info.saddr, a->u.net->sport, "saddr", "src"); print_ipv4_addr(ab, a->u.net->v4info.daddr, a->u.net->dport, "daddr", "dest"); break; case AF_INET6: print_ipv6_addr(ab, &a->u.net->v6info.saddr, a->u.net->sport, "saddr", "src"); print_ipv6_addr(ab, &a->u.net->v6info.daddr, a->u.net->dport, "daddr", "dest"); break; } if (a->u.net->netif > 0) { struct net_device *dev; /* NOTE: we always use init's namespace */ dev = dev_get_by_index(&init_net, a->u.net->netif); if (dev) { audit_log_format(ab, " netif=%s", dev->name); dev_put(dev); } } break; #ifdef CONFIG_KEYS case LSM_AUDIT_DATA_KEY: audit_log_format(ab, " key_serial=%u", a->u.key_struct.key); if (a->u.key_struct.key_desc) { audit_log_format(ab, " key_desc="); audit_log_untrustedstring(ab, a->u.key_struct.key_desc); } break; #endif case LSM_AUDIT_DATA_KMOD: audit_log_format(ab, " kmod="); audit_log_untrustedstring(ab, a->u.kmod_name); break; case LSM_AUDIT_DATA_IBPKEY: { struct in6_addr sbn_pfx; memset(&sbn_pfx.s6_addr, 0, sizeof(sbn_pfx.s6_addr)); memcpy(&sbn_pfx.s6_addr, &a->u.ibpkey->subnet_prefix, sizeof(a->u.ibpkey->subnet_prefix)); audit_log_format(ab, " pkey=0x%x subnet_prefix=%pI6c", a->u.ibpkey->pkey, &sbn_pfx); break; } case LSM_AUDIT_DATA_IBENDPORT: audit_log_format(ab, " device=%s port_num=%u", a->u.ibendport->dev_name, a->u.ibendport->port); break; case LSM_AUDIT_DATA_LOCKDOWN: audit_log_format(ab, " lockdown_reason=\"%s\"", lockdown_reasons[a->u.reason]); break; case LSM_AUDIT_DATA_ANONINODE: audit_log_format(ab, " anonclass=%s", a->u.anonclass); break; case LSM_AUDIT_DATA_NLMSGTYPE: audit_log_format(ab, " nl-msgtype=%hu", a->u.nlmsg_type); break; } /* switch (a->type) */ } /** * dump_common_audit_data - helper to dump common audit data * @ab : the audit buffer * @a : common audit data */ static void dump_common_audit_data(struct audit_buffer *ab, const struct common_audit_data *a) { char comm[sizeof(current->comm)]; audit_log_format(ab, " pid=%d comm=", task_tgid_nr(current)); audit_log_untrustedstring(ab, get_task_comm(comm, current)); audit_log_lsm_data(ab, a); } /** * common_lsm_audit - generic LSM auditing function * @a: auxiliary audit data * @pre_audit: lsm-specific pre-audit callback * @post_audit: lsm-specific post-audit callback * * setup the audit buffer for common security information * uses callback to print LSM specific information */ void common_lsm_audit(struct common_audit_data *a, void (*pre_audit)(struct audit_buffer *, void *), void (*post_audit)(struct audit_buffer *, void *)) { struct audit_buffer *ab; if (a == NULL) return; /* we use GFP_ATOMIC so we won't sleep */ ab = audit_log_start(audit_context(), GFP_ATOMIC | __GFP_NOWARN, AUDIT_AVC); if (ab == NULL) return; if (pre_audit) pre_audit(ab, a); dump_common_audit_data(ab, a); if (post_audit) post_audit(ab, a); audit_log_end(ab); } |
| 4 4 | 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 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* raw.c - Raw sockets for protocol family CAN * * Copyright (c) 2002-2007 Volkswagen Group Electronic Research * 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 name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * 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. * */ #include <linux/module.h> #include <linux/init.h> #include <linux/uio.h> #include <linux/net.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/socket.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> #include <linux/can/dev.h> /* for can_is_canxl_dev_mtu() */ #include <linux/can/skb.h> #include <linux/can/raw.h> #include <net/sock.h> #include <net/net_namespace.h> MODULE_DESCRIPTION("PF_CAN raw protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>"); MODULE_ALIAS("can-proto-1"); #define RAW_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex) #define MASK_ALL 0 /* A raw socket has a list of can_filters attached to it, each receiving * the CAN frames matching that filter. If the filter list is empty, * no CAN frames will be received by the socket. The default after * opening the socket, is to have one filter which receives all frames. * The filter list is allocated dynamically with the exception of the * list containing only one item. This common case is optimized by * storing the single filter in dfilter, to avoid using dynamic memory. */ struct uniqframe { const struct sk_buff *skb; int skbcnt; unsigned int join_rx_count; }; struct raw_sock { struct sock sk; struct net_device *dev; netdevice_tracker dev_tracker; struct list_head notifier; int ifindex; unsigned int bound:1; unsigned int loopback:1; unsigned int recv_own_msgs:1; unsigned int fd_frames:1; unsigned int xl_frames:1; unsigned int join_filters:1; struct can_raw_vcid_options raw_vcid_opts; canid_t tx_vcid_shifted; canid_t rx_vcid_shifted; canid_t rx_vcid_mask_shifted; can_err_mask_t err_mask; int count; /* number of active filters */ struct can_filter dfilter; /* default/single filter */ struct can_filter *filter; /* pointer to filter(s) */ struct uniqframe __percpu *uniq; }; static LIST_HEAD(raw_notifier_list); static DEFINE_SPINLOCK(raw_notifier_lock); static struct raw_sock *raw_busy_notifier; /* Return pointer to store the extra msg flags for raw_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' * in skb->cb. */ static inline unsigned int *raw_flags(struct sk_buff *skb) { sock_skb_cb_check_size(sizeof(struct sockaddr_can) + sizeof(unsigned int)); /* return pointer after struct sockaddr_can */ return (unsigned int *)(&((struct sockaddr_can *)skb->cb)[1]); } static inline struct raw_sock *raw_sk(const struct sock *sk) { return (struct raw_sock *)sk; } static void raw_rcv(struct sk_buff *oskb, void *data) { struct sock *sk = (struct sock *)data; struct raw_sock *ro = raw_sk(sk); enum skb_drop_reason reason; struct sockaddr_can *addr; struct sk_buff *skb; unsigned int *pflags; /* check the received tx sock reference */ if (!ro->recv_own_msgs && oskb->sk == sk) return; /* make sure to not pass oversized frames to the socket */ if (!ro->fd_frames && can_is_canfd_skb(oskb)) return; if (can_is_canxl_skb(oskb)) { struct canxl_frame *cxl = (struct canxl_frame *)oskb->data; /* make sure to not pass oversized frames to the socket */ if (!ro->xl_frames) return; /* filter CAN XL VCID content */ if (ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_RX_FILTER) { /* apply VCID filter if user enabled the filter */ if ((cxl->prio & ro->rx_vcid_mask_shifted) != (ro->rx_vcid_shifted & ro->rx_vcid_mask_shifted)) return; } else { /* no filter => do not forward VCID tagged frames */ if (cxl->prio & CANXL_VCID_MASK) return; } } /* eliminate multiple filter matches for the same skb */ if (this_cpu_ptr(ro->uniq)->skb == oskb && this_cpu_ptr(ro->uniq)->skbcnt == can_skb_prv(oskb)->skbcnt) { if (!ro->join_filters) return; this_cpu_inc(ro->uniq->join_rx_count); /* drop frame until all enabled filters matched */ if (this_cpu_ptr(ro->uniq)->join_rx_count < ro->count) return; } else { this_cpu_ptr(ro->uniq)->skb = oskb; this_cpu_ptr(ro->uniq)->skbcnt = can_skb_prv(oskb)->skbcnt; this_cpu_ptr(ro->uniq)->join_rx_count = 1; /* drop first frame to check all enabled filters? */ if (ro->join_filters && ro->count > 1) return; } /* clone the given skb to be able to enqueue it into the rcv queue */ skb = skb_clone(oskb, GFP_ATOMIC); if (!skb) return; /* Put the datagram to the queue so that raw_recvmsg() can get * it from there. We need to pass the interface index to * raw_recvmsg(). We pass a whole struct sockaddr_can in * skb->cb containing the interface index. */ sock_skb_cb_check_size(sizeof(struct sockaddr_can)); addr = (struct sockaddr_can *)skb->cb; memset(addr, 0, sizeof(*addr)); addr->can_family = AF_CAN; addr->can_ifindex = skb->dev->ifindex; /* add CAN specific message flags for raw_recvmsg() */ pflags = raw_flags(skb); *pflags = 0; if (oskb->sk) *pflags |= MSG_DONTROUTE; if (oskb->sk == sk) *pflags |= MSG_CONFIRM; if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) sk_skb_reason_drop(sk, skb, reason); } static int raw_enable_filters(struct net *net, struct net_device *dev, struct sock *sk, struct can_filter *filter, int count) { int err = 0; int i; for (i = 0; i < count; i++) { err = can_rx_register(net, dev, filter[i].can_id, filter[i].can_mask, raw_rcv, sk, "raw", sk); if (err) { /* clean up successfully registered filters */ while (--i >= 0) can_rx_unregister(net, dev, filter[i].can_id, filter[i].can_mask, raw_rcv, sk); break; } } return err; } static int raw_enable_errfilter(struct net *net, struct net_device *dev, struct sock *sk, can_err_mask_t err_mask) { int err = 0; if (err_mask) err = can_rx_register(net, dev, 0, err_mask | CAN_ERR_FLAG, raw_rcv, sk, "raw", sk); return err; } static void raw_disable_filters(struct net *net, struct net_device *dev, struct sock *sk, struct can_filter *filter, int count) { int i; for (i = 0; i < count; i++) can_rx_unregister(net, dev, filter[i].can_id, filter[i].can_mask, raw_rcv, sk); } static inline void raw_disable_errfilter(struct net *net, struct net_device *dev, struct sock *sk, can_err_mask_t err_mask) { if (err_mask) can_rx_unregister(net, dev, 0, err_mask | CAN_ERR_FLAG, raw_rcv, sk); } static inline void raw_disable_allfilters(struct net *net, struct net_device *dev, struct sock *sk) { struct raw_sock *ro = raw_sk(sk); raw_disable_filters(net, dev, sk, ro->filter, ro->count); raw_disable_errfilter(net, dev, sk, ro->err_mask); } static int raw_enable_allfilters(struct net *net, struct net_device *dev, struct sock *sk) { struct raw_sock *ro = raw_sk(sk); int err; err = raw_enable_filters(net, dev, sk, ro->filter, ro->count); if (!err) { err = raw_enable_errfilter(net, dev, sk, ro->err_mask); if (err) raw_disable_filters(net, dev, sk, ro->filter, ro->count); } return err; } static void raw_notify(struct raw_sock *ro, unsigned long msg, struct net_device *dev) { struct sock *sk = &ro->sk; if (!net_eq(dev_net(dev), sock_net(sk))) return; if (ro->dev != dev) return; switch (msg) { case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ if (ro->bound) { raw_disable_allfilters(dev_net(dev), dev, sk); netdev_put(dev, &ro->dev_tracker); } if (ro->count > 1) kfree(ro->filter); ro->ifindex = 0; ro->bound = 0; ro->dev = NULL; ro->count = 0; release_sock(sk); sk->sk_err = ENODEV; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); break; case NETDEV_DOWN: sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); break; } } static int raw_notifier(struct notifier_block *nb, unsigned long msg, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (dev->type != ARPHRD_CAN) return NOTIFY_DONE; if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) return NOTIFY_DONE; if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */ return NOTIFY_DONE; spin_lock(&raw_notifier_lock); list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) { spin_unlock(&raw_notifier_lock); raw_notify(raw_busy_notifier, msg, dev); spin_lock(&raw_notifier_lock); } raw_busy_notifier = NULL; spin_unlock(&raw_notifier_lock); return NOTIFY_DONE; } static int raw_init(struct sock *sk) { struct raw_sock *ro = raw_sk(sk); ro->bound = 0; ro->ifindex = 0; ro->dev = NULL; /* set default filter to single entry dfilter */ ro->dfilter.can_id = 0; ro->dfilter.can_mask = MASK_ALL; ro->filter = &ro->dfilter; ro->count = 1; /* set default loopback behaviour */ ro->loopback = 1; ro->recv_own_msgs = 0; ro->fd_frames = 0; ro->xl_frames = 0; ro->join_filters = 0; /* alloc_percpu provides zero'ed memory */ ro->uniq = alloc_percpu(struct uniqframe); if (unlikely(!ro->uniq)) return -ENOMEM; /* set notifier */ spin_lock(&raw_notifier_lock); list_add_tail(&ro->notifier, &raw_notifier_list); spin_unlock(&raw_notifier_lock); return 0; } static int raw_release(struct socket *sock) { struct sock *sk = sock->sk; struct raw_sock *ro; struct net *net; if (!sk) return 0; ro = raw_sk(sk); net = sock_net(sk); spin_lock(&raw_notifier_lock); while (raw_busy_notifier == ro) { spin_unlock(&raw_notifier_lock); schedule_timeout_uninterruptible(1); spin_lock(&raw_notifier_lock); } list_del(&ro->notifier); spin_unlock(&raw_notifier_lock); rtnl_lock(); lock_sock(sk); /* remove current filters & unregister */ if (ro->bound) { if (ro->dev) { raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); netdev_put(ro->dev, &ro->dev_tracker); } else { raw_disable_allfilters(net, NULL, sk); } } if (ro->count > 1) kfree(ro->filter); ro->ifindex = 0; ro->bound = 0; ro->dev = NULL; ro->count = 0; free_percpu(ro->uniq); sock_orphan(sk); sock->sk = NULL; release_sock(sk); rtnl_unlock(); sock_prot_inuse_add(net, sk->sk_prot, -1); sock_put(sk); return 0; } static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); struct net_device *dev = NULL; int ifindex; int err = 0; int notify_enetdown = 0; if (len < RAW_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; rtnl_lock(); lock_sock(sk); if (ro->bound && addr->can_ifindex == ro->ifindex) goto out; if (addr->can_ifindex) { dev = dev_get_by_index(sock_net(sk), addr->can_ifindex); if (!dev) { err = -ENODEV; goto out; } if (dev->type != ARPHRD_CAN) { err = -ENODEV; goto out_put_dev; } if (!(dev->flags & IFF_UP)) notify_enetdown = 1; ifindex = dev->ifindex; /* filters set by default/setsockopt */ err = raw_enable_allfilters(sock_net(sk), dev, sk); if (err) goto out_put_dev; } else { ifindex = 0; /* filters set by default/setsockopt */ err = raw_enable_allfilters(sock_net(sk), NULL, sk); } if (!err) { if (ro->bound) { /* unregister old filters */ if (ro->dev) { raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); /* drop reference to old ro->dev */ netdev_put(ro->dev, &ro->dev_tracker); } else { raw_disable_allfilters(sock_net(sk), NULL, sk); } } ro->ifindex = ifindex; ro->bound = 1; /* bind() ok -> hold a reference for new ro->dev */ ro->dev = dev; if (ro->dev) netdev_hold(ro->dev, &ro->dev_tracker, GFP_KERNEL); } out_put_dev: /* remove potential reference from dev_get_by_index() */ dev_put(dev); out: release_sock(sk); rtnl_unlock(); if (notify_enetdown) { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } return err; } static int raw_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); if (peer) return -EOPNOTSUPP; memset(addr, 0, RAW_MIN_NAMELEN); addr->can_family = AF_CAN; addr->can_ifindex = ro->ifindex; return RAW_MIN_NAMELEN; } static int raw_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); struct can_filter *filter = NULL; /* dyn. alloc'ed filters */ struct can_filter sfilter; /* single filter */ struct net_device *dev = NULL; can_err_mask_t err_mask = 0; int count = 0; int flag; int err = 0; if (level != SOL_CAN_RAW) return -EINVAL; switch (optname) { case CAN_RAW_FILTER: if (optlen % sizeof(struct can_filter) != 0) return -EINVAL; if (optlen > CAN_RAW_FILTER_MAX * sizeof(struct can_filter)) return -EINVAL; count = optlen / sizeof(struct can_filter); if (count > 1) { /* filter does not fit into dfilter => alloc space */ filter = memdup_sockptr(optval, optlen); if (IS_ERR(filter)) return PTR_ERR(filter); } else if (count == 1) { if (copy_from_sockptr(&sfilter, optval, sizeof(sfilter))) return -EFAULT; } rtnl_lock(); lock_sock(sk); dev = ro->dev; if (ro->bound && dev) { if (dev->reg_state != NETREG_REGISTERED) { if (count > 1) kfree(filter); err = -ENODEV; goto out_fil; } } if (ro->bound) { /* (try to) register the new filters */ if (count == 1) err = raw_enable_filters(sock_net(sk), dev, sk, &sfilter, 1); else err = raw_enable_filters(sock_net(sk), dev, sk, filter, count); if (err) { if (count > 1) kfree(filter); goto out_fil; } /* remove old filter registrations */ raw_disable_filters(sock_net(sk), dev, sk, ro->filter, ro->count); } /* remove old filter space */ if (ro->count > 1) kfree(ro->filter); /* link new filters to the socket */ if (count == 1) { /* copy filter data for single filter */ ro->dfilter = sfilter; filter = &ro->dfilter; } ro->filter = filter; ro->count = count; out_fil: release_sock(sk); rtnl_unlock(); break; case CAN_RAW_ERR_FILTER: if (optlen != sizeof(err_mask)) return -EINVAL; if (copy_from_sockptr(&err_mask, optval, optlen)) return -EFAULT; err_mask &= CAN_ERR_MASK; rtnl_lock(); lock_sock(sk); dev = ro->dev; if (ro->bound && dev) { if (dev->reg_state != NETREG_REGISTERED) { err = -ENODEV; goto out_err; } } /* remove current error mask */ if (ro->bound) { /* (try to) register the new err_mask */ err = raw_enable_errfilter(sock_net(sk), dev, sk, err_mask); if (err) goto out_err; /* remove old err_mask registration */ raw_disable_errfilter(sock_net(sk), dev, sk, ro->err_mask); } /* link new err_mask to the socket */ ro->err_mask = err_mask; out_err: release_sock(sk); rtnl_unlock(); break; case CAN_RAW_LOOPBACK: if (optlen != sizeof(flag)) return -EINVAL; if (copy_from_sockptr(&flag, optval, optlen)) return -EFAULT; ro->loopback = !!flag; break; case CAN_RAW_RECV_OWN_MSGS: if (optlen != sizeof(flag)) return -EINVAL; if (copy_from_sockptr(&flag, optval, optlen)) return -EFAULT; ro->recv_own_msgs = !!flag; break; case CAN_RAW_FD_FRAMES: if (optlen != sizeof(flag)) return -EINVAL; if (copy_from_sockptr(&flag, optval, optlen)) return -EFAULT; /* Enabling CAN XL includes CAN FD */ if (ro->xl_frames && !flag) return -EINVAL; ro->fd_frames = !!flag; break; case CAN_RAW_XL_FRAMES: if (optlen != sizeof(flag)) return -EINVAL; if (copy_from_sockptr(&flag, optval, optlen)) return -EFAULT; ro->xl_frames = !!flag; /* Enabling CAN XL includes CAN FD */ if (ro->xl_frames) ro->fd_frames = ro->xl_frames; break; case CAN_RAW_XL_VCID_OPTS: if (optlen != sizeof(ro->raw_vcid_opts)) return -EINVAL; if (copy_from_sockptr(&ro->raw_vcid_opts, optval, optlen)) return -EFAULT; /* prepare 32 bit values for handling in hot path */ ro->tx_vcid_shifted = ro->raw_vcid_opts.tx_vcid << CANXL_VCID_OFFSET; ro->rx_vcid_shifted = ro->raw_vcid_opts.rx_vcid << CANXL_VCID_OFFSET; ro->rx_vcid_mask_shifted = ro->raw_vcid_opts.rx_vcid_mask << CANXL_VCID_OFFSET; break; case CAN_RAW_JOIN_FILTERS: if (optlen != sizeof(flag)) return -EINVAL; if (copy_from_sockptr(&flag, optval, optlen)) return -EFAULT; ro->join_filters = !!flag; break; default: return -ENOPROTOOPT; } return err; } static int raw_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); int flag; int len; void *val; if (level != SOL_CAN_RAW) return -EINVAL; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case CAN_RAW_FILTER: { int err = 0; lock_sock(sk); if (ro->count > 0) { int fsize = ro->count * sizeof(struct can_filter); /* user space buffer to small for filter list? */ if (len < fsize) { /* return -ERANGE and needed space in optlen */ err = -ERANGE; if (put_user(fsize, optlen)) err = -EFAULT; } else { if (len > fsize) len = fsize; if (copy_to_user(optval, ro->filter, len)) err = -EFAULT; } } else { len = 0; } release_sock(sk); if (!err) err = put_user(len, optlen); return err; } case CAN_RAW_ERR_FILTER: if (len > sizeof(can_err_mask_t)) len = sizeof(can_err_mask_t); val = &ro->err_mask; break; case CAN_RAW_LOOPBACK: if (len > sizeof(int)) len = sizeof(int); flag = ro->loopback; val = &flag; break; case CAN_RAW_RECV_OWN_MSGS: if (len > sizeof(int)) len = sizeof(int); flag = ro->recv_own_msgs; val = &flag; break; case CAN_RAW_FD_FRAMES: if (len > sizeof(int)) len = sizeof(int); flag = ro->fd_frames; val = &flag; break; case CAN_RAW_XL_FRAMES: if (len > sizeof(int)) len = sizeof(int); flag = ro->xl_frames; val = &flag; break; case CAN_RAW_XL_VCID_OPTS: { int err = 0; /* user space buffer to small for VCID opts? */ if (len < sizeof(ro->raw_vcid_opts)) { /* return -ERANGE and needed space in optlen */ err = -ERANGE; if (put_user(sizeof(ro->raw_vcid_opts), optlen)) err = -EFAULT; } else { if (len > sizeof(ro->raw_vcid_opts)) len = sizeof(ro->raw_vcid_opts); if (copy_to_user(optval, &ro->raw_vcid_opts, len)) err = -EFAULT; } if (!err) err = put_user(len, optlen); return err; } case CAN_RAW_JOIN_FILTERS: if (len > sizeof(int)) len = sizeof(int); flag = ro->join_filters; val = &flag; break; default: return -ENOPROTOOPT; } if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, val, len)) return -EFAULT; return 0; } static void raw_put_canxl_vcid(struct raw_sock *ro, struct sk_buff *skb) { struct canxl_frame *cxl = (struct canxl_frame *)skb->data; /* sanitize non CAN XL bits */ cxl->prio &= (CANXL_PRIO_MASK | CANXL_VCID_MASK); /* clear VCID in CAN XL frame if pass through is disabled */ if (!(ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_TX_PASS)) cxl->prio &= CANXL_PRIO_MASK; /* set VCID in CAN XL frame if enabled */ if (ro->raw_vcid_opts.flags & CAN_RAW_XL_VCID_TX_SET) { cxl->prio &= CANXL_PRIO_MASK; cxl->prio |= ro->tx_vcid_shifted; } } static unsigned int raw_check_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu) { /* Classical CAN -> no checks for flags and device capabilities */ if (can_is_can_skb(skb)) return CAN_MTU; /* CAN FD -> needs to be enabled and a CAN FD or CAN XL device */ if (ro->fd_frames && can_is_canfd_skb(skb) && (mtu == CANFD_MTU || can_is_canxl_dev_mtu(mtu))) return CANFD_MTU; /* CAN XL -> needs to be enabled and a CAN XL device */ if (ro->xl_frames && can_is_canxl_skb(skb) && can_is_canxl_dev_mtu(mtu)) return CANXL_MTU; return 0; } static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); struct sockcm_cookie sockc; struct sk_buff *skb; struct net_device *dev; unsigned int txmtu; int ifindex; int err = -EINVAL; /* check for valid CAN frame sizes */ if (size < CANXL_HDR_SIZE + CANXL_MIN_DLEN || size > CANXL_MTU) return -EINVAL; if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); if (msg->msg_namelen < RAW_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; ifindex = addr->can_ifindex; } else { ifindex = ro->ifindex; } dev = dev_get_by_index(sock_net(sk), ifindex); if (!dev) return -ENXIO; skb = sock_alloc_send_skb(sk, size + sizeof(struct can_skb_priv), msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) goto put_dev; can_skb_reserve(skb); can_skb_prv(skb)->ifindex = dev->ifindex; can_skb_prv(skb)->skbcnt = 0; /* fill the skb before testing for valid CAN frames */ err = memcpy_from_msg(skb_put(skb, size), msg, size); if (err < 0) goto free_skb; err = -EINVAL; /* check for valid CAN (CC/FD/XL) frame content */ txmtu = raw_check_txframe(ro, skb, READ_ONCE(dev->mtu)); if (!txmtu) goto free_skb; /* only CANXL: clear/forward/set VCID value */ if (txmtu == CANXL_MTU) raw_put_canxl_vcid(ro, skb); sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto free_skb; } skb->dev = dev; skb->priority = sockc.priority; skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, &sockc); err = can_send(skb, ro->loopback); dev_put(dev); if (err) goto send_failed; return size; free_skb: kfree_skb(skb); put_dev: dev_put(dev); send_failed: return err; } static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int err = 0; if (flags & MSG_ERRQUEUE) return sock_recv_errqueue(sk, msg, size, SOL_CAN_RAW, SCM_CAN_RAW_ERRQUEUE); skb = skb_recv_datagram(sk, flags, &err); if (!skb) return err; if (size < skb->len) msg->msg_flags |= MSG_TRUNC; else size = skb->len; err = memcpy_to_msg(msg, skb->data, size); if (err < 0) { skb_free_datagram(sk, skb); return err; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { __sockaddr_check_size(RAW_MIN_NAMELEN); msg->msg_namelen = RAW_MIN_NAMELEN; memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } /* assign the flags that have been recorded in raw_rcv() */ msg->msg_flags |= *(raw_flags(skb)); skb_free_datagram(sk, skb); return size; } static int raw_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { /* no ioctls for socket layer -> hand it down to NIC layer */ return -ENOIOCTLCMD; } static const struct proto_ops raw_ops = { .family = PF_CAN, .release = raw_release, .bind = raw_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = raw_getname, .poll = datagram_poll, .ioctl = raw_sock_no_ioctlcmd, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = raw_setsockopt, .getsockopt = raw_getsockopt, .sendmsg = raw_sendmsg, .recvmsg = raw_recvmsg, .mmap = sock_no_mmap, }; static struct proto raw_proto __read_mostly = { .name = "CAN_RAW", .owner = THIS_MODULE, .obj_size = sizeof(struct raw_sock), .init = raw_init, }; static const struct can_proto raw_can_proto = { .type = SOCK_RAW, .protocol = CAN_RAW, .ops = &raw_ops, .prot = &raw_proto, }; static struct notifier_block canraw_notifier = { .notifier_call = raw_notifier }; static __init int raw_module_init(void) { int err; pr_info("can: raw protocol\n"); err = register_netdevice_notifier(&canraw_notifier); if (err) return err; err = can_proto_register(&raw_can_proto); if (err < 0) { pr_err("can: registration of raw protocol failed\n"); goto register_proto_failed; } return 0; register_proto_failed: unregister_netdevice_notifier(&canraw_notifier); return err; } static __exit void raw_module_exit(void) { can_proto_unregister(&raw_can_proto); unregister_netdevice_notifier(&canraw_notifier); } module_init(raw_module_init); module_exit(raw_module_exit); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __BEN_VLAN_802_1Q_INC__ #define __BEN_VLAN_802_1Q_INC__ #include <linux/if_vlan.h> #include <linux/u64_stats_sync.h> #include <linux/list.h> /* if this changes, algorithm will have to be reworked because this * depends on completely exhausting the VLAN identifier space. Thus * it gives constant time look-up, but in many cases it wastes memory. */ #define VLAN_GROUP_ARRAY_SPLIT_PARTS 8 #define VLAN_GROUP_ARRAY_PART_LEN (VLAN_N_VID/VLAN_GROUP_ARRAY_SPLIT_PARTS) enum vlan_protos { VLAN_PROTO_8021Q = 0, VLAN_PROTO_8021AD, VLAN_PROTO_NUM, }; struct vlan_group { unsigned int nr_vlan_devs; struct hlist_node hlist; /* linked list */ struct net_device **vlan_devices_arrays[VLAN_PROTO_NUM] [VLAN_GROUP_ARRAY_SPLIT_PARTS]; }; struct vlan_info { struct net_device *real_dev; /* The ethernet(like) device * the vlan is attached to. */ struct vlan_group grp; struct list_head vid_list; unsigned int nr_vids; bool auto_vid0; struct rcu_head rcu; }; static inline int vlan_proto_idx(__be16 proto) { switch (proto) { case htons(ETH_P_8021Q): return VLAN_PROTO_8021Q; case htons(ETH_P_8021AD): return VLAN_PROTO_8021AD; default: WARN(1, "invalid VLAN protocol: 0x%04x\n", ntohs(proto)); return -EINVAL; } } static inline struct net_device *__vlan_group_get_device(struct vlan_group *vg, unsigned int pidx, u16 vlan_id) { struct net_device **array; array = vg->vlan_devices_arrays[pidx] [vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; /* paired with smp_wmb() in vlan_group_prealloc_vid() */ smp_rmb(); return array ? array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] : NULL; } static inline struct net_device *vlan_group_get_device(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id) { int pidx = vlan_proto_idx(vlan_proto); if (pidx < 0) return NULL; return __vlan_group_get_device(vg, pidx, vlan_id); } static inline void vlan_group_set_device(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id, struct net_device *dev) { int pidx = vlan_proto_idx(vlan_proto); struct net_device **array; if (!vg || pidx < 0) return; array = vg->vlan_devices_arrays[pidx] [vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev; } /* Must be invoked with rcu_read_lock or with RTNL. */ static inline struct net_device *vlan_find_dev(struct net_device *real_dev, __be16 vlan_proto, u16 vlan_id) { struct vlan_info *vlan_info = rcu_dereference_rtnl(real_dev->vlan_info); if (vlan_info) return vlan_group_get_device(&vlan_info->grp, vlan_proto, vlan_id); return NULL; } static inline netdev_features_t vlan_tnl_features(struct net_device *real_dev) { netdev_features_t ret; ret = real_dev->hw_enc_features & (NETIF_F_CSUM_MASK | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL); if ((ret & NETIF_F_GSO_ENCAP_ALL) && (ret & NETIF_F_CSUM_MASK)) return (ret & ~NETIF_F_CSUM_MASK) | NETIF_F_HW_CSUM; return 0; } #define vlan_group_for_each_dev(grp, i, dev) \ for ((i) = 0; i < VLAN_PROTO_NUM * VLAN_N_VID; i++) \ if (((dev) = __vlan_group_get_device((grp), (i) / VLAN_N_VID, \ (i) % VLAN_N_VID))) int vlan_filter_push_vids(struct vlan_info *vlan_info, __be16 proto); void vlan_filter_drop_vids(struct vlan_info *vlan_info, __be16 proto); /* found in vlan_dev.c */ void vlan_dev_set_ingress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); int vlan_dev_set_egress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); void vlan_dev_free_egress_priority(const struct net_device *dev); int vlan_dev_change_flags(const struct net_device *dev, u32 flag, u32 mask); void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, size_t size); int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id, struct netlink_ext_ack *extack); void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev); static inline u32 vlan_get_ingress_priority(struct net_device *dev, u16 vlan_tci) { struct vlan_dev_priv *vip = vlan_dev_priv(dev); return vip->ingress_priority_map[(vlan_tci >> VLAN_PRIO_SHIFT) & 0x7]; } #ifdef CONFIG_VLAN_8021Q_GVRP int vlan_gvrp_request_join(const struct net_device *dev); void vlan_gvrp_request_leave(const struct net_device *dev); int vlan_gvrp_init_applicant(struct net_device *dev); void vlan_gvrp_uninit_applicant(struct net_device *dev); int vlan_gvrp_init(void); void vlan_gvrp_uninit(void); #else static inline int vlan_gvrp_request_join(const struct net_device *dev) { return 0; } static inline void vlan_gvrp_request_leave(const struct net_device *dev) {} static inline int vlan_gvrp_init_applicant(struct net_device *dev) { return 0; } static inline void vlan_gvrp_uninit_applicant(struct net_device *dev) {} static inline int vlan_gvrp_init(void) { return 0; } static inline void vlan_gvrp_uninit(void) {} #endif #ifdef CONFIG_VLAN_8021Q_MVRP int vlan_mvrp_request_join(const struct net_device *dev); void vlan_mvrp_request_leave(const struct net_device *dev); int vlan_mvrp_init_applicant(struct net_device *dev); void vlan_mvrp_uninit_applicant(struct net_device *dev); int vlan_mvrp_init(void); void vlan_mvrp_uninit(void); #else static inline int vlan_mvrp_request_join(const struct net_device *dev) { return 0; } static inline void vlan_mvrp_request_leave(const struct net_device *dev) {} static inline int vlan_mvrp_init_applicant(struct net_device *dev) { return 0; } static inline void vlan_mvrp_uninit_applicant(struct net_device *dev) {} static inline int vlan_mvrp_init(void) { return 0; } static inline void vlan_mvrp_uninit(void) {} #endif extern const char vlan_fullname[]; extern const char vlan_version[]; int vlan_netlink_init(void); void vlan_netlink_fini(void); extern struct rtnl_link_ops vlan_link_ops; extern unsigned int vlan_net_id; struct proc_dir_entry; struct vlan_net { /* /proc/net/vlan */ struct proc_dir_entry *proc_vlan_dir; /* /proc/net/vlan/config */ struct proc_dir_entry *proc_vlan_conf; /* Determines interface naming scheme. */ unsigned short name_type; }; #endif /* !(__BEN_VLAN_802_1Q_INC__) */ |
| 138 223 222 138 223 6 36 138 1 1 223 138 138 138 1 138 138 613 615 613 614 612 616 64 223 64 64 27 256 222 188 187 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* memcontrol.h - Memory Controller * * Copyright IBM Corporation, 2007 * Author Balbir Singh <balbir@linux.vnet.ibm.com> * * Copyright 2007 OpenVZ SWsoft Inc * Author: Pavel Emelianov <xemul@openvz.org> */ #ifndef _LINUX_MEMCONTROL_H #define _LINUX_MEMCONTROL_H #include <linux/cgroup.h> #include <linux/vm_event_item.h> #include <linux/hardirq.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/page_counter.h> #include <linux/vmpressure.h> #include <linux/eventfd.h> #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/writeback.h> #include <linux/page-flags.h> #include <linux/shrinker.h> struct mem_cgroup; struct obj_cgroup; struct page; struct mm_struct; struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, MEMCG_PERCPU_B, MEMCG_VMALLOC, MEMCG_KMEM, MEMCG_ZSWAP_B, MEMCG_ZSWAPPED, MEMCG_NR_STAT, }; enum memcg_memory_event { MEMCG_LOW, MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, MEMCG_OOM_GROUP_KILL, MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, }; struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; int generation; }; #ifdef CONFIG_MEMCG #define MEM_CGROUP_ID_SHIFT 16 struct mem_cgroup_id { int id; refcount_t ref; }; struct memcg_vmstats_percpu; struct memcg1_events_percpu; struct memcg_vmstats; struct lruvec_stats_percpu; struct lruvec_stats; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; /* scan generation, increased every round-trip */ atomic_t generation; }; /* * per-node information in memory controller. */ struct mem_cgroup_per_node { /* Keep the read-only fields at the start */ struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ struct lruvec_stats_percpu __percpu *lruvec_stats_percpu; struct lruvec_stats *lruvec_stats; struct shrinker_info __rcu *shrinker_info; #ifdef CONFIG_MEMCG_V1 /* * Memcg-v1 only stuff in middle as buffer between read mostly fields * and update often fields to avoid false sharing. If v1 stuff is * not present, an explicit padding is needed. */ struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; #else CACHELINE_PADDING(_pad1_); #endif /* Fields which get updated often at the end. */ struct lruvec lruvec; CACHELINE_PADDING(_pad2_); unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter; #ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC /* slab stats for nmi context */ atomic_t slab_reclaimable; atomic_t slab_unreclaimable; #endif }; struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; unsigned long threshold; }; /* For threshold */ struct mem_cgroup_threshold_ary { /* An array index points to threshold just below or equal to usage. */ int current_threshold; /* Size of entries[] */ unsigned int size; /* Array of thresholds */ struct mem_cgroup_threshold entries[] __counted_by(size); }; struct mem_cgroup_thresholds { /* Primary thresholds array */ struct mem_cgroup_threshold_ary *primary; /* * Spare threshold array. * This is needed to make mem_cgroup_unregister_event() "never fail". * It must be able to store at least primary->size - 1 entries. */ struct mem_cgroup_threshold_ary *spare; }; /* * Remember four most recent foreign writebacks with dirty pages in this * cgroup. Inode sharing is expected to be uncommon and, even if we miss * one in a given round, we're likely to catch it later if it keeps * foreign-dirtying, so a fairly low count should be enough. * * See mem_cgroup_track_foreign_dirty_slowpath() for details. */ #define MEMCG_CGWB_FRN_CNT 4 struct memcg_cgwb_frn { u64 bdi_id; /* bdi->id of the foreign inode */ int memcg_id; /* memcg->css.id of foreign inode */ u64 at; /* jiffies_64 at the time of dirtying */ struct wb_completion done; /* tracks in-flight foreign writebacks */ }; /* * Bucket for arbitrarily byte-sized objects charged to a memory * cgroup. The bucket can be reparented in one piece when the cgroup * is destroyed, without having to round up the individual references * of all live memory objects in the wild. */ struct obj_cgroup { struct percpu_ref refcnt; struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; }; /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide * statistics based on the statistics developed by Rik Van Riel for clock-pro, * to help the administrator determine what knobs to tune. */ struct mem_cgroup { struct cgroup_subsys_state css; /* Private memcg ID. Used to ID objects that outlive the cgroup */ struct mem_cgroup_id id; /* Accounted resources */ struct page_counter memory; /* Both v1 & v2 */ union { struct page_counter swap; /* v2 only */ struct page_counter memsw; /* v1 only */ }; /* registered local peak watchers */ struct list_head memory_peaks; struct list_head swap_peaks; spinlock_t peaks_lock; /* Range enforcement for interrupt charges */ struct work_struct high_work; #ifdef CONFIG_ZSWAP unsigned long zswap_max; /* * Prevent pages from this memcg from being written back from zswap to * swap, and from being swapped out on zswap store failures. */ bool zswap_writeback; #endif /* vmpressure notifications */ struct vmpressure vmpressure; /* * Should the OOM killer kill all belonging tasks, had it kill one? */ bool oom_group; int swappiness; /* memory.events and memory.events.local */ struct cgroup_file events_file; struct cgroup_file events_local_file; /* handle for "memory.swap.events" */ struct cgroup_file swap_events_file; /* memory.stat */ struct memcg_vmstats *vmstats; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; #ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC /* MEMCG_KMEM for nmi context */ atomic_t kmem_stat; #endif /* * Hint of reclaim pressure for socket memroy management. Note * that this indicator should NOT be used in legacy cgroup mode * where socket memory is accounted/charged separately. */ u64 socket_pressure; #if BITS_PER_LONG < 64 seqlock_t socket_pressure_seqlock; #endif int kmemcg_id; /* * memcg->objcg is wiped out as a part of the objcg repaprenting * process. memcg->orig_objcg preserves a pointer (and a reference) * to the original objcg until the end of live of memcg. */ struct obj_cgroup __rcu *objcg; struct obj_cgroup *orig_objcg; /* list of inherited objcgs, protected by objcg_lock */ struct list_head objcg_list; struct memcg_vmstats_percpu __percpu *vmstats_percpu; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif #ifdef CONFIG_LRU_GEN_WALKS_MMU /* per-memcg mm_struct list */ struct lru_gen_mm_list mm_list; #endif #ifdef CONFIG_MEMCG_V1 /* Legacy consumer-oriented counters */ struct page_counter kmem; /* v1 only */ struct page_counter tcpmem; /* v1 only */ struct memcg1_events_percpu __percpu *events_percpu; unsigned long soft_limit; /* protected by memcg_oom_lock */ bool oom_lock; int under_oom; /* OOM-Killer disable */ int oom_kill_disable; /* protect arrays of thresholds */ struct mutex thresholds_lock; /* thresholds for memory usage. RCU-protected */ struct mem_cgroup_thresholds thresholds; /* thresholds for mem+swap usage. RCU-protected */ struct mem_cgroup_thresholds memsw_thresholds; /* For oom notifier event fd */ struct list_head oom_notify; /* Legacy tcp memory accounting */ bool tcpmem_active; int tcpmem_pressure; /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; #endif /* CONFIG_MEMCG_V1 */ struct mem_cgroup_per_node *nodeinfo[]; }; /* * size of first charge trial. * TODO: maybe necessary to use big numbers in big irons or dynamic based of the * workload. */ #define MEMCG_CHARGE_BATCH 64U extern struct mem_cgroup *root_mem_cgroup; enum page_memcg_data_flags { /* page->memcg_data is a pointer to an slabobj_ext vector */ MEMCG_DATA_OBJEXTS = (1UL << 0), /* page has been accounted as a non-slab kernel page */ MEMCG_DATA_KMEM = (1UL << 1), /* the next bit after the last actual flag */ __NR_MEMCG_DATA_FLAGS = (1UL << 2), }; #define __OBJEXTS_ALLOC_FAIL MEMCG_DATA_OBJEXTS #define __FIRST_OBJEXT_FLAG __NR_MEMCG_DATA_FLAGS #else /* CONFIG_MEMCG */ #define __OBJEXTS_ALLOC_FAIL (1UL << 0) #define __FIRST_OBJEXT_FLAG (1UL << 0) #endif /* CONFIG_MEMCG */ enum objext_flags { /* * Use bit 0 with zero other bits to signal that slabobj_ext vector * failed to allocate. The same bit 0 with valid upper bits means * MEMCG_DATA_OBJEXTS. */ OBJEXTS_ALLOC_FAIL = __OBJEXTS_ALLOC_FAIL, /* slabobj_ext vector allocated with kmalloc_nolock() */ OBJEXTS_NOSPIN_ALLOC = __FIRST_OBJEXT_FLAG, /* the next bit after the last actual flag */ __NR_OBJEXTS_FLAGS = (__FIRST_OBJEXT_FLAG << 1), }; #define OBJEXTS_FLAGS_MASK (__NR_OBJEXTS_FLAGS - 1) #ifdef CONFIG_MEMCG static inline bool folio_memcg_kmem(struct folio *folio); /* * After the initialization objcg->memcg is always pointing at * a valid memcg, but can be atomically swapped to the parent memcg. * * The caller must ensure that the returned memcg won't be released. */ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) { lockdep_assert_once(rcu_read_lock_held() || lockdep_is_held(&cgroup_mutex)); return READ_ONCE(objcg->memcg); } /* * __folio_memcg - Get the memory cgroup associated with a non-kmem folio * @folio: Pointer to the folio. * * Returns a pointer to the memory cgroup associated with the folio, * or NULL. This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function * against some type of folios, e.g. slab folios or ex-slab folios or * kmem folios. */ static inline struct mem_cgroup *__folio_memcg(struct folio *folio) { unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio); VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio); return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* * __folio_objcg - get the object cgroup associated with a kmem folio. * @folio: Pointer to the folio. * * Returns a pointer to the object cgroup associated with the folio, * or NULL. This function assumes that the folio is known to have a * proper object cgroup pointer. It's not safe to call this function * against some type of folios, e.g. slab folios or ex-slab folios or * LRU folios. */ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) { unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio); VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio); return (struct obj_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* * folio_memcg - Get the memory cgroup associated with a folio. * @folio: Pointer to the folio. * * Returns a pointer to the memory cgroup associated with the folio, * or NULL. This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function * against some type of folios, e.g. slab folios or ex-slab folios. * * For a non-kmem folio any of the following ensures folio and memcg binding * stability: * * - the folio lock * - LRU isolation * - exclusive reference * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. */ static inline struct mem_cgroup *folio_memcg(struct folio *folio) { if (folio_memcg_kmem(folio)) return obj_cgroup_memcg(__folio_objcg(folio)); return __folio_memcg(folio); } /* * folio_memcg_charged - If a folio is charged to a memory cgroup. * @folio: Pointer to the folio. * * Returns true if folio is charged to a memory cgroup, otherwise returns false. */ static inline bool folio_memcg_charged(struct folio *folio) { return folio->memcg_data != 0; } /* * folio_memcg_check - Get the memory cgroup associated with a folio. * @folio: Pointer to the folio. * * Returns a pointer to the memory cgroup associated with the folio, * or NULL. This function unlike folio_memcg() can take any folio * as an argument. It has to be used in cases when it's not known if a folio * has an associated memory cgroup pointer or an object cgroups vector or * an object cgroup. * * For a non-kmem folio any of the following ensures folio and memcg binding * stability: * * - the folio lock * - LRU isolation * - exclusive reference * * For a kmem folio a caller should hold an rcu read lock to protect memcg * associated with a kmem folio from being released. */ static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) { /* * Because folio->memcg_data might be changed asynchronously * for slabs, READ_ONCE() should be used here. */ unsigned long memcg_data = READ_ONCE(folio->memcg_data); if (memcg_data & MEMCG_DATA_OBJEXTS) return NULL; if (memcg_data & MEMCG_DATA_KMEM) { struct obj_cgroup *objcg; objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); return obj_cgroup_memcg(objcg); } return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } static inline struct mem_cgroup *page_memcg_check(struct page *page) { if (PageTail(page)) return NULL; return folio_memcg_check((struct folio *)page); } static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) { struct mem_cgroup *memcg; rcu_read_lock(); retry: memcg = obj_cgroup_memcg(objcg); if (unlikely(!css_tryget(&memcg->css))) goto retry; rcu_read_unlock(); return memcg; } /* * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. * @folio: Pointer to the folio. * * Checks if the folio has MemcgKmem flag set. The caller must ensure * that the folio has an associated memory cgroup. It's not safe to call * this function against some types of folios, e.g. slab folios. */ static inline bool folio_memcg_kmem(struct folio *folio) { VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page); VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJEXTS, folio); return folio->memcg_data & MEMCG_DATA_KMEM; } static inline bool PageMemcgKmem(struct page *page) { return folio_memcg_kmem(page_folio(page)); } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); } static inline bool mem_cgroup_disabled(void) { return !cgroup_subsys_enabled(memory_cgrp_subsys); } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low) { *min = *low = 0; if (mem_cgroup_disabled()) return; /* * There is no reclaim protection applied to a targeted reclaim. * We are special casing this specific case here because * mem_cgroup_calculate_protection is not robust enough to keep * the protection invariant for calculated effective values for * parallel reclaimers with different reclaim target. This is * especially a problem for tail memcgs (as they have pages on LRU) * which would want to have effective values 0 for targeted reclaim * but a different value for external reclaim. * * Example * Let's have global and A's reclaim in parallel: * | * A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G) * |\ * | C (low = 1G, usage = 2.5G) * B (low = 1G, usage = 0.5G) * * For the global reclaim * A.elow = A.low * B.elow = min(B.usage, B.low) because children_low_usage <= A.elow * C.elow = min(C.usage, C.low) * * With the effective values resetting we have A reclaim * A.elow = 0 * B.elow = B.low * C.elow = C.low * * If the global reclaim races with A's reclaim then * B.elow = C.elow = 0 because children_low_usage > A.elow) * is possible and reclaiming B would be violating the protection. * */ if (root == memcg) return; *min = READ_ONCE(memcg->memory.emin); *low = READ_ONCE(memcg->memory.elow); } void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg); static inline bool mem_cgroup_unprotected(struct mem_cgroup *target, struct mem_cgroup *memcg) { /* * The root memcg doesn't account charges, and doesn't support * protection. The target memcg's protection is ignored, see * mem_cgroup_calculate_protection() and mem_cgroup_protection() */ return mem_cgroup_disabled() || mem_cgroup_is_root(memcg) || memcg == target; } static inline bool mem_cgroup_below_low(struct mem_cgroup *target, struct mem_cgroup *memcg) { if (mem_cgroup_unprotected(target, memcg)) return false; return READ_ONCE(memcg->memory.elow) >= page_counter_read(&memcg->memory); } static inline bool mem_cgroup_below_min(struct mem_cgroup *target, struct mem_cgroup *memcg) { if (mem_cgroup_unprotected(target, memcg)) return false; return READ_ONCE(memcg->memory.emin) >= page_counter_read(&memcg->memory); } int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp); /** * mem_cgroup_charge - Charge a newly allocated folio to a cgroup. * @folio: Folio to charge. * @mm: mm context of the allocating task. * @gfp: Reclaim mode. * * Try to charge @folio to the memcg that @mm belongs to, reclaiming * pages according to @gfp if necessary. If @mm is NULL, try to * charge to the active memcg. * * Do not use this for folios allocated for swapin. * * Return: 0 on success. Otherwise, an error code is returned. */ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { if (mem_cgroup_disabled()) return 0; return __mem_cgroup_charge(folio, mm, gfp); } int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp); int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); void __mem_cgroup_uncharge(struct folio *folio); /** * mem_cgroup_uncharge - Uncharge a folio. * @folio: Folio to uncharge. * * Uncharge a folio previously charged with mem_cgroup_charge(). */ static inline void mem_cgroup_uncharge(struct folio *folio) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge(folio); } void __mem_cgroup_uncharge_folios(struct folio_batch *folios); static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge_folios(folios); } void mem_cgroup_replace_folio(struct folio *old, struct folio *new); void mem_cgroup_migrate(struct folio *old, struct folio *new); /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node * @memcg: memcg of the wanted lruvec * @pgdat: pglist_data * * Returns the lru list vector holding pages for a given @memcg & * @pgdat combination. This can be the node lruvec, if the memory * controller is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { struct mem_cgroup_per_node *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { lruvec = &pgdat->__lruvec; goto out; } if (!memcg) memcg = root_mem_cgroup; mz = memcg->nodeinfo[pgdat->node_id]; lruvec = &mz->lruvec; out: /* * Since a node can be onlined after the mem_cgroup was created, * we have to be prepared to initialize lruvec->pgdat here; * and if offlined then reonlined, we need to reinitialize it. */ if (unlikely(lruvec->pgdat != pgdat)) lruvec->pgdat = pgdat; return lruvec; } /** * folio_lruvec - return lruvec for isolating/putting an LRU folio * @folio: Pointer to the folio. * * This function relies on folio->mem_cgroup being stable. */ static inline struct lruvec *folio_lruvec(struct folio *folio) { struct mem_cgroup *memcg = folio_memcg(folio); VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled(), folio); return mem_cgroup_lruvec(memcg, folio_pgdat(folio)); } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); struct mem_cgroup *get_mem_cgroup_from_current(void); struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio); struct lruvec *folio_lruvec_lock(struct folio *folio); struct lruvec *folio_lruvec_lock_irq(struct folio *folio); struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flags); #ifdef CONFIG_DEBUG_VM void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio); #else static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { } #endif static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg) { return percpu_ref_tryget(&objcg->refcnt); } static inline void obj_cgroup_get(struct obj_cgroup *objcg) { percpu_ref_get(&objcg->refcnt); } static inline void obj_cgroup_get_many(struct obj_cgroup *objcg, unsigned long nr) { percpu_ref_get_many(&objcg->refcnt, nr); } static inline void obj_cgroup_put(struct obj_cgroup *objcg) { if (objcg) percpu_ref_put(&objcg->refcnt); } static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) { return !memcg || css_tryget(&memcg->css); } static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg) { return !memcg || css_tryget_online(&memcg->css); } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { if (memcg) css_put(&memcg->css); } #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*)(struct task_struct *, void *), void *arg); static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return 0; return memcg->id.id; } struct mem_cgroup *mem_cgroup_from_id(unsigned short id); #ifdef CONFIG_SHRINKER_DEBUG static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg) { return memcg ? cgroup_ino(memcg->css.cgroup) : 0; } struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino); #endif static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return mem_cgroup_from_css(seq_css(m)); } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { struct mem_cgroup_per_node *mz; if (mem_cgroup_disabled()) return NULL; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return mz->memcg; } /** * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find * * Returns the parent memcg, or NULL if this is the root. */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return mem_cgroup_from_css(memcg->css.parent); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root) { if (root == memcg) return true; return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { struct mem_cgroup *task_memcg; bool match = false; rcu_read_lock(); task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (task_memcg) match = mem_cgroup_is_descendant(task_memcg, memcg); rcu_read_unlock(); return match; } struct cgroup_subsys_state *mem_cgroup_css_from_folio(struct folio *folio); ino_t page_cgroup_ino(struct page *page); static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return true; return !!(memcg->css.flags & CSS_ONLINE); } void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, int nr_pages); static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { struct mem_cgroup_per_node *mz; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } void __mem_cgroup_handle_over_high(gfp_t gfp_mask); static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { if (unlikely(current->memcg_nr_pages_over_high)) __mem_cgroup_handle_over_high(gfp_mask); } unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); unsigned long mem_cgroup_size(struct mem_cgroup *memcg); void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p); void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg); struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); /* idx can be of type enum memcg_stat_item or node_stat_item */ void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int val); static inline void mod_memcg_page_state(struct page *page, enum memcg_stat_item idx, int val) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = folio_memcg(page_folio(page)); if (memcg) mod_memcg_state(memcg, idx, val); rcu_read_unlock(); } unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx); unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx); unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx); void mem_cgroup_flush_stats(struct mem_cgroup *memcg); void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg); void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val); static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_kmem_state(p, idx, val); local_irq_restore(flags); } void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { struct mem_cgroup *memcg = folio_memcg(folio); if (memcg) count_memcg_events(memcg, idx, nr); } static inline void count_memcg_events_mm(struct mm_struct *mm, enum vm_event_item idx, unsigned long count) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) count_memcg_events(memcg, idx, count); rcu_read_unlock(); } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { count_memcg_events_mm(mm, idx, 1); } static inline void __memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event, bool allow_spinning) { bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX || event == MEMCG_SWAP_FAIL; /* For now only MEMCG_MAX can happen with !allow_spinning context. */ VM_WARN_ON_ONCE(!allow_spinning && event != MEMCG_MAX); atomic_long_inc(&memcg->memory_events_local[event]); if (!swap_event && allow_spinning) cgroup_file_notify(&memcg->events_local_file); do { atomic_long_inc(&memcg->memory_events[event]); if (allow_spinning) { if (swap_event) cgroup_file_notify(&memcg->swap_events_file); else cgroup_file_notify(&memcg->events_file); } if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) break; if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) break; } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { __memcg_memory_event(memcg, event, true); } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) memcg_memory_event(memcg, event); rcu_read_unlock(); } void split_page_memcg(struct page *first, unsigned order); void folio_split_memcg_refs(struct folio *folio, unsigned old_order, unsigned new_order); static inline u64 cgroup_id_from_mm(struct mm_struct *mm) { struct mem_cgroup *memcg; u64 id; if (mem_cgroup_disabled()) return 0; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (!memcg) memcg = root_mem_cgroup; id = cgroup_id(memcg->css.cgroup); rcu_read_unlock(); return id; } extern int mem_cgroup_init(void); #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 #define root_mem_cgroup (NULL) static inline struct mem_cgroup *folio_memcg(struct folio *folio) { return NULL; } static inline bool folio_memcg_charged(struct folio *folio) { return false; } static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) { return NULL; } static inline struct mem_cgroup *page_memcg_check(struct page *page) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) { return NULL; } static inline bool folio_memcg_kmem(struct folio *folio) { return false; } static inline bool PageMemcgKmem(struct page *page) { return false; } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_disabled(void) { return true; } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low) { *min = *low = 0; } static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg) { } static inline bool mem_cgroup_unprotected(struct mem_cgroup *target, struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_below_low(struct mem_cgroup *target, struct mem_cgroup *memcg) { return false; } static inline bool mem_cgroup_below_min(struct mem_cgroup *target, struct mem_cgroup *memcg) { return false; } static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { return 0; } static inline int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp) { return 0; } static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) { return 0; } static inline void mem_cgroup_uncharge(struct folio *folio) { } static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { } static inline void mem_cgroup_replace_folio(struct folio *old, struct folio *new) { } static inline void mem_cgroup_migrate(struct folio *old, struct folio *new) { } static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { return &pgdat->__lruvec; } static inline struct lruvec *folio_lruvec(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); return &pgdat->__lruvec; } static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { } static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return NULL; } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { return true; } static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_current(void) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio) { return NULL; } static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) { return NULL; } static inline void obj_cgroup_get(struct obj_cgroup *objcg) { } static inline void obj_cgroup_put(struct obj_cgroup *objcg) { } static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg) { return true; } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } static inline struct lruvec *folio_lruvec_lock(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); spin_lock(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); spin_lock_irq(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flagsp) { struct pglist_data *pgdat = folio_pgdat(folio); spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp); return &pgdat->__lruvec; } static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim) { return NULL; } static inline void mem_cgroup_iter_break(struct mem_cgroup *root, struct mem_cgroup *prev) { } static inline void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*fn)(struct task_struct *, void *), void *arg) { } static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { return 0; } static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { WARN_ON_ONCE(id); /* XXX: This should always return root_mem_cgroup */ return NULL; } #ifdef CONFIG_SHRINKER_DEBUG static inline unsigned long mem_cgroup_ino(struct mem_cgroup *memcg) { return 0; } static inline struct mem_cgroup *mem_cgroup_get_from_ino(unsigned long ino) { return NULL; } #endif static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return NULL; } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { return NULL; } static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { return true; } static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { return 0; } static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) { return 0; } static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg) { return 0; } static inline void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) { } static inline void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { } static inline struct mem_cgroup *mem_cgroup_get_oom_group( struct task_struct *victim, struct mem_cgroup *oom_domain) { return NULL; } static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) { } static inline void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int nr) { } static inline void mod_memcg_page_state(struct page *page, enum memcg_stat_item idx, int val) { } static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return 0; } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline void mem_cgroup_flush_stats(struct mem_cgroup *memcg) { } static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg) { } static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); __mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); mod_node_page_state(page_pgdat(page), idx, val); } static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { } static inline void count_memcg_events_mm(struct mm_struct *mm, enum vm_event_item idx, unsigned long count) { } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } static inline void split_page_memcg(struct page *first, unsigned order) { } static inline void folio_split_memcg_refs(struct folio *folio, unsigned old_order, unsigned new_order) { } static inline u64 cgroup_id_from_mm(struct mm_struct *mm) { return 0; } static inline int mem_cgroup_init(void) { return 0; } #endif /* CONFIG_MEMCG */ /* * Extended information for slab objects stored as an array in page->memcg_data * if MEMCG_DATA_OBJEXTS is set. */ struct slabobj_ext { #ifdef CONFIG_MEMCG struct obj_cgroup *objcg; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING union codetag_ref ref; #endif } __aligned(8); static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx) { __mod_lruvec_kmem_state(p, idx, 1); } static inline void __dec_lruvec_kmem_state(void *p, enum node_stat_item idx) { __mod_lruvec_kmem_state(p, idx, -1); } static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) { struct mem_cgroup *memcg; memcg = lruvec_memcg(lruvec); if (!memcg) return NULL; memcg = parent_mem_cgroup(memcg); if (!memcg) return NULL; return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); } static inline void unlock_page_lruvec(struct lruvec *lruvec) { spin_unlock(&lruvec->lru_lock); } static inline void unlock_page_lruvec_irq(struct lruvec *lruvec) { spin_unlock_irq(&lruvec->lru_lock); } static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, unsigned long flags) { spin_unlock_irqrestore(&lruvec->lru_lock, flags); } /* Test requires a stable folio->memcg binding, see folio_memcg() */ static inline bool folio_matches_lruvec(struct folio *folio, struct lruvec *lruvec) { return lruvec_pgdat(lruvec) == folio_pgdat(folio) && lruvec_memcg(lruvec) == folio_memcg(folio); } /* Don't lock again iff page's lruvec locked */ static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio, struct lruvec *locked_lruvec) { if (locked_lruvec) { if (folio_matches_lruvec(folio, locked_lruvec)) return locked_lruvec; unlock_page_lruvec_irq(locked_lruvec); } return folio_lruvec_lock_irq(folio); } /* Don't lock again iff folio's lruvec locked */ static inline void folio_lruvec_relock_irqsave(struct folio *folio, struct lruvec **lruvecp, unsigned long *flags) { if (*lruvecp) { if (folio_matches_lruvec(folio, *lruvecp)) return; unlock_page_lruvec_irqrestore(*lruvecp, *flags); } *lruvecp = folio_lruvec_lock_irqsave(folio, flags); } #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, struct bdi_writeback *wb); static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; memcg = folio_memcg(folio); if (unlikely(memcg && &memcg->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(folio, wb); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); #else /* CONFIG_CGROUP_WRITEBACK */ static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) { return NULL; } static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback) { } static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { } static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) { } #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk); bool mem_cgroup_sk_charge(const struct sock *sk, unsigned int nr_pages, gfp_t gfp_mask); void mem_cgroup_sk_uncharge(const struct sock *sk, unsigned int nr_pages); #if BITS_PER_LONG < 64 static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg) { u64 val = get_jiffies_64() + HZ; unsigned long flags; write_seqlock_irqsave(&memcg->socket_pressure_seqlock, flags); memcg->socket_pressure = val; write_sequnlock_irqrestore(&memcg->socket_pressure_seqlock, flags); } static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg) { unsigned int seq; u64 val; do { seq = read_seqbegin(&memcg->socket_pressure_seqlock); val = memcg->socket_pressure; } while (read_seqretry(&memcg->socket_pressure_seqlock, seq)); return val; } #else static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg) { WRITE_ONCE(memcg->socket_pressure, jiffies + HZ); } static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg) { return READ_ONCE(memcg->socket_pressure); } #endif int alloc_shrinker_info(struct mem_cgroup *memcg); void free_shrinker_info(struct mem_cgroup *memcg); void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); void reparent_shrinker_deferred(struct mem_cgroup *memcg); #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { } static inline void mem_cgroup_sk_free(struct sock *sk) { } static inline void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk) { } static inline bool mem_cgroup_sk_charge(const struct sock *sk, unsigned int nr_pages, gfp_t gfp_mask) { return false; } static inline void mem_cgroup_sk_uncharge(const struct sock *sk, unsigned int nr_pages) { } static inline void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { } #endif #ifdef CONFIG_MEMCG bool mem_cgroup_kmem_disabled(void); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); /* * The returned objcg pointer is safe to use without additional * protection within a scope. The scope is defined either by * the current task (similar to the "current" global variable) * or by set_active_memcg() pair. * Please, use obj_cgroup_get() to get a reference if the pointer * needs to be used outside of the local scope. */ struct obj_cgroup *current_obj_cgroup(void); struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio); static inline struct obj_cgroup *get_obj_cgroup_from_current(void) { struct obj_cgroup *objcg = current_obj_cgroup(); if (objcg) obj_cgroup_get(objcg); return objcg; } int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); extern struct static_key_false memcg_bpf_enabled_key; static inline bool memcg_bpf_enabled(void) { return static_branch_likely(&memcg_bpf_enabled_key); } extern struct static_key_false memcg_kmem_online_key; static inline bool memcg_kmem_online(void) { return static_branch_likely(&memcg_kmem_online_key); } static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { if (memcg_kmem_online()) return __memcg_kmem_charge_page(page, gfp, order); return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { if (memcg_kmem_online()) __memcg_kmem_uncharge_page(page, order); } /* * A helper for accessing memcg's kmem_id, used for getting * corresponding LRU lists. */ static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return memcg ? memcg->kmemcg_id : -1; } struct mem_cgroup *mem_cgroup_from_slab_obj(void *p); static inline void count_objcg_events(struct obj_cgroup *objcg, enum vm_event_item idx, unsigned long count) { struct mem_cgroup *memcg; if (!memcg_kmem_online()) return; rcu_read_lock(); memcg = obj_cgroup_memcg(objcg); count_memcg_events(memcg, idx, count); rcu_read_unlock(); } bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid); #else static inline bool mem_cgroup_kmem_disabled(void) { return true; } static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { } static inline int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } static inline struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio) { return NULL; } static inline bool memcg_bpf_enabled(void) { return false; } static inline bool memcg_kmem_online(void) { return false; } static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return -1; } static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p) { return NULL; } static inline void count_objcg_events(struct obj_cgroup *objcg, enum vm_event_item idx, unsigned long count) { } static inline ino_t page_cgroup_ino(struct page *page) { return 0; } static inline bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid) { return true; } #endif /* CONFIG_MEMCG */ #if defined(CONFIG_MEMCG) && defined(CONFIG_ZSWAP) bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg); #else static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) { return true; } static inline void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size) { } static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size) { } static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg) { /* if zswap is disabled, do not block pages going to the swapping device */ return true; } #endif /* Cgroup v1-related declarations */ #ifdef CONFIG_MEMCG_V1 unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); bool mem_cgroup_oom_synchronize(bool wait); static inline bool task_in_memcg_oom(struct task_struct *p) { return p->memcg_in_oom; } static inline void mem_cgroup_enter_user_fault(void) { WARN_ON(current->in_user_fault); current->in_user_fault = 1; } static inline void mem_cgroup_exit_user_fault(void) { WARN_ON(!current->in_user_fault); current->in_user_fault = 0; } void memcg1_swapout(struct folio *folio, swp_entry_t entry); void memcg1_swapin(swp_entry_t entry, unsigned int nr_pages); #else /* CONFIG_MEMCG_V1 */ static inline unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned) { return 0; } static inline bool task_in_memcg_oom(struct task_struct *p) { return false; } static inline bool mem_cgroup_oom_synchronize(bool wait) { return false; } static inline void mem_cgroup_enter_user_fault(void) { } static inline void mem_cgroup_exit_user_fault(void) { } static inline void memcg1_swapout(struct folio *folio, swp_entry_t entry) { } static inline void memcg1_swapin(swp_entry_t entry, unsigned int nr_pages) { } #endif /* CONFIG_MEMCG_V1 */ #endif /* _LINUX_MEMCONTROL_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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2023 ARM Ltd. */ #ifndef __ASM_GCS_H #define __ASM_GCS_H #include <asm/types.h> #include <asm/uaccess.h> struct kernel_clone_args; struct ksignal; static inline void gcsb_dsync(void) { asm volatile(".inst 0xd503227f" : : : "memory"); } static inline void gcsstr(u64 *addr, u64 val) { register u64 *_addr __asm__ ("x0") = addr; register long _val __asm__ ("x1") = val; /* GCSSTTR x1, [x0] */ asm volatile( ".inst 0xd91f1c01\n" : : "rZ" (_val), "r" (_addr) : "memory"); } static inline void gcsss1(u64 Xt) { asm volatile ( "sys #3, C7, C7, #2, %0\n" : : "rZ" (Xt) : "memory"); } static inline u64 gcsss2(void) { u64 Xt; asm volatile( "SYSL %0, #3, C7, C7, #3\n" : "=r" (Xt) : : "memory"); return Xt; } #define PR_SHADOW_STACK_SUPPORTED_STATUS_MASK \ (PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE | PR_SHADOW_STACK_PUSH) #ifdef CONFIG_ARM64_GCS static inline bool task_gcs_el0_enabled(struct task_struct *task) { return task->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE; } void gcs_set_el0_mode(struct task_struct *task); void gcs_free(struct task_struct *task); void gcs_preserve_current_state(void); unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, const struct kernel_clone_args *args); static inline int gcs_check_locked(struct task_struct *task, unsigned long new_val) { unsigned long cur_val = task->thread.gcs_el0_mode; cur_val &= task->thread.gcs_el0_locked; new_val &= task->thread.gcs_el0_locked; if (cur_val != new_val) return -EBUSY; return 0; } static inline int gcssttr(unsigned long __user *addr, unsigned long val) { register unsigned long __user *_addr __asm__ ("x0") = addr; register unsigned long _val __asm__ ("x1") = val; int err = 0; /* GCSSTTR x1, [x0] */ asm volatile( "1: .inst 0xd91f1c01\n" "2: \n" _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %w0) : "+r" (err) : "rZ" (_val), "r" (_addr) : "memory"); return err; } static inline void put_user_gcs(unsigned long val, unsigned long __user *addr, int *err) { int ret; if (!access_ok((char __user *)addr, sizeof(u64))) { *err = -EFAULT; return; } uaccess_ttbr0_enable(); ret = gcssttr(addr, val); if (ret != 0) *err = ret; uaccess_ttbr0_disable(); } static inline void push_user_gcs(unsigned long val, int *err) { u64 gcspr = read_sysreg_s(SYS_GCSPR_EL0); gcspr -= sizeof(u64); put_user_gcs(val, (unsigned long __user *)gcspr, err); if (!*err) write_sysreg_s(gcspr, SYS_GCSPR_EL0); } /* * Unlike put/push_user_gcs() above, get/pop_user_gsc() doesn't * validate the GCS permission is set on the page being read. This * differs from how the hardware works when it consumes data stored at * GCSPR. Callers should ensure this is acceptable. */ static inline u64 get_user_gcs(unsigned long __user *addr, int *err) { unsigned long ret; u64 load = 0; /* Ensure previous GCS operation are visible before we read the page */ gcsb_dsync(); ret = copy_from_user(&load, addr, sizeof(load)); if (ret != 0) *err = ret; return load; } static inline u64 pop_user_gcs(int *err) { u64 gcspr = read_sysreg_s(SYS_GCSPR_EL0); u64 read_val; read_val = get_user_gcs((__force unsigned long __user *)gcspr, err); if (!*err) write_sysreg_s(gcspr + sizeof(u64), SYS_GCSPR_EL0); return read_val; } #else static inline bool task_gcs_el0_enabled(struct task_struct *task) { return false; } static inline void gcs_set_el0_mode(struct task_struct *task) { } static inline void gcs_free(struct task_struct *task) { } static inline void gcs_preserve_current_state(void) { } static inline void put_user_gcs(unsigned long val, unsigned long __user *addr, int *err) { } static inline void push_user_gcs(unsigned long val, int *err) { } static inline unsigned long gcs_alloc_thread_stack(struct task_struct *tsk, const struct kernel_clone_args *args) { return -ENOTSUPP; } static inline int gcs_check_locked(struct task_struct *task, unsigned long new_val) { return 0; } static inline u64 get_user_gcs(unsigned long __user *addr, int *err) { *err = -EFAULT; return 0; } static inline u64 pop_user_gcs(int *err) { return 0; } #endif #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_NULLS_H #define _LINUX_RCULIST_NULLS_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list_nulls.h> #include <linux/rcupdate.h> /** * hlist_nulls_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: hlist_nulls_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_nulls_add_head_rcu() or * hlist_nulls_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_nulls_for_each_entry_rcu(). */ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) { if (!hlist_nulls_unhashed(n)) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, NULL); } } /** * hlist_nulls_first_rcu - returns the first element of the hash list. * @head: the head of the list. */ #define hlist_nulls_first_rcu(head) \ (*((struct hlist_nulls_node __rcu __force **)&(head)->first)) /** * hlist_nulls_next_rcu - returns the element of the list after @node. * @node: element of the list. */ #define hlist_nulls_next_rcu(node) \ (*((struct hlist_nulls_node __rcu __force **)&(node)->next)) /** * hlist_nulls_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: hlist_nulls_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_nulls_add_head_rcu() * or hlist_nulls_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_nulls_for_each_entry(). */ static inline void hlist_nulls_del_rcu(struct hlist_nulls_node *n) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_nulls_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_nulls, * 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_nulls_add_head_rcu() * or hlist_nulls_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_nulls_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_nulls_add_head_rcu(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *first = h->first; WRITE_ONCE(n->next, first); WRITE_ONCE(n->pprev, &h->first); rcu_assign_pointer(hlist_nulls_first_rcu(h), n); if (!is_a_nulls(first)) WRITE_ONCE(first->pprev, &n->next); } /** * hlist_nulls_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_nulls, * 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_nulls_add_head_rcu() * or hlist_nulls_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_nulls_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_nulls_add_tail_rcu(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; !is_a_nulls(i); i = i->next) last = i; if (last) { WRITE_ONCE(n->next, last->next); n->pprev = &last->next; rcu_assign_pointer(hlist_nulls_next_rcu(last), n); } else { hlist_nulls_add_head_rcu(n, h); } } /* after that hlist_nulls_del will work */ static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n) { n->pprev = &n->next; n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL); } /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_nulls_node to use as a loop cursor. * @head: the head of the list. * @member: the name of the hlist_nulls_node within the struct. * * The barrier() is needed to make sure compiler doesn't cache first element [1], * as this loop can be restarted [2] * [1] Documentation/memory-barriers.txt around line 1533 * [2] Documentation/RCU/rculist_nulls.rst around line 146 */ #define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \ for (({barrier();}), \ pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos))) /** * hlist_nulls_for_each_entry_safe - * iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_nulls_node to use as a loop cursor. * @head: the head of the list. * @member: the name of the hlist_nulls_node within the struct. */ #define hlist_nulls_for_each_entry_safe(tpos, pos, head, member) \ for (({barrier();}), \ pos = rcu_dereference_raw(hlist_nulls_first_rcu(head)); \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); \ pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)); 1; });) #endif #endif |
| 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 | /* 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_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_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 */ |
| 18 656 429 124 126 93 93 93 430 429 430 93 94 92 19 19 19 19 19 19 3 3 15 15 15 15 5 5 202 203 6 6 6 6 13 13 19 19 14 14 45 47 654 656 656 109 112 135 137 136 1418 1424 189 87 258 260 256 257 201 202 189 190 6 6 342 346 524 524 388 266 268 18 18 18 5 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Security plug functions * * Copyright (C) 2001 WireX Communications, Inc <chris@wirex.com> * Copyright (C) 2001-2002 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2001 Networks Associates Technology, Inc <ssmalley@nai.com> * Copyright (C) 2016 Mellanox Technologies * Copyright (C) 2023 Microsoft Corporation <paul@paul-moore.com> */ #define pr_fmt(fmt) "LSM: " fmt #include <linux/bpf.h> #include <linux/capability.h> #include <linux/dcache.h> #include <linux/export.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/lsm_hooks.h> #include <linux/mman.h> #include <linux/mount.h> #include <linux/personality.h> #include <linux/backing-dev.h> #include <linux/string.h> #include <linux/xattr.h> #include <linux/msg.h> #include <linux/overflow.h> #include <linux/perf_event.h> #include <linux/fs.h> #include <net/flow.h> #include <net/sock.h> #define SECURITY_HOOK_ACTIVE_KEY(HOOK, IDX) security_hook_active_##HOOK##_##IDX /* * Identifier for the LSM static calls. * HOOK is an LSM hook as defined in linux/lsm_hookdefs.h * IDX is the index of the static call. 0 <= NUM < MAX_LSM_COUNT */ #define LSM_STATIC_CALL(HOOK, IDX) lsm_static_call_##HOOK##_##IDX /* * Call the macro M for each LSM hook MAX_LSM_COUNT times. */ #define LSM_LOOP_UNROLL(M, ...) \ do { \ UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__) \ } while (0) #define LSM_DEFINE_UNROLL(M, ...) UNROLL(MAX_LSM_COUNT, M, __VA_ARGS__) /* * These are descriptions of the reasons that can be passed to the * security_locked_down() LSM hook. Placing this array here allows * all security modules to use the same descriptions for auditing * purposes. */ const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX + 1] = { [LOCKDOWN_NONE] = "none", [LOCKDOWN_MODULE_SIGNATURE] = "unsigned module loading", [LOCKDOWN_DEV_MEM] = "/dev/mem,kmem,port", [LOCKDOWN_EFI_TEST] = "/dev/efi_test access", [LOCKDOWN_KEXEC] = "kexec of unsigned images", [LOCKDOWN_HIBERNATION] = "hibernation", [LOCKDOWN_PCI_ACCESS] = "direct PCI access", [LOCKDOWN_IOPORT] = "raw io port access", [LOCKDOWN_MSR] = "raw MSR access", [LOCKDOWN_ACPI_TABLES] = "modifying ACPI tables", [LOCKDOWN_DEVICE_TREE] = "modifying device tree contents", [LOCKDOWN_PCMCIA_CIS] = "direct PCMCIA CIS storage", [LOCKDOWN_TIOCSSERIAL] = "reconfiguration of serial port IO", [LOCKDOWN_MODULE_PARAMETERS] = "unsafe module parameters", [LOCKDOWN_MMIOTRACE] = "unsafe mmio", [LOCKDOWN_DEBUGFS] = "debugfs access", [LOCKDOWN_XMON_WR] = "xmon write access", [LOCKDOWN_BPF_WRITE_USER] = "use of bpf to write user RAM", [LOCKDOWN_DBG_WRITE_KERNEL] = "use of kgdb/kdb to write kernel RAM", [LOCKDOWN_RTAS_ERROR_INJECTION] = "RTAS error injection", [LOCKDOWN_INTEGRITY_MAX] = "integrity", [LOCKDOWN_KCORE] = "/proc/kcore access", [LOCKDOWN_KPROBES] = "use of kprobes", [LOCKDOWN_BPF_READ_KERNEL] = "use of bpf to read kernel RAM", [LOCKDOWN_DBG_READ_KERNEL] = "use of kgdb/kdb to read kernel RAM", [LOCKDOWN_PERF] = "unsafe use of perf", [LOCKDOWN_TRACEFS] = "use of tracefs", [LOCKDOWN_XMON_RW] = "xmon read and write access", [LOCKDOWN_XFRM_SECRET] = "xfrm SA secret", [LOCKDOWN_CONFIDENTIALITY_MAX] = "confidentiality", }; static BLOCKING_NOTIFIER_HEAD(blocking_lsm_notifier_chain); static struct kmem_cache *lsm_file_cache; static struct kmem_cache *lsm_inode_cache; char *lsm_names; static struct lsm_blob_sizes blob_sizes __ro_after_init; /* Boot-time LSM user choice */ static __initdata const char *chosen_lsm_order; static __initdata const char *chosen_major_lsm; static __initconst const char *const builtin_lsm_order = CONFIG_LSM; /* Ordered list of LSMs to initialize. */ static __initdata struct lsm_info *ordered_lsms[MAX_LSM_COUNT + 1]; static __initdata struct lsm_info *exclusive; #ifdef CONFIG_HAVE_STATIC_CALL #define LSM_HOOK_TRAMP(NAME, NUM) \ &STATIC_CALL_TRAMP(LSM_STATIC_CALL(NAME, NUM)) #else #define LSM_HOOK_TRAMP(NAME, NUM) NULL #endif /* * Define static calls and static keys for each LSM hook. */ #define DEFINE_LSM_STATIC_CALL(NUM, NAME, RET, ...) \ DEFINE_STATIC_CALL_NULL(LSM_STATIC_CALL(NAME, NUM), \ *((RET(*)(__VA_ARGS__))NULL)); \ DEFINE_STATIC_KEY_FALSE(SECURITY_HOOK_ACTIVE_KEY(NAME, NUM)); #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ LSM_DEFINE_UNROLL(DEFINE_LSM_STATIC_CALL, NAME, RET, __VA_ARGS__) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK #undef DEFINE_LSM_STATIC_CALL /* * Initialise a table of static calls for each LSM hook. * DEFINE_STATIC_CALL_NULL invocation above generates a key (STATIC_CALL_KEY) * and a trampoline (STATIC_CALL_TRAMP) which are used to call * __static_call_update when updating the static call. * * The static calls table is used by early LSMs, some architectures can fault on * unaligned accesses and the fault handling code may not be ready by then. * Thus, the static calls table should be aligned to avoid any unhandled faults * in early init. */ struct lsm_static_calls_table static_calls_table __ro_after_init __aligned(sizeof(u64)) = { #define INIT_LSM_STATIC_CALL(NUM, NAME) \ (struct lsm_static_call) { \ .key = &STATIC_CALL_KEY(LSM_STATIC_CALL(NAME, NUM)), \ .trampoline = LSM_HOOK_TRAMP(NAME, NUM), \ .active = &SECURITY_HOOK_ACTIVE_KEY(NAME, NUM), \ }, #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ .NAME = { \ LSM_DEFINE_UNROLL(INIT_LSM_STATIC_CALL, NAME) \ }, #include <linux/lsm_hook_defs.h> #undef LSM_HOOK #undef INIT_LSM_STATIC_CALL }; static __initdata bool debug; #define init_debug(...) \ do { \ if (debug) \ pr_info(__VA_ARGS__); \ } while (0) static bool __init is_enabled(struct lsm_info *lsm) { if (!lsm->enabled) return false; return *lsm->enabled; } /* Mark an LSM's enabled flag. */ static int lsm_enabled_true __initdata = 1; static int lsm_enabled_false __initdata = 0; static void __init set_enabled(struct lsm_info *lsm, bool enabled) { /* * When an LSM hasn't configured an enable variable, we can use * a hard-coded location for storing the default enabled state. */ if (!lsm->enabled) { if (enabled) lsm->enabled = &lsm_enabled_true; else lsm->enabled = &lsm_enabled_false; } else if (lsm->enabled == &lsm_enabled_true) { if (!enabled) lsm->enabled = &lsm_enabled_false; } else if (lsm->enabled == &lsm_enabled_false) { if (enabled) lsm->enabled = &lsm_enabled_true; } else { *lsm->enabled = enabled; } } /* Is an LSM already listed in the ordered LSMs list? */ static bool __init exists_ordered_lsm(struct lsm_info *lsm) { struct lsm_info **check; for (check = ordered_lsms; *check; check++) if (*check == lsm) return true; return false; } /* Append an LSM to the list of ordered LSMs to initialize. */ static int last_lsm __initdata; static void __init append_ordered_lsm(struct lsm_info *lsm, const char *from) { /* Ignore duplicate selections. */ if (exists_ordered_lsm(lsm)) return; if (WARN(last_lsm == MAX_LSM_COUNT, "%s: out of LSM static calls!?\n", from)) return; /* Enable this LSM, if it is not already set. */ if (!lsm->enabled) lsm->enabled = &lsm_enabled_true; ordered_lsms[last_lsm++] = lsm; init_debug("%s ordered: %s (%s)\n", from, lsm->name, is_enabled(lsm) ? "enabled" : "disabled"); } /* Is an LSM allowed to be initialized? */ static bool __init lsm_allowed(struct lsm_info *lsm) { /* Skip if the LSM is disabled. */ if (!is_enabled(lsm)) return false; /* Not allowed if another exclusive LSM already initialized. */ if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && exclusive) { init_debug("exclusive disabled: %s\n", lsm->name); return false; } return true; } static void __init lsm_set_blob_size(int *need, int *lbs) { int offset; if (*need <= 0) return; offset = ALIGN(*lbs, sizeof(void *)); *lbs = offset + *need; *need = offset; } static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) { if (!needed) return; lsm_set_blob_size(&needed->lbs_cred, &blob_sizes.lbs_cred); lsm_set_blob_size(&needed->lbs_file, &blob_sizes.lbs_file); lsm_set_blob_size(&needed->lbs_ib, &blob_sizes.lbs_ib); /* * The inode blob gets an rcu_head in addition to * what the modules might need. */ if (needed->lbs_inode && blob_sizes.lbs_inode == 0) blob_sizes.lbs_inode = sizeof(struct rcu_head); lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode); lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc); lsm_set_blob_size(&needed->lbs_key, &blob_sizes.lbs_key); lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg); lsm_set_blob_size(&needed->lbs_perf_event, &blob_sizes.lbs_perf_event); lsm_set_blob_size(&needed->lbs_sock, &blob_sizes.lbs_sock); lsm_set_blob_size(&needed->lbs_superblock, &blob_sizes.lbs_superblock); lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task); lsm_set_blob_size(&needed->lbs_tun_dev, &blob_sizes.lbs_tun_dev); lsm_set_blob_size(&needed->lbs_xattr_count, &blob_sizes.lbs_xattr_count); lsm_set_blob_size(&needed->lbs_bdev, &blob_sizes.lbs_bdev); lsm_set_blob_size(&needed->lbs_bpf_map, &blob_sizes.lbs_bpf_map); lsm_set_blob_size(&needed->lbs_bpf_prog, &blob_sizes.lbs_bpf_prog); lsm_set_blob_size(&needed->lbs_bpf_token, &blob_sizes.lbs_bpf_token); } /* Prepare LSM for initialization. */ static void __init prepare_lsm(struct lsm_info *lsm) { int enabled = lsm_allowed(lsm); /* Record enablement (to handle any following exclusive LSMs). */ set_enabled(lsm, enabled); /* If enabled, do pre-initialization work. */ if (enabled) { if ((lsm->flags & LSM_FLAG_EXCLUSIVE) && !exclusive) { exclusive = lsm; init_debug("exclusive chosen: %s\n", lsm->name); } lsm_set_blob_sizes(lsm->blobs); } } /* Initialize a given LSM, if it is enabled. */ static void __init initialize_lsm(struct lsm_info *lsm) { if (is_enabled(lsm)) { int ret; init_debug("initializing %s\n", lsm->name); ret = lsm->init(); WARN(ret, "%s failed to initialize: %d\n", lsm->name, ret); } } /* * Current index to use while initializing the lsm id list. */ u32 lsm_active_cnt __ro_after_init; const struct lsm_id *lsm_idlist[MAX_LSM_COUNT]; /* Populate ordered LSMs list from comma-separated LSM name list. */ static void __init ordered_lsm_parse(const char *order, const char *origin) { struct lsm_info *lsm; char *sep, *name, *next; /* LSM_ORDER_FIRST is always first. */ for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (lsm->order == LSM_ORDER_FIRST) append_ordered_lsm(lsm, " first"); } /* Process "security=", if given. */ if (chosen_major_lsm) { struct lsm_info *major; /* * To match the original "security=" behavior, this * explicitly does NOT fallback to another Legacy Major * if the selected one was separately disabled: disable * all non-matching Legacy Major LSMs. */ for (major = __start_lsm_info; major < __end_lsm_info; major++) { if ((major->flags & LSM_FLAG_LEGACY_MAJOR) && strcmp(major->name, chosen_major_lsm) != 0) { set_enabled(major, false); init_debug("security=%s disabled: %s (only one legacy major LSM)\n", chosen_major_lsm, major->name); } } } sep = kstrdup(order, GFP_KERNEL); next = sep; /* Walk the list, looking for matching LSMs. */ while ((name = strsep(&next, ",")) != NULL) { bool found = false; for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (strcmp(lsm->name, name) == 0) { if (lsm->order == LSM_ORDER_MUTABLE) append_ordered_lsm(lsm, origin); found = true; } } if (!found) init_debug("%s ignored: %s (not built into kernel)\n", origin, name); } /* Process "security=", if given. */ if (chosen_major_lsm) { for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (exists_ordered_lsm(lsm)) continue; if (strcmp(lsm->name, chosen_major_lsm) == 0) append_ordered_lsm(lsm, "security="); } } /* LSM_ORDER_LAST is always last. */ for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (lsm->order == LSM_ORDER_LAST) append_ordered_lsm(lsm, " last"); } /* Disable all LSMs not in the ordered list. */ for (lsm = __start_lsm_info; lsm < __end_lsm_info; lsm++) { if (exists_ordered_lsm(lsm)) continue; set_enabled(lsm, false); init_debug("%s skipped: %s (not in requested order)\n", origin, lsm->name); } kfree(sep); } static void __init lsm_static_call_init(struct security_hook_list *hl) { struct lsm_static_call *scall = hl->scalls; int i; for (i = 0; i < MAX_LSM_COUNT; i++) { /* Update the first static call that is not used yet */ if (!scall->hl) { __static_call_update(scall->key, scall->trampoline, hl->hook.lsm_func_addr); scall->hl = hl; static_branch_enable(scall->active); return; } scall++; } panic("%s - Ran out of static slots.\n", __func__); } static void __init lsm_early_cred(struct cred *cred); static void __init lsm_early_task(struct task_struct *task); static int lsm_append(const char *new, char **result); static void __init report_lsm_order(void) { struct lsm_info **lsm, *early; int first = 0; pr_info("initializing lsm="); /* Report each enabled LSM name, comma separated. */ for (early = __start_early_lsm_info; early < __end_early_lsm_info; early++) if (is_enabled(early)) pr_cont("%s%s", first++ == 0 ? "" : ",", early->name); for (lsm = ordered_lsms; *lsm; lsm++) if (is_enabled(*lsm)) pr_cont("%s%s", first++ == 0 ? "" : ",", (*lsm)->name); pr_cont("\n"); } static void __init ordered_lsm_init(void) { struct lsm_info **lsm; if (chosen_lsm_order) { if (chosen_major_lsm) { pr_warn("security=%s is ignored because it is superseded by lsm=%s\n", chosen_major_lsm, chosen_lsm_order); chosen_major_lsm = NULL; } ordered_lsm_parse(chosen_lsm_order, "cmdline"); } else ordered_lsm_parse(builtin_lsm_order, "builtin"); for (lsm = ordered_lsms; *lsm; lsm++) prepare_lsm(*lsm); report_lsm_order(); init_debug("cred blob size = %d\n", blob_sizes.lbs_cred); init_debug("file blob size = %d\n", blob_sizes.lbs_file); init_debug("ib blob size = %d\n", blob_sizes.lbs_ib); init_debug("inode blob size = %d\n", blob_sizes.lbs_inode); init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc); #ifdef CONFIG_KEYS init_debug("key blob size = %d\n", blob_sizes.lbs_key); #endif /* CONFIG_KEYS */ init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg); init_debug("sock blob size = %d\n", blob_sizes.lbs_sock); init_debug("superblock blob size = %d\n", blob_sizes.lbs_superblock); init_debug("perf event blob size = %d\n", blob_sizes.lbs_perf_event); init_debug("task blob size = %d\n", blob_sizes.lbs_task); init_debug("tun device blob size = %d\n", blob_sizes.lbs_tun_dev); init_debug("xattr slots = %d\n", blob_sizes.lbs_xattr_count); init_debug("bdev blob size = %d\n", blob_sizes.lbs_bdev); init_debug("bpf map blob size = %d\n", blob_sizes.lbs_bpf_map); init_debug("bpf prog blob size = %d\n", blob_sizes.lbs_bpf_prog); init_debug("bpf token blob size = %d\n", blob_sizes.lbs_bpf_token); /* * Create any kmem_caches needed for blobs */ if (blob_sizes.lbs_file) lsm_file_cache = kmem_cache_create("lsm_file_cache", blob_sizes.lbs_file, 0, SLAB_PANIC, NULL); if (blob_sizes.lbs_inode) lsm_inode_cache = kmem_cache_create("lsm_inode_cache", blob_sizes.lbs_inode, 0, SLAB_PANIC, NULL); lsm_early_cred((struct cred *) current->cred); lsm_early_task(current); for (lsm = ordered_lsms; *lsm; lsm++) initialize_lsm(*lsm); } int __init early_security_init(void) { struct lsm_info *lsm; for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) { if (!lsm->enabled) lsm->enabled = &lsm_enabled_true; prepare_lsm(lsm); initialize_lsm(lsm); } return 0; } /** * security_init - initializes the security framework * * This should be called early in the kernel initialization sequence. */ int __init security_init(void) { struct lsm_info *lsm; init_debug("legacy security=%s\n", chosen_major_lsm ? : " *unspecified*"); init_debug(" CONFIG_LSM=%s\n", builtin_lsm_order); init_debug("boot arg lsm=%s\n", chosen_lsm_order ? : " *unspecified*"); /* * Append the names of the early LSM modules now that kmalloc() is * available */ for (lsm = __start_early_lsm_info; lsm < __end_early_lsm_info; lsm++) { init_debug(" early started: %s (%s)\n", lsm->name, is_enabled(lsm) ? "enabled" : "disabled"); if (lsm->enabled) lsm_append(lsm->name, &lsm_names); } /* Load LSMs in specified order. */ ordered_lsm_init(); return 0; } /* Save user chosen LSM */ static int __init choose_major_lsm(char *str) { chosen_major_lsm = str; return 1; } __setup("security=", choose_major_lsm); /* Explicitly choose LSM initialization order. */ static int __init choose_lsm_order(char *str) { chosen_lsm_order = str; return 1; } __setup("lsm=", choose_lsm_order); /* Enable LSM order debugging. */ static int __init enable_debug(char *str) { debug = true; return 1; } __setup("lsm.debug", enable_debug); static bool match_last_lsm(const char *list, const char *lsm) { const char *last; if (WARN_ON(!list || !lsm)) return false; last = strrchr(list, ','); if (last) /* Pass the comma, strcmp() will check for '\0' */ last++; else last = list; return !strcmp(last, lsm); } static int lsm_append(const char *new, char **result) { char *cp; if (*result == NULL) { *result = kstrdup(new, GFP_KERNEL); if (*result == NULL) return -ENOMEM; } else { /* Check if it is the last registered name */ if (match_last_lsm(*result, new)) return 0; cp = kasprintf(GFP_KERNEL, "%s,%s", *result, new); if (cp == NULL) return -ENOMEM; kfree(*result); *result = cp; } return 0; } /** * security_add_hooks - Add a modules hooks to the hook lists. * @hooks: the hooks to add * @count: the number of hooks to add * @lsmid: the identification information for the security module * * Each LSM has to register its hooks with the infrastructure. */ void __init security_add_hooks(struct security_hook_list *hooks, int count, const struct lsm_id *lsmid) { int i; /* * A security module may call security_add_hooks() more * than once during initialization, and LSM initialization * is serialized. Landlock is one such case. * Look at the previous entry, if there is one, for duplication. */ if (lsm_active_cnt == 0 || lsm_idlist[lsm_active_cnt - 1] != lsmid) { if (lsm_active_cnt >= MAX_LSM_COUNT) panic("%s Too many LSMs registered.\n", __func__); lsm_idlist[lsm_active_cnt++] = lsmid; } for (i = 0; i < count; i++) { hooks[i].lsmid = lsmid; lsm_static_call_init(&hooks[i]); } /* * Don't try to append during early_security_init(), we'll come back * and fix this up afterwards. */ if (slab_is_available()) { if (lsm_append(lsmid->name, &lsm_names) < 0) panic("%s - Cannot get early memory.\n", __func__); } } int call_blocking_lsm_notifier(enum lsm_event event, void *data) { return blocking_notifier_call_chain(&blocking_lsm_notifier_chain, event, data); } EXPORT_SYMBOL(call_blocking_lsm_notifier); int register_blocking_lsm_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&blocking_lsm_notifier_chain, nb); } EXPORT_SYMBOL(register_blocking_lsm_notifier); int unregister_blocking_lsm_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&blocking_lsm_notifier_chain, nb); } EXPORT_SYMBOL(unregister_blocking_lsm_notifier); /** * lsm_blob_alloc - allocate a composite blob * @dest: the destination for the blob * @size: the size of the blob * @gfp: allocation type * * Allocate a blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_blob_alloc(void **dest, size_t size, gfp_t gfp) { if (size == 0) { *dest = NULL; return 0; } *dest = kzalloc(size, gfp); if (*dest == NULL) return -ENOMEM; return 0; } /** * lsm_cred_alloc - allocate a composite cred blob * @cred: the cred that needs a blob * @gfp: allocation type * * Allocate the cred blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_cred_alloc(struct cred *cred, gfp_t gfp) { return lsm_blob_alloc(&cred->security, blob_sizes.lbs_cred, gfp); } /** * lsm_early_cred - during initialization allocate a composite cred blob * @cred: the cred that needs a blob * * Allocate the cred blob for all the modules */ static void __init lsm_early_cred(struct cred *cred) { int rc = lsm_cred_alloc(cred, GFP_KERNEL); if (rc) panic("%s: Early cred alloc failed.\n", __func__); } /** * lsm_file_alloc - allocate a composite file blob * @file: the file that needs a blob * * Allocate the file blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_file_alloc(struct file *file) { if (!lsm_file_cache) { file->f_security = NULL; return 0; } file->f_security = kmem_cache_zalloc(lsm_file_cache, GFP_KERNEL); if (file->f_security == NULL) return -ENOMEM; return 0; } /** * lsm_inode_alloc - allocate a composite inode blob * @inode: the inode that needs a blob * @gfp: allocation flags * * Allocate the inode blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_inode_alloc(struct inode *inode, gfp_t gfp) { if (!lsm_inode_cache) { inode->i_security = NULL; return 0; } inode->i_security = kmem_cache_zalloc(lsm_inode_cache, gfp); if (inode->i_security == NULL) return -ENOMEM; return 0; } /** * lsm_task_alloc - allocate a composite task blob * @task: the task that needs a blob * * Allocate the task blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_task_alloc(struct task_struct *task) { return lsm_blob_alloc(&task->security, blob_sizes.lbs_task, GFP_KERNEL); } /** * lsm_ipc_alloc - allocate a composite ipc blob * @kip: the ipc that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_ipc_alloc(struct kern_ipc_perm *kip) { return lsm_blob_alloc(&kip->security, blob_sizes.lbs_ipc, GFP_KERNEL); } #ifdef CONFIG_KEYS /** * lsm_key_alloc - allocate a composite key blob * @key: the key that needs a blob * * Allocate the key blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_key_alloc(struct key *key) { return lsm_blob_alloc(&key->security, blob_sizes.lbs_key, GFP_KERNEL); } #endif /* CONFIG_KEYS */ /** * lsm_msg_msg_alloc - allocate a composite msg_msg blob * @mp: the msg_msg that needs a blob * * Allocate the ipc blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_msg_msg_alloc(struct msg_msg *mp) { return lsm_blob_alloc(&mp->security, blob_sizes.lbs_msg_msg, GFP_KERNEL); } /** * lsm_bdev_alloc - allocate a composite block_device blob * @bdev: the block_device that needs a blob * * Allocate the block_device blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bdev_alloc(struct block_device *bdev) { return lsm_blob_alloc(&bdev->bd_security, blob_sizes.lbs_bdev, GFP_KERNEL); } #ifdef CONFIG_BPF_SYSCALL /** * lsm_bpf_map_alloc - allocate a composite bpf_map blob * @map: the bpf_map that needs a blob * * Allocate the bpf_map blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bpf_map_alloc(struct bpf_map *map) { return lsm_blob_alloc(&map->security, blob_sizes.lbs_bpf_map, GFP_KERNEL); } /** * lsm_bpf_prog_alloc - allocate a composite bpf_prog blob * @prog: the bpf_prog that needs a blob * * Allocate the bpf_prog blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bpf_prog_alloc(struct bpf_prog *prog) { return lsm_blob_alloc(&prog->aux->security, blob_sizes.lbs_bpf_prog, GFP_KERNEL); } /** * lsm_bpf_token_alloc - allocate a composite bpf_token blob * @token: the bpf_token that needs a blob * * Allocate the bpf_token blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_bpf_token_alloc(struct bpf_token *token) { return lsm_blob_alloc(&token->security, blob_sizes.lbs_bpf_token, GFP_KERNEL); } #endif /* CONFIG_BPF_SYSCALL */ /** * lsm_early_task - during initialization allocate a composite task blob * @task: the task that needs a blob * * Allocate the task blob for all the modules */ static void __init lsm_early_task(struct task_struct *task) { int rc = lsm_task_alloc(task); if (rc) panic("%s: Early task alloc failed.\n", __func__); } /** * lsm_superblock_alloc - allocate a composite superblock blob * @sb: the superblock that needs a blob * * Allocate the superblock blob for all the modules * * Returns 0, or -ENOMEM if memory can't be allocated. */ static int lsm_superblock_alloc(struct super_block *sb) { return lsm_blob_alloc(&sb->s_security, blob_sizes.lbs_superblock, GFP_KERNEL); } /** * lsm_fill_user_ctx - Fill a user space lsm_ctx structure * @uctx: a userspace LSM context to be filled * @uctx_len: available uctx size (input), used uctx size (output) * @val: the new LSM context value * @val_len: the size of the new LSM context value * @id: LSM id * @flags: LSM defined flags * * Fill all of the fields in a userspace lsm_ctx structure. If @uctx is NULL * simply calculate the required size to output via @utc_len and return * success. * * Returns 0 on success, -E2BIG if userspace buffer is not large enough, * -EFAULT on a copyout error, -ENOMEM if memory can't be allocated. */ int lsm_fill_user_ctx(struct lsm_ctx __user *uctx, u32 *uctx_len, void *val, size_t val_len, u64 id, u64 flags) { struct lsm_ctx *nctx = NULL; size_t nctx_len; int rc = 0; nctx_len = ALIGN(struct_size(nctx, ctx, val_len), sizeof(void *)); if (nctx_len > *uctx_len) { rc = -E2BIG; goto out; } /* no buffer - return success/0 and set @uctx_len to the req size */ if (!uctx) goto out; nctx = kzalloc(nctx_len, GFP_KERNEL); if (nctx == NULL) { rc = -ENOMEM; goto out; } nctx->id = id; nctx->flags = flags; nctx->len = nctx_len; nctx->ctx_len = val_len; memcpy(nctx->ctx, val, val_len); if (copy_to_user(uctx, nctx, nctx_len)) rc = -EFAULT; out: kfree(nctx); *uctx_len = nctx_len; return rc; } /* * The default value of the LSM hook is defined in linux/lsm_hook_defs.h and * can be accessed with: * * LSM_RET_DEFAULT(<hook_name>) * * The macros below define static constants for the default value of each * LSM hook. */ #define LSM_RET_DEFAULT(NAME) (NAME##_default) #define DECLARE_LSM_RET_DEFAULT_void(DEFAULT, NAME) #define DECLARE_LSM_RET_DEFAULT_int(DEFAULT, NAME) \ static const int __maybe_unused LSM_RET_DEFAULT(NAME) = (DEFAULT); #define LSM_HOOK(RET, DEFAULT, NAME, ...) \ DECLARE_LSM_RET_DEFAULT_##RET(DEFAULT, NAME) #include <linux/lsm_hook_defs.h> #undef LSM_HOOK /* * Hook list operation macros. * * call_void_hook: * This is a hook that does not return a value. * * call_int_hook: * This is a hook that returns a value. */ #define __CALL_STATIC_VOID(NUM, HOOK, ...) \ do { \ if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) { \ static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__); \ } \ } while (0); #define call_void_hook(HOOK, ...) \ do { \ LSM_LOOP_UNROLL(__CALL_STATIC_VOID, HOOK, __VA_ARGS__); \ } while (0) #define __CALL_STATIC_INT(NUM, R, HOOK, LABEL, ...) \ do { \ if (static_branch_unlikely(&SECURITY_HOOK_ACTIVE_KEY(HOOK, NUM))) { \ R = static_call(LSM_STATIC_CALL(HOOK, NUM))(__VA_ARGS__); \ if (R != LSM_RET_DEFAULT(HOOK)) \ goto LABEL; \ } \ } while (0); #define call_int_hook(HOOK, ...) \ ({ \ __label__ OUT; \ int RC = LSM_RET_DEFAULT(HOOK); \ \ LSM_LOOP_UNROLL(__CALL_STATIC_INT, RC, HOOK, OUT, __VA_ARGS__); \ OUT: \ RC; \ }) #define lsm_for_each_hook(scall, NAME) \ for (scall = static_calls_table.NAME; \ scall - static_calls_table.NAME < MAX_LSM_COUNT; scall++) \ if (static_key_enabled(&scall->active->key)) /* Security operations */ /** * security_binder_set_context_mgr() - Check if becoming binder ctx mgr is ok * @mgr: task credentials of current binder process * * Check whether @mgr is allowed to be the binder context manager. * * Return: Return 0 if permission is granted. */ int security_binder_set_context_mgr(const struct cred *mgr) { return call_int_hook(binder_set_context_mgr, mgr); } /** * security_binder_transaction() - Check if a binder transaction is allowed * @from: sending process * @to: receiving process * * Check whether @from is allowed to invoke a binder transaction call to @to. * * Return: Returns 0 if permission is granted. */ int security_binder_transaction(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transaction, from, to); } /** * security_binder_transfer_binder() - Check if a binder transfer is allowed * @from: sending process * @to: receiving process * * Check whether @from is allowed to transfer a binder reference to @to. * * Return: Returns 0 if permission is granted. */ int security_binder_transfer_binder(const struct cred *from, const struct cred *to) { return call_int_hook(binder_transfer_binder, from, to); } /** * security_binder_transfer_file() - Check if a binder file xfer is allowed * @from: sending process * @to: receiving process * @file: file being transferred * * Check whether @from is allowed to transfer @file to @to. * * Return: Returns 0 if permission is granted. */ int security_binder_transfer_file(const struct cred *from, const struct cred *to, const struct file *file) { return call_int_hook(binder_transfer_file, from, to, file); } /** * security_ptrace_access_check() - Check if tracing is allowed * @child: target process * @mode: PTRACE_MODE flags * * Check permission before allowing the current process to trace the @child * process. Security modules may also want to perform a process tracing check * during an execve in the set_security or apply_creds hooks of tracing check * during an execve in the bprm_set_creds hook of binprm_security_ops if the * process is being traced and its security attributes would be changed by the * execve. * * Return: Returns 0 if permission is granted. */ int security_ptrace_access_check(struct task_struct *child, unsigned int mode) { return call_int_hook(ptrace_access_check, child, mode); } /** * security_ptrace_traceme() - Check if tracing is allowed * @parent: tracing process * * Check that the @parent process has sufficient permission to trace the * current process before allowing the current process to present itself to the * @parent process for tracing. * * Return: Returns 0 if permission is granted. */ int security_ptrace_traceme(struct task_struct *parent) { return call_int_hook(ptrace_traceme, parent); } /** * security_capget() - Get the capability sets for a process * @target: target process * @effective: effective capability set * @inheritable: inheritable capability set * @permitted: permitted capability set * * Get the @effective, @inheritable, and @permitted capability sets for the * @target process. The hook may also perform permission checking to determine * if the current process is allowed to see the capability sets of the @target * process. * * Return: Returns 0 if the capability sets were successfully obtained. */ int security_capget(const struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted) { return call_int_hook(capget, target, effective, inheritable, permitted); } /** * security_capset() - Set the capability sets for a process * @new: new credentials for the target process * @old: current credentials of the target process * @effective: effective capability set * @inheritable: inheritable capability set * @permitted: permitted capability set * * Set the @effective, @inheritable, and @permitted capability sets for the * current process. * * Return: Returns 0 and update @new if permission is granted. */ int security_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted) { return call_int_hook(capset, new, old, effective, inheritable, permitted); } /** * security_capable() - Check if a process has the necessary capability * @cred: credentials to examine * @ns: user namespace * @cap: capability requested * @opts: capability check options * * Check whether the @tsk process has the @cap capability in the indicated * credentials. @cap contains the capability <include/linux/capability.h>. * @opts contains options for the capable check <include/linux/security.h>. * * Return: Returns 0 if the capability is granted. */ int security_capable(const struct cred *cred, struct user_namespace *ns, int cap, unsigned int opts) { return call_int_hook(capable, cred, ns, cap, opts); } /** * security_quotactl() - Check if a quotactl() syscall is allowed for this fs * @cmds: commands * @type: type * @id: id * @sb: filesystem * * Check whether the quotactl syscall is allowed for this @sb. * * Return: Returns 0 if permission is granted. */ int security_quotactl(int cmds, int type, int id, const struct super_block *sb) { return call_int_hook(quotactl, cmds, type, id, sb); } /** * security_quota_on() - Check if QUOTAON is allowed for a dentry * @dentry: dentry * * Check whether QUOTAON is allowed for @dentry. * * Return: Returns 0 if permission is granted. */ int security_quota_on(struct dentry *dentry) { return call_int_hook(quota_on, dentry); } /** * security_syslog() - Check if accessing the kernel message ring is allowed * @type: SYSLOG_ACTION_* type * * Check permission before accessing the kernel message ring or changing * logging to the console. See the syslog(2) manual page for an explanation of * the @type values. * * Return: Return 0 if permission is granted. */ int security_syslog(int type) { return call_int_hook(syslog, type); } /** * security_settime64() - Check if changing the system time is allowed * @ts: new time * @tz: timezone * * Check permission to change the system time, struct timespec64 is defined in * <include/linux/time64.h> and timezone is defined in <include/linux/time.h>. * * Return: Returns 0 if permission is granted. */ int security_settime64(const struct timespec64 *ts, const struct timezone *tz) { return call_int_hook(settime, ts, tz); } /** * security_vm_enough_memory_mm() - Check if allocating a new mem map is allowed * @mm: mm struct * @pages: number of pages * * Check permissions for allocating a new virtual mapping. If all LSMs return * a positive value, __vm_enough_memory() will be called with cap_sys_admin * set. If at least one LSM returns 0 or negative, __vm_enough_memory() will be * called with cap_sys_admin cleared. * * Return: Returns 0 if permission is granted by the LSM infrastructure to the * caller. */ int security_vm_enough_memory_mm(struct mm_struct *mm, long pages) { struct lsm_static_call *scall; int cap_sys_admin = 1; int rc; /* * The module will respond with 0 if it thinks the __vm_enough_memory() * call should be made with the cap_sys_admin set. If all of the modules * agree that it should be set it will. If any module thinks it should * not be set it won't. */ lsm_for_each_hook(scall, vm_enough_memory) { rc = scall->hl->hook.vm_enough_memory(mm, pages); if (rc < 0) { cap_sys_admin = 0; break; } } return __vm_enough_memory(mm, pages, cap_sys_admin); } /** * security_bprm_creds_for_exec() - Prepare the credentials for exec() * @bprm: binary program information * * If the setup in prepare_exec_creds did not setup @bprm->cred->security * properly for executing @bprm->file, update the LSM's portion of * @bprm->cred->security to be what commit_creds needs to install for the new * program. This hook may also optionally check permissions (e.g. for * transitions between security domains). The hook must set @bprm->secureexec * to 1 if AT_SECURE should be set to request libc enable secure mode. @bprm * contains the linux_binprm structure. * * If execveat(2) is called with the AT_EXECVE_CHECK flag, bprm->is_check is * set. The result must be the same as without this flag even if the execution * will never really happen and @bprm will always be dropped. * * This hook must not change current->cred, only @bprm->cred. * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_creds_for_exec(struct linux_binprm *bprm) { return call_int_hook(bprm_creds_for_exec, bprm); } /** * security_bprm_creds_from_file() - Update linux_binprm creds based on file * @bprm: binary program information * @file: associated file * * If @file is setpcap, suid, sgid or otherwise marked to change privilege upon * exec, update @bprm->cred to reflect that change. This is called after * finding the binary that will be executed without an interpreter. This * ensures that the credentials will not be derived from a script that the * binary will need to reopen, which when reopend may end up being a completely * different file. This hook may also optionally check permissions (e.g. for * transitions between security domains). The hook must set @bprm->secureexec * to 1 if AT_SECURE should be set to request libc enable secure mode. The * hook must add to @bprm->per_clear any personality flags that should be * cleared from current->personality. @bprm contains the linux_binprm * structure. * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_creds_from_file(struct linux_binprm *bprm, const struct file *file) { return call_int_hook(bprm_creds_from_file, bprm, file); } /** * security_bprm_check() - Mediate binary handler search * @bprm: binary program information * * This hook mediates the point when a search for a binary handler will begin. * It allows a check against the @bprm->cred->security value which was set in * the preceding creds_for_exec call. The argv list and envp list are reliably * available in @bprm. This hook may be called multiple times during a single * execve. @bprm contains the linux_binprm structure. * * Return: Returns 0 if the hook is successful and permission is granted. */ int security_bprm_check(struct linux_binprm *bprm) { return call_int_hook(bprm_check_security, bprm); } /** * security_bprm_committing_creds() - Install creds for a process during exec() * @bprm: binary program information * * Prepare to install the new security attributes of a process being * transformed by an execve operation, based on the old credentials pointed to * by @current->cred and the information set in @bprm->cred by the * bprm_creds_for_exec hook. @bprm points to the linux_binprm structure. This * hook is a good place to perform state changes on the process such as closing * open file descriptors to which access will no longer be granted when the * attributes are changed. This is called immediately before commit_creds(). */ void security_bprm_committing_creds(const struct linux_binprm *bprm) { call_void_hook(bprm_committing_creds, bprm); } /** * security_bprm_committed_creds() - Tidy up after cred install during exec() * @bprm: binary program information * * Tidy up after the installation of the new security attributes of a process * being transformed by an execve operation. The new credentials have, by this * point, been set to @current->cred. @bprm points to the linux_binprm * structure. This hook is a good place to perform state changes on the * process such as clearing out non-inheritable signal state. This is called * immediately after commit_creds(). */ void security_bprm_committed_creds(const struct linux_binprm *bprm) { call_void_hook(bprm_committed_creds, bprm); } /** * security_fs_context_submount() - Initialise fc->security * @fc: new filesystem context * @reference: dentry reference for submount/remount * * Fill out the ->security field for a new fs_context. * * Return: Returns 0 on success or negative error code on failure. */ int security_fs_context_submount(struct fs_context *fc, struct super_block *reference) { return call_int_hook(fs_context_submount, fc, reference); } /** * security_fs_context_dup() - Duplicate a fs_context LSM blob * @fc: destination filesystem context * @src_fc: source filesystem context * * Allocate and attach a security structure to sc->security. This pointer is * initialised to NULL by the caller. @fc indicates the new filesystem context. * @src_fc indicates the original filesystem context. * * Return: Returns 0 on success or a negative error code on failure. */ int security_fs_context_dup(struct fs_context *fc, struct fs_context *src_fc) { return call_int_hook(fs_context_dup, fc, src_fc); } /** * security_fs_context_parse_param() - Configure a filesystem context * @fc: filesystem context * @param: filesystem parameter * * Userspace provided a parameter to configure a superblock. The LSM can * consume the parameter or return it to the caller for use elsewhere. * * Return: If the parameter is used by the LSM it should return 0, if it is * returned to the caller -ENOPARAM is returned, otherwise a negative * error code is returned. */ int security_fs_context_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct lsm_static_call *scall; int trc; int rc = -ENOPARAM; lsm_for_each_hook(scall, fs_context_parse_param) { trc = scall->hl->hook.fs_context_parse_param(fc, param); if (trc == 0) rc = 0; else if (trc != -ENOPARAM) return trc; } return rc; } /** * security_sb_alloc() - Allocate a super_block LSM blob * @sb: filesystem superblock * * Allocate and attach a security structure to the sb->s_security field. The * s_security field is initialized to NULL when the structure is allocated. * @sb contains the super_block structure to be modified. * * Return: Returns 0 if operation was successful. */ int security_sb_alloc(struct super_block *sb) { int rc = lsm_superblock_alloc(sb); if (unlikely(rc)) return rc; rc = call_int_hook(sb_alloc_security, sb); if (unlikely(rc)) security_sb_free(sb); return rc; } /** * security_sb_delete() - Release super_block LSM associated objects * @sb: filesystem superblock * * Release objects tied to a superblock (e.g. inodes). @sb contains the * super_block structure being released. */ void security_sb_delete(struct super_block *sb) { call_void_hook(sb_delete, sb); } /** * security_sb_free() - Free a super_block LSM blob * @sb: filesystem superblock * * Deallocate and clear the sb->s_security field. @sb contains the super_block * structure to be modified. */ void security_sb_free(struct super_block *sb) { call_void_hook(sb_free_security, sb); kfree(sb->s_security); sb->s_security = NULL; } /** * security_free_mnt_opts() - Free memory associated with mount options * @mnt_opts: LSM processed mount options * * Free memory associated with @mnt_ops. */ void security_free_mnt_opts(void **mnt_opts) { if (!*mnt_opts) return; call_void_hook(sb_free_mnt_opts, *mnt_opts); *mnt_opts = NULL; } EXPORT_SYMBOL(security_free_mnt_opts); /** * security_sb_eat_lsm_opts() - Consume LSM mount options * @options: mount options * @mnt_opts: LSM processed mount options * * Eat (scan @options) and save them in @mnt_opts. * * Return: Returns 0 on success, negative values on failure. */ int security_sb_eat_lsm_opts(char *options, void **mnt_opts) { return call_int_hook(sb_eat_lsm_opts, options, mnt_opts); } EXPORT_SYMBOL(security_sb_eat_lsm_opts); /** * security_sb_mnt_opts_compat() - Check if new mount options are allowed * @sb: filesystem superblock * @mnt_opts: new mount options * * Determine if the new mount options in @mnt_opts are allowed given the * existing mounted filesystem at @sb. @sb superblock being compared. * * Return: Returns 0 if options are compatible. */ int security_sb_mnt_opts_compat(struct super_block *sb, void *mnt_opts) { return call_int_hook(sb_mnt_opts_compat, sb, mnt_opts); } EXPORT_SYMBOL(security_sb_mnt_opts_compat); /** * security_sb_remount() - Verify no incompatible mount changes during remount * @sb: filesystem superblock * @mnt_opts: (re)mount options * * Extracts security system specific mount options and verifies no changes are * being made to those options. * * Return: Returns 0 if permission is granted. */ int security_sb_remount(struct super_block *sb, void *mnt_opts) { return call_int_hook(sb_remount, sb, mnt_opts); } EXPORT_SYMBOL(security_sb_remount); /** * security_sb_kern_mount() - Check if a kernel mount is allowed * @sb: filesystem superblock * * Mount this @sb if allowed by permissions. * * Return: Returns 0 if permission is granted. */ int security_sb_kern_mount(const struct super_block *sb) { return call_int_hook(sb_kern_mount, sb); } /** * security_sb_show_options() - Output the mount options for a superblock * @m: output file * @sb: filesystem superblock * * Show (print on @m) mount options for this @sb. * * Return: Returns 0 on success, negative values on failure. */ int security_sb_show_options(struct seq_file *m, struct super_block *sb) { return call_int_hook(sb_show_options, m, sb); } /** * security_sb_statfs() - Check if accessing fs stats is allowed * @dentry: superblock handle * * Check permission before obtaining filesystem statistics for the @mnt * mountpoint. @dentry is a handle on the superblock for the filesystem. * * Return: Returns 0 if permission is granted. */ int security_sb_statfs(struct dentry *dentry) { return call_int_hook(sb_statfs, dentry); } /** * security_sb_mount() - Check permission for mounting a filesystem * @dev_name: filesystem backing device * @path: mount point * @type: filesystem type * @flags: mount flags * @data: filesystem specific data * * Check permission before an object specified by @dev_name is mounted on the * mount point named by @nd. For an ordinary mount, @dev_name identifies a * device if the file system type requires a device. For a remount * (@flags & MS_REMOUNT), @dev_name is irrelevant. For a loopback/bind mount * (@flags & MS_BIND), @dev_name identifies the pathname of the object being * mounted. * * Return: Returns 0 if permission is granted. */ int security_sb_mount(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data) { return call_int_hook(sb_mount, dev_name, path, type, flags, data); } /** * security_sb_umount() - Check permission for unmounting a filesystem * @mnt: mounted filesystem * @flags: unmount flags * * Check permission before the @mnt file system is unmounted. * * Return: Returns 0 if permission is granted. */ int security_sb_umount(struct vfsmount *mnt, int flags) { return call_int_hook(sb_umount, mnt, flags); } /** * security_sb_pivotroot() - Check permissions for pivoting the rootfs * @old_path: new location for current rootfs * @new_path: location of the new rootfs * * Check permission before pivoting the root filesystem. * * Return: Returns 0 if permission is granted. */ int security_sb_pivotroot(const struct path *old_path, const struct path *new_path) { return call_int_hook(sb_pivotroot, old_path, new_path); } /** * security_sb_set_mnt_opts() - Set the mount options for a filesystem * @sb: filesystem superblock * @mnt_opts: binary mount options * @kern_flags: kernel flags (in) * @set_kern_flags: kernel flags (out) * * Set the security relevant mount options used for a superblock. * * Return: Returns 0 on success, error on failure. */ int security_sb_set_mnt_opts(struct super_block *sb, void *mnt_opts, unsigned long kern_flags, unsigned long *set_kern_flags) { struct lsm_static_call *scall; int rc = mnt_opts ? -EOPNOTSUPP : LSM_RET_DEFAULT(sb_set_mnt_opts); lsm_for_each_hook(scall, sb_set_mnt_opts) { rc = scall->hl->hook.sb_set_mnt_opts(sb, mnt_opts, kern_flags, set_kern_flags); if (rc != LSM_RET_DEFAULT(sb_set_mnt_opts)) break; } return rc; } EXPORT_SYMBOL(security_sb_set_mnt_opts); /** * security_sb_clone_mnt_opts() - Duplicate superblock mount options * @oldsb: source superblock * @newsb: destination superblock * @kern_flags: kernel flags (in) * @set_kern_flags: kernel flags (out) * * Copy all security options from a given superblock to another. * * Return: Returns 0 on success, error on failure. */ int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) { return call_int_hook(sb_clone_mnt_opts, oldsb, newsb, kern_flags, set_kern_flags); } EXPORT_SYMBOL(security_sb_clone_mnt_opts); /** * security_move_mount() - Check permissions for moving a mount * @from_path: source mount point * @to_path: destination mount point * * Check permission before a mount is moved. * * Return: Returns 0 if permission is granted. */ int security_move_mount(const struct path *from_path, const struct path *to_path) { return call_int_hook(move_mount, from_path, to_path); } /** * security_path_notify() - Check if setting a watch is allowed * @path: file path * @mask: event mask * @obj_type: file path type * * Check permissions before setting a watch on events as defined by @mask, on * an object at @path, whose type is defined by @obj_type. * * Return: Returns 0 if permission is granted. */ int security_path_notify(const struct path *path, u64 mask, unsigned int obj_type) { return call_int_hook(path_notify, path, mask, obj_type); } /** * security_inode_alloc() - Allocate an inode LSM blob * @inode: the inode * @gfp: allocation flags * * Allocate and attach a security structure to @inode->i_security. The * i_security field is initialized to NULL when the inode structure is * allocated. * * Return: Return 0 if operation was successful. */ int security_inode_alloc(struct inode *inode, gfp_t gfp) { int rc = lsm_inode_alloc(inode, gfp); if (unlikely(rc)) return rc; rc = call_int_hook(inode_alloc_security, inode); if (unlikely(rc)) security_inode_free(inode); return rc; } static void inode_free_by_rcu(struct rcu_head *head) { /* The rcu head is at the start of the inode blob */ call_void_hook(inode_free_security_rcu, head); kmem_cache_free(lsm_inode_cache, head); } /** * security_inode_free() - Free an inode's LSM blob * @inode: the inode * * Release any LSM resources associated with @inode, although due to the * inode's RCU protections it is possible that the resources will not be * fully released until after the current RCU grace period has elapsed. * * It is important for LSMs to note that despite being present in a call to * security_inode_free(), @inode may still be referenced in a VFS path walk * and calls to security_inode_permission() may be made during, or after, * a call to security_inode_free(). For this reason the inode->i_security * field is released via a call_rcu() callback and any LSMs which need to * retain inode state for use in security_inode_permission() should only * release that state in the inode_free_security_rcu() LSM hook callback. */ void security_inode_free(struct inode *inode) { call_void_hook(inode_free_security, inode); if (!inode->i_security) return; call_rcu((struct rcu_head *)inode->i_security, inode_free_by_rcu); } /** * security_dentry_init_security() - Perform dentry initialization * @dentry: the dentry to initialize * @mode: mode used to determine resource type * @name: name of the last path component * @xattr_name: name of the security/LSM xattr * @lsmctx: pointer to the resulting LSM context * * Compute a context for a dentry as the inode is not yet available since NFSv4 * has no label backed by an EA anyway. It is important to note that * @xattr_name does not need to be free'd by the caller, it is a static string. * * Return: Returns 0 on success, negative values on failure. */ int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, struct lsm_context *lsmctx) { return call_int_hook(dentry_init_security, dentry, mode, name, xattr_name, lsmctx); } EXPORT_SYMBOL(security_dentry_init_security); /** * security_dentry_create_files_as() - Perform dentry initialization * @dentry: the dentry to initialize * @mode: mode used to determine resource type * @name: name of the last path component * @old: creds to use for LSM context calculations * @new: creds to modify * * Compute a context for a dentry as the inode is not yet available and set * that context in passed in creds so that new files are created using that * context. Context is calculated using the passed in creds and not the creds * of the caller. * * Return: Returns 0 on success, error on failure. */ int security_dentry_create_files_as(struct dentry *dentry, int mode, const struct qstr *name, const struct cred *old, struct cred *new) { return call_int_hook(dentry_create_files_as, dentry, mode, name, old, new); } EXPORT_SYMBOL(security_dentry_create_files_as); /** * security_inode_init_security() - Initialize an inode's LSM context * @inode: the inode * @dir: parent directory * @qstr: last component of the pathname * @initxattrs: callback function to write xattrs * @fs_data: filesystem specific data * * Obtain the security attribute name suffix and value to set on a newly * created inode and set up the incore security field for the new inode. This * hook is called by the fs code as part of the inode creation transaction and * provides for atomic labeling of the inode, unlike the post_create/mkdir/... * hooks called by the VFS. * * The hook function is expected to populate the xattrs array, by calling * lsm_get_xattr_slot() to retrieve the slots reserved by the security module * with the lbs_xattr_count field of the lsm_blob_sizes structure. For each * slot, the hook function should set ->name to the attribute name suffix * (e.g. selinux), to allocate ->value (will be freed by the caller) and set it * to the attribute value, to set ->value_len to the length of the value. If * the security module does not use security attributes or does not wish to put * a security attribute on this particular inode, then it should return * -EOPNOTSUPP to skip this processing. * * Return: Returns 0 if the LSM successfully initialized all of the inode * security attributes that are required, negative values otherwise. */ int security_inode_init_security(struct inode *inode, struct inode *dir, const struct qstr *qstr, const initxattrs initxattrs, void *fs_data) { struct lsm_static_call *scall; struct xattr *new_xattrs = NULL; int ret = -EOPNOTSUPP, xattr_count = 0; if (unlikely(IS_PRIVATE(inode))) return 0; if (!blob_sizes.lbs_xattr_count) return 0; if (initxattrs) { /* Allocate +1 as terminator. */ new_xattrs = kcalloc(blob_sizes.lbs_xattr_count + 1, sizeof(*new_xattrs), GFP_NOFS); if (!new_xattrs) return -ENOMEM; } lsm_for_each_hook(scall, inode_init_security) { ret = scall->hl->hook.inode_init_security(inode, dir, qstr, new_xattrs, &xattr_count); if (ret && ret != -EOPNOTSUPP) goto out; /* * As documented in lsm_hooks.h, -EOPNOTSUPP in this context * means that the LSM is not willing to provide an xattr, not * that it wants to signal an error. Thus, continue to invoke * the remaining LSMs. */ } /* If initxattrs() is NULL, xattr_count is zero, skip the call. */ if (!xattr_count) goto out; ret = initxattrs(inode, new_xattrs, fs_data); out: for (; xattr_count > 0; xattr_count--) kfree(new_xattrs[xattr_count - 1].value); kfree(new_xattrs); return (ret == -EOPNOTSUPP) ? 0 : ret; } EXPORT_SYMBOL(security_inode_init_security); /** * security_inode_init_security_anon() - Initialize an anonymous inode * @inode: the inode * @name: the anonymous inode class * @context_inode: an optional related inode * * Set up the incore security field for the new anonymous inode and return * whether the inode creation is permitted by the security module or not. * * Return: Returns 0 on success, -EACCES if the security module denies the * creation of this inode, or another -errno upon other errors. */ int security_inode_init_security_anon(struct inode *inode, const struct qstr *name, const struct inode *context_inode) { return call_int_hook(inode_init_security_anon, inode, name, context_inode); } #ifdef CONFIG_SECURITY_PATH /** * security_path_mknod() - Check if creating a special file is allowed * @dir: parent directory * @dentry: new file * @mode: new file mode * @dev: device number * * Check permissions when creating a file. Note that this hook is called even * if mknod operation is being done for a regular file. * * Return: Returns 0 if permission is granted. */ int security_path_mknod(const struct path *dir, struct dentry *dentry, umode_t mode, unsigned int dev) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mknod, dir, dentry, mode, dev); } EXPORT_SYMBOL(security_path_mknod); /** * security_path_post_mknod() - Update inode security after reg file creation * @idmap: idmap of the mount * @dentry: new file * * Update inode security field after a regular file has been created. */ void security_path_post_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return; call_void_hook(path_post_mknod, idmap, dentry); } /** * security_path_mkdir() - Check if creating a new directory is allowed * @dir: parent directory * @dentry: new directory * @mode: new directory mode * * Check permissions to create a new directory in the existing directory. * * Return: Returns 0 if permission is granted. */ int security_path_mkdir(const struct path *dir, struct dentry *dentry, umode_t mode) { if (unlikely(IS_PRIVATE(d_backing_inode(dir->dentry)))) return 0; return call_int_hook(path_mkdir, dir, dentry, mode); } |