| 3 2 1 41 60 5 5 10 2 1 2 1 3 5 53 53 10 61 41 3 62 61 1 3 14 1 1 2 1 2 2 32 279 30 4 2 2 2 1 2 2 2 10 1 1 2 3 1 1 1 9 4 3 29 1 2 12 11 1 5 5 2 2 1 1 1 7 1 11 1 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 | // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2019 Arm Ltd. #include <linux/arm-smccc.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <kvm/arm_hypercalls.h> #include <kvm/arm_psci.h> #define KVM_ARM_SMCCC_STD_FEATURES \ GENMASK(KVM_REG_ARM_STD_BMAP_BIT_COUNT - 1, 0) #define KVM_ARM_SMCCC_STD_HYP_FEATURES \ GENMASK(KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT - 1, 0) #define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES \ GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT - 1, 0) #define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES_2 \ GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_2_BIT_COUNT - 1, 0) static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) { struct system_time_snapshot systime_snapshot; u64 cycles = ~0UL; u32 feature; /* * system time and counter value must captured at the same * time to keep consistency and precision. */ ktime_get_snapshot(&systime_snapshot); /* * This is only valid if the current clocksource is the * architected counter, as this is the only one the guest * can see. */ if (systime_snapshot.cs_id != CSID_ARM_ARCH_COUNTER) return; /* * The guest selects one of the two reference counters * (virtual or physical) with the first argument of the SMCCC * call. In case the identifier is not supported, error out. */ feature = smccc_get_arg1(vcpu); switch (feature) { case KVM_PTP_VIRT_COUNTER: cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.voffset; break; case KVM_PTP_PHYS_COUNTER: cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.poffset; break; default: return; } /* * This relies on the top bit of val[0] never being set for * valid values of system time, because that is *really* far * in the future (about 292 years from 1970, and at that stage * nobody will give a damn about it). */ val[0] = upper_32_bits(systime_snapshot.real); val[1] = lower_32_bits(systime_snapshot.real); val[2] = upper_32_bits(cycles); val[3] = lower_32_bits(cycles); } static bool kvm_smccc_default_allowed(u32 func_id) { switch (func_id) { /* * List of function-ids that are not gated with the bitmapped * feature firmware registers, and are to be allowed for * servicing the call by default. */ case ARM_SMCCC_VERSION_FUNC_ID: case ARM_SMCCC_ARCH_FEATURES_FUNC_ID: return true; default: /* PSCI 0.2 and up is in the 0:0x1f range */ if (ARM_SMCCC_OWNER_NUM(func_id) == ARM_SMCCC_OWNER_STANDARD && ARM_SMCCC_FUNC_NUM(func_id) <= 0x1f) return true; /* * KVM's PSCI 0.1 doesn't comply with SMCCC, and has * its own function-id base and range */ if (func_id >= KVM_PSCI_FN(0) && func_id <= KVM_PSCI_FN(3)) return true; return false; } } static bool kvm_smccc_test_fw_bmap(struct kvm_vcpu *vcpu, u32 func_id) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; switch (func_id) { case ARM_SMCCC_TRNG_VERSION: case ARM_SMCCC_TRNG_FEATURES: case ARM_SMCCC_TRNG_GET_UUID: case ARM_SMCCC_TRNG_RND32: case ARM_SMCCC_TRNG_RND64: return test_bit(KVM_REG_ARM_STD_BIT_TRNG_V1_0, &smccc_feat->std_bmap); case ARM_SMCCC_HV_PV_TIME_FEATURES: case ARM_SMCCC_HV_PV_TIME_ST: return test_bit(KVM_REG_ARM_STD_HYP_BIT_PV_TIME, &smccc_feat->std_hyp_bmap); case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID: return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT, &smccc_feat->vendor_hyp_bmap); case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID: return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_PTP, &smccc_feat->vendor_hyp_bmap); default: return false; } } #define SMC32_ARCH_RANGE_BEGIN ARM_SMCCC_VERSION_FUNC_ID #define SMC32_ARCH_RANGE_END ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_32, \ 0, ARM_SMCCC_FUNC_MASK) #define SMC64_ARCH_RANGE_BEGIN ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_64, \ 0, 0) #define SMC64_ARCH_RANGE_END ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_64, \ 0, ARM_SMCCC_FUNC_MASK) static int kvm_smccc_filter_insert_reserved(struct kvm *kvm) { int r; /* * Prevent userspace from handling any SMCCC calls in the architecture * range, avoiding the risk of misrepresenting Spectre mitigation status * to the guest. */ r = mtree_insert_range(&kvm->arch.smccc_filter, SMC32_ARCH_RANGE_BEGIN, SMC32_ARCH_RANGE_END, xa_mk_value(KVM_SMCCC_FILTER_HANDLE), GFP_KERNEL_ACCOUNT); if (r) goto out_destroy; r = mtree_insert_range(&kvm->arch.smccc_filter, SMC64_ARCH_RANGE_BEGIN, SMC64_ARCH_RANGE_END, xa_mk_value(KVM_SMCCC_FILTER_HANDLE), GFP_KERNEL_ACCOUNT); if (r) goto out_destroy; return 0; out_destroy: mtree_destroy(&kvm->arch.smccc_filter); return r; } static bool kvm_smccc_filter_configured(struct kvm *kvm) { return !mtree_empty(&kvm->arch.smccc_filter); } static int kvm_smccc_set_filter(struct kvm *kvm, struct kvm_smccc_filter __user *uaddr) { const void *zero_page = page_to_virt(ZERO_PAGE(0)); struct kvm_smccc_filter filter; u32 start, end; int r; if (copy_from_user(&filter, uaddr, sizeof(filter))) return -EFAULT; if (memcmp(filter.pad, zero_page, sizeof(filter.pad))) return -EINVAL; start = filter.base; end = start + filter.nr_functions - 1; if (end < start || filter.action >= NR_SMCCC_FILTER_ACTIONS) return -EINVAL; mutex_lock(&kvm->arch.config_lock); if (kvm_vm_has_ran_once(kvm)) { r = -EBUSY; goto out_unlock; } if (!kvm_smccc_filter_configured(kvm)) { r = kvm_smccc_filter_insert_reserved(kvm); if (WARN_ON_ONCE(r)) goto out_unlock; } r = mtree_insert_range(&kvm->arch.smccc_filter, start, end, xa_mk_value(filter.action), GFP_KERNEL_ACCOUNT); out_unlock: mutex_unlock(&kvm->arch.config_lock); return r; } static u8 kvm_smccc_filter_get_action(struct kvm *kvm, u32 func_id) { unsigned long idx = func_id; void *val; if (!kvm_smccc_filter_configured(kvm)) return KVM_SMCCC_FILTER_HANDLE; /* * But where's the error handling, you say? * * mt_find() returns NULL if no entry was found, which just so happens * to match KVM_SMCCC_FILTER_HANDLE. */ val = mt_find(&kvm->arch.smccc_filter, &idx, idx); return xa_to_value(val); } static u8 kvm_smccc_get_action(struct kvm_vcpu *vcpu, u32 func_id) { /* * Intervening actions in the SMCCC filter take precedence over the * pseudo-firmware register bitmaps. */ u8 action = kvm_smccc_filter_get_action(vcpu->kvm, func_id); if (action != KVM_SMCCC_FILTER_HANDLE) return action; if (kvm_smccc_test_fw_bmap(vcpu, func_id) || kvm_smccc_default_allowed(func_id)) return KVM_SMCCC_FILTER_HANDLE; return KVM_SMCCC_FILTER_DENY; } static void kvm_prepare_hypercall_exit(struct kvm_vcpu *vcpu, u32 func_id) { u8 ec = ESR_ELx_EC(kvm_vcpu_get_esr(vcpu)); struct kvm_run *run = vcpu->run; u64 flags = 0; if (ec == ESR_ELx_EC_SMC32 || ec == ESR_ELx_EC_SMC64) flags |= KVM_HYPERCALL_EXIT_SMC; if (!kvm_vcpu_trap_il_is32bit(vcpu)) flags |= KVM_HYPERCALL_EXIT_16BIT; run->exit_reason = KVM_EXIT_HYPERCALL; run->hypercall = (typeof(run->hypercall)) { .nr = func_id, .flags = flags, }; } int kvm_smccc_call_handler(struct kvm_vcpu *vcpu) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; u32 func_id = smccc_get_function(vcpu); u64 val[4] = {SMCCC_RET_NOT_SUPPORTED}; u32 feature; u8 action; gpa_t gpa; uuid_t uuid; action = kvm_smccc_get_action(vcpu, func_id); switch (action) { case KVM_SMCCC_FILTER_HANDLE: break; case KVM_SMCCC_FILTER_DENY: goto out; case KVM_SMCCC_FILTER_FWD_TO_USER: kvm_prepare_hypercall_exit(vcpu, func_id); return 0; default: WARN_RATELIMIT(1, "Unhandled SMCCC filter action: %d\n", action); goto out; } switch (func_id) { case ARM_SMCCC_VERSION_FUNC_ID: val[0] = ARM_SMCCC_VERSION_1_1; break; case ARM_SMCCC_ARCH_FEATURES_FUNC_ID: feature = smccc_get_arg1(vcpu); switch (feature) { case ARM_SMCCC_ARCH_WORKAROUND_1: switch (arm64_get_spectre_v2_state()) { case SPECTRE_VULNERABLE: break; case SPECTRE_MITIGATED: val[0] = SMCCC_RET_SUCCESS; break; case SPECTRE_UNAFFECTED: val[0] = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED; break; } break; case ARM_SMCCC_ARCH_WORKAROUND_2: switch (arm64_get_spectre_v4_state()) { case SPECTRE_VULNERABLE: break; case SPECTRE_MITIGATED: /* * SSBS everywhere: Indicate no firmware * support, as the SSBS support will be * indicated to the guest and the default is * safe. * * Otherwise, expose a permanent mitigation * to the guest, and hide SSBS so that the * guest stays protected. */ if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP)) break; fallthrough; case SPECTRE_UNAFFECTED: val[0] = SMCCC_RET_NOT_REQUIRED; break; } break; case ARM_SMCCC_ARCH_WORKAROUND_3: switch (arm64_get_spectre_bhb_state()) { case SPECTRE_VULNERABLE: break; case SPECTRE_MITIGATED: val[0] = SMCCC_RET_SUCCESS; break; case SPECTRE_UNAFFECTED: val[0] = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED; break; } break; case ARM_SMCCC_HV_PV_TIME_FEATURES: if (test_bit(KVM_REG_ARM_STD_HYP_BIT_PV_TIME, &smccc_feat->std_hyp_bmap)) val[0] = SMCCC_RET_SUCCESS; break; } break; case ARM_SMCCC_HV_PV_TIME_FEATURES: val[0] = kvm_hypercall_pv_features(vcpu); break; case ARM_SMCCC_HV_PV_TIME_ST: gpa = kvm_init_stolen_time(vcpu); if (gpa != INVALID_GPA) val[0] = gpa; break; case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID: uuid = ARM_SMCCC_VENDOR_HYP_UID_KVM; val[0] = smccc_uuid_to_reg(&uuid, 0); val[1] = smccc_uuid_to_reg(&uuid, 1); val[2] = smccc_uuid_to_reg(&uuid, 2); val[3] = smccc_uuid_to_reg(&uuid, 3); break; case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: val[0] = smccc_feat->vendor_hyp_bmap; /* Function numbers 2-63 are reserved for pKVM for now */ val[2] = smccc_feat->vendor_hyp_bmap_2; break; case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID: kvm_ptp_get_time(vcpu, val); break; case ARM_SMCCC_TRNG_VERSION: case ARM_SMCCC_TRNG_FEATURES: case ARM_SMCCC_TRNG_GET_UUID: case ARM_SMCCC_TRNG_RND32: case ARM_SMCCC_TRNG_RND64: return kvm_trng_call(vcpu); default: return kvm_psci_call(vcpu); } out: smccc_set_retval(vcpu, val[0], val[1], val[2], val[3]); return 1; } static const u64 kvm_arm_fw_reg_ids[] = { KVM_REG_ARM_PSCI_VERSION, KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3, KVM_REG_ARM_STD_BMAP, KVM_REG_ARM_STD_HYP_BMAP, KVM_REG_ARM_VENDOR_HYP_BMAP, KVM_REG_ARM_VENDOR_HYP_BMAP_2, }; void kvm_arm_init_hypercalls(struct kvm *kvm) { struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat; smccc_feat->std_bmap = KVM_ARM_SMCCC_STD_FEATURES; smccc_feat->std_hyp_bmap = KVM_ARM_SMCCC_STD_HYP_FEATURES; smccc_feat->vendor_hyp_bmap = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; mt_init(&kvm->arch.smccc_filter); } void kvm_arm_teardown_hypercalls(struct kvm *kvm) { mtree_destroy(&kvm->arch.smccc_filter); } int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) { return ARRAY_SIZE(kvm_arm_fw_reg_ids); } int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) { int i; for (i = 0; i < ARRAY_SIZE(kvm_arm_fw_reg_ids); i++) { if (put_user(kvm_arm_fw_reg_ids[i], uindices++)) return -EFAULT; } return 0; } #define KVM_REG_FEATURE_LEVEL_MASK GENMASK(3, 0) /* * Convert the workaround level into an easy-to-compare number, where higher * values mean better protection. */ static int get_kernel_wa_level(struct kvm_vcpu *vcpu, u64 regid) { switch (regid) { case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: switch (arm64_get_spectre_v2_state()) { case SPECTRE_VULNERABLE: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; case SPECTRE_MITIGATED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL; case SPECTRE_UNAFFECTED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED; } return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: switch (arm64_get_spectre_v4_state()) { case SPECTRE_MITIGATED: /* * As for the hypercall discovery, we pretend we * don't have any FW mitigation if SSBS is there at * all times. */ if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP)) return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; fallthrough; case SPECTRE_UNAFFECTED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; case SPECTRE_VULNERABLE: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; } break; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: switch (arm64_get_spectre_bhb_state()) { case SPECTRE_VULNERABLE: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; case SPECTRE_MITIGATED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL; case SPECTRE_UNAFFECTED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED; } return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; } return -EINVAL; } int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; void __user *uaddr = (void __user *)(long)reg->addr; u64 val; switch (reg->id) { case KVM_REG_ARM_PSCI_VERSION: val = kvm_psci_version(vcpu); break; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: val = get_kernel_wa_level(vcpu, reg->id) & KVM_REG_FEATURE_LEVEL_MASK; break; case KVM_REG_ARM_STD_BMAP: val = READ_ONCE(smccc_feat->std_bmap); break; case KVM_REG_ARM_STD_HYP_BMAP: val = READ_ONCE(smccc_feat->std_hyp_bmap); break; case KVM_REG_ARM_VENDOR_HYP_BMAP: val = READ_ONCE(smccc_feat->vendor_hyp_bmap); break; case KVM_REG_ARM_VENDOR_HYP_BMAP_2: val = READ_ONCE(smccc_feat->vendor_hyp_bmap_2); break; default: return -ENOENT; } if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id))) return -EFAULT; return 0; } static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val) { int ret = 0; struct kvm *kvm = vcpu->kvm; struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat; unsigned long *fw_reg_bmap, fw_reg_features; switch (reg_id) { case KVM_REG_ARM_STD_BMAP: fw_reg_bmap = &smccc_feat->std_bmap; fw_reg_features = KVM_ARM_SMCCC_STD_FEATURES; break; case KVM_REG_ARM_STD_HYP_BMAP: fw_reg_bmap = &smccc_feat->std_hyp_bmap; fw_reg_features = KVM_ARM_SMCCC_STD_HYP_FEATURES; break; case KVM_REG_ARM_VENDOR_HYP_BMAP: fw_reg_bmap = &smccc_feat->vendor_hyp_bmap; fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; break; case KVM_REG_ARM_VENDOR_HYP_BMAP_2: fw_reg_bmap = &smccc_feat->vendor_hyp_bmap_2; fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES_2; break; default: return -ENOENT; } /* Check for unsupported bit */ if (val & ~fw_reg_features) return -EINVAL; mutex_lock(&kvm->arch.config_lock); if (kvm_vm_has_ran_once(kvm) && val != *fw_reg_bmap) { ret = -EBUSY; goto out; } WRITE_ONCE(*fw_reg_bmap, val); out: mutex_unlock(&kvm->arch.config_lock); return ret; } int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(long)reg->addr; u64 val; int wa_level; if (KVM_REG_SIZE(reg->id) != sizeof(val)) return -ENOENT; if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id))) return -EFAULT; switch (reg->id) { case KVM_REG_ARM_PSCI_VERSION: { bool wants_02; wants_02 = vcpu_has_feature(vcpu, KVM_ARM_VCPU_PSCI_0_2); switch (val) { case KVM_ARM_PSCI_0_1: if (wants_02) return -EINVAL; vcpu->kvm->arch.psci_version = val; return 0; case KVM_ARM_PSCI_0_2: case KVM_ARM_PSCI_1_0: case KVM_ARM_PSCI_1_1: case KVM_ARM_PSCI_1_2: case KVM_ARM_PSCI_1_3: if (!wants_02) return -EINVAL; vcpu->kvm->arch.psci_version = val; return 0; } break; } case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: if (val & ~KVM_REG_FEATURE_LEVEL_MASK) return -EINVAL; if (get_kernel_wa_level(vcpu, reg->id) < val) return -EINVAL; return 0; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: if (val & ~(KVM_REG_FEATURE_LEVEL_MASK | KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED)) return -EINVAL; /* The enabled bit must not be set unless the level is AVAIL. */ if ((val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED) && (val & KVM_REG_FEATURE_LEVEL_MASK) != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL) return -EINVAL; /* * Map all the possible incoming states to the only two we * really want to deal with. */ switch (val & KVM_REG_FEATURE_LEVEL_MASK) { case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; break; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; break; default: return -EINVAL; } /* * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the * other way around. */ if (get_kernel_wa_level(vcpu, reg->id) < wa_level) return -EINVAL; return 0; case KVM_REG_ARM_STD_BMAP: case KVM_REG_ARM_STD_HYP_BMAP: case KVM_REG_ARM_VENDOR_HYP_BMAP: case KVM_REG_ARM_VENDOR_HYP_BMAP_2: return kvm_arm_set_fw_reg_bmap(vcpu, reg->id, val); default: return -ENOENT; } return -EINVAL; } int kvm_vm_smccc_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) { switch (attr->attr) { case KVM_ARM_VM_SMCCC_FILTER: return 0; default: return -ENXIO; } } int kvm_vm_smccc_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) { void __user *uaddr = (void __user *)attr->addr; switch (attr->attr) { case KVM_ARM_VM_SMCCC_FILTER: return kvm_smccc_set_filter(kvm, uaddr); default: return -ENXIO; } } |
| 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2002,2003 by Andreas Gruenbacher <a.gruenbacher@computer.org> * * Fixes from William Schumacher incorporated on 15 March 2001. * (Reported by Charles Bertsch, <CBertsch@microtest.com>). */ /* * This file contains generic functions for manipulating * POSIX 1003.1e draft standard 17 ACLs. */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/atomic.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> #include <linux/xattr.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/namei.h> #include <linux/mnt_idmapping.h> #include <linux/iversion.h> #include <linux/security.h> #include <linux/fsnotify.h> #include <linux/filelock.h> #include "internal.h" static struct posix_acl **acl_by_type(struct inode *inode, int type) { switch (type) { case ACL_TYPE_ACCESS: return &inode->i_acl; case ACL_TYPE_DEFAULT: return &inode->i_default_acl; default: BUG(); } } struct posix_acl *get_cached_acl(struct inode *inode, int type) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *acl; for (;;) { rcu_read_lock(); acl = rcu_dereference(*p); if (!acl || is_uncached_acl(acl) || refcount_inc_not_zero(&acl->a_refcount)) break; rcu_read_unlock(); cpu_relax(); } rcu_read_unlock(); return acl; } EXPORT_SYMBOL(get_cached_acl); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type) { struct posix_acl *acl = rcu_dereference(*acl_by_type(inode, type)); if (acl == ACL_DONT_CACHE) { struct posix_acl *ret; ret = inode->i_op->get_inode_acl(inode, type, LOOKUP_RCU); if (!IS_ERR(ret)) acl = ret; } return acl; } EXPORT_SYMBOL(get_cached_acl_rcu); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl) { struct posix_acl **p = acl_by_type(inode, type); struct posix_acl *old; old = xchg(p, posix_acl_dup(acl)); if (!is_uncached_acl(old)) posix_acl_release(old); } EXPORT_SYMBOL(set_cached_acl); static void __forget_cached_acl(struct posix_acl **p) { struct posix_acl *old; old = xchg(p, ACL_NOT_CACHED); if (!is_uncached_acl(old)) posix_acl_release(old); } void forget_cached_acl(struct inode *inode, int type) { __forget_cached_acl(acl_by_type(inode, type)); } EXPORT_SYMBOL(forget_cached_acl); void forget_all_cached_acls(struct inode *inode) { __forget_cached_acl(&inode->i_acl); __forget_cached_acl(&inode->i_default_acl); } EXPORT_SYMBOL(forget_all_cached_acls); static struct posix_acl *__get_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, int type) { struct posix_acl *sentinel; struct posix_acl **p; struct posix_acl *acl; /* * The sentinel is used to detect when another operation like * set_cached_acl() or forget_cached_acl() races with get_inode_acl(). * It is guaranteed that is_uncached_acl(sentinel) is true. */ acl = get_cached_acl(inode, type); if (!is_uncached_acl(acl)) return acl; if (!IS_POSIXACL(inode)) return NULL; sentinel = uncached_acl_sentinel(current); p = acl_by_type(inode, type); /* * If the ACL isn't being read yet, set our sentinel. Otherwise, the * current value of the ACL will not be ACL_NOT_CACHED and so our own * sentinel will not be set; another task will update the cache. We * could wait for that other task to complete its job, but it's easier * to just call ->get_inode_acl to fetch the ACL ourself. (This is * going to be an unlikely race.) */ cmpxchg(p, ACL_NOT_CACHED, sentinel); /* * Normally, the ACL returned by ->get{_inode}_acl will be cached. * A filesystem can prevent that by calling * forget_cached_acl(inode, type) in ->get{_inode}_acl. * * If the filesystem doesn't have a get{_inode}_ acl() function at all, * we'll just create the negative cache entry. */ if (dentry && inode->i_op->get_acl) { acl = inode->i_op->get_acl(idmap, dentry, type); } else if (inode->i_op->get_inode_acl) { acl = inode->i_op->get_inode_acl(inode, type, false); } else { set_cached_acl(inode, type, NULL); return NULL; } if (IS_ERR(acl)) { /* * Remove our sentinel so that we don't block future attempts * to cache the ACL. */ cmpxchg(p, sentinel, ACL_NOT_CACHED); return acl; } /* * Cache the result, but only if our sentinel is still in place. */ posix_acl_dup(acl); if (unlikely(!try_cmpxchg(p, &sentinel, acl))) posix_acl_release(acl); return acl; } struct posix_acl *get_inode_acl(struct inode *inode, int type) { return __get_acl(&nop_mnt_idmap, NULL, inode, type); } EXPORT_SYMBOL(get_inode_acl); /* * Init a fresh posix_acl */ void posix_acl_init(struct posix_acl *acl, int count) { refcount_set(&acl->a_refcount, 1); acl->a_count = count; } EXPORT_SYMBOL(posix_acl_init); /* * Allocate a new ACL with the specified number of entries. */ struct posix_acl * posix_acl_alloc(unsigned int count, gfp_t flags) { struct posix_acl *acl; acl = kmalloc(struct_size(acl, a_entries, count), flags); if (acl) posix_acl_init(acl, count); return acl; } EXPORT_SYMBOL(posix_acl_alloc); /* * Clone an ACL. */ struct posix_acl * posix_acl_clone(const struct posix_acl *acl, gfp_t flags) { struct posix_acl *clone = NULL; if (acl) { clone = kmemdup(acl, struct_size(acl, a_entries, acl->a_count), flags); if (clone) refcount_set(&clone->a_refcount, 1); } return clone; } EXPORT_SYMBOL_GPL(posix_acl_clone); /* * Check if an acl is valid. Returns 0 if it is, or -E... otherwise. */ int posix_acl_valid(struct user_namespace *user_ns, const struct posix_acl *acl) { const struct posix_acl_entry *pa, *pe; int state = ACL_USER_OBJ; int needs_mask = 0; FOREACH_ACL_ENTRY(pa, acl, pe) { if (pa->e_perm & ~(ACL_READ|ACL_WRITE|ACL_EXECUTE)) return -EINVAL; switch (pa->e_tag) { case ACL_USER_OBJ: if (state == ACL_USER_OBJ) { state = ACL_USER; break; } return -EINVAL; case ACL_USER: if (state != ACL_USER) return -EINVAL; if (!kuid_has_mapping(user_ns, pa->e_uid)) return -EINVAL; needs_mask = 1; break; case ACL_GROUP_OBJ: if (state == ACL_USER) { state = ACL_GROUP; break; } return -EINVAL; case ACL_GROUP: if (state != ACL_GROUP) return -EINVAL; if (!kgid_has_mapping(user_ns, pa->e_gid)) return -EINVAL; needs_mask = 1; break; case ACL_MASK: if (state != ACL_GROUP) return -EINVAL; state = ACL_OTHER; break; case ACL_OTHER: if (state == ACL_OTHER || (state == ACL_GROUP && !needs_mask)) { state = 0; break; } return -EINVAL; default: return -EINVAL; } } if (state == 0) return 0; return -EINVAL; } EXPORT_SYMBOL(posix_acl_valid); /* * Returns 0 if the acl can be exactly represented in the traditional * file mode permission bits, or else 1. Returns -E... on error. */ int posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p) { const struct posix_acl_entry *pa, *pe; umode_t mode = 0; int not_equiv = 0; /* * A null ACL can always be presented as mode bits. */ if (!acl) return 0; FOREACH_ACL_ENTRY(pa, acl, pe) { switch (pa->e_tag) { case ACL_USER_OBJ: mode |= (pa->e_perm & S_IRWXO) << 6; break; case ACL_GROUP_OBJ: mode |= (pa->e_perm & S_IRWXO) << 3; break; case ACL_OTHER: mode |= pa->e_perm & S_IRWXO; break; case ACL_MASK: mode = (mode & ~S_IRWXG) | ((pa->e_perm & S_IRWXO) << 3); not_equiv = 1; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; default: return -EINVAL; } } if (mode_p) *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } EXPORT_SYMBOL(posix_acl_equiv_mode); /* * Create an ACL representing the file mode permission bits of an inode. */ struct posix_acl * posix_acl_from_mode(umode_t mode, gfp_t flags) { struct posix_acl *acl = posix_acl_alloc(3, flags); if (!acl) return ERR_PTR(-ENOMEM); acl->a_entries[0].e_tag = ACL_USER_OBJ; acl->a_entries[0].e_perm = (mode & S_IRWXU) >> 6; acl->a_entries[1].e_tag = ACL_GROUP_OBJ; acl->a_entries[1].e_perm = (mode & S_IRWXG) >> 3; acl->a_entries[2].e_tag = ACL_OTHER; acl->a_entries[2].e_perm = (mode & S_IRWXO); return acl; } EXPORT_SYMBOL(posix_acl_from_mode); /* * Return 0 if current is granted want access to the inode * by the acl. Returns -E... otherwise. */ int posix_acl_permission(struct mnt_idmap *idmap, struct inode *inode, const struct posix_acl *acl, int want) { const struct posix_acl_entry *pa, *pe, *mask_obj; struct user_namespace *fs_userns = i_user_ns(inode); int found = 0; vfsuid_t vfsuid; vfsgid_t vfsgid; want &= MAY_READ | MAY_WRITE | MAY_EXEC; FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: /* (May have been checked already) */ vfsuid = i_uid_into_vfsuid(idmap, inode); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto check_perm; break; case ACL_USER: vfsuid = make_vfsuid(idmap, fs_userns, pa->e_uid); if (vfsuid_eq_kuid(vfsuid, current_fsuid())) goto mask; break; case ACL_GROUP_OBJ: vfsgid = i_gid_into_vfsgid(idmap, inode); if (vfsgid_in_group_p(vfsgid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_GROUP: vfsgid = make_vfsgid(idmap, fs_userns, pa->e_gid); if (vfsgid_in_group_p(vfsgid)) { found = 1; if ((pa->e_perm & want) == want) goto mask; } break; case ACL_MASK: break; case ACL_OTHER: if (found) return -EACCES; else goto check_perm; default: return -EIO; } } return -EIO; mask: for (mask_obj = pa+1; mask_obj != pe; mask_obj++) { if (mask_obj->e_tag == ACL_MASK) { if ((pa->e_perm & mask_obj->e_perm & want) == want) return 0; return -EACCES; } } check_perm: if ((pa->e_perm & want) == want) return 0; return -EACCES; } /* * Modify acl when creating a new inode. The caller must ensure the acl is * only referenced once. * * mode_p initially must contain the mode parameter to the open() / creat() * system calls. All permissions that are not granted by the acl are removed. * The permissions in the acl are changed to reflect the mode_p parameter. */ static int posix_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) { struct posix_acl_entry *pa, *pe; struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; umode_t mode = *mode_p; int not_equiv = 0; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: pa->e_perm &= (mode >> 6) | ~S_IRWXO; mode &= (pa->e_perm << 6) | ~S_IRWXU; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_OTHER: pa->e_perm &= mode | ~S_IRWXO; mode &= pa->e_perm | ~S_IRWXO; break; case ACL_MASK: mask_obj = pa; not_equiv = 1; break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (mask_obj->e_perm << 3) | ~S_IRWXG; } else { if (!group_obj) return -EIO; group_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (group_obj->e_perm << 3) | ~S_IRWXG; } *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } /* * Modify the ACL for the chmod syscall. */ static int __posix_acl_chmod_masq(struct posix_acl *acl, umode_t mode) { struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; struct posix_acl_entry *pa, *pe; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch(pa->e_tag) { case ACL_USER_OBJ: pa->e_perm = (mode & S_IRWXU) >> 6; break; case ACL_USER: case ACL_GROUP: break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_MASK: mask_obj = pa; break; case ACL_OTHER: pa->e_perm = (mode & S_IRWXO); break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm = (mode & S_IRWXG) >> 3; } else { if (!group_obj) return -EIO; group_obj->e_perm = (mode & S_IRWXG) >> 3; } return 0; } int __posix_acl_create(struct posix_acl **acl, gfp_t gfp, umode_t *mode_p) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; if (clone) { err = posix_acl_create_masq(clone, mode_p); if (err < 0) { posix_acl_release(clone); clone = NULL; } } posix_acl_release(*acl); *acl = clone; return err; } EXPORT_SYMBOL(__posix_acl_create); int __posix_acl_chmod(struct posix_acl **acl, gfp_t gfp, umode_t mode) { struct posix_acl *clone = posix_acl_clone(*acl, gfp); int err = -ENOMEM; if (clone) { err = __posix_acl_chmod_masq(clone, mode); if (err) { posix_acl_release(clone); clone = NULL; } } posix_acl_release(*acl); *acl = clone; return err; } EXPORT_SYMBOL(__posix_acl_chmod); /** * posix_acl_chmod - chmod a posix acl * * @idmap: idmap of the mount @inode was found from * @dentry: dentry to check permissions on * @mode: the new mode of @inode * * If the dentry has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. */ int posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode) { struct inode *inode = d_inode(dentry); struct posix_acl *acl; int ret = 0; if (!IS_POSIXACL(inode)) return 0; if (!inode->i_op->set_acl) return -EOPNOTSUPP; acl = get_inode_acl(inode, ACL_TYPE_ACCESS); if (IS_ERR_OR_NULL(acl)) { if (acl == ERR_PTR(-EOPNOTSUPP)) return 0; return PTR_ERR(acl); } ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode); if (ret) return ret; ret = inode->i_op->set_acl(idmap, dentry, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); return ret; } EXPORT_SYMBOL(posix_acl_chmod); int posix_acl_create(struct inode *dir, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { struct posix_acl *p; struct posix_acl *clone; int ret; *acl = NULL; *default_acl = NULL; if (S_ISLNK(*mode) || !IS_POSIXACL(dir)) return 0; p = get_inode_acl(dir, ACL_TYPE_DEFAULT); if (!p || p == ERR_PTR(-EOPNOTSUPP)) { *mode &= ~current_umask(); return 0; } if (IS_ERR(p)) return PTR_ERR(p); ret = -ENOMEM; clone = posix_acl_clone(p, GFP_NOFS); if (!clone) goto err_release; ret = posix_acl_create_masq(clone, mode); if (ret < 0) goto err_release_clone; if (ret == 0) posix_acl_release(clone); else *acl = clone; if (!S_ISDIR(*mode)) posix_acl_release(p); else *default_acl = p; return 0; err_release_clone: posix_acl_release(clone); err_release: posix_acl_release(p); return ret; } EXPORT_SYMBOL_GPL(posix_acl_create); /** * posix_acl_update_mode - update mode in set_acl * @idmap: idmap of the mount @inode was found from * @inode: target inode * @mode_p: mode (pointer) for update * @acl: acl pointer * * Update the file mode when setting an ACL: compute the new file permission * bits based on the ACL. In addition, if the ACL is equivalent to the new * file mode, set *@acl to NULL to indicate that no ACL should be set. * * As with chmod, clear the setgid bit if the caller is not in the owning group * or capable of CAP_FSETID (see inode_change_ok). * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then * take care to map the inode according to @idmap before checking * permissions. On non-idmapped mounts or if permission checking is to be * performed on the raw inode simply pass @nop_mnt_idmap. * * Called from set_acl inode operations. */ int posix_acl_update_mode(struct mnt_idmap *idmap, struct inode *inode, umode_t *mode_p, struct posix_acl **acl) { umode_t mode = inode->i_mode; int error; error = posix_acl_equiv_mode(*acl, &mode); if (error < 0) return error; if (error == 0) *acl = NULL; if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) mode &= ~S_ISGID; *mode_p = mode; return 0; } EXPORT_SYMBOL(posix_acl_update_mode); /* * Fix up the uids and gids in posix acl extended attributes in place. */ static int posix_acl_fix_xattr_common(const void *value, size_t size) { const struct posix_acl_xattr_header *header = value; int count; if (!header) return -EINVAL; if (size < sizeof(struct posix_acl_xattr_header)) return -EINVAL; if (header->a_version != cpu_to_le32(POSIX_ACL_XATTR_VERSION)) return -EOPNOTSUPP; count = posix_acl_xattr_count(size); if (count < 0) return -EINVAL; if (count == 0) return 0; return count; } /** * posix_acl_from_xattr - convert POSIX ACLs from backing store to VFS format * @userns: the filesystem's idmapping * @value: the uapi representation of POSIX ACLs * @size: the size of @void * * Filesystems that store POSIX ACLs in the unaltered uapi format should use * posix_acl_from_xattr() when reading them from the backing store and * converting them into the struct posix_acl VFS format. The helper is * specifically intended to be called from the acl inode operation. * * The posix_acl_from_xattr() function will map the raw {g,u}id values stored * in ACL_{GROUP,USER} entries into idmapping in @userns. * * Note that posix_acl_from_xattr() does not take idmapped mounts into account. * If it did it calling it from the get acl inode operation would return POSIX * ACLs mapped according to an idmapped mount which would mean that the value * couldn't be cached for the filesystem. Idmapped mounts are taken into * account on the fly during permission checking or right at the VFS - * userspace boundary before reporting them to the user. * * Return: Allocated struct posix_acl on success, NULL for a valid header but * without actual POSIX ACL entries, or ERR_PTR() encoded error code. */ struct posix_acl *posix_acl_from_xattr(struct user_namespace *userns, const void *value, size_t size) { const struct posix_acl_xattr_header *header = value; const struct posix_acl_xattr_entry *entry = (const void *)(header + 1), *end; int count; struct posix_acl *acl; struct posix_acl_entry *acl_e; count = posix_acl_fix_xattr_common(value, size); if (count < 0) return ERR_PTR(count); if (count == 0) return NULL; acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) return ERR_PTR(-ENOMEM); acl_e = acl->a_entries; for (end = entry + count; entry != end; acl_e++, entry++) { acl_e->e_tag = le16_to_cpu(entry->e_tag); acl_e->e_perm = le16_to_cpu(entry->e_perm); switch(acl_e->e_tag) { case ACL_USER_OBJ: case ACL_GROUP_OBJ: case ACL_MASK: case ACL_OTHER: break; case ACL_USER: acl_e->e_uid = make_kuid(userns, le32_to_cpu(entry->e_id)); if (!uid_valid(acl_e->e_uid)) goto fail; break; case ACL_GROUP: acl_e->e_gid = make_kgid(userns, le32_to_cpu(entry->e_id)); if (!gid_valid(acl_e->e_gid)) goto fail; break; default: goto fail; } } return acl; fail: posix_acl_release(acl); return ERR_PTR(-EINVAL); } EXPORT_SYMBOL (posix_acl_from_xattr); /* * Convert from in-memory to extended attribute representation. */ int posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl, void *buffer, size_t size) { struct posix_acl_xattr_header *ext_acl = buffer; struct posix_acl_xattr_entry *ext_entry; int real_size, n; real_size = posix_acl_xattr_size(acl->a_count); if (!buffer) return real_size; if (real_size > size) return -ERANGE; ext_entry = (void *)(ext_acl + 1); ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION); for (n=0; n < acl->a_count; n++, ext_entry++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext_entry->e_tag = cpu_to_le16(acl_e->e_tag); ext_entry->e_perm = cpu_to_le16(acl_e->e_perm); switch(acl_e->e_tag) { case ACL_USER: ext_entry->e_id = cpu_to_le32(from_kuid(user_ns, acl_e->e_uid)); break; case ACL_GROUP: ext_entry->e_id = cpu_to_le32(from_kgid(user_ns, acl_e->e_gid)); break; default: ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); break; } } return real_size; } EXPORT_SYMBOL (posix_acl_to_xattr); /** * vfs_posix_acl_to_xattr - convert from kernel to userspace representation * @idmap: idmap of the mount * @inode: inode the posix acls are set on * @acl: the posix acls as represented by the vfs * @buffer: the buffer into which to convert @acl * @size: size of @buffer * * This converts @acl from the VFS representation in the filesystem idmapping * to the uapi form reportable to userspace. And mount and caller idmappings * are handled appropriately. * * Return: On success, the size of the stored uapi posix acls, on error a * negative errno. */ static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap, struct inode *inode, const struct posix_acl *acl, void *buffer, size_t size) { struct posix_acl_xattr_header *ext_acl = buffer; struct posix_acl_xattr_entry *ext_entry; struct user_namespace *fs_userns, *caller_userns; ssize_t real_size, n; vfsuid_t vfsuid; vfsgid_t vfsgid; real_size = posix_acl_xattr_size(acl->a_count); if (!buffer) return real_size; if (real_size > size) return -ERANGE; ext_entry = (void *)(ext_acl + 1); ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION); fs_userns = i_user_ns(inode); caller_userns = current_user_ns(); for (n=0; n < acl->a_count; n++, ext_entry++) { const struct posix_acl_entry *acl_e = &acl->a_entries[n]; ext_entry->e_tag = cpu_to_le16(acl_e->e_tag); ext_entry->e_perm = cpu_to_le16(acl_e->e_perm); switch(acl_e->e_tag) { case ACL_USER: vfsuid = make_vfsuid(idmap, fs_userns, acl_e->e_uid); ext_entry->e_id = cpu_to_le32(from_kuid( caller_userns, vfsuid_into_kuid(vfsuid))); break; case ACL_GROUP: vfsgid = make_vfsgid(idmap, fs_userns, acl_e->e_gid); ext_entry->e_id = cpu_to_le32(from_kgid( caller_userns, vfsgid_into_kgid(vfsgid))); break; default: ext_entry->e_id = cpu_to_le32(ACL_UNDEFINED_ID); break; } } return real_size; } int set_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type, struct posix_acl *acl) { struct inode *inode = d_inode(dentry); if (!IS_POSIXACL(inode)) return -EOPNOTSUPP; if (!inode->i_op->set_acl) return -EOPNOTSUPP; if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (acl) { int ret = posix_acl_valid(inode->i_sb->s_user_ns, acl); if (ret) return ret; } return inode->i_op->set_acl(idmap, dentry, acl, type); } EXPORT_SYMBOL(set_posix_acl); int posix_acl_listxattr(struct inode *inode, char **buffer, ssize_t *remaining_size) { int err; if (!IS_POSIXACL(inode)) return 0; if (inode->i_acl) { err = xattr_list_one(buffer, remaining_size, XATTR_NAME_POSIX_ACL_ACCESS); if (err) return err; } if (inode->i_default_acl) { err = xattr_list_one(buffer, remaining_size, XATTR_NAME_POSIX_ACL_DEFAULT); if (err) return err; } return 0; } static bool posix_acl_xattr_list(struct dentry *dentry) { return IS_POSIXACL(d_backing_inode(dentry)); } /* * nop_posix_acl_access - legacy xattr handler for access POSIX ACLs * * This is the legacy POSIX ACL access xattr handler. It is used by some * filesystems to implement their ->listxattr() inode operation. New code * should never use them. */ const struct xattr_handler nop_posix_acl_access = { .name = XATTR_NAME_POSIX_ACL_ACCESS, .list = posix_acl_xattr_list, }; EXPORT_SYMBOL_GPL(nop_posix_acl_access); /* * nop_posix_acl_default - legacy xattr handler for default POSIX ACLs * * This is the legacy POSIX ACL default xattr handler. It is used by some * filesystems to implement their ->listxattr() inode operation. New code * should never use them. */ const struct xattr_handler nop_posix_acl_default = { .name = XATTR_NAME_POSIX_ACL_DEFAULT, .list = posix_acl_xattr_list, }; EXPORT_SYMBOL_GPL(nop_posix_acl_default); int simple_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { int error; struct inode *inode = d_inode(dentry); if (type == ACL_TYPE_ACCESS) { error = posix_acl_update_mode(idmap, inode, &inode->i_mode, &acl); if (error) return error; } inode_set_ctime_current(inode); if (IS_I_VERSION(inode)) inode_inc_iversion(inode); set_cached_acl(inode, type, acl); return 0; } int simple_acl_create(struct inode *dir, struct inode *inode) { struct posix_acl *default_acl, *acl; int error; error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); if (error) return error; set_cached_acl(inode, ACL_TYPE_DEFAULT, default_acl); set_cached_acl(inode, ACL_TYPE_ACCESS, acl); if (default_acl) posix_acl_release(default_acl); if (acl) posix_acl_release(acl); return 0; } static int vfs_set_acl_idmapped_mnt(struct mnt_idmap *idmap, struct user_namespace *fs_userns, struct posix_acl *acl) { for (int n = 0; n < acl->a_count; n++) { struct posix_acl_entry *acl_e = &acl->a_entries[n]; switch (acl_e->e_tag) { case ACL_USER: acl_e->e_uid = from_vfsuid(idmap, fs_userns, VFSUIDT_INIT(acl_e->e_uid)); break; case ACL_GROUP: acl_e->e_gid = from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(acl_e->e_gid)); break; } } return 0; } /** * vfs_set_acl - set posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to set the posix acls * @acl_name: the name of the posix acl * @kacl: the posix acls in the appropriate VFS format * * This function sets @kacl. The caller must all posix_acl_release() on @kacl * afterwards. * * Return: On success 0, on error negative errno. */ int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, struct posix_acl *kacl) { int acl_type; int error; struct inode *inode = d_inode(dentry); struct inode *delegated_inode = NULL; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return -EINVAL; if (kacl) { /* * If we're on an idmapped mount translate from mount specific * vfs{g,u}id_t into global filesystem k{g,u}id_t. * Afterwards we can cache the POSIX ACLs filesystem wide and - * if this is a filesystem with a backing store - ultimately * translate them to backing store values. */ error = vfs_set_acl_idmapped_mnt(idmap, i_user_ns(inode), kacl); if (error) return error; } retry_deleg: inode_lock(inode); /* * We only care about restrictions the inode struct itself places upon * us otherwise POSIX ACLs aren't subject to any VFS restrictions. */ error = may_write_xattr(idmap, inode); if (error) goto out_inode_unlock; error = security_inode_set_acl(idmap, dentry, acl_name, kacl); if (error) goto out_inode_unlock; error = try_break_deleg(inode, &delegated_inode); if (error) goto out_inode_unlock; if (likely(!is_bad_inode(inode))) error = set_posix_acl(idmap, dentry, acl_type, kacl); else error = -EIO; if (!error) { fsnotify_xattr(dentry); security_inode_post_set_acl(dentry, acl_name, kacl); } out_inode_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_set_acl); /** * vfs_get_acl - get posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to retrieve the posix acls * @acl_name: the name of the posix acl * * This function retrieves @kacl from the filesystem. The caller must all * posix_acl_release() on @kacl. * * Return: On success POSIX ACLs in VFS format, on error negative errno. */ struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { struct inode *inode = d_inode(dentry); struct posix_acl *acl; int acl_type, error; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return ERR_PTR(-EINVAL); /* * The VFS has no restrictions on reading POSIX ACLs so calling * something like xattr_permission() isn't needed. Only LSMs get a say. */ error = security_inode_get_acl(idmap, dentry, acl_name); if (error) return ERR_PTR(error); if (!IS_POSIXACL(inode)) return ERR_PTR(-EOPNOTSUPP); if (S_ISLNK(inode->i_mode)) return ERR_PTR(-EOPNOTSUPP); acl = __get_acl(idmap, dentry, inode, acl_type); if (IS_ERR(acl)) return acl; if (!acl) return ERR_PTR(-ENODATA); return acl; } EXPORT_SYMBOL_GPL(vfs_get_acl); /** * vfs_remove_acl - remove posix acls * @idmap: idmap of the mount * @dentry: the dentry based on which to retrieve the posix acls * @acl_name: the name of the posix acl * * This function removes posix acls. * * Return: On success 0, on error negative errno. */ int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name) { int acl_type; int error; struct inode *inode = d_inode(dentry); struct inode *delegated_inode = NULL; acl_type = posix_acl_type(acl_name); if (acl_type < 0) return -EINVAL; retry_deleg: inode_lock(inode); /* * We only care about restrictions the inode struct itself places upon * us otherwise POSIX ACLs aren't subject to any VFS restrictions. */ error = may_write_xattr(idmap, inode); if (error) goto out_inode_unlock; error = security_inode_remove_acl(idmap, dentry, acl_name); if (error) goto out_inode_unlock; error = try_break_deleg(inode, &delegated_inode); if (error) goto out_inode_unlock; if (likely(!is_bad_inode(inode))) error = set_posix_acl(idmap, dentry, acl_type, NULL); else error = -EIO; if (!error) { fsnotify_xattr(dentry); security_inode_post_remove_acl(idmap, dentry, acl_name); } out_inode_unlock: inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } return error; } EXPORT_SYMBOL_GPL(vfs_remove_acl); int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size) { int error; struct posix_acl *acl = NULL; if (size) { /* * Note that posix_acl_from_xattr() uses GFP_NOFS when it * probably doesn't need to here. */ acl = posix_acl_from_xattr(current_user_ns(), kvalue, size); if (IS_ERR(acl)) return PTR_ERR(acl); } error = vfs_set_acl(idmap, dentry, acl_name, acl); posix_acl_release(acl); return error; } ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size) { ssize_t error; struct posix_acl *acl; acl = vfs_get_acl(idmap, dentry, acl_name); if (IS_ERR(acl)) return PTR_ERR(acl); error = vfs_posix_acl_to_xattr(idmap, d_inode(dentry), acl, kvalue, size); posix_acl_release(acl); return error; } |
| 30 1 33 31 31 575 570 31 33 33 33 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. * Authors: David Chinner and Glauber Costa * * Generic LRU infrastructure */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/list_lru.h> #include <linux/slab.h> #include <linux/mutex.h> #include <linux/memcontrol.h> #include "slab.h" #include "internal.h" #ifdef CONFIG_MEMCG static LIST_HEAD(memcg_list_lrus); static DEFINE_MUTEX(list_lrus_mutex); static inline bool list_lru_memcg_aware(struct list_lru *lru) { return lru->memcg_aware; } static void list_lru_register(struct list_lru *lru) { if (!list_lru_memcg_aware(lru)) return; mutex_lock(&list_lrus_mutex); list_add(&lru->list, &memcg_list_lrus); mutex_unlock(&list_lrus_mutex); } static void list_lru_unregister(struct list_lru *lru) { if (!list_lru_memcg_aware(lru)) return; mutex_lock(&list_lrus_mutex); list_del(&lru->list); mutex_unlock(&list_lrus_mutex); } static int lru_shrinker_id(struct list_lru *lru) { return lru->shrinker_id; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { if (list_lru_memcg_aware(lru) && idx >= 0) { struct list_lru_memcg *mlru = xa_load(&lru->xa, idx); return mlru ? &mlru->node[nid] : NULL; } return &lru->node[nid].lru; } static inline bool lock_list_lru(struct list_lru_one *l, bool irq) { if (irq) spin_lock_irq(&l->lock); else spin_lock(&l->lock); if (unlikely(READ_ONCE(l->nr_items) == LONG_MIN)) { if (irq) spin_unlock_irq(&l->lock); else spin_unlock(&l->lock); return false; } return true; } static inline struct list_lru_one * lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg, bool irq, bool skip_empty) { struct list_lru_one *l; rcu_read_lock(); again: l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); if (likely(l) && lock_list_lru(l, irq)) { rcu_read_unlock(); return l; } /* * Caller may simply bail out if raced with reparenting or * may iterate through the list_lru and expect empty slots. */ if (skip_empty) { rcu_read_unlock(); return NULL; } VM_WARN_ON(!css_is_dying(&memcg->css)); memcg = parent_mem_cgroup(memcg); goto again; } static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off) { if (irq_off) spin_unlock_irq(&l->lock); else spin_unlock(&l->lock); } #else static void list_lru_register(struct list_lru *lru) { } static void list_lru_unregister(struct list_lru *lru) { } static int lru_shrinker_id(struct list_lru *lru) { return -1; } static inline bool list_lru_memcg_aware(struct list_lru *lru) { return false; } static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { return &lru->node[nid].lru; } static inline struct list_lru_one * lock_list_lru_of_memcg(struct list_lru *lru, int nid, struct mem_cgroup *memcg, bool irq, bool skip_empty) { struct list_lru_one *l = &lru->node[nid].lru; if (irq) spin_lock_irq(&l->lock); else spin_lock(&l->lock); return l; } static inline void unlock_list_lru(struct list_lru_one *l, bool irq_off) { if (irq_off) spin_unlock_irq(&l->lock); else spin_unlock(&l->lock); } #endif /* CONFIG_MEMCG */ /* The caller must ensure the memcg lifetime. */ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; l = lock_list_lru_of_memcg(lru, nid, memcg, false, false); if (!l) return false; if (list_empty(item)) { list_add_tail(item, &l->list); /* Set shrinker bit if the first element was added */ if (!l->nr_items++) set_shrinker_bit(memcg, nid, lru_shrinker_id(lru)); unlock_list_lru(l, false); atomic_long_inc(&nlru->nr_items); return true; } unlock_list_lru(l, false); return false; } bool list_lru_add_obj(struct list_lru *lru, struct list_head *item) { bool ret; int nid = page_to_nid(virt_to_page(item)); if (list_lru_memcg_aware(lru)) { rcu_read_lock(); ret = list_lru_add(lru, item, nid, mem_cgroup_from_slab_obj(item)); rcu_read_unlock(); } else { ret = list_lru_add(lru, item, nid, NULL); } return ret; } EXPORT_SYMBOL_GPL(list_lru_add_obj); /* The caller must ensure the memcg lifetime. */ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l; l = lock_list_lru_of_memcg(lru, nid, memcg, false, false); if (!l) return false; if (!list_empty(item)) { list_del_init(item); l->nr_items--; unlock_list_lru(l, false); atomic_long_dec(&nlru->nr_items); return true; } unlock_list_lru(l, false); return false; } bool list_lru_del_obj(struct list_lru *lru, struct list_head *item) { bool ret; int nid = page_to_nid(virt_to_page(item)); if (list_lru_memcg_aware(lru)) { rcu_read_lock(); ret = list_lru_del(lru, item, nid, mem_cgroup_from_slab_obj(item)); rcu_read_unlock(); } else { ret = list_lru_del(lru, item, nid, NULL); } return ret; } EXPORT_SYMBOL_GPL(list_lru_del_obj); void list_lru_isolate(struct list_lru_one *list, struct list_head *item) { list_del_init(item); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head) { list_move(item, head); list->nr_items--; } EXPORT_SYMBOL_GPL(list_lru_isolate_move); unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg) { struct list_lru_one *l; long count; rcu_read_lock(); l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); count = l ? READ_ONCE(l->nr_items) : 0; rcu_read_unlock(); if (unlikely(count < 0)) count = 0; return count; } EXPORT_SYMBOL_GPL(list_lru_count_one); unsigned long list_lru_count_node(struct list_lru *lru, int nid) { struct list_lru_node *nlru; nlru = &lru->node[nid]; return atomic_long_read(&nlru->nr_items); } EXPORT_SYMBOL_GPL(list_lru_count_node); static unsigned long __list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk, bool irq_off) { struct list_lru_node *nlru = &lru->node[nid]; struct list_lru_one *l = NULL; struct list_head *item, *n; unsigned long isolated = 0; restart: l = lock_list_lru_of_memcg(lru, nid, memcg, irq_off, true); if (!l) return isolated; list_for_each_safe(item, n, &l->list) { enum lru_status ret; /* * decrement nr_to_walk first so that we don't livelock if we * get stuck on large numbers of LRU_RETRY items */ if (!*nr_to_walk) break; --*nr_to_walk; ret = isolate(item, l, cb_arg); switch (ret) { /* * LRU_RETRY, LRU_REMOVED_RETRY and LRU_STOP will drop the lru * lock. List traversal will have to restart from scratch. */ case LRU_RETRY: goto restart; case LRU_REMOVED_RETRY: fallthrough; case LRU_REMOVED: isolated++; atomic_long_dec(&nlru->nr_items); if (ret == LRU_REMOVED_RETRY) goto restart; break; case LRU_ROTATE: list_move_tail(item, &l->list); break; case LRU_SKIP: break; case LRU_STOP: goto out; default: BUG(); } } unlock_list_lru(l, irq_off); out: return isolated; } unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { return __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, nr_to_walk, false); } EXPORT_SYMBOL_GPL(list_lru_walk_one); unsigned long list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { return __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, nr_to_walk, true); } unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk) { long isolated = 0; isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg, nr_to_walk); #ifdef CONFIG_MEMCG if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { struct list_lru_memcg *mlru; struct mem_cgroup *memcg; unsigned long index; xa_for_each(&lru->xa, index, mlru) { rcu_read_lock(); memcg = mem_cgroup_from_id(index); if (!mem_cgroup_tryget(memcg)) { rcu_read_unlock(); continue; } rcu_read_unlock(); isolated += __list_lru_walk_one(lru, nid, memcg, isolate, cb_arg, nr_to_walk, false); mem_cgroup_put(memcg); if (*nr_to_walk <= 0) break; } } #endif return isolated; } EXPORT_SYMBOL_GPL(list_lru_walk_node); static void init_one_lru(struct list_lru *lru, struct list_lru_one *l) { INIT_LIST_HEAD(&l->list); spin_lock_init(&l->lock); l->nr_items = 0; #ifdef CONFIG_LOCKDEP if (lru->key) lockdep_set_class(&l->lock, lru->key); #endif } #ifdef CONFIG_MEMCG static struct list_lru_memcg *memcg_init_list_lru_one(struct list_lru *lru, gfp_t gfp) { int nid; struct list_lru_memcg *mlru; mlru = kmalloc(struct_size(mlru, node, nr_node_ids), gfp); if (!mlru) return NULL; for_each_node(nid) init_one_lru(lru, &mlru->node[nid]); return mlru; } static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { if (memcg_aware) xa_init_flags(&lru->xa, XA_FLAGS_LOCK_IRQ); lru->memcg_aware = memcg_aware; } static void memcg_destroy_list_lru(struct list_lru *lru) { XA_STATE(xas, &lru->xa, 0); struct list_lru_memcg *mlru; if (!list_lru_memcg_aware(lru)) return; xas_lock_irq(&xas); xas_for_each(&xas, mlru, ULONG_MAX) { kfree(mlru); xas_store(&xas, NULL); } xas_unlock_irq(&xas); } static void memcg_reparent_list_lru_one(struct list_lru *lru, int nid, struct list_lru_one *src, struct mem_cgroup *dst_memcg) { int dst_idx = dst_memcg->kmemcg_id; struct list_lru_one *dst; spin_lock_irq(&src->lock); dst = list_lru_from_memcg_idx(lru, nid, dst_idx); spin_lock_nested(&dst->lock, SINGLE_DEPTH_NESTING); list_splice_init(&src->list, &dst->list); if (src->nr_items) { WARN_ON(src->nr_items < 0); dst->nr_items += src->nr_items; set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); } /* Mark the list_lru_one dead */ src->nr_items = LONG_MIN; spin_unlock(&dst->lock); spin_unlock_irq(&src->lock); } void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent) { struct list_lru *lru; int i; mutex_lock(&list_lrus_mutex); list_for_each_entry(lru, &memcg_list_lrus, list) { struct list_lru_memcg *mlru; XA_STATE(xas, &lru->xa, memcg->kmemcg_id); /* * Lock the Xarray to ensure no on going list_lru_memcg * allocation and further allocation will see css_is_dying(). */ xas_lock_irq(&xas); mlru = xas_store(&xas, NULL); xas_unlock_irq(&xas); if (!mlru) continue; /* * With Xarray value set to NULL, holding the lru lock below * prevents list_lru_{add,del,isolate} from touching the lru, * safe to reparent. */ for_each_node(i) memcg_reparent_list_lru_one(lru, i, &mlru->node[i], parent); /* * Here all list_lrus corresponding to the cgroup are guaranteed * to remain empty, we can safely free this lru, any further * memcg_list_lru_alloc() call will simply bail out. */ kvfree_rcu(mlru, rcu); } mutex_unlock(&list_lrus_mutex); } static inline bool memcg_list_lru_allocated(struct mem_cgroup *memcg, struct list_lru *lru) { int idx = memcg->kmemcg_id; return idx < 0 || xa_load(&lru->xa, idx); } int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp) { unsigned long flags; struct list_lru_memcg *mlru = NULL; struct mem_cgroup *pos, *parent; XA_STATE(xas, &lru->xa, 0); if (!list_lru_memcg_aware(lru) || memcg_list_lru_allocated(memcg, lru)) return 0; gfp &= GFP_RECLAIM_MASK; /* * Because the list_lru can be reparented to the parent cgroup's * list_lru, we should make sure that this cgroup and all its * ancestors have allocated list_lru_memcg. */ do { /* * Keep finding the farest parent that wasn't populated * until found memcg itself. */ pos = memcg; parent = parent_mem_cgroup(pos); while (!memcg_list_lru_allocated(parent, lru)) { pos = parent; parent = parent_mem_cgroup(pos); } if (!mlru) { mlru = memcg_init_list_lru_one(lru, gfp); if (!mlru) return -ENOMEM; } xas_set(&xas, pos->kmemcg_id); do { xas_lock_irqsave(&xas, flags); if (!xas_load(&xas) && !css_is_dying(&pos->css)) { xas_store(&xas, mlru); if (!xas_error(&xas)) mlru = NULL; } xas_unlock_irqrestore(&xas, flags); } while (xas_nomem(&xas, gfp)); } while (pos != memcg && !css_is_dying(&pos->css)); if (unlikely(mlru)) kfree(mlru); return xas_error(&xas); } #else static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { } static void memcg_destroy_list_lru(struct list_lru *lru) { } #endif /* CONFIG_MEMCG */ int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct shrinker *shrinker) { int i; #ifdef CONFIG_MEMCG if (shrinker) lru->shrinker_id = shrinker->id; else lru->shrinker_id = -1; if (mem_cgroup_kmem_disabled()) memcg_aware = false; #endif lru->node = kcalloc(nr_node_ids, sizeof(*lru->node), GFP_KERNEL); if (!lru->node) return -ENOMEM; for_each_node(i) init_one_lru(lru, &lru->node[i].lru); memcg_init_list_lru(lru, memcg_aware); list_lru_register(lru); return 0; } EXPORT_SYMBOL_GPL(__list_lru_init); void list_lru_destroy(struct list_lru *lru) { /* Already destroyed or not yet initialized? */ if (!lru->node) return; list_lru_unregister(lru); memcg_destroy_list_lru(lru); kfree(lru->node); lru->node = NULL; #ifdef CONFIG_MEMCG lru->shrinker_id = -1; #endif } EXPORT_SYMBOL_GPL(list_lru_destroy); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef __DSA_USER_H #define __DSA_USER_H #include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/list.h> #include <linux/netpoll.h> #include <linux/types.h> #include <net/dsa.h> #include <net/gro_cells.h> struct net_device; struct netlink_ext_ack; extern struct notifier_block dsa_user_switchdev_notifier; extern struct notifier_block dsa_user_switchdev_blocking_notifier; struct dsa_user_priv { /* Copy of CPU port xmit for faster access in user transmit hot path */ struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); struct gro_cells gcells; /* DSA port data, such as switch, port index, etc. */ struct dsa_port *dp; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif /* TC context */ struct list_head mall_tc_list; }; void dsa_user_mii_bus_init(struct dsa_switch *ds); int dsa_user_create(struct dsa_port *dp); void dsa_user_destroy(struct net_device *user_dev); int dsa_user_suspend(struct net_device *user_dev); int dsa_user_resume(struct net_device *user_dev); int dsa_user_register_notifier(void); void dsa_user_unregister_notifier(void); int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr); void dsa_user_host_uc_uninstall(struct net_device *dev); void dsa_user_sync_ha(struct net_device *dev); void dsa_user_unsync_ha(struct net_device *dev); void dsa_user_setup_tagger(struct net_device *user); int dsa_user_change_mtu(struct net_device *dev, int new_mtu); int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, struct netlink_ext_ack *extack); int dsa_user_manage_vlan_filtering(struct net_device *dev, bool vlan_filtering); static inline struct dsa_port *dsa_user_to_port(const struct net_device *dev) { struct dsa_user_priv *p = netdev_priv(dev); return p->dp; } static inline struct net_device * dsa_user_to_conduit(const struct net_device *dev) { struct dsa_port *dp = dsa_user_to_port(dev); return dsa_port_to_conduit(dp); } #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FUTEX_H #define _FUTEX_H #include <linux/futex.h> #include <linux/rtmutex.h> #include <linux/sched/wake_q.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <linux/cleanup.h> #ifdef CONFIG_PREEMPT_RT #include <linux/rcuwait.h> #endif #include <asm/futex.h> /* * Futex flags used to encode options to functions and preserve them across * restarts. */ #define FLAGS_SIZE_8 0x0000 #define FLAGS_SIZE_16 0x0001 #define FLAGS_SIZE_32 0x0002 #define FLAGS_SIZE_64 0x0003 #define FLAGS_SIZE_MASK 0x0003 #ifdef CONFIG_MMU # define FLAGS_SHARED 0x0010 #else /* * NOMMU does not have per process address space. Let the compiler optimize * code away. */ # define FLAGS_SHARED 0x0000 #endif #define FLAGS_CLOCKRT 0x0020 #define FLAGS_HAS_TIMEOUT 0x0040 #define FLAGS_NUMA 0x0080 #define FLAGS_STRICT 0x0100 #define FLAGS_MPOL 0x0200 /* FUTEX_ to FLAGS_ */ static inline unsigned int futex_to_flags(unsigned int op) { unsigned int flags = FLAGS_SIZE_32; if (!(op & FUTEX_PRIVATE_FLAG)) flags |= FLAGS_SHARED; if (op & FUTEX_CLOCK_REALTIME) flags |= FLAGS_CLOCKRT; return flags; } #define FUTEX2_VALID_MASK (FUTEX2_SIZE_MASK | FUTEX2_NUMA | FUTEX2_MPOL | FUTEX2_PRIVATE) /* FUTEX2_ to FLAGS_ */ static inline unsigned int futex2_to_flags(unsigned int flags2) { unsigned int flags = flags2 & FUTEX2_SIZE_MASK; if (!(flags2 & FUTEX2_PRIVATE)) flags |= FLAGS_SHARED; if (flags2 & FUTEX2_NUMA) flags |= FLAGS_NUMA; if (flags2 & FUTEX2_MPOL) flags |= FLAGS_MPOL; return flags; } static inline unsigned int futex_size(unsigned int flags) { return 1 << (flags & FLAGS_SIZE_MASK); } static inline bool futex_flags_valid(unsigned int flags) { /* Only 64bit futexes for 64bit code */ if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall()) { if ((flags & FLAGS_SIZE_MASK) == FLAGS_SIZE_64) return false; } /* Only 32bit futexes are implemented -- for now */ if ((flags & FLAGS_SIZE_MASK) != FLAGS_SIZE_32) return false; /* * Must be able to represent both FUTEX_NO_NODE and every valid nodeid * in a futex word. */ if (flags & FLAGS_NUMA) { int bits = 8 * futex_size(flags); u64 max = ~0ULL; max >>= 64 - bits; if (nr_node_ids >= max) return false; } return true; } static inline bool futex_validate_input(unsigned int flags, u64 val) { int bits = 8 * futex_size(flags); if (bits < 64 && (val >> bits)) return false; return true; } #ifdef CONFIG_FAIL_FUTEX extern bool should_fail_futex(bool fshared); #else static inline bool should_fail_futex(bool fshared) { return false; } #endif /* * Hash buckets are shared by all the futex_keys that hash to the same * location. Each key may have multiple futex_q structures, one for each task * waiting on a futex. */ struct futex_hash_bucket { atomic_t waiters; spinlock_t lock; struct plist_head chain; struct futex_private_hash *priv; } ____cacheline_aligned_in_smp; /* * Priority Inheritance state: */ struct futex_pi_state { /* * list of 'owned' pi_state instances - these have to be * cleaned up in do_exit() if the task exits prematurely: */ struct list_head list; /* * The PI object: */ struct rt_mutex_base pi_mutex; struct task_struct *owner; refcount_t refcount; union futex_key key; } __randomize_layout; struct futex_q; typedef void (futex_wake_fn)(struct wake_q_head *wake_q, struct futex_q *q); /** * struct futex_q - The hashed futex queue entry, one per waiting task * @list: priority-sorted list of tasks waiting on this futex * @task: the task waiting on the futex * @lock_ptr: the hash bucket lock * @wake: the wake handler for this queue * @wake_data: data associated with the wake handler * @key: the key the futex is hashed on * @pi_state: optional priority inheritance state * @rt_waiter: rt_waiter storage for use with requeue_pi * @requeue_pi_key: the requeue_pi target futex key * @bitset: bitset for the optional bitmasked wakeup * @requeue_state: State field for futex_requeue_pi() * @drop_hb_ref: Waiter should drop the extra hash bucket reference if true * @requeue_wait: RCU wait for futex_requeue_pi() (RT only) * * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so * we can wake only the relevant ones (hashed queues may be shared). * * A futex_q has a woken state, just like tasks have TASK_RUNNING. * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0. * The order of wakeup is always to make the first condition true, then * the second. * * PI futexes are typically woken before they are removed from the hash list via * the rt_mutex code. See futex_unqueue_pi(). */ struct futex_q { struct plist_node list; struct task_struct *task; spinlock_t *lock_ptr; futex_wake_fn *wake; void *wake_data; union futex_key key; struct futex_pi_state *pi_state; struct rt_mutex_waiter *rt_waiter; union futex_key *requeue_pi_key; u32 bitset; atomic_t requeue_state; bool drop_hb_ref; #ifdef CONFIG_PREEMPT_RT struct rcuwait requeue_wait; #endif } __randomize_layout; extern const struct futex_q futex_q_init; enum futex_access { FUTEX_READ, FUTEX_WRITE }; extern int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key, enum futex_access rw); extern void futex_q_lockptr_lock(struct futex_q *q); extern struct hrtimer_sleeper * futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout, int flags, u64 range_ns); extern struct futex_hash_bucket *futex_hash(union futex_key *key); #ifdef CONFIG_FUTEX_PRIVATE_HASH extern void futex_hash_get(struct futex_hash_bucket *hb); extern void futex_hash_put(struct futex_hash_bucket *hb); extern struct futex_private_hash *futex_private_hash(void); extern void futex_private_hash_put(struct futex_private_hash *fph); #else /* !CONFIG_FUTEX_PRIVATE_HASH */ static inline void futex_hash_get(struct futex_hash_bucket *hb) { } static inline void futex_hash_put(struct futex_hash_bucket *hb) { } static inline struct futex_private_hash *futex_private_hash(void) { return NULL; } static inline void futex_private_hash_put(struct futex_private_hash *fph) { } #endif DEFINE_CLASS(hb, struct futex_hash_bucket *, if (_T) futex_hash_put(_T), futex_hash(key), union futex_key *key); DEFINE_CLASS(private_hash, struct futex_private_hash *, if (_T) futex_private_hash_put(_T), futex_private_hash(), void); /** * futex_match - Check whether two futex keys are equal * @key1: Pointer to key1 * @key2: Pointer to key2 * * Return 1 if two futex_keys are equal, 0 otherwise. */ static inline int futex_match(union futex_key *key1, union futex_key *key2) { return (key1 && key2 && key1->both.word == key2->both.word && key1->both.ptr == key2->both.ptr && key1->both.offset == key2->both.offset); } extern int futex_wait_setup(u32 __user *uaddr, u32 val, unsigned int flags, struct futex_q *q, union futex_key *key2, struct task_struct *task); extern void futex_do_wait(struct futex_q *q, struct hrtimer_sleeper *timeout); extern bool __futex_wake_mark(struct futex_q *q); extern void futex_wake_mark(struct wake_q_head *wake_q, struct futex_q *q); extern int fault_in_user_writeable(u32 __user *uaddr); extern struct futex_q *futex_top_waiter(struct futex_hash_bucket *hb, union futex_key *key); static inline int futex_cmpxchg_value_locked(u32 *curval, u32 __user *uaddr, u32 uval, u32 newval) { int ret; pagefault_disable(); ret = futex_atomic_cmpxchg_inatomic(curval, uaddr, uval, newval); pagefault_enable(); return ret; } /* * This does a plain atomic user space read, and the user pointer has * already been verified earlier by get_futex_key() to be both aligned * and actually in user space, just like futex_atomic_cmpxchg_inatomic(). * * We still want to avoid any speculation, and while __get_user() is * the traditional model for this, it's actually slower than doing * this manually these days. * * We could just have a per-architecture special function for it, * the same way we do futex_atomic_cmpxchg_inatomic(), but rather * than force everybody to do that, write it out long-hand using * the low-level user-access infrastructure. * * This looks a bit overkill, but generally just results in a couple * of instructions. */ static __always_inline int futex_get_value(u32 *dest, u32 __user *from) { u32 val; if (can_do_masked_user_access()) from = masked_user_access_begin(from); else if (!user_read_access_begin(from, sizeof(*from))) return -EFAULT; unsafe_get_user(val, from, Efault); user_read_access_end(); *dest = val; return 0; Efault: user_read_access_end(); return -EFAULT; } static __always_inline int futex_put_value(u32 val, u32 __user *to) { if (can_do_masked_user_access()) to = masked_user_access_begin(to); else if (!user_write_access_begin(to, sizeof(*to))) return -EFAULT; unsafe_put_user(val, to, Efault); user_write_access_end(); return 0; Efault: user_write_access_end(); return -EFAULT; } static inline int futex_get_value_locked(u32 *dest, u32 __user *from) { int ret; pagefault_disable(); ret = futex_get_value(dest, from); pagefault_enable(); return ret; } extern void __futex_unqueue(struct futex_q *q); extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, struct task_struct *task); extern int futex_unqueue(struct futex_q *q); /** * futex_queue() - Enqueue the futex_q on the futex_hash_bucket * @q: The futex_q to enqueue * @hb: The destination hash bucket * @task: Task queueing this futex * * The hb->lock must be held by the caller, and is released here. A call to * futex_queue() is typically paired with exactly one call to futex_unqueue(). The * exceptions involve the PI related operations, which may use futex_unqueue_pi() * or nothing if the unqueue is done as part of the wake process and the unqueue * state is implicit in the state of woken task (see futex_wait_requeue_pi() for * an example). * * Note that @task may be NULL, for async usage of futexes. */ static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, struct task_struct *task) __releases(&hb->lock) { __futex_queue(q, hb, task); spin_unlock(&hb->lock); } extern void futex_unqueue_pi(struct futex_q *q); extern void wait_for_owner_exiting(int ret, struct task_struct *exiting); /* * Reflects a new waiter being added to the waitqueue. */ static inline void futex_hb_waiters_inc(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP atomic_inc(&hb->waiters); /* * Full barrier (A), see the ordering comment above. */ smp_mb__after_atomic(); #endif } /* * Reflects a waiter being removed from the waitqueue by wakeup * paths. */ static inline void futex_hb_waiters_dec(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP atomic_dec(&hb->waiters); #endif } static inline int futex_hb_waiters_pending(struct futex_hash_bucket *hb) { #ifdef CONFIG_SMP /* * Full barrier (B), see the ordering comment above. */ smp_mb(); return atomic_read(&hb->waiters); #else return 1; #endif } extern void futex_q_lock(struct futex_q *q, struct futex_hash_bucket *hb); extern void futex_q_unlock(struct futex_hash_bucket *hb); extern int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb, union futex_key *key, struct futex_pi_state **ps, struct task_struct *task, struct task_struct **exiting, int set_waiters); extern int refill_pi_state_cache(void); extern void get_pi_state(struct futex_pi_state *pi_state); extern void put_pi_state(struct futex_pi_state *pi_state); extern int fixup_pi_owner(u32 __user *uaddr, struct futex_q *q, int locked); /* * Express the locking dependencies for lockdep: */ static inline void double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) { if (hb1 > hb2) swap(hb1, hb2); spin_lock(&hb1->lock); if (hb1 != hb2) spin_lock_nested(&hb2->lock, SINGLE_DEPTH_NESTING); } static inline void double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) { spin_unlock(&hb1->lock); if (hb1 != hb2) spin_unlock(&hb2->lock); } /* syscalls */ extern int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset, u32 __user *uaddr2); extern int futex_requeue(u32 __user *uaddr1, unsigned int flags1, u32 __user *uaddr2, unsigned int flags2, int nr_wake, int nr_requeue, u32 *cmpval, int requeue_pi); extern int __futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, struct hrtimer_sleeper *to, u32 bitset); extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset); /** * struct futex_vector - Auxiliary struct for futex_waitv() * @w: Userspace provided data * @q: Kernel side data * * Struct used to build an array with all data need for futex_waitv() */ struct futex_vector { struct futex_waitv w; struct futex_q q; }; extern int futex_parse_waitv(struct futex_vector *futexv, struct futex_waitv __user *uwaitv, unsigned int nr_futexes, futex_wake_fn *wake, void *wake_data); extern int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken); extern int futex_unqueue_multiple(struct futex_vector *v, int count); extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count, struct hrtimer_sleeper *to); extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset); extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, int nr_wake, int nr_wake2, int op); extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags); extern int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock); #endif /* _FUTEX_H */ |
| 1842 1839 1836 1854 1843 1839 | 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 */ /* * Common arm64 stack unwinder code. * * See: arch/arm64/kernel/stacktrace.c for the reference implementation. * * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_STACKTRACE_COMMON_H #define __ASM_STACKTRACE_COMMON_H #include <linux/types.h> struct stack_info { unsigned long low; unsigned long high; }; /** * struct unwind_state - state used for robust unwinding. * * @fp: The fp value in the frame record (or the real fp) * @pc: The lr value in the frame record (or the real lr) * * @stack: The stack currently being unwound. * @stacks: An array of stacks which can be unwound. * @nr_stacks: The number of stacks in @stacks. */ struct unwind_state { unsigned long fp; unsigned long pc; struct stack_info stack; struct stack_info *stacks; int nr_stacks; }; static inline struct stack_info stackinfo_get_unknown(void) { return (struct stack_info) { .low = 0, .high = 0, }; } static inline bool stackinfo_on_stack(const struct stack_info *info, unsigned long sp, unsigned long size) { if (!info->low) return false; if (sp < info->low || sp + size < sp || sp + size > info->high) return false; return true; } static inline void unwind_init_common(struct unwind_state *state) { state->stack = stackinfo_get_unknown(); } /** * unwind_find_stack() - Find the accessible stack which entirely contains an * object. * * @state: the current unwind state. * @sp: the base address of the object. * @size: the size of the object. * * Return: a pointer to the relevant stack_info if found; NULL otherwise. */ static struct stack_info *unwind_find_stack(struct unwind_state *state, unsigned long sp, unsigned long size) { struct stack_info *info = &state->stack; if (stackinfo_on_stack(info, sp, size)) return info; for (int i = 0; i < state->nr_stacks; i++) { info = &state->stacks[i]; if (stackinfo_on_stack(info, sp, size)) return info; } return NULL; } /** * unwind_consume_stack() - Update stack boundaries so that future unwind steps * cannot consume this object again. * * @state: the current unwind state. * @info: the stack_info of the stack containing the object. * @sp: the base address of the object. * @size: the size of the object. * * Return: 0 upon success, an error code otherwise. */ static inline void unwind_consume_stack(struct unwind_state *state, struct stack_info *info, unsigned long sp, unsigned long size) { struct stack_info tmp; /* * Stack transitions are strictly one-way, and once we've * transitioned from one stack to another, it's never valid to * unwind back to the old stack. * * Destroy the old stack info so that it cannot be found upon a * subsequent transition. If the stack has not changed, we'll * immediately restore the current stack info. * * Note that stacks can nest in several valid orders, e.g. * * TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL * TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW * HYP -> OVERFLOW * * ... so we do not check the specific order of stack * transitions. */ tmp = *info; *info = stackinfo_get_unknown(); state->stack = tmp; /* * Future unwind steps can only consume stack above this frame record. * Update the current stack to start immediately above it. */ state->stack.low = sp + size; } /** * unwind_next_frame_record() - Unwind to the next frame record. * * @state: the current unwind state. * * Return: 0 upon success, an error code otherwise. */ static inline int unwind_next_frame_record(struct unwind_state *state) { struct stack_info *info; struct frame_record *record; unsigned long fp = state->fp; if (fp & 0x7) return -EINVAL; info = unwind_find_stack(state, fp, sizeof(*record)); if (!info) return -EINVAL; unwind_consume_stack(state, info, fp, sizeof(*record)); /* * Record this frame record's values. */ record = (struct frame_record *)fp; state->fp = READ_ONCE(record->fp); state->pc = READ_ONCE(record->lr); return 0; } #endif /* __ASM_STACKTRACE_COMMON_H */ |
| 18 16 2 14 4 11 7 12 6 14 4 15 3 12 6 26 22 4 20 6 21 6 24 3 24 3 22 5 22 5 4 2 2 2 1 16 16 15 14 11 2 11 2 4 9 3 10 27 17 3 13 16 13 2 2 13 13 3 2 2 20 3 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fs.h> #include <linux/security.h> #include <linux/fscrypt.h> #include <linux/fileattr.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/namei.h> #include "internal.h" /** * fileattr_fill_xflags - initialize fileattr with xflags * @fa: fileattr pointer * @xflags: FS_XFLAG_* flags * * Set ->fsx_xflags, ->fsx_valid and ->flags (translated xflags). All * other fields are zeroed. */ void fileattr_fill_xflags(struct file_kattr *fa, u32 xflags) { memset(fa, 0, sizeof(*fa)); fa->fsx_valid = true; fa->fsx_xflags = xflags; if (fa->fsx_xflags & FS_XFLAG_IMMUTABLE) fa->flags |= FS_IMMUTABLE_FL; if (fa->fsx_xflags & FS_XFLAG_APPEND) fa->flags |= FS_APPEND_FL; if (fa->fsx_xflags & FS_XFLAG_SYNC) fa->flags |= FS_SYNC_FL; if (fa->fsx_xflags & FS_XFLAG_NOATIME) fa->flags |= FS_NOATIME_FL; if (fa->fsx_xflags & FS_XFLAG_NODUMP) fa->flags |= FS_NODUMP_FL; if (fa->fsx_xflags & FS_XFLAG_DAX) fa->flags |= FS_DAX_FL; if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) fa->flags |= FS_PROJINHERIT_FL; } EXPORT_SYMBOL(fileattr_fill_xflags); /** * fileattr_fill_flags - initialize fileattr with flags * @fa: fileattr pointer * @flags: FS_*_FL flags * * Set ->flags, ->flags_valid and ->fsx_xflags (translated flags). * All other fields are zeroed. */ void fileattr_fill_flags(struct file_kattr *fa, u32 flags) { memset(fa, 0, sizeof(*fa)); fa->flags_valid = true; fa->flags = flags; if (fa->flags & FS_SYNC_FL) fa->fsx_xflags |= FS_XFLAG_SYNC; if (fa->flags & FS_IMMUTABLE_FL) fa->fsx_xflags |= FS_XFLAG_IMMUTABLE; if (fa->flags & FS_APPEND_FL) fa->fsx_xflags |= FS_XFLAG_APPEND; if (fa->flags & FS_NODUMP_FL) fa->fsx_xflags |= FS_XFLAG_NODUMP; if (fa->flags & FS_NOATIME_FL) fa->fsx_xflags |= FS_XFLAG_NOATIME; if (fa->flags & FS_DAX_FL) fa->fsx_xflags |= FS_XFLAG_DAX; if (fa->flags & FS_PROJINHERIT_FL) fa->fsx_xflags |= FS_XFLAG_PROJINHERIT; } EXPORT_SYMBOL(fileattr_fill_flags); /** * vfs_fileattr_get - retrieve miscellaneous file attributes * @dentry: the object to retrieve from * @fa: fileattr pointer * * Call i_op->fileattr_get() callback, if exists. * * Return: 0 on success, or a negative error on failure. */ int vfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa) { struct inode *inode = d_inode(dentry); int error; if (!inode->i_op->fileattr_get) return -ENOIOCTLCMD; error = security_inode_file_getattr(dentry, fa); if (error) return error; return inode->i_op->fileattr_get(dentry, fa); } EXPORT_SYMBOL(vfs_fileattr_get); static void fileattr_to_file_attr(const struct file_kattr *fa, struct file_attr *fattr) { __u32 mask = FS_XFLAGS_MASK; memset(fattr, 0, sizeof(struct file_attr)); fattr->fa_xflags = fa->fsx_xflags & mask; fattr->fa_extsize = fa->fsx_extsize; fattr->fa_nextents = fa->fsx_nextents; fattr->fa_projid = fa->fsx_projid; fattr->fa_cowextsize = fa->fsx_cowextsize; } /** * copy_fsxattr_to_user - copy fsxattr to userspace. * @fa: fileattr pointer * @ufa: fsxattr user pointer * * Return: 0 on success, or -EFAULT on failure. */ int copy_fsxattr_to_user(const struct file_kattr *fa, struct fsxattr __user *ufa) { struct fsxattr xfa; __u32 mask = FS_XFLAGS_MASK; memset(&xfa, 0, sizeof(xfa)); xfa.fsx_xflags = fa->fsx_xflags & mask; xfa.fsx_extsize = fa->fsx_extsize; xfa.fsx_nextents = fa->fsx_nextents; xfa.fsx_projid = fa->fsx_projid; xfa.fsx_cowextsize = fa->fsx_cowextsize; if (copy_to_user(ufa, &xfa, sizeof(xfa))) return -EFAULT; return 0; } EXPORT_SYMBOL(copy_fsxattr_to_user); static int file_attr_to_fileattr(const struct file_attr *fattr, struct file_kattr *fa) { __u64 mask = FS_XFLAGS_MASK; if (fattr->fa_xflags & ~mask) return -EINVAL; fileattr_fill_xflags(fa, fattr->fa_xflags); fa->fsx_xflags &= ~FS_XFLAG_RDONLY_MASK; fa->fsx_extsize = fattr->fa_extsize; fa->fsx_projid = fattr->fa_projid; fa->fsx_cowextsize = fattr->fa_cowextsize; return 0; } static int copy_fsxattr_from_user(struct file_kattr *fa, struct fsxattr __user *ufa) { struct fsxattr xfa; __u32 mask = FS_XFLAGS_MASK; if (copy_from_user(&xfa, ufa, sizeof(xfa))) return -EFAULT; if (xfa.fsx_xflags & ~mask) return -EOPNOTSUPP; fileattr_fill_xflags(fa, xfa.fsx_xflags); fa->fsx_xflags &= ~FS_XFLAG_RDONLY_MASK; fa->fsx_extsize = xfa.fsx_extsize; fa->fsx_nextents = xfa.fsx_nextents; fa->fsx_projid = xfa.fsx_projid; fa->fsx_cowextsize = xfa.fsx_cowextsize; return 0; } /* * Generic function to check FS_IOC_FSSETXATTR/FS_IOC_SETFLAGS values and reject * any invalid configurations. * * Note: must be called with inode lock held. */ static int fileattr_set_prepare(struct inode *inode, const struct file_kattr *old_ma, struct file_kattr *fa) { int err; /* * The IMMUTABLE and APPEND_ONLY flags can only be changed by * the relevant capability. */ if ((fa->flags ^ old_ma->flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; err = fscrypt_prepare_setflags(inode, old_ma->flags, fa->flags); if (err) return err; /* * Project Quota ID state is only allowed to change from within the init * namespace. Enforce that restriction only if we are trying to change * the quota ID state. Everything else is allowed in user namespaces. */ if (current_user_ns() != &init_user_ns) { if (old_ma->fsx_projid != fa->fsx_projid) return -EINVAL; if ((old_ma->fsx_xflags ^ fa->fsx_xflags) & FS_XFLAG_PROJINHERIT) return -EINVAL; } else { /* * Caller is allowed to change the project ID. If it is being * changed, make sure that the new value is valid. */ if (old_ma->fsx_projid != fa->fsx_projid && !projid_valid(make_kprojid(&init_user_ns, fa->fsx_projid))) return -EINVAL; } /* Check extent size hints. */ if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) && !S_ISDIR(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) && !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return -EINVAL; /* * It is only valid to set the DAX flag on regular files and * directories on filesystems. */ if ((fa->fsx_xflags & FS_XFLAG_DAX) && !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; /* Extent size hints of zero turn off the flags. */ if (fa->fsx_extsize == 0) fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT); if (fa->fsx_cowextsize == 0) fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; return 0; } /** * vfs_fileattr_set - change miscellaneous file attributes * @idmap: idmap of the mount * @dentry: the object to change * @fa: fileattr pointer * * After verifying permissions, call i_op->fileattr_set() callback, if * exists. * * Verifying attributes involves retrieving current attributes with * i_op->fileattr_get(), this also allows initializing attributes that have * not been set by the caller to current values. Inode lock is held * thoughout to prevent racing with another instance. * * Return: 0 on success, or a negative error on failure. */ int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct file_kattr *fa) { struct inode *inode = d_inode(dentry); struct file_kattr old_ma = {}; int err; if (!inode->i_op->fileattr_set) return -ENOIOCTLCMD; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; inode_lock(inode); err = vfs_fileattr_get(dentry, &old_ma); if (!err) { /* initialize missing bits from old_ma */ if (fa->flags_valid) { fa->fsx_xflags |= old_ma.fsx_xflags & ~FS_XFLAG_COMMON; fa->fsx_extsize = old_ma.fsx_extsize; fa->fsx_nextents = old_ma.fsx_nextents; fa->fsx_projid = old_ma.fsx_projid; fa->fsx_cowextsize = old_ma.fsx_cowextsize; } else { fa->flags |= old_ma.flags & ~FS_COMMON_FL; } err = fileattr_set_prepare(inode, &old_ma, fa); if (err) goto out; err = security_inode_file_setattr(dentry, fa); if (err) goto out; err = inode->i_op->fileattr_set(idmap, dentry, fa); if (err) goto out; } out: inode_unlock(inode); return err; } EXPORT_SYMBOL(vfs_fileattr_set); int ioctl_getflags(struct file *file, unsigned int __user *argp) { struct file_kattr fa = { .flags_valid = true }; /* hint only */ int err; err = vfs_fileattr_get(file->f_path.dentry, &fa); if (!err) err = put_user(fa.flags, argp); return err; } EXPORT_SYMBOL(ioctl_getflags); int ioctl_setflags(struct file *file, unsigned int __user *argp) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct dentry *dentry = file->f_path.dentry; struct file_kattr fa; unsigned int flags; int err; err = get_user(flags, argp); if (!err) { err = mnt_want_write_file(file); if (!err) { fileattr_fill_flags(&fa, flags); err = vfs_fileattr_set(idmap, dentry, &fa); mnt_drop_write_file(file); } } return err; } EXPORT_SYMBOL(ioctl_setflags); int ioctl_fsgetxattr(struct file *file, void __user *argp) { struct file_kattr fa = { .fsx_valid = true }; /* hint only */ int err; err = vfs_fileattr_get(file->f_path.dentry, &fa); if (!err) err = copy_fsxattr_to_user(&fa, argp); return err; } EXPORT_SYMBOL(ioctl_fsgetxattr); int ioctl_fssetxattr(struct file *file, void __user *argp) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct dentry *dentry = file->f_path.dentry; struct file_kattr fa; int err; err = copy_fsxattr_from_user(&fa, argp); if (!err) { err = mnt_want_write_file(file); if (!err) { err = vfs_fileattr_set(idmap, dentry, &fa); mnt_drop_write_file(file); } } return err; } EXPORT_SYMBOL(ioctl_fssetxattr); SYSCALL_DEFINE5(file_getattr, int, dfd, const char __user *, filename, struct file_attr __user *, ufattr, size_t, usize, unsigned int, at_flags) { struct path filepath __free(path_put) = {}; struct filename *name __free(putname) = NULL; unsigned int lookup_flags = 0; struct file_attr fattr; struct file_kattr fa; int error; BUILD_BUG_ON(sizeof(struct file_attr) < FILE_ATTR_SIZE_VER0); BUILD_BUG_ON(sizeof(struct file_attr) != FILE_ATTR_SIZE_LATEST); if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; if (!(at_flags & AT_SYMLINK_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (usize > PAGE_SIZE) return -E2BIG; if (usize < FILE_ATTR_SIZE_VER0) return -EINVAL; name = getname_maybe_null(filename, at_flags); if (IS_ERR(name)) return PTR_ERR(name); if (!name && dfd >= 0) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; filepath = fd_file(f)->f_path; path_get(&filepath); } else { error = filename_lookup(dfd, name, lookup_flags, &filepath, NULL); if (error) return error; } error = vfs_fileattr_get(filepath.dentry, &fa); if (error == -ENOIOCTLCMD || error == -ENOTTY) error = -EOPNOTSUPP; if (error) return error; fileattr_to_file_attr(&fa, &fattr); error = copy_struct_to_user(ufattr, usize, &fattr, sizeof(struct file_attr), NULL); return error; } SYSCALL_DEFINE5(file_setattr, int, dfd, const char __user *, filename, struct file_attr __user *, ufattr, size_t, usize, unsigned int, at_flags) { struct path filepath __free(path_put) = {}; struct filename *name __free(putname) = NULL; unsigned int lookup_flags = 0; struct file_attr fattr; struct file_kattr fa; int error; BUILD_BUG_ON(sizeof(struct file_attr) < FILE_ATTR_SIZE_VER0); BUILD_BUG_ON(sizeof(struct file_attr) != FILE_ATTR_SIZE_LATEST); if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return -EINVAL; if (!(at_flags & AT_SYMLINK_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (usize > PAGE_SIZE) return -E2BIG; if (usize < FILE_ATTR_SIZE_VER0) return -EINVAL; error = copy_struct_from_user(&fattr, sizeof(struct file_attr), ufattr, usize); if (error) return error; error = file_attr_to_fileattr(&fattr, &fa); if (error) return error; name = getname_maybe_null(filename, at_flags); if (IS_ERR(name)) return PTR_ERR(name); if (!name && dfd >= 0) { CLASS(fd, f)(dfd); if (fd_empty(f)) return -EBADF; filepath = fd_file(f)->f_path; path_get(&filepath); } else { error = filename_lookup(dfd, name, lookup_flags, &filepath, NULL); if (error) return error; } error = mnt_want_write(filepath.mnt); if (!error) { error = vfs_fileattr_set(mnt_idmap(filepath.mnt), filepath.dentry, &fa); if (error == -ENOIOCTLCMD || error == -ENOTTY) error = -EOPNOTSUPP; mnt_drop_write(filepath.mnt); } return error; } |
| 333 5 328 328 20 20 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 329 329 31 31 2 2 70 70 70 70 466 6 6 6 5 2 6 5 5 5 5 5 5 5 6 2 5 5 5 1 1 307 305 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/libfs.c * Library for filesystems writers. */ #include <linux/blkdev.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/mount.h> #include <linux/vfs.h> #include <linux/quotaops.h> #include <linux/mutex.h> #include <linux/namei.h> #include <linux/exportfs.h> #include <linux/iversion.h> #include <linux/writeback.h> #include <linux/buffer_head.h> /* sync_mapping_buffers */ #include <linux/fs_context.h> #include <linux/pseudo_fs.h> #include <linux/fsnotify.h> #include <linux/unicode.h> #include <linux/fscrypt.h> #include <linux/pidfs.h> #include <linux/uaccess.h> #include "internal.h" int simple_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->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9); return 0; } EXPORT_SYMBOL(simple_getattr); int simple_statfs(struct dentry *dentry, struct kstatfs *buf) { u64 id = huge_encode_dev(dentry->d_sb->s_dev); buf->f_fsid = u64_to_fsid(id); buf->f_type = dentry->d_sb->s_magic; buf->f_bsize = PAGE_SIZE; buf->f_namelen = NAME_MAX; return 0; } EXPORT_SYMBOL(simple_statfs); /* * Retaining negative dentries for an in-memory filesystem just wastes * memory and lookup time: arrange for them to be deleted immediately. */ int always_delete_dentry(const struct dentry *dentry) { return 1; } EXPORT_SYMBOL(always_delete_dentry); /* * Lookup the data. This is trivial - if the dentry didn't already * exist, we know it is negative. Set d_op to delete negative dentries. */ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); if (!dentry->d_op && !(dentry->d_flags & DCACHE_DONTCACHE)) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_DONTCACHE; spin_unlock(&dentry->d_lock); } if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir)) return NULL; d_add(dentry, NULL); return NULL; } EXPORT_SYMBOL(simple_lookup); int dcache_dir_open(struct inode *inode, struct file *file) { file->private_data = d_alloc_cursor(file->f_path.dentry); return file->private_data ? 0 : -ENOMEM; } EXPORT_SYMBOL(dcache_dir_open); int dcache_dir_close(struct inode *inode, struct file *file) { dput(file->private_data); return 0; } EXPORT_SYMBOL(dcache_dir_close); /* parent is locked at least shared */ /* * Returns an element of siblings' list. * We are looking for <count>th positive after <p>; if * found, dentry is grabbed and returned to caller. * If no such element exists, NULL is returned. */ static struct dentry *scan_positives(struct dentry *cursor, struct hlist_node **p, loff_t count, struct dentry *last) { struct dentry *dentry = cursor->d_parent, *found = NULL; spin_lock(&dentry->d_lock); while (*p) { struct dentry *d = hlist_entry(*p, struct dentry, d_sib); p = &d->d_sib.next; // we must at least skip cursors, to avoid livelocks if (d->d_flags & DCACHE_DENTRY_CURSOR) continue; if (simple_positive(d) && !--count) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) found = dget_dlock(d); spin_unlock(&d->d_lock); if (likely(found)) break; count = 1; } if (need_resched()) { if (!hlist_unhashed(&cursor->d_sib)) __hlist_del(&cursor->d_sib); hlist_add_behind(&cursor->d_sib, &d->d_sib); p = &cursor->d_sib.next; spin_unlock(&dentry->d_lock); cond_resched(); spin_lock(&dentry->d_lock); } } spin_unlock(&dentry->d_lock); dput(last); return found; } loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) { struct dentry *dentry = file->f_path.dentry; switch (whence) { case 1: offset += file->f_pos; fallthrough; case 0: if (offset >= 0) break; fallthrough; default: return -EINVAL; } if (offset != file->f_pos) { struct dentry *cursor = file->private_data; struct dentry *to = NULL; inode_lock_shared(dentry->d_inode); if (offset > 2) to = scan_positives(cursor, &dentry->d_children.first, offset - 2, NULL); spin_lock(&dentry->d_lock); hlist_del_init(&cursor->d_sib); if (to) hlist_add_behind(&cursor->d_sib, &to->d_sib); spin_unlock(&dentry->d_lock); dput(to); file->f_pos = offset; inode_unlock_shared(dentry->d_inode); } return offset; } EXPORT_SYMBOL(dcache_dir_lseek); /* * Directory is locked and all positive dentries in it are safe, since * for ramfs-type trees they can't go away without unlink() or rmdir(), * both impossible due to the lock on directory. */ int dcache_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct dentry *cursor = file->private_data; struct dentry *next = NULL; struct hlist_node **p; if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos == 2) p = &dentry->d_children.first; else p = &cursor->d_sib.next; while ((next = scan_positives(cursor, p, 1, next)) != NULL) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, d_inode(next)->i_ino, fs_umode_to_dtype(d_inode(next)->i_mode))) break; ctx->pos++; p = &next->d_sib.next; } spin_lock(&dentry->d_lock); hlist_del_init(&cursor->d_sib); if (next) hlist_add_before(&cursor->d_sib, &next->d_sib); spin_unlock(&dentry->d_lock); dput(next); return 0; } EXPORT_SYMBOL(dcache_readdir); ssize_t generic_read_dir(struct file *filp, char __user *buf, size_t siz, loff_t *ppos) { return -EISDIR; } EXPORT_SYMBOL(generic_read_dir); const struct file_operations simple_dir_operations = { .open = dcache_dir_open, .release = dcache_dir_close, .llseek = dcache_dir_lseek, .read = generic_read_dir, .iterate_shared = dcache_readdir, .fsync = noop_fsync, }; EXPORT_SYMBOL(simple_dir_operations); const struct inode_operations simple_dir_inode_operations = { .lookup = simple_lookup, }; EXPORT_SYMBOL(simple_dir_inode_operations); /* simple_offset_add() never assigns these to a dentry */ enum { DIR_OFFSET_FIRST = 2, /* Find first real entry */ DIR_OFFSET_EOD = S32_MAX, }; /* simple_offset_add() allocation range */ enum { DIR_OFFSET_MIN = DIR_OFFSET_FIRST + 1, DIR_OFFSET_MAX = DIR_OFFSET_EOD - 1, }; static void offset_set(struct dentry *dentry, long offset) { dentry->d_fsdata = (void *)offset; } static long dentry2offset(struct dentry *dentry) { return (long)dentry->d_fsdata; } static struct lock_class_key simple_offset_lock_class; /** * simple_offset_init - initialize an offset_ctx * @octx: directory offset map to be initialized * */ void simple_offset_init(struct offset_ctx *octx) { mt_init_flags(&octx->mt, MT_FLAGS_ALLOC_RANGE); lockdep_set_class(&octx->mt.ma_lock, &simple_offset_lock_class); octx->next_offset = DIR_OFFSET_MIN; } /** * simple_offset_add - Add an entry to a directory's offset map * @octx: directory offset ctx to be updated * @dentry: new dentry being added * * Returns zero on success. @octx and the dentry's offset are updated. * Otherwise, a negative errno value is returned. */ int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry) { unsigned long offset; int ret; if (dentry2offset(dentry) != 0) return -EBUSY; ret = mtree_alloc_cyclic(&octx->mt, &offset, dentry, DIR_OFFSET_MIN, DIR_OFFSET_MAX, &octx->next_offset, GFP_KERNEL); if (unlikely(ret < 0)) return ret == -EBUSY ? -ENOSPC : ret; offset_set(dentry, offset); return 0; } static int simple_offset_replace(struct offset_ctx *octx, struct dentry *dentry, long offset) { int ret; ret = mtree_store(&octx->mt, offset, dentry, GFP_KERNEL); if (ret) return ret; offset_set(dentry, offset); return 0; } /** * simple_offset_remove - Remove an entry to a directory's offset map * @octx: directory offset ctx to be updated * @dentry: dentry being removed * */ void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry) { long offset; offset = dentry2offset(dentry); if (offset == 0) return; mtree_erase(&octx->mt, offset); offset_set(dentry, 0); } /** * simple_offset_rename - handle directory offsets for rename * @old_dir: parent directory of source entry * @old_dentry: dentry of source entry * @new_dir: parent_directory of destination entry * @new_dentry: dentry of destination * * Caller provides appropriate serialization. * * User space expects the directory offset value of the replaced * (new) directory entry to be unchanged after a rename. * * Returns zero on success, a negative errno value on failure. */ int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir); struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir); long new_offset = dentry2offset(new_dentry); simple_offset_remove(old_ctx, old_dentry); if (new_offset) { offset_set(new_dentry, 0); return simple_offset_replace(new_ctx, old_dentry, new_offset); } return simple_offset_add(new_ctx, old_dentry); } /** * simple_offset_rename_exchange - exchange rename with directory offsets * @old_dir: parent of dentry being moved * @old_dentry: dentry being moved * @new_dir: destination parent * @new_dentry: destination dentry * * This API preserves the directory offset values. Caller provides * appropriate serialization. * * Returns zero on success. Otherwise a negative errno is returned and the * rename is rolled back. */ int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct offset_ctx *old_ctx = old_dir->i_op->get_offset_ctx(old_dir); struct offset_ctx *new_ctx = new_dir->i_op->get_offset_ctx(new_dir); long old_index = dentry2offset(old_dentry); long new_index = dentry2offset(new_dentry); int ret; simple_offset_remove(old_ctx, old_dentry); simple_offset_remove(new_ctx, new_dentry); ret = simple_offset_replace(new_ctx, old_dentry, new_index); if (ret) goto out_restore; ret = simple_offset_replace(old_ctx, new_dentry, old_index); if (ret) { simple_offset_remove(new_ctx, old_dentry); goto out_restore; } ret = simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); if (ret) { simple_offset_remove(new_ctx, old_dentry); simple_offset_remove(old_ctx, new_dentry); goto out_restore; } return 0; out_restore: (void)simple_offset_replace(old_ctx, old_dentry, old_index); (void)simple_offset_replace(new_ctx, new_dentry, new_index); return ret; } /** * simple_offset_destroy - Release offset map * @octx: directory offset ctx that is about to be destroyed * * During fs teardown (eg. umount), a directory's offset map might still * contain entries. xa_destroy() cleans out anything that remains. */ void simple_offset_destroy(struct offset_ctx *octx) { mtree_destroy(&octx->mt); } /** * offset_dir_llseek - Advance the read position of a directory descriptor * @file: an open directory whose position is to be updated * @offset: a byte offset * @whence: enumerator describing the starting position for this update * * SEEK_END, SEEK_DATA, and SEEK_HOLE are not supported for directories. * * Returns the updated read position if successful; otherwise a * negative errno is returned and the read position remains unchanged. */ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_CUR: offset += file->f_pos; fallthrough; case SEEK_SET: if (offset >= 0) break; fallthrough; default: return -EINVAL; } return vfs_setpos(file, offset, LONG_MAX); } static struct dentry *find_positive_dentry(struct dentry *parent, struct dentry *dentry, bool next) { struct dentry *found = NULL; spin_lock(&parent->d_lock); if (next) dentry = d_next_sibling(dentry); else if (!dentry) dentry = d_first_child(parent); hlist_for_each_entry_from(dentry, d_sib) { if (!simple_positive(dentry)) continue; spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(dentry)) found = dget_dlock(dentry); spin_unlock(&dentry->d_lock); if (likely(found)) break; } spin_unlock(&parent->d_lock); return found; } static noinline_for_stack struct dentry * offset_dir_lookup(struct dentry *parent, loff_t offset) { struct inode *inode = d_inode(parent); struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *child, *found = NULL; MA_STATE(mas, &octx->mt, offset, offset); if (offset == DIR_OFFSET_FIRST) found = find_positive_dentry(parent, NULL, false); else { rcu_read_lock(); child = mas_find_rev(&mas, DIR_OFFSET_MIN); found = find_positive_dentry(parent, child, false); rcu_read_unlock(); } return found; } static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) { struct inode *inode = d_inode(dentry); return dir_emit(ctx, dentry->d_name.name, dentry->d_name.len, inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } static void offset_iterate_dir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; struct dentry *dentry; dentry = offset_dir_lookup(dir, ctx->pos); if (!dentry) goto out_eod; while (true) { struct dentry *next; ctx->pos = dentry2offset(dentry); if (!offset_dir_emit(ctx, dentry)) break; next = find_positive_dentry(dir, dentry, true); dput(dentry); if (!next) goto out_eod; dentry = next; } dput(dentry); return; out_eod: ctx->pos = DIR_OFFSET_EOD; } /** * offset_readdir - Emit entries starting at offset @ctx->pos * @file: an open directory to iterate over * @ctx: directory iteration context * * Caller must hold @file's i_rwsem to prevent insertion or removal of * entries during this call. * * On entry, @ctx->pos contains an offset that represents the first entry * to be read from the directory. * * The operation continues until there are no more entries to read, or * until the ctx->actor indicates there is no more space in the caller's * output buffer. * * On return, @ctx->pos contains an offset that will read the next entry * in this directory when offset_readdir() is called again with @ctx. * Caller places this value in the d_off field of the last entry in the * user's buffer. * * Return values: * %0 - Complete */ static int offset_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; lockdep_assert_held(&d_inode(dir)->i_rwsem); if (!dir_emit_dots(file, ctx)) return 0; if (ctx->pos != DIR_OFFSET_EOD) offset_iterate_dir(file, ctx); return 0; } const struct file_operations simple_offset_dir_operations = { .llseek = offset_dir_llseek, .iterate_shared = offset_readdir, .read = generic_read_dir, .fsync = noop_fsync, }; struct dentry *find_next_child(struct dentry *parent, struct dentry *prev) { struct dentry *child = NULL, *d; spin_lock(&parent->d_lock); d = prev ? d_next_sibling(prev) : d_first_child(parent); hlist_for_each_entry_from(d, d_sib) { if (simple_positive(d)) { spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(d)) child = dget_dlock(d); spin_unlock(&d->d_lock); if (likely(child)) break; } } spin_unlock(&parent->d_lock); dput(prev); return child; } EXPORT_SYMBOL(find_next_child); static void __simple_recursive_removal(struct dentry *dentry, void (*callback)(struct dentry *), bool locked) { struct dentry *this = dget(dentry); while (true) { struct dentry *victim = NULL, *child; struct inode *inode = this->d_inode; inode_lock_nested(inode, I_MUTEX_CHILD); if (d_is_dir(this)) inode->i_flags |= S_DEAD; while ((child = find_next_child(this, victim)) == NULL) { // kill and ascend // update metadata while it's still locked inode_set_ctime_current(inode); clear_nlink(inode); inode_unlock(inode); victim = this; this = this->d_parent; inode = this->d_inode; if (!locked || victim != dentry) inode_lock_nested(inode, I_MUTEX_CHILD); if (simple_positive(victim)) { d_invalidate(victim); // avoid lost mounts if (callback) callback(victim); fsnotify_delete(inode, d_inode(victim), victim); dput(victim); // unpin it } if (victim == dentry) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (d_is_dir(dentry)) drop_nlink(inode); if (!locked) inode_unlock(inode); dput(dentry); return; } } inode_unlock(inode); this = child; } } void simple_recursive_removal(struct dentry *dentry, void (*callback)(struct dentry *)) { return __simple_recursive_removal(dentry, callback, false); } EXPORT_SYMBOL(simple_recursive_removal); /* caller holds parent directory with I_MUTEX_PARENT */ void locked_recursive_removal(struct dentry *dentry, void (*callback)(struct dentry *)) { return __simple_recursive_removal(dentry, callback, true); } EXPORT_SYMBOL(locked_recursive_removal); static const struct super_operations simple_super_operations = { .statfs = simple_statfs, }; static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc) { struct pseudo_fs_context *ctx = fc->fs_private; struct inode *root; s->s_maxbytes = MAX_LFS_FILESIZE; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = ctx->magic; s->s_op = ctx->ops ?: &simple_super_operations; s->s_export_op = ctx->eops; s->s_xattr = ctx->xattr; s->s_time_gran = 1; root = new_inode(s); if (!root) return -ENOMEM; /* * since this is the first inode, make it number 1. New inodes created * after this must take care not to collide with it (by passing * max_reserved of 1 to iunique). */ root->i_ino = 1; root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR; simple_inode_init_ts(root); s->s_root = d_make_root(root); if (!s->s_root) return -ENOMEM; set_default_d_op(s, ctx->dops); return 0; } static int pseudo_fs_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, pseudo_fs_fill_super); } static void pseudo_fs_free(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations pseudo_fs_context_ops = { .free = pseudo_fs_free, .get_tree = pseudo_fs_get_tree, }; /* * Common helper for pseudo-filesystems (sockfs, pipefs, bdev - stuff that * will never be mountable) */ struct pseudo_fs_context *init_pseudo(struct fs_context *fc, unsigned long magic) { struct pseudo_fs_context *ctx; ctx = kzalloc(sizeof(struct pseudo_fs_context), GFP_KERNEL); if (likely(ctx)) { ctx->magic = magic; fc->fs_private = ctx; fc->ops = &pseudo_fs_context_ops; fc->sb_flags |= SB_NOUSER; fc->global = true; } return ctx; } EXPORT_SYMBOL(init_pseudo); int simple_open(struct inode *inode, struct file *file) { if (inode->i_private) file->private_data = inode->i_private; return 0; } EXPORT_SYMBOL(simple_open); int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); inc_nlink(inode); ihold(inode); dget(dentry); d_instantiate(dentry, inode); return 0; } EXPORT_SYMBOL(simple_link); int simple_empty(struct dentry *dentry) { struct dentry *child; int ret = 0; spin_lock(&dentry->d_lock); hlist_for_each_entry(child, &dentry->d_children, d_sib) { spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED); if (simple_positive(child)) { spin_unlock(&child->d_lock); goto out; } spin_unlock(&child->d_lock); } ret = 1; out: spin_unlock(&dentry->d_lock); return ret; } EXPORT_SYMBOL(simple_empty); int simple_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); drop_nlink(inode); dput(dentry); return 0; } EXPORT_SYMBOL(simple_unlink); int simple_rmdir(struct inode *dir, struct dentry *dentry) { if (!simple_empty(dentry)) return -ENOTEMPTY; drop_nlink(d_inode(dentry)); simple_unlink(dir, dentry); drop_nlink(dir); return 0; } EXPORT_SYMBOL(simple_rmdir); /** * simple_rename_timestamp - update the various inode timestamps for rename * @old_dir: old parent directory * @old_dentry: dentry that is being renamed * @new_dir: new parent directory * @new_dentry: target for rename * * POSIX mandates that the old and new parent directories have their ctime and * mtime updated, and that inodes of @old_dentry and @new_dentry (if any), have * their ctime updated. */ void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct inode *newino = d_inode(new_dentry); inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir)); if (new_dir != old_dir) inode_set_mtime_to_ts(new_dir, inode_set_ctime_current(new_dir)); inode_set_ctime_current(d_inode(old_dentry)); if (newino) inode_set_ctime_current(newino); } EXPORT_SYMBOL_GPL(simple_rename_timestamp); int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { bool old_is_dir = d_is_dir(old_dentry); bool new_is_dir = d_is_dir(new_dentry); if (old_dir != new_dir && old_is_dir != new_is_dir) { if (old_is_dir) { drop_nlink(old_dir); inc_nlink(new_dir); } else { drop_nlink(new_dir); inc_nlink(old_dir); } } simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); return 0; } EXPORT_SYMBOL_GPL(simple_rename_exchange); int simple_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { int they_are_dirs = d_is_dir(old_dentry); if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) return -EINVAL; if (flags & RENAME_EXCHANGE) return simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); if (!simple_empty(new_dentry)) return -ENOTEMPTY; if (d_really_is_positive(new_dentry)) { simple_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); } simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); return 0; } EXPORT_SYMBOL(simple_rename); /** * simple_setattr - setattr for simple filesystem * @idmap: idmap of the target mount * @dentry: dentry * @iattr: iattr structure * * Returns 0 on success, -error on failure. * * simple_setattr is a simple ->setattr implementation without a proper * implementation of size changes. * * It can either be used for in-memory filesystems or special files * on simple regular filesystems. Anything that needs to change on-disk * or wire state on size changes needs its own setattr method. */ int simple_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); int error; error = setattr_prepare(idmap, dentry, iattr); if (error) return error; if (iattr->ia_valid & ATTR_SIZE) truncate_setsize(inode, iattr->ia_size); setattr_copy(idmap, inode, iattr); mark_inode_dirty(inode); return 0; } EXPORT_SYMBOL(simple_setattr); static int simple_read_folio(struct file *file, struct folio *folio) { folio_zero_range(folio, 0, folio_size(folio)); flush_dcache_folio(folio); folio_mark_uptodate(folio); folio_unlock(folio); return 0; } int simple_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { struct folio *folio; folio = __filemap_get_folio(mapping, pos / PAGE_SIZE, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); *foliop = folio; if (!folio_test_uptodate(folio) && (len != folio_size(folio))) { size_t from = offset_in_folio(folio, pos); folio_zero_segments(folio, 0, from, from + len, folio_size(folio)); } return 0; } EXPORT_SYMBOL(simple_write_begin); /** * simple_write_end - .write_end helper for non-block-device FSes * @iocb: kernel I/O control block * @mapping: " * @pos: " * @len: " * @copied: " * @folio: " * @fsdata: " * * simple_write_end does the minimum needed for updating a folio after * writing is done. It has the same API signature as the .write_end of * address_space_operations vector. So it can just be set onto .write_end for * FSes that don't need any other processing. i_rwsem is assumed to be held * exclusively. * Block based filesystems should use generic_write_end(). * NOTE: Even though i_size might get updated by this function, mark_inode_dirty * is not called, so a filesystem that actually does store data in .write_inode * should extend on what's done here with a call to mark_inode_dirty() in the * case that i_size has changed. * * Use *ONLY* with simple_read_folio() */ static int simple_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 = folio->mapping->host; loff_t last_pos = pos + copied; /* zero the stale part of the folio if we did a short copy */ if (!folio_test_uptodate(folio)) { if (copied < len) { size_t from = offset_in_folio(folio, pos); folio_zero_range(folio, from + copied, len - copied); } folio_mark_uptodate(folio); } /* * No need to use i_size_read() here, the i_size * cannot change under us because we hold the i_rwsem. */ if (last_pos > inode->i_size) i_size_write(inode, last_pos); folio_mark_dirty(folio); folio_unlock(folio); folio_put(folio); return copied; } /* * Provides ramfs-style behavior: data in the pagecache, but no writeback. */ const struct address_space_operations ram_aops = { .read_folio = simple_read_folio, .write_begin = simple_write_begin, .write_end = simple_write_end, .dirty_folio = noop_dirty_folio, }; EXPORT_SYMBOL(ram_aops); /* * the inodes created here are not hashed. If you use iunique to generate * unique inode values later for this filesystem, then you must take care * to pass it an appropriate max_reserved value to avoid collisions. */ int simple_fill_super(struct super_block *s, unsigned long magic, const struct tree_descr *files) { struct inode *inode; struct dentry *dentry; int i; s->s_blocksize = PAGE_SIZE; s->s_blocksize_bits = PAGE_SHIFT; s->s_magic = magic; s->s_op = &simple_super_operations; s->s_time_gran = 1; inode = new_inode(s); if (!inode) return -ENOMEM; /* * because the root inode is 1, the files array must not contain an * entry at index 1 */ inode->i_ino = 1; inode->i_mode = S_IFDIR | 0755; simple_inode_init_ts(inode); inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; set_nlink(inode, 2); s->s_root = d_make_root(inode); if (!s->s_root) return -ENOMEM; for (i = 0; !files->name || files->name[0]; i++, files++) { if (!files->name) continue; /* warn if it tries to conflict with the root inode */ if (unlikely(i == 1)) printk(KERN_WARNING "%s: %s passed in a files array" "with an index of 1!\n", __func__, s->s_type->name); dentry = d_alloc_name(s->s_root, files->name); if (!dentry) return -ENOMEM; inode = new_inode(s); if (!inode) { dput(dentry); return -ENOMEM; } inode->i_mode = S_IFREG | files->mode; simple_inode_init_ts(inode); inode->i_fop = files->ops; inode->i_ino = i; d_add(dentry, inode); } return 0; } EXPORT_SYMBOL(simple_fill_super); static DEFINE_SPINLOCK(pin_fs_lock); int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count) { struct vfsmount *mnt = NULL; spin_lock(&pin_fs_lock); if (unlikely(!*mount)) { spin_unlock(&pin_fs_lock); mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL); if (IS_ERR(mnt)) return PTR_ERR(mnt); spin_lock(&pin_fs_lock); if (!*mount) *mount = mnt; } mntget(*mount); ++*count; spin_unlock(&pin_fs_lock); mntput(mnt); return 0; } EXPORT_SYMBOL(simple_pin_fs); void simple_release_fs(struct vfsmount **mount, int *count) { struct vfsmount *mnt; spin_lock(&pin_fs_lock); mnt = *mount; if (!--*count) *mount = NULL; spin_unlock(&pin_fs_lock); mntput(mnt); } EXPORT_SYMBOL(simple_release_fs); /** * simple_read_from_buffer - copy data from the buffer to user space * @to: the user space buffer to read to * @count: the maximum number of bytes to read * @ppos: the current position in the buffer * @from: the buffer to read from * @available: the size of the buffer * * The simple_read_from_buffer() function reads up to @count bytes from the * buffer @from at offset @ppos into the user space address starting at @to. * * On success, the number of bytes read is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available) { loff_t pos = *ppos; size_t ret; if (pos < 0) return -EINVAL; if (pos >= available || !count) return 0; if (count > available - pos) count = available - pos; ret = copy_to_user(to, from + pos, count); if (ret == count) return -EFAULT; count -= ret; *ppos = pos + count; return count; } EXPORT_SYMBOL(simple_read_from_buffer); /** * simple_write_to_buffer - copy data from user space to the buffer * @to: the buffer to write to * @available: the size of the buffer * @ppos: the current position in the buffer * @from: the user space buffer to read from * @count: the maximum number of bytes to read * * The simple_write_to_buffer() function reads up to @count bytes from the user * space address starting at @from into the buffer @to at offset @ppos. * * On success, the number of bytes written is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count) { loff_t pos = *ppos; size_t res; if (pos < 0) return -EINVAL; if (pos >= available || !count) return 0; if (count > available - pos) count = available - pos; res = copy_from_user(to + pos, from, count); if (res == count) return -EFAULT; count -= res; *ppos = pos + count; return count; } EXPORT_SYMBOL(simple_write_to_buffer); /** * memory_read_from_buffer - copy data from the buffer * @to: the kernel space buffer to read to * @count: the maximum number of bytes to read * @ppos: the current position in the buffer * @from: the buffer to read from * @available: the size of the buffer * * The memory_read_from_buffer() function reads up to @count bytes from the * buffer @from at offset @ppos into the kernel space address starting at @to. * * On success, the number of bytes read is returned and the offset @ppos is * advanced by this number, or negative value is returned on error. **/ ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos, const void *from, size_t available) { loff_t pos = *ppos; if (pos < 0) return -EINVAL; if (pos >= available) return 0; if (count > available - pos) count = available - pos; memcpy(to, from + pos, count); *ppos = pos + count; return count; } EXPORT_SYMBOL(memory_read_from_buffer); /* * Transaction based IO. * The file expects a single write which triggers the transaction, and then * possibly a read which collects the result - which is stored in a * file-local buffer. */ void simple_transaction_set(struct file *file, size_t n) { struct simple_transaction_argresp *ar = file->private_data; BUG_ON(n > SIMPLE_TRANSACTION_LIMIT); /* * The barrier ensures that ar->size will really remain zero until * ar->data is ready for reading. */ smp_mb(); ar->size = n; } EXPORT_SYMBOL(simple_transaction_set); char *simple_transaction_get(struct file *file, const char __user *buf, size_t size) { struct simple_transaction_argresp *ar; static DEFINE_SPINLOCK(simple_transaction_lock); if (size > SIMPLE_TRANSACTION_LIMIT - 1) return ERR_PTR(-EFBIG); ar = (struct simple_transaction_argresp *)get_zeroed_page(GFP_KERNEL); if (!ar) return ERR_PTR(-ENOMEM); spin_lock(&simple_transaction_lock); /* only one write allowed per open */ if (file->private_data) { spin_unlock(&simple_transaction_lock); free_page((unsigned long)ar); return ERR_PTR(-EBUSY); } file->private_data = ar; spin_unlock(&simple_transaction_lock); if (copy_from_user(ar->data, buf, size)) return ERR_PTR(-EFAULT); return ar->data; } EXPORT_SYMBOL(simple_transaction_get); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos) { struct simple_transaction_argresp *ar = file->private_data; if (!ar) return 0; return simple_read_from_buffer(buf, size, pos, ar->data, ar->size); } EXPORT_SYMBOL(simple_transaction_read); int simple_transaction_release(struct inode *inode, struct file *file) { free_page((unsigned long)file->private_data); return 0; } EXPORT_SYMBOL(simple_transaction_release); /* Simple attribute files */ struct simple_attr { int (*get)(void *, u64 *); int (*set)(void *, u64); char get_buf[24]; /* enough to store a u64 and "\n\0" */ char set_buf[24]; void *data; const char *fmt; /* format for read operation */ struct mutex mutex; /* protects access to these buffers */ }; /* simple_attr_open is called by an actual attribute open file operation * to set the attribute specific access operations. */ int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt) { struct simple_attr *attr; attr = kzalloc(sizeof(*attr), GFP_KERNEL); if (!attr) return -ENOMEM; attr->get = get; attr->set = set; attr->data = inode->i_private; attr->fmt = fmt; mutex_init(&attr->mutex); file->private_data = attr; return nonseekable_open(inode, file); } EXPORT_SYMBOL_GPL(simple_attr_open); int simple_attr_release(struct inode *inode, struct file *file) { kfree(file->private_data); return 0; } EXPORT_SYMBOL_GPL(simple_attr_release); /* GPL-only? This? Really? */ /* read from the buffer that is filled with the get function */ ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { struct simple_attr *attr; size_t size; ssize_t ret; attr = file->private_data; if (!attr->get) return -EACCES; ret = mutex_lock_interruptible(&attr->mutex); if (ret) return ret; if (*ppos && attr->get_buf[0]) { /* continued read */ size = strlen(attr->get_buf); } else { /* first read */ u64 val; ret = attr->get(attr->data, &val); if (ret) goto out; size = scnprintf(attr->get_buf, sizeof(attr->get_buf), attr->fmt, (unsigned long long)val); } ret = simple_read_from_buffer(buf, len, ppos, attr->get_buf, size); out: mutex_unlock(&attr->mutex); return ret; } EXPORT_SYMBOL_GPL(simple_attr_read); /* interpret the buffer as a number to call the set function with */ static ssize_t simple_attr_write_xsigned(struct file *file, const char __user *buf, size_t len, loff_t *ppos, bool is_signed) { struct simple_attr *attr; unsigned long long val; size_t size; ssize_t ret; attr = file->private_data; if (!attr->set) return -EACCES; ret = mutex_lock_interruptible(&attr->mutex); if (ret) return ret; ret = -EFAULT; size = min(sizeof(attr->set_buf) - 1, len); if (copy_from_user(attr->set_buf, buf, size)) goto out; attr->set_buf[size] = '\0'; if (is_signed) ret = kstrtoll(attr->set_buf, 0, &val); else ret = kstrtoull(attr->set_buf, 0, &val); if (ret) goto out; ret = attr->set(attr->data, val); if (ret == 0) ret = len; /* on success, claim we got the whole input */ out: mutex_unlock(&attr->mutex); return ret; } ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return simple_attr_write_xsigned(file, buf, len, ppos, false); } EXPORT_SYMBOL_GPL(simple_attr_write); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return simple_attr_write_xsigned(file, buf, len, ppos, true); } EXPORT_SYMBOL_GPL(simple_attr_write_signed); /** * generic_encode_ino32_fh - generic export_operations->encode_fh function * @inode: the object to encode * @fh: where to store the file handle fragment * @max_len: maximum length to store there (in 4 byte units) * @parent: parent directory inode, if wanted * * This generic encode_fh function assumes that the 32 inode number * is suitable for locating an inode, and that the generation number * can be used to check that it is still valid. It places them in the * filehandle fragment where export_decode_fh expects to find them. */ int generic_encode_ino32_fh(struct inode *inode, __u32 *fh, int *max_len, struct inode *parent) { struct fid *fid = (void *)fh; int len = *max_len; int type = FILEID_INO32_GEN; if (parent && (len < 4)) { *max_len = 4; return FILEID_INVALID; } else if (len < 2) { *max_len = 2; return FILEID_INVALID; } len = 2; fid->i32.ino = inode->i_ino; fid->i32.gen = inode->i_generation; if (parent) { fid->i32.parent_ino = parent->i_ino; fid->i32.parent_gen = parent->i_generation; len = 4; type = FILEID_INO32_GEN_PARENT; } *max_len = len; return type; } EXPORT_SYMBOL_GPL(generic_encode_ino32_fh); /** * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation * @sb: filesystem to do the file handle conversion on * @fid: file handle to convert * @fh_len: length of the file handle in bytes * @fh_type: type of file handle * @get_inode: filesystem callback to retrieve inode * * This function decodes @fid as long as it has one of the well-known * Linux filehandle types and calls @get_inode on it to retrieve the * inode for the object specified in the file handle. */ struct dentry *generic_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)) { struct inode *inode = NULL; if (fh_len < 2) return NULL; switch (fh_type) { case FILEID_INO32_GEN: case FILEID_INO32_GEN_PARENT: inode = get_inode(sb, fid->i32.ino, fid->i32.gen); break; } return d_obtain_alias(inode); } EXPORT_SYMBOL_GPL(generic_fh_to_dentry); /** * generic_fh_to_parent - generic helper for the fh_to_parent export operation * @sb: filesystem to do the file handle conversion on * @fid: file handle to convert * @fh_len: length of the file handle in bytes * @fh_type: type of file handle * @get_inode: filesystem callback to retrieve inode * * This function decodes @fid as long as it has one of the well-known * Linux filehandle types and calls @get_inode on it to retrieve the * inode for the _parent_ object specified in the file handle if it * is specified in the file handle, or NULL otherwise. */ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type, struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen)) { struct inode *inode = NULL; if (fh_len <= 2) return NULL; switch (fh_type) { case FILEID_INO32_GEN_PARENT: inode = get_inode(sb, fid->i32.parent_ino, (fh_len > 3 ? fid->i32.parent_gen : 0)); break; } return d_obtain_alias(inode); } EXPORT_SYMBOL_GPL(generic_fh_to_parent); /** * __generic_file_fsync - generic fsync implementation for simple filesystems * * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. */ int __generic_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; int err; int ret; err = file_write_and_wait_range(file, start, end); if (err) return err; inode_lock(inode); ret = sync_mapping_buffers(inode->i_mapping); if (!(inode->i_state & I_DIRTY_ALL)) goto out; if (datasync && !(inode->i_state & I_DIRTY_DATASYNC)) goto out; err = sync_inode_metadata(inode, 1); if (ret == 0) ret = err; out: inode_unlock(inode); /* check and advance again to catch errors after syncing out buffers */ err = file_check_and_advance_wb_err(file); if (ret == 0) ret = err; return ret; } EXPORT_SYMBOL(__generic_file_fsync); /** * generic_file_fsync - generic fsync implementation for simple filesystems * with flush * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * */ int generic_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct inode *inode = file->f_mapping->host; int err; err = __generic_file_fsync(file, start, end, datasync); if (err) return err; return blkdev_issue_flush(inode->i_sb->s_bdev); } EXPORT_SYMBOL(generic_file_fsync); /** * generic_check_addressable - Check addressability of file system * @blocksize_bits: log of file system block size * @num_blocks: number of blocks in file system * * Determine whether a file system with @num_blocks blocks (and a * block size of 2**@blocksize_bits) is addressable by the sector_t * and page cache of the system. Return 0 if so and -EFBIG otherwise. */ int generic_check_addressable(unsigned blocksize_bits, u64 num_blocks) { u64 last_fs_block = num_blocks - 1; u64 last_fs_page, max_bytes; if (check_shl_overflow(num_blocks, blocksize_bits, &max_bytes)) return -EFBIG; last_fs_page = (max_bytes >> PAGE_SHIFT) - 1; if (unlikely(num_blocks == 0)) return 0; if (blocksize_bits < 9) return -EINVAL; if ((last_fs_block > (sector_t)(~0ULL) >> (blocksize_bits - 9)) || (last_fs_page > (pgoff_t)(~0ULL))) { return -EFBIG; } return 0; } EXPORT_SYMBOL(generic_check_addressable); /* * No-op implementation of ->fsync for in-memory filesystems. */ int noop_fsync(struct file *file, loff_t start, loff_t end, int datasync) { return 0; } EXPORT_SYMBOL(noop_fsync); ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { /* * iomap based filesystems support direct I/O without need for * this callback. However, it still needs to be set in * inode->a_ops so that open/fcntl know that direct I/O is * generally supported. */ return -EINVAL; } EXPORT_SYMBOL_GPL(noop_direct_IO); /* Because kfree isn't assignment-compatible with void(void*) ;-/ */ void kfree_link(void *p) { kfree(p); } EXPORT_SYMBOL(kfree_link); struct inode *alloc_anon_inode(struct super_block *s) { static const struct address_space_operations anon_aops = { .dirty_folio = noop_dirty_folio, }; struct inode *inode = new_inode_pseudo(s); if (!inode) return ERR_PTR(-ENOMEM); inode->i_ino = get_next_ino(); inode->i_mapping->a_ops = &anon_aops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because mark_inode_dirty() will think * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; /* * Historically anonymous inodes don't have a type at all and * userspace has come to rely on this. */ inode->i_mode = S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_flags |= S_PRIVATE | S_ANON_INODE; simple_inode_init_ts(inode); return inode; } EXPORT_SYMBOL(alloc_anon_inode); /** * simple_nosetlease - generic helper for prohibiting leases * @filp: file pointer * @arg: type of lease to obtain * @flp: new lease supplied for insertion * @priv: private data for lm_setup operation * * Generic helper for filesystems that do not wish to allow leases to be set. * All arguments are ignored and it just returns -EINVAL. */ int simple_nosetlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { return -EINVAL; } EXPORT_SYMBOL(simple_nosetlease); /** * simple_get_link - generic helper to get the target of "fast" symlinks * @dentry: not used here * @inode: the symlink inode * @done: not used here * * Generic helper for filesystems to use for symlink inodes where a pointer to * the symlink target is stored in ->i_link. NOTE: this isn't normally called, * since as an optimization the path lookup code uses any non-NULL ->i_link * directly, without calling ->get_link(). But ->get_link() still must be set, * to mark the inode_operations as being for a symlink. * * Return: the symlink target */ const char *simple_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { return inode->i_link; } EXPORT_SYMBOL(simple_get_link); const struct inode_operations simple_symlink_inode_operations = { .get_link = simple_get_link, }; EXPORT_SYMBOL(simple_symlink_inode_operations); /* * Operations for a permanently empty directory. */ static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { return ERR_PTR(-ENOENT); } static int empty_dir_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return -EPERM; } static ssize_t empty_dir_listxattr(struct dentry *dentry, char *list, size_t size) { return -EOPNOTSUPP; } static const struct inode_operations empty_dir_inode_operations = { .lookup = empty_dir_lookup, .setattr = empty_dir_setattr, .listxattr = empty_dir_listxattr, }; static loff_t empty_dir_llseek(struct file *file, loff_t offset, int whence) { /* An empty directory has two entries . and .. at offsets 0 and 1 */ return generic_file_llseek_size(file, offset, whence, 2, 2); } static int empty_dir_readdir(struct file *file, struct dir_context *ctx) { dir_emit_dots(file, ctx); return 0; } static const struct file_operations empty_dir_operations = { .llseek = empty_dir_llseek, .read = generic_read_dir, .iterate_shared = empty_dir_readdir, .fsync = noop_fsync, }; void make_empty_dir_inode(struct inode *inode) { set_nlink(inode, 2); inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_rdev = 0; inode->i_size = 0; inode->i_blkbits = PAGE_SHIFT; inode->i_blocks = 0; inode->i_op = &empty_dir_inode_operations; inode->i_opflags &= ~IOP_XATTR; inode->i_fop = &empty_dir_operations; } bool is_empty_dir_inode(struct inode *inode) { return (inode->i_fop == &empty_dir_operations) && (inode->i_op == &empty_dir_inode_operations); } #if IS_ENABLED(CONFIG_UNICODE) /** * generic_ci_d_compare - generic d_compare implementation for casefolding filesystems * @dentry: dentry whose name we are checking against * @len: len of name of dentry * @str: str pointer to name of dentry * @name: Name to compare against * * Return: 0 if names match, 1 if mismatch, or -ERRNO */ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { const struct dentry *parent; const struct inode *dir; union shortname_store strbuf; struct qstr qstr; /* * Attempt a case-sensitive match first. It is cheaper and * should cover most lookups, including all the sane * applications that expect a case-sensitive filesystem. * * This comparison is safe under RCU because the caller * guarantees the consistency between str and len. See * __d_lookup_rcu_op_compare() for details. */ if (len == name->len && !memcmp(str, name->name, len)) return 0; parent = READ_ONCE(dentry->d_parent); dir = READ_ONCE(parent->d_inode); if (!dir || !IS_CASEFOLDED(dir)) return 1; qstr.len = len; qstr.name = str; /* * If the dentry name is stored in-line, then it may be concurrently * modified by a rename. If this happens, the VFS will eventually retry * the lookup, so it doesn't matter what ->d_compare() returns. * However, it's unsafe to call utf8_strncasecmp() with an unstable * string. Therefore, we have to copy the name into a temporary buffer. * As above, len is guaranteed to match str, so the shortname case * is exactly when str points to ->d_shortname. */ if (qstr.name == dentry->d_shortname.string) { strbuf = dentry->d_shortname; // NUL is guaranteed to be in there qstr.name = strbuf.string; /* prevent compiler from optimizing out the temporary buffer */ barrier(); } return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr); } EXPORT_SYMBOL(generic_ci_d_compare); /** * generic_ci_d_hash - generic d_hash implementation for casefolding filesystems * @dentry: dentry of the parent directory * @str: qstr of name whose hash we should fill in * * Return: 0 if hash was successful or unchanged, and -EINVAL on error */ int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str) { const struct inode *dir = READ_ONCE(dentry->d_inode); struct super_block *sb = dentry->d_sb; const struct unicode_map *um = sb->s_encoding; int ret; if (!dir || !IS_CASEFOLDED(dir)) return 0; ret = utf8_casefold_hash(um, dentry, str); if (ret < 0 && sb_has_strict_encoding(sb)) return -EINVAL; return 0; } EXPORT_SYMBOL(generic_ci_d_hash); static const struct dentry_operations generic_ci_dentry_ops = { .d_hash = generic_ci_d_hash, .d_compare = generic_ci_d_compare, #ifdef CONFIG_FS_ENCRYPTION .d_revalidate = fscrypt_d_revalidate, #endif }; /** * generic_ci_match() - Match a name (case-insensitively) with a dirent. * This is a filesystem helper for comparison with directory entries. * generic_ci_d_compare should be used in VFS' ->d_compare instead. * * @parent: Inode of the parent of the dirent under comparison * @name: name under lookup. * @folded_name: Optional pre-folded name under lookup * @de_name: Dirent name. * @de_name_len: dirent name length. * * Test whether a case-insensitive directory entry matches the filename * being searched. If @folded_name is provided, it is used instead of * recalculating the casefold of @name. * * Return: > 0 if the directory entry matches, 0 if it doesn't match, or * < 0 on error. */ int generic_ci_match(const struct inode *parent, const struct qstr *name, const struct qstr *folded_name, const u8 *de_name, u32 de_name_len) { const struct super_block *sb = parent->i_sb; const struct unicode_map *um = sb->s_encoding; struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len); struct qstr dirent = QSTR_INIT(de_name, de_name_len); int res = 0; if (IS_ENCRYPTED(parent)) { const struct fscrypt_str encrypted_name = FSTR_INIT((u8 *) de_name, de_name_len); if (WARN_ON_ONCE(!fscrypt_has_encryption_key(parent))) return -EINVAL; decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL); if (!decrypted_name.name) return -ENOMEM; res = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name, &decrypted_name); if (res < 0) { kfree(decrypted_name.name); return res; } dirent.name = decrypted_name.name; dirent.len = decrypted_name.len; } /* * Attempt a case-sensitive match first. It is cheaper and * should cover most lookups, including all the sane * applications that expect a case-sensitive filesystem. */ if (dirent.len == name->len && !memcmp(name->name, dirent.name, dirent.len)) goto out; if (folded_name->name) res = utf8_strncasecmp_folded(um, folded_name, &dirent); else res = utf8_strncasecmp(um, name, &dirent); out: kfree(decrypted_name.name); if (res < 0 && sb_has_strict_encoding(sb)) { pr_err_ratelimited("Directory contains filename that is invalid UTF-8"); return 0; } return !res; } EXPORT_SYMBOL(generic_ci_match); #endif #ifdef CONFIG_FS_ENCRYPTION static const struct dentry_operations generic_encrypted_dentry_ops = { .d_revalidate = fscrypt_d_revalidate, }; #endif /** * generic_set_sb_d_ops - helper for choosing the set of * filesystem-wide dentry operations for the enabled features * @sb: superblock to be configured * * Filesystems supporting casefolding and/or fscrypt can call this * helper at mount-time to configure default dentry_operations to the * best set of dentry operations required for the enabled features. * The helper must be called after these have been configured, but * before the root dentry is created. */ void generic_set_sb_d_ops(struct super_block *sb) { #if IS_ENABLED(CONFIG_UNICODE) if (sb->s_encoding) { set_default_d_op(sb, &generic_ci_dentry_ops); return; } #endif #ifdef CONFIG_FS_ENCRYPTION if (sb->s_cop) { set_default_d_op(sb, &generic_encrypted_dentry_ops); return; } #endif } EXPORT_SYMBOL(generic_set_sb_d_ops); /** * inode_maybe_inc_iversion - increments i_version * @inode: inode with the i_version that should be updated * @force: increment the counter even if it's not necessary? * * Every time the inode is modified, the i_version field must be seen to have * changed by any observer. * * If "force" is set or the QUERIED flag is set, then ensure that we increment * the value, and clear the queried flag. * * In the common case where neither is set, then we can return "false" without * updating i_version. * * If this function returns false, and no other metadata has changed, then we * can avoid logging the metadata. */ bool inode_maybe_inc_iversion(struct inode *inode, bool force) { u64 cur, new; /* * The i_version field is not strictly ordered with any other inode * information, but the legacy inode_inc_iversion code used a spinlock * to serialize increments. * * We add a full memory barrier to ensure that any de facto ordering * with other state is preserved (either implicitly coming from cmpxchg * or explicitly from smp_mb if we don't know upfront if we will execute * the former). * * These barriers pair with inode_query_iversion(). */ cur = inode_peek_iversion_raw(inode); if (!force && !(cur & I_VERSION_QUERIED)) { smp_mb(); cur = inode_peek_iversion_raw(inode); } do { /* If flag is clear then we needn't do anything */ if (!force && !(cur & I_VERSION_QUERIED)) return false; /* Since lowest bit is flag, add 2 to avoid it */ new = (cur & ~I_VERSION_QUERIED) + I_VERSION_INCREMENT; } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return true; } EXPORT_SYMBOL(inode_maybe_inc_iversion); /** * inode_query_iversion - read i_version for later use * @inode: inode from which i_version should be read * * Read the inode i_version counter. This should be used by callers that wish * to store the returned i_version for later comparison. This will guarantee * that a later query of the i_version will result in a different value if * anything has changed. * * In this implementation, we fetch the current value, set the QUERIED flag and * then try to swap it into place with a cmpxchg, if it wasn't already set. If * that fails, we try again with the newly fetched value from the cmpxchg. */ u64 inode_query_iversion(struct inode *inode) { u64 cur, new; bool fenced = false; /* * Memory barriers (implicit in cmpxchg, explicit in smp_mb) pair with * inode_maybe_inc_iversion(), see that routine for more details. */ cur = inode_peek_iversion_raw(inode); do { /* If flag is already set, then no need to swap */ if (cur & I_VERSION_QUERIED) { if (!fenced) smp_mb(); break; } fenced = true; new = cur | I_VERSION_QUERIED; } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, new)); return cur >> I_VERSION_QUERIED_SHIFT; } EXPORT_SYMBOL(inode_query_iversion); ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, ssize_t direct_written, ssize_t buffered_written) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos - buffered_written; loff_t end = iocb->ki_pos - 1; int err; /* * If the buffered write fallback returned an error, we want to return * the number of bytes which were written by direct I/O, or the error * code if that was zero. * * Note that this differs from normal direct-io semantics, which will * return -EFOO even if some bytes were written. */ if (unlikely(buffered_written < 0)) { if (direct_written) return direct_written; return buffered_written; } /* * We need to ensure that the page cache pages are written to disk and * invalidated to preserve the expected O_DIRECT semantics. */ err = filemap_write_and_wait_range(mapping, pos, end); if (err < 0) { /* * We don't know how much we wrote, so just return the number of * bytes which were direct-written */ iocb->ki_pos -= buffered_written; if (direct_written) return direct_written; return err; } invalidate_mapping_pages(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); return direct_written + buffered_written; } EXPORT_SYMBOL_GPL(direct_write_fallback); /** * simple_inode_init_ts - initialize the timestamps for a new inode * @inode: inode to be initialized * * When a new inode is created, most filesystems set the timestamps to the * current time. Add a helper to do this. */ struct timespec64 simple_inode_init_ts(struct inode *inode) { struct timespec64 ts = inode_set_ctime_current(inode); inode_set_atime_to_ts(inode, ts); inode_set_mtime_to_ts(inode, ts); return ts; } EXPORT_SYMBOL(simple_inode_init_ts); struct dentry *stashed_dentry_get(struct dentry **stashed) { struct dentry *dentry; guard(rcu)(); dentry = rcu_dereference(*stashed); if (!dentry) return NULL; if (IS_ERR(dentry)) return dentry; if (!lockref_get_not_dead(&dentry->d_lockref)) return NULL; return dentry; } static struct dentry *prepare_anon_dentry(struct dentry **stashed, struct super_block *sb, void *data) { struct dentry *dentry; struct inode *inode; const struct stashed_operations *sops = sb->s_fs_info; int ret; inode = new_inode_pseudo(sb); if (!inode) { sops->put_data(data); return ERR_PTR(-ENOMEM); } inode->i_flags |= S_IMMUTABLE; inode->i_mode = S_IFREG; simple_inode_init_ts(inode); ret = sops->init_inode(inode, data); if (ret < 0) { iput(inode); return ERR_PTR(ret); } /* Notice when this is changed. */ WARN_ON_ONCE(!S_ISREG(inode->i_mode)); dentry = d_alloc_anon(sb); if (!dentry) { iput(inode); return ERR_PTR(-ENOMEM); } /* Store address of location where dentry's supposed to be stashed. */ dentry->d_fsdata = stashed; /* @data is now owned by the fs */ d_instantiate(dentry, inode); return dentry; } struct dentry *stash_dentry(struct dentry **stashed, struct dentry *dentry) { guard(rcu)(); for (;;) { struct dentry *old; /* Assume any old dentry was cleared out. */ old = cmpxchg(stashed, NULL, dentry); if (likely(!old)) return dentry; /* Check if somebody else installed a reusable dentry. */ if (lockref_get_not_dead(&old->d_lockref)) return old; /* There's an old dead dentry there, try to take it over. */ if (likely(try_cmpxchg(stashed, &old, dentry))) return dentry; } } /** * path_from_stashed - create path from stashed or new dentry * @stashed: where to retrieve or stash dentry * @mnt: mnt of the filesystems to use * @data: data to store in inode->i_private * @path: path to create * * The function tries to retrieve a stashed dentry from @stashed. If the dentry * is still valid then it will be reused. If the dentry isn't able the function * will allocate a new dentry and inode. It will then check again whether it * can reuse an existing dentry in case one has been added in the meantime or * update @stashed with the newly added dentry. * * Special-purpose helper for nsfs and pidfs. * * Return: On success zero and on failure a negative error is returned. */ int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data, struct path *path) { struct dentry *dentry, *res; const struct stashed_operations *sops = mnt->mnt_sb->s_fs_info; /* See if dentry can be reused. */ res = stashed_dentry_get(stashed); if (IS_ERR(res)) return PTR_ERR(res); if (res) { sops->put_data(data); goto make_path; } /* Allocate a new dentry. */ dentry = prepare_anon_dentry(stashed, mnt->mnt_sb, data); if (IS_ERR(dentry)) return PTR_ERR(dentry); /* Added a new dentry. @data is now owned by the filesystem. */ if (sops->stash_dentry) res = sops->stash_dentry(stashed, dentry); else res = stash_dentry(stashed, dentry); if (IS_ERR(res)) { dput(dentry); return PTR_ERR(res); } if (res != dentry) dput(dentry); make_path: path->dentry = res; path->mnt = mntget(mnt); VFS_WARN_ON_ONCE(path->dentry->d_fsdata != stashed); VFS_WARN_ON_ONCE(d_inode(path->dentry)->i_private != data); return 0; } void stashed_dentry_prune(struct dentry *dentry) { struct dentry **stashed = dentry->d_fsdata; struct inode *inode = d_inode(dentry); if (WARN_ON_ONCE(!stashed)) return; if (!inode) return; /* * Only replace our own @dentry as someone else might've * already cleared out @dentry and stashed their own * dentry in there. */ cmpxchg(stashed, dentry, NULL); } /* parent must be held exclusive */ struct dentry *simple_start_creating(struct dentry *parent, const char *name) { struct dentry *dentry; struct inode *dir = d_inode(parent); inode_lock(dir); if (unlikely(IS_DEADDIR(dir))) { inode_unlock(dir); return ERR_PTR(-ENOENT); } dentry = lookup_noperm(&QSTR(name), parent); if (IS_ERR(dentry)) { inode_unlock(dir); return dentry; } if (dentry->d_inode) { dput(dentry); inode_unlock(dir); return ERR_PTR(-EEXIST); } return dentry; } EXPORT_SYMBOL(simple_start_creating); |
| 7 7 7 7 7 8 8 7 7 2 7 7 2 319 319 319 317 319 319 280 280 279 8 1 7 7 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright 2019 Arm Limited * Author: Andrew Murray <Andrew.Murray@arm.com> */ #include <linux/kvm_host.h> #include <linux/perf_event.h> #include <linux/perf/arm_pmu.h> #include <linux/perf/arm_pmuv3.h> static DEFINE_PER_CPU(struct kvm_pmu_events, kvm_pmu_events); /* * Given the perf event attributes and system type, determine * if we are going to need to switch counters at guest entry/exit. */ static bool kvm_pmu_switch_needed(struct perf_event_attr *attr) { /** * With VHE the guest kernel runs at EL1 and the host at EL2, * where user (EL0) is excluded then we have no reason to switch * counters. */ if (has_vhe() && attr->exclude_user) return false; /* Only switch if attributes are different */ return (attr->exclude_host != attr->exclude_guest); } struct kvm_pmu_events *kvm_get_pmu_events(void) { return this_cpu_ptr(&kvm_pmu_events); } /* * Add events to track that we may want to switch at guest entry/exit * time. */ void kvm_set_pmu_events(u64 set, struct perf_event_attr *attr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); if (!system_supports_pmuv3() || !kvm_pmu_switch_needed(attr)) return; if (!attr->exclude_host) pmu->events_host |= set; if (!attr->exclude_guest) pmu->events_guest |= set; } /* * Stop tracking events */ void kvm_clr_pmu_events(u64 clr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); if (!system_supports_pmuv3()) return; pmu->events_host &= ~clr; pmu->events_guest &= ~clr; } /* * Read a value direct from PMEVTYPER<idx> where idx is 0-30 * or PMxCFILTR_EL0 where idx is 31-32. */ static u64 kvm_vcpu_pmu_read_evtype_direct(int idx) { if (idx == ARMV8_PMU_CYCLE_IDX) return read_pmccfiltr(); else if (idx == ARMV8_PMU_INSTR_IDX) return read_pmicfiltr(); return read_pmevtypern(idx); } /* * Write a value direct to PMEVTYPER<idx> where idx is 0-30 * or PMxCFILTR_EL0 where idx is 31-32. */ static void kvm_vcpu_pmu_write_evtype_direct(int idx, u32 val) { if (idx == ARMV8_PMU_CYCLE_IDX) write_pmccfiltr(val); else if (idx == ARMV8_PMU_INSTR_IDX) write_pmicfiltr(val); else write_pmevtypern(idx, val); } /* * Modify ARMv8 PMU events to include EL0 counting */ static void kvm_vcpu_pmu_enable_el0(unsigned long events) { u64 typer; u32 counter; for_each_set_bit(counter, &events, ARMPMU_MAX_HWEVENTS) { typer = kvm_vcpu_pmu_read_evtype_direct(counter); typer &= ~ARMV8_PMU_EXCLUDE_EL0; kvm_vcpu_pmu_write_evtype_direct(counter, typer); } } /* * Modify ARMv8 PMU events to exclude EL0 counting */ static void kvm_vcpu_pmu_disable_el0(unsigned long events) { u64 typer; u32 counter; for_each_set_bit(counter, &events, ARMPMU_MAX_HWEVENTS) { typer = kvm_vcpu_pmu_read_evtype_direct(counter); typer |= ARMV8_PMU_EXCLUDE_EL0; kvm_vcpu_pmu_write_evtype_direct(counter, typer); } } /* * On VHE ensure that only guest events have EL0 counting enabled. * This is called from both vcpu_{load,put} and the sysreg handling. * Since the latter is preemptible, special care must be taken to * disable preemption. */ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) { struct kvm_pmu_events *pmu; u64 events_guest, events_host; if (!system_supports_pmuv3() || !has_vhe()) return; preempt_disable(); pmu = kvm_get_pmu_events(); events_guest = pmu->events_guest; events_host = pmu->events_host; kvm_vcpu_pmu_enable_el0(events_guest); kvm_vcpu_pmu_disable_el0(events_host); preempt_enable(); } /* * On VHE ensure that only host events have EL0 counting enabled */ void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) { struct kvm_pmu_events *pmu; u64 events_guest, events_host; if (!system_supports_pmuv3() || !has_vhe()) return; pmu = kvm_get_pmu_events(); events_guest = pmu->events_guest; events_host = pmu->events_host; kvm_vcpu_pmu_enable_el0(events_host); kvm_vcpu_pmu_disable_el0(events_guest); } /* * With VHE, keep track of the PMUSERENR_EL0 value for the host EL0 on the pCPU * where PMUSERENR_EL0 for the guest is loaded, since PMUSERENR_EL0 is switched * to the value for the guest on vcpu_load(). The value for the host EL0 * will be restored on vcpu_put(), before returning to userspace. * This isn't necessary for nVHE, as the register is context switched for * every guest enter/exit. * * Return true if KVM takes care of the register. Otherwise return false. */ bool kvm_set_pmuserenr(u64 val) { struct kvm_cpu_context *hctxt; struct kvm_vcpu *vcpu; if (!system_supports_pmuv3() || !has_vhe()) return false; vcpu = kvm_get_running_vcpu(); if (!vcpu || !vcpu_get_flag(vcpu, PMUSERENR_ON_CPU)) return false; hctxt = host_data_ptr(host_ctxt); ctxt_sys_reg(hctxt, PMUSERENR_EL0) = val; return true; } /* * If we interrupted the guest to update the host PMU context, make * sure we re-apply the guest EL0 state. */ void kvm_vcpu_pmu_resync_el0(void) { struct kvm_vcpu *vcpu; if (!has_vhe() || !in_interrupt()) return; vcpu = kvm_get_running_vcpu(); if (!vcpu) return; kvm_make_request(KVM_REQ_RESYNC_PMU_EL0, vcpu); } |
| 8 8 8 8 8 8 7 8 8 5 8 8 7 7 7 7 7 7 7 7 7 7 7 7 8 7 7 8 8 8 8 7 1 7 7 7 8 8 8 8 8 21 21 7 6 7 7 7 7 1 1 7 7 8 8 8 20 20 20 20 20 20 20 20 20 20 18 14 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 | // SPDX-License-Identifier: GPL-2.0-only /* * ARMv8 PMUv3 Performance Events handling code. * * Copyright (C) 2012 ARM Limited * Author: Will Deacon <will.deacon@arm.com> * * This code is based heavily on the ARMv7 perf event code. */ #include <asm/irq_regs.h> #include <asm/perf_event.h> #include <asm/virt.h> #include <clocksource/arm_arch_timer.h> #include <linux/acpi.h> #include <linux/bitfield.h> #include <linux/clocksource.h> #include <linux/of.h> #include <linux/perf/arm_pmu.h> #include <linux/perf/arm_pmuv3.h> #include <linux/platform_device.h> #include <linux/sched_clock.h> #include <linux/smp.h> #include <linux/nmi.h> #include "arm_brbe.h" /* ARMv8 Cortex-A53 specific event types. */ #define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2 /* ARMv8 Cavium ThunderX specific event types. */ #define ARMV8_THUNDER_PERFCTR_L1D_CACHE_MISS_ST 0xE9 #define ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_ACCESS 0xEA #define ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_MISS 0xEB #define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_ACCESS 0xEC #define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS 0xED /* * ARMv8 Architectural defined events, not all of these may * be supported on any given implementation. Unsupported events will * be disabled at run-time based on the PMCEID registers. */ static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = { PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CPU_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INST_RETIRED, [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE, [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED, [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES, [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV8_PMUV3_PERFCTR_STALL_FRONTEND, [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV8_PMUV3_PERFCTR_STALL_BACKEND, }; static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { PERF_CACHE_MAP_ALL_UNSUPPORTED, [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE, [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL, [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE, [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL, [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL, [C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_TLB, [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL, [C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB, [C(LL)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD, [C(LL)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_LL_CACHE_RD, [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED, [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED, }; static const unsigned armv8_a53_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { PERF_CACHE_MAP_ALL_UNSUPPORTED, [C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_A53_PERFCTR_PREF_LINEFILL, [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD, [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR, }; static const unsigned armv8_a57_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { PERF_CACHE_MAP_ALL_UNSUPPORTED, [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD, [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD, [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR, [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR, [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD, [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR, [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD, [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR, }; static const unsigned armv8_a73_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { PERF_CACHE_MAP_ALL_UNSUPPORTED, [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD, [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR, }; static const unsigned armv8_thunder_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { PERF_CACHE_MAP_ALL_UNSUPPORTED, [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD, [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD, [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR, [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_THUNDER_PERFCTR_L1D_CACHE_MISS_ST, [C(L1D)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_ACCESS, [C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_MISS, [C(L1I)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_ACCESS, [C(L1I)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS, [C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD, [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD, [C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR, [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR, }; static const unsigned armv8_vulcan_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = { PERF_CACHE_MAP_ALL_UNSUPPORTED, [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD, [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD, [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR, [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR, [C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD, [C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR, [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD, [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR, [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD, [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR, }; static ssize_t armv8pmu_events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { struct perf_pmu_events_attr *pmu_attr; pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); return sprintf(page, "event=0x%04llx\n", pmu_attr->id); } #define ARMV8_EVENT_ATTR(name, config) \ PMU_EVENT_ATTR_ID(name, armv8pmu_events_sysfs_show, config) static struct attribute *armv8_pmuv3_event_attrs[] = { /* * Don't expose the sw_incr event in /sys. It's not usable as writes to * PMSWINC_EL0 will trap as PMUSERENR.{SW,EN}=={0,0} and event rotation * means we don't have a fixed event<->counter relationship regardless. */ ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL), ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL), ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL), ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE), ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL), ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED), ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED), ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED), ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN), ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN), ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED), ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED), ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED), ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED), ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED), ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED), ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES), ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED), ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS), ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE), ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB), ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE), ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL), ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB), ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS), ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR), ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC), ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED), ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES), /* Don't expose the chain event in /sys, since it's useless in isolation */ ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE), ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE), ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED), ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED), ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND), ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND), ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB), ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB), ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE), ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL), ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE), ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL), ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE), ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB), ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL), ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL), ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB), ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB), ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS), ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE), ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS), ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK), ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK), ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD), ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD), ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD), ARMV8_EVENT_ATTR(l1d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD), ARMV8_EVENT_ATTR(op_retired, ARMV8_PMUV3_PERFCTR_OP_RETIRED), ARMV8_EVENT_ATTR(op_spec, ARMV8_PMUV3_PERFCTR_OP_SPEC), ARMV8_EVENT_ATTR(stall, ARMV8_PMUV3_PERFCTR_STALL), ARMV8_EVENT_ATTR(stall_slot_backend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND), ARMV8_EVENT_ATTR(stall_slot_frontend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND), ARMV8_EVENT_ATTR(stall_slot, ARMV8_PMUV3_PERFCTR_STALL_SLOT), ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP), ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED), ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE), ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION), ARMV8_EVENT_ATTR(cnt_cycles, ARMV8_AMU_PERFCTR_CNT_CYCLES), ARMV8_EVENT_ATTR(stall_backend_mem, ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM), ARMV8_EVENT_ATTR(l1i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS), ARMV8_EVENT_ATTR(l2d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD), ARMV8_EVENT_ATTR(l2i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS), ARMV8_EVENT_ATTR(l3d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD), ARMV8_EVENT_ATTR(trb_wrap, ARMV8_PMUV3_PERFCTR_TRB_WRAP), ARMV8_EVENT_ATTR(trb_trig, ARMV8_PMUV3_PERFCTR_TRB_TRIG), ARMV8_EVENT_ATTR(trcextout0, ARMV8_PMUV3_PERFCTR_TRCEXTOUT0), ARMV8_EVENT_ATTR(trcextout1, ARMV8_PMUV3_PERFCTR_TRCEXTOUT1), ARMV8_EVENT_ATTR(trcextout2, ARMV8_PMUV3_PERFCTR_TRCEXTOUT2), ARMV8_EVENT_ATTR(trcextout3, ARMV8_PMUV3_PERFCTR_TRCEXTOUT3), ARMV8_EVENT_ATTR(cti_trigout4, ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT4), ARMV8_EVENT_ATTR(cti_trigout5, ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT5), ARMV8_EVENT_ATTR(cti_trigout6, ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT6), ARMV8_EVENT_ATTR(cti_trigout7, ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT7), ARMV8_EVENT_ATTR(ldst_align_lat, ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT), ARMV8_EVENT_ATTR(ld_align_lat, ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT), ARMV8_EVENT_ATTR(st_align_lat, ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT), ARMV8_EVENT_ATTR(mem_access_checked, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED), ARMV8_EVENT_ATTR(mem_access_checked_rd, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD), ARMV8_EVENT_ATTR(mem_access_checked_wr, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR), NULL, }; static umode_t armv8pmu_event_attr_is_visible(struct kobject *kobj, struct attribute *attr, int unused) { struct device *dev = kobj_to_dev(kobj); struct pmu *pmu = dev_get_drvdata(dev); struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); struct perf_pmu_events_attr *pmu_attr; pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr); if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS && test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap)) return attr->mode; if (pmu_attr->id >= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE) { u64 id = pmu_attr->id - ARMV8_PMUV3_EXT_COMMON_EVENT_BASE; if (id < ARMV8_PMUV3_MAX_COMMON_EVENTS && test_bit(id, cpu_pmu->pmceid_ext_bitmap)) return attr->mode; } return 0; } static const struct attribute_group armv8_pmuv3_events_attr_group = { .name = "events", .attrs = armv8_pmuv3_event_attrs, .is_visible = armv8pmu_event_attr_is_visible, }; /* User ABI */ #define ATTR_CFG_FLD_event_CFG config #define ATTR_CFG_FLD_event_LO 0 #define ATTR_CFG_FLD_event_HI 15 #define ATTR_CFG_FLD_long_CFG config1 #define ATTR_CFG_FLD_long_LO 0 #define ATTR_CFG_FLD_long_HI 0 #define ATTR_CFG_FLD_rdpmc_CFG config1 #define ATTR_CFG_FLD_rdpmc_LO 1 #define ATTR_CFG_FLD_rdpmc_HI 1 #define ATTR_CFG_FLD_threshold_count_CFG config1 /* PMEVTYPER.TC[0] */ #define ATTR_CFG_FLD_threshold_count_LO 2 #define ATTR_CFG_FLD_threshold_count_HI 2 #define ATTR_CFG_FLD_threshold_compare_CFG config1 /* PMEVTYPER.TC[2:1] */ #define ATTR_CFG_FLD_threshold_compare_LO 3 #define ATTR_CFG_FLD_threshold_compare_HI 4 #define ATTR_CFG_FLD_threshold_CFG config1 /* PMEVTYPER.TH */ #define ATTR_CFG_FLD_threshold_LO 5 #define ATTR_CFG_FLD_threshold_HI 16 GEN_PMU_FORMAT_ATTR(event); GEN_PMU_FORMAT_ATTR(long); GEN_PMU_FORMAT_ATTR(rdpmc); GEN_PMU_FORMAT_ATTR(threshold_count); GEN_PMU_FORMAT_ATTR(threshold_compare); GEN_PMU_FORMAT_ATTR(threshold); static int sysctl_perf_user_access __read_mostly; static bool armv8pmu_event_is_64bit(struct perf_event *event) { return ATTR_CFG_GET_FLD(&event->attr, long); } static bool armv8pmu_event_want_user_access(struct perf_event *event) { return ATTR_CFG_GET_FLD(&event->attr, rdpmc); } static u32 armv8pmu_event_get_threshold(struct perf_event_attr *attr) { return ATTR_CFG_GET_FLD(attr, threshold); } static u8 armv8pmu_event_threshold_control(struct perf_event_attr *attr) { u8 th_compare = ATTR_CFG_GET_FLD(attr, threshold_compare); u8 th_count = ATTR_CFG_GET_FLD(attr, threshold_count); /* * The count bit is always the bottom bit of the full control field, and * the comparison is the upper two bits, but it's not explicitly * labelled in the Arm ARM. For the Perf interface we split it into two * fields, so reconstruct it here. */ return (th_compare << 1) | th_count; } static struct attribute *armv8_pmuv3_format_attrs[] = { &format_attr_event.attr, &format_attr_long.attr, &format_attr_rdpmc.attr, &format_attr_threshold.attr, &format_attr_threshold_compare.attr, &format_attr_threshold_count.attr, NULL, }; static const struct attribute_group armv8_pmuv3_format_attr_group = { .name = "format", .attrs = armv8_pmuv3_format_attrs, }; static ssize_t slots_show(struct device *dev, struct device_attribute *attr, char *page) { struct pmu *pmu = dev_get_drvdata(dev); struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); u32 slots = FIELD_GET(ARMV8_PMU_SLOTS, cpu_pmu->reg_pmmir); return sysfs_emit(page, "0x%08x\n", slots); } static DEVICE_ATTR_RO(slots); static ssize_t bus_slots_show(struct device *dev, struct device_attribute *attr, char *page) { struct pmu *pmu = dev_get_drvdata(dev); struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); u32 bus_slots = FIELD_GET(ARMV8_PMU_BUS_SLOTS, cpu_pmu->reg_pmmir); return sysfs_emit(page, "0x%08x\n", bus_slots); } static DEVICE_ATTR_RO(bus_slots); static ssize_t bus_width_show(struct device *dev, struct device_attribute *attr, char *page) { struct pmu *pmu = dev_get_drvdata(dev); struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); u32 bus_width = FIELD_GET(ARMV8_PMU_BUS_WIDTH, cpu_pmu->reg_pmmir); u32 val = 0; /* Encoded as Log2(number of bytes), plus one */ if (bus_width > 2 && bus_width < 13) val = 1 << (bus_width - 1); return sysfs_emit(page, "0x%08x\n", val); } static DEVICE_ATTR_RO(bus_width); static u32 threshold_max(struct arm_pmu *cpu_pmu) { /* * PMMIR.THWIDTH is readable and non-zero on aarch32, but it would be * impossible to write the threshold in the upper 32 bits of PMEVTYPER. */ if (IS_ENABLED(CONFIG_ARM)) return 0; /* * The largest value that can be written to PMEVTYPER<n>_EL0.TH is * (2 ^ PMMIR.THWIDTH) - 1. */ return (1 << FIELD_GET(ARMV8_PMU_THWIDTH, cpu_pmu->reg_pmmir)) - 1; } static ssize_t threshold_max_show(struct device *dev, struct device_attribute *attr, char *page) { struct pmu *pmu = dev_get_drvdata(dev); struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); return sysfs_emit(page, "0x%08x\n", threshold_max(cpu_pmu)); } static DEVICE_ATTR_RO(threshold_max); static ssize_t branches_show(struct device *dev, struct device_attribute *attr, char *page) { struct pmu *pmu = dev_get_drvdata(dev); struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); return sysfs_emit(page, "%d\n", brbe_num_branch_records(cpu_pmu)); } static DEVICE_ATTR_RO(branches); static struct attribute *armv8_pmuv3_caps_attrs[] = { &dev_attr_branches.attr, &dev_attr_slots.attr, &dev_attr_bus_slots.attr, &dev_attr_bus_width.attr, &dev_attr_threshold_max.attr, NULL, }; static umode_t caps_is_visible(struct kobject *kobj, struct attribute *attr, int i) { struct device *dev = kobj_to_dev(kobj); struct pmu *pmu = dev_get_drvdata(dev); struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); if (i == 0) return brbe_num_branch_records(cpu_pmu) ? attr->mode : 0; return attr->mode; } static const struct attribute_group armv8_pmuv3_caps_attr_group = { .name = "caps", .attrs = armv8_pmuv3_caps_attrs, .is_visible = caps_is_visible, }; /* * We unconditionally enable ARMv8.5-PMU long event counter support * (64-bit events) where supported. Indicate if this arm_pmu has long * event counter support. * * On AArch32, long counters make no sense (you can't access the top * bits), so we only enable this on AArch64. */ static bool armv8pmu_has_long_event(struct arm_pmu *cpu_pmu) { return (IS_ENABLED(CONFIG_ARM64) && is_pmuv3p5(cpu_pmu->pmuver)); } static bool armv8pmu_event_has_user_read(struct perf_event *event) { return event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT; } /* * We must chain two programmable counters for 64 bit events, * except when we have allocated the 64bit cycle counter (for CPU * cycles event) or when user space counter access is enabled. */ static bool armv8pmu_event_is_chained(struct perf_event *event) { int idx = event->hw.idx; struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); return !armv8pmu_event_has_user_read(event) && armv8pmu_event_is_64bit(event) && !armv8pmu_has_long_event(cpu_pmu) && (idx < ARMV8_PMU_MAX_GENERAL_COUNTERS); } /* * ARMv8 low level PMU access */ static u64 armv8pmu_pmcr_read(void) { return read_pmcr(); } static void armv8pmu_pmcr_write(u64 val) { val &= ARMV8_PMU_PMCR_MASK; isb(); write_pmcr(val); } static int armv8pmu_has_overflowed(u64 pmovsr) { return !!(pmovsr & ARMV8_PMU_OVERFLOWED_MASK); } static int armv8pmu_counter_has_overflowed(u64 pmnc, int idx) { return !!(pmnc & BIT(idx)); } static u64 armv8pmu_read_evcntr(int idx) { return read_pmevcntrn(idx); } static u64 armv8pmu_read_hw_counter(struct perf_event *event) { int idx = event->hw.idx; u64 val = armv8pmu_read_evcntr(idx); if (armv8pmu_event_is_chained(event)) val = (val << 32) | armv8pmu_read_evcntr(idx - 1); return val; } /* * The cycle counter is always a 64-bit counter. When ARMV8_PMU_PMCR_LP * is set the event counters also become 64-bit counters. Unless the * user has requested a long counter (attr.config1) then we want to * interrupt upon 32-bit overflow - we achieve this by applying a bias. */ static bool armv8pmu_event_needs_bias(struct perf_event *event) { struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; if (armv8pmu_event_is_64bit(event)) return false; if (armv8pmu_has_long_event(cpu_pmu) || idx >= ARMV8_PMU_MAX_GENERAL_COUNTERS) return true; return false; } static u64 armv8pmu_bias_long_counter(struct perf_event *event, u64 value) { if (armv8pmu_event_needs_bias(event)) value |= GENMASK_ULL(63, 32); return value; } static u64 armv8pmu_unbias_long_counter(struct perf_event *event, u64 value) { if (armv8pmu_event_needs_bias(event)) value &= ~GENMASK_ULL(63, 32); return value; } static u64 armv8pmu_read_counter(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; u64 value; if (idx == ARMV8_PMU_CYCLE_IDX) value = read_pmccntr(); else if (idx == ARMV8_PMU_INSTR_IDX) value = read_pmicntr(); else value = armv8pmu_read_hw_counter(event); return armv8pmu_unbias_long_counter(event, value); } static void armv8pmu_write_evcntr(int idx, u64 value) { write_pmevcntrn(idx, value); } static void armv8pmu_write_hw_counter(struct perf_event *event, u64 value) { int idx = event->hw.idx; if (armv8pmu_event_is_chained(event)) { armv8pmu_write_evcntr(idx, upper_32_bits(value)); armv8pmu_write_evcntr(idx - 1, lower_32_bits(value)); } else { armv8pmu_write_evcntr(idx, value); } } static void armv8pmu_write_counter(struct perf_event *event, u64 value) { struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; value = armv8pmu_bias_long_counter(event, value); if (idx == ARMV8_PMU_CYCLE_IDX) write_pmccntr(value); else if (idx == ARMV8_PMU_INSTR_IDX) write_pmicntr(value); else armv8pmu_write_hw_counter(event, value); } static void armv8pmu_write_evtype(int idx, unsigned long val) { unsigned long mask = ARMV8_PMU_EVTYPE_EVENT | ARMV8_PMU_INCLUDE_EL2 | ARMV8_PMU_EXCLUDE_EL0 | ARMV8_PMU_EXCLUDE_EL1; if (IS_ENABLED(CONFIG_ARM64)) mask |= ARMV8_PMU_EVTYPE_TC | ARMV8_PMU_EVTYPE_TH; val &= mask; write_pmevtypern(idx, val); } static void armv8pmu_write_event_type(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; /* * For chained events, the low counter is programmed to count * the event of interest and the high counter is programmed * with CHAIN event code with filters set to count at all ELs. */ if (armv8pmu_event_is_chained(event)) { u32 chain_evt = ARMV8_PMUV3_PERFCTR_CHAIN | ARMV8_PMU_INCLUDE_EL2; armv8pmu_write_evtype(idx - 1, hwc->config_base); armv8pmu_write_evtype(idx, chain_evt); } else { if (idx == ARMV8_PMU_CYCLE_IDX) write_pmccfiltr(hwc->config_base); else if (idx == ARMV8_PMU_INSTR_IDX) write_pmicfiltr(hwc->config_base); else armv8pmu_write_evtype(idx, hwc->config_base); } } static u64 armv8pmu_event_cnten_mask(struct perf_event *event) { int counter = event->hw.idx; u64 mask = BIT(counter); if (armv8pmu_event_is_chained(event)) mask |= BIT(counter - 1); return mask; } static void armv8pmu_enable_counter(u64 mask) { /* * Make sure event configuration register writes are visible before we * enable the counter. * */ isb(); write_pmcntenset(mask); } static void armv8pmu_enable_event_counter(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; u64 mask = armv8pmu_event_cnten_mask(event); kvm_set_pmu_events(mask, attr); /* We rely on the hypervisor switch code to enable guest counters */ if (!kvm_pmu_counter_deferred(attr)) armv8pmu_enable_counter(mask); } static void armv8pmu_disable_counter(u64 mask) { write_pmcntenclr(mask); /* * Make sure the effects of disabling the counter are visible before we * start configuring the event. */ isb(); } static void armv8pmu_disable_event_counter(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; u64 mask = armv8pmu_event_cnten_mask(event); kvm_clr_pmu_events(mask); /* We rely on the hypervisor switch code to disable guest counters */ if (!kvm_pmu_counter_deferred(attr)) armv8pmu_disable_counter(mask); } static void armv8pmu_enable_intens(u64 mask) { write_pmintenset(mask); } static void armv8pmu_enable_event_irq(struct perf_event *event) { armv8pmu_enable_intens(BIT(event->hw.idx)); } static void armv8pmu_disable_intens(u64 mask) { write_pmintenclr(mask); isb(); /* Clear the overflow flag in case an interrupt is pending. */ write_pmovsclr(mask); isb(); } static void armv8pmu_disable_event_irq(struct perf_event *event) { armv8pmu_disable_intens(BIT(event->hw.idx)); } static u64 armv8pmu_getreset_flags(void) { u64 value; /* Read */ value = read_pmovsclr(); /* Write to clear flags */ value &= ARMV8_PMU_OVERFLOWED_MASK; write_pmovsclr(value); return value; } static void update_pmuserenr(u64 val) { lockdep_assert_irqs_disabled(); /* * The current PMUSERENR_EL0 value might be the value for the guest. * If that's the case, have KVM keep tracking of the register value * for the host EL0 so that KVM can restore it before returning to * the host EL0. Otherwise, update the register now. */ if (kvm_set_pmuserenr(val)) return; write_pmuserenr(val); } static void armv8pmu_disable_user_access(void) { update_pmuserenr(0); } static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu) { int i; struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events); if (is_pmuv3p9(cpu_pmu->pmuver)) { u64 mask = 0; for_each_set_bit(i, cpuc->used_mask, ARMPMU_MAX_HWEVENTS) { if (armv8pmu_event_has_user_read(cpuc->events[i])) mask |= BIT(i); } write_pmuacr(mask); } else { /* Clear any unused counters to avoid leaking their contents */ for_each_andnot_bit(i, cpu_pmu->cntr_mask, cpuc->used_mask, ARMPMU_MAX_HWEVENTS) { if (i == ARMV8_PMU_CYCLE_IDX) write_pmccntr(0); else if (i == ARMV8_PMU_INSTR_IDX) write_pmicntr(0); else armv8pmu_write_evcntr(i, 0); } } update_pmuserenr(ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_UEN); } static void armv8pmu_enable_event(struct perf_event *event) { armv8pmu_write_event_type(event); armv8pmu_enable_event_irq(event); armv8pmu_enable_event_counter(event); } static void armv8pmu_disable_event(struct perf_event *event) { armv8pmu_disable_event_counter(event); armv8pmu_disable_event_irq(event); } static void armv8pmu_start(struct arm_pmu *cpu_pmu) { struct perf_event_context *ctx; struct pmu_hw_events *hw_events = this_cpu_ptr(cpu_pmu->hw_events); int nr_user = 0; ctx = perf_cpu_task_ctx(); if (ctx) nr_user = ctx->nr_user; if (sysctl_perf_user_access && nr_user) armv8pmu_enable_user_access(cpu_pmu); else armv8pmu_disable_user_access(); kvm_vcpu_pmu_resync_el0(); if (hw_events->branch_users) brbe_enable(cpu_pmu); /* Enable all counters */ armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E); } static void armv8pmu_stop(struct arm_pmu *cpu_pmu) { struct pmu_hw_events *hw_events = this_cpu_ptr(cpu_pmu->hw_events); if (hw_events->branch_users) brbe_disable(); /* Disable all counters */ armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E); } static void read_branch_records(struct pmu_hw_events *cpuc, struct perf_event *event, struct perf_sample_data *data) { struct perf_branch_stack *branch_stack = cpuc->branch_stack; brbe_read_filtered_entries(branch_stack, event); perf_sample_save_brstack(data, event, branch_stack, NULL); } static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu) { u64 pmovsr; struct perf_sample_data data; struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events); struct pt_regs *regs; int idx; /* * Get and reset the IRQ flags */ pmovsr = armv8pmu_getreset_flags(); /* * Did an overflow occur? */ if (!armv8pmu_has_overflowed(pmovsr)) return IRQ_NONE; /* * Handle the counter(s) overflow(s) */ regs = get_irq_regs(); /* * Stop the PMU while processing the counter overflows * to prevent skews in group events. */ armv8pmu_stop(cpu_pmu); for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; /* Ignore if we don't have an event. */ if (!event) continue; /* * We have a single interrupt for all counters. Check that * each counter has overflowed before we process it. */ if (!armv8pmu_counter_has_overflowed(pmovsr, idx)) continue; hwc = &event->hw; armpmu_event_update(event); perf_sample_data_init(&data, 0, hwc->last_period); if (!armpmu_event_set_period(event)) continue; if (has_branch_stack(event)) read_branch_records(cpuc, event, &data); /* * Perf event overflow will queue the processing of the event as * an irq_work which will be taken care of in the handling of * IPI_IRQ_WORK. */ perf_event_overflow(event, &data, regs); } armv8pmu_start(cpu_pmu); return IRQ_HANDLED; } static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc, struct arm_pmu *cpu_pmu) { int idx; for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) { if (!test_and_set_bit(idx, cpuc->used_mask)) return idx; } return -EAGAIN; } static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc, struct arm_pmu *cpu_pmu) { int idx; /* * Chaining requires two consecutive event counters, where * the lower idx must be even. */ for_each_set_bit(idx, cpu_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS) { if (!(idx & 0x1)) continue; if (!test_and_set_bit(idx, cpuc->used_mask)) { /* Check if the preceding even counter is available */ if (!test_and_set_bit(idx - 1, cpuc->used_mask)) return idx; /* Release the Odd counter */ clear_bit(idx, cpuc->used_mask); } } return -EAGAIN; } static bool armv8pmu_can_use_pmccntr(struct pmu_hw_events *cpuc, struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT; if (evtype != ARMV8_PMUV3_PERFCTR_CPU_CYCLES) return false; /* * A CPU_CYCLES event with threshold counting cannot use PMCCNTR_EL0 * since it lacks threshold support. */ if (armv8pmu_event_get_threshold(&event->attr)) return false; /* * PMCCNTR_EL0 is not affected by BRBE controls like BRBCR_ELx.FZP. * So don't use it for branch events. */ if (has_branch_stack(event)) return false; return true; } static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc, struct perf_event *event) { struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT; /* Always prefer to place a cycle counter into the cycle counter. */ if (armv8pmu_can_use_pmccntr(cpuc, event)) { if (!test_and_set_bit(ARMV8_PMU_CYCLE_IDX, cpuc->used_mask)) return ARMV8_PMU_CYCLE_IDX; else if (armv8pmu_event_is_64bit(event) && armv8pmu_event_want_user_access(event) && !armv8pmu_has_long_event(cpu_pmu)) return -EAGAIN; } /* * Always prefer to place a instruction counter into the instruction counter, * but don't expose the instruction counter to userspace access as userspace * may not know how to handle it. */ if ((evtype == ARMV8_PMUV3_PERFCTR_INST_RETIRED) && !armv8pmu_event_get_threshold(&event->attr) && test_bit(ARMV8_PMU_INSTR_IDX, cpu_pmu->cntr_mask) && !armv8pmu_event_want_user_access(event)) { if (!test_and_set_bit(ARMV8_PMU_INSTR_IDX, cpuc->used_mask)) return ARMV8_PMU_INSTR_IDX; } /* * Otherwise use events counters */ if (armv8pmu_event_is_chained(event)) return armv8pmu_get_chain_idx(cpuc, cpu_pmu); else return armv8pmu_get_single_idx(cpuc, cpu_pmu); } static void armv8pmu_clear_event_idx(struct pmu_hw_events *cpuc, struct perf_event *event) { int idx = event->hw.idx; clear_bit(idx, cpuc->used_mask); if (armv8pmu_event_is_chained(event)) clear_bit(idx - 1, cpuc->used_mask); } static int armv8pmu_user_event_idx(struct perf_event *event) { if (!sysctl_perf_user_access || !armv8pmu_event_has_user_read(event)) return 0; return event->hw.idx + 1; } static void armv8pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, struct task_struct *task, bool sched_in) { struct arm_pmu *armpmu = *this_cpu_ptr(&cpu_armpmu); struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events); if (!hw_events->branch_users) return; if (sched_in) brbe_invalidate(); } /* * Add an event filter to a given event. */ static int armv8pmu_set_event_filter(struct hw_perf_event *event, struct perf_event_attr *attr) { unsigned long config_base = 0; struct perf_event *perf_event = container_of(attr, struct perf_event, attr); struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu); u32 th; if (attr->exclude_idle) { pr_debug("ARM performance counters do not support mode exclusion\n"); return -EOPNOTSUPP; } if (has_branch_stack(perf_event)) { if (!brbe_num_branch_records(cpu_pmu) || !brbe_branch_attr_valid(perf_event)) return -EOPNOTSUPP; perf_event->attach_state |= PERF_ATTACH_SCHED_CB; } /* * If we're running in hyp mode, then we *are* the hypervisor. * Therefore we ignore exclude_hv in this configuration, since * there's no hypervisor to sample anyway. This is consistent * with other architectures (x86 and Power). */ if (is_kernel_in_hyp_mode()) { if (!attr->exclude_kernel && !attr->exclude_host) config_base |= ARMV8_PMU_INCLUDE_EL2; if (attr->exclude_guest) config_base |= ARMV8_PMU_EXCLUDE_EL1; if (attr->exclude_host) config_base |= ARMV8_PMU_EXCLUDE_EL0; } else { if (!attr->exclude_hv && !attr->exclude_host) config_base |= ARMV8_PMU_INCLUDE_EL2; } /* * Filter out !VHE kernels and guest kernels */ if (attr->exclude_kernel) config_base |= ARMV8_PMU_EXCLUDE_EL1; if (attr->exclude_user) config_base |= ARMV8_PMU_EXCLUDE_EL0; /* * If FEAT_PMUv3_TH isn't implemented, then THWIDTH (threshold_max) will * be 0 and will also trigger this check, preventing it from being used. */ th = armv8pmu_event_get_threshold(attr); if (th > threshold_max(cpu_pmu)) { pr_debug("PMU event threshold exceeds max value\n"); return -EINVAL; } if (th) { config_base |= FIELD_PREP(ARMV8_PMU_EVTYPE_TH, th); config_base |= FIELD_PREP(ARMV8_PMU_EVTYPE_TC, armv8pmu_event_threshold_control(attr)); } /* * Install the filter into config_base as this is used to * construct the event type. */ event->config_base = config_base; return 0; } static void armv8pmu_reset(void *info) { struct arm_pmu *cpu_pmu = (struct arm_pmu *)info; u64 pmcr, mask; bitmap_to_arr64(&mask, cpu_pmu->cntr_mask, ARMPMU_MAX_HWEVENTS); /* The counter and interrupt enable registers are unknown at reset. */ armv8pmu_disable_counter(mask); armv8pmu_disable_intens(mask); /* Clear the counters we flip at guest entry/exit */ kvm_clr_pmu_events(mask); if (brbe_num_branch_records(cpu_pmu)) { brbe_disable(); brbe_invalidate(); } /* * Initialize & Reset PMNC. Request overflow interrupt for * 64 bit cycle counter but cheat in armv8pmu_write_counter(). */ pmcr = ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_LC; /* Enable long event counter support where available */ if (armv8pmu_has_long_event(cpu_pmu)) pmcr |= ARMV8_PMU_PMCR_LP; armv8pmu_pmcr_write(pmcr); } static int __armv8_pmuv3_map_event_id(struct arm_pmu *armpmu, struct perf_event *event) { if (event->attr.type == PERF_TYPE_HARDWARE && event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS) { if (test_bit(ARMV8_PMUV3_PERFCTR_BR_RETIRED, armpmu->pmceid_bitmap)) return ARMV8_PMUV3_PERFCTR_BR_RETIRED; if (test_bit(ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED, armpmu->pmceid_bitmap)) return ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED; return HW_OP_UNSUPPORTED; } return armpmu_map_event(event, &armv8_pmuv3_perf_map, &armv8_pmuv3_perf_cache_map, ARMV8_PMU_EVTYPE_EVENT); } static int __armv8_pmuv3_map_event(struct perf_event *event, const unsigned (*extra_event_map) [PERF_COUNT_HW_MAX], const unsigned (*extra_cache_map) [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]) { int hw_event_id; struct arm_pmu *armpmu = to_arm_pmu(event->pmu); hw_event_id = __armv8_pmuv3_map_event_id(armpmu, event); /* * CHAIN events only work when paired with an adjacent counter, and it * never makes sense for a user to open one in isolation, as they'll be * rotated arbitrarily. */ if (hw_event_id == ARMV8_PMUV3_PERFCTR_CHAIN) return -EINVAL; if (armv8pmu_event_is_64bit(event)) event->hw.flags |= ARMPMU_EVT_64BIT; /* * User events must be allocated into a single counter, and so * must not be chained. * * Most 64-bit events require long counter support, but 64-bit * CPU_CYCLES events can be placed into the dedicated cycle * counter when this is free. */ if (armv8pmu_event_want_user_access(event)) { if (!(event->attach_state & PERF_ATTACH_TASK)) return -EINVAL; if (armv8pmu_event_is_64bit(event) && (hw_event_id != ARMV8_PMUV3_PERFCTR_CPU_CYCLES) && !armv8pmu_has_long_event(armpmu)) return -EOPNOTSUPP; event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT; } /* Only expose micro/arch events supported by this PMU */ if ((hw_event_id > 0) && (hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS) && test_bit(hw_event_id, armpmu->pmceid_bitmap)) { return hw_event_id; } return armpmu_map_event(event, extra_event_map, extra_cache_map, ARMV8_PMU_EVTYPE_EVENT); } static int armv8_pmuv3_map_event(struct perf_event *event) { return __armv8_pmuv3_map_event(event, NULL, NULL); } static int armv8_a53_map_event(struct perf_event *event) { return __armv8_pmuv3_map_event(event, NULL, &armv8_a53_perf_cache_map); } static int armv8_a57_map_event(struct perf_event *event) { return __armv8_pmuv3_map_event(event, NULL, &armv8_a57_perf_cache_map); } static int armv8_a73_map_event(struct perf_event *event) { return __armv8_pmuv3_map_event(event, NULL, &armv8_a73_perf_cache_map); } static int armv8_thunder_map_event(struct perf_event *event) { return __armv8_pmuv3_map_event(event, NULL, &armv8_thunder_perf_cache_map); } static int armv8_vulcan_map_event(struct perf_event *event) { return __armv8_pmuv3_map_event(event, NULL, &armv8_vulcan_perf_cache_map); } struct armv8pmu_probe_info { struct arm_pmu *pmu; bool present; }; static void __armv8pmu_probe_pmu(void *info) { struct armv8pmu_probe_info *probe = info; struct arm_pmu *cpu_pmu = probe->pmu; u64 pmceid_raw[2]; u32 pmceid[2]; int pmuver; pmuver = read_pmuver(); if (!pmuv3_implemented(pmuver)) return; cpu_pmu->pmuver = pmuver; probe->present = true; /* Read the nb of CNTx counters supported from PMNC */ bitmap_set(cpu_pmu->cntr_mask, 0, FIELD_GET(ARMV8_PMU_PMCR_N, armv8pmu_pmcr_read())); /* Add the CPU cycles counter */ set_bit(ARMV8_PMU_CYCLE_IDX, cpu_pmu->cntr_mask); /* Add the CPU instructions counter */ if (pmuv3_has_icntr()) set_bit(ARMV8_PMU_INSTR_IDX, cpu_pmu->cntr_mask); pmceid[0] = pmceid_raw[0] = read_pmceid0(); pmceid[1] = pmceid_raw[1] = read_pmceid1(); bitmap_from_arr32(cpu_pmu->pmceid_bitmap, pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS); pmceid[0] = pmceid_raw[0] >> 32; pmceid[1] = pmceid_raw[1] >> 32; bitmap_from_arr32(cpu_pmu->pmceid_ext_bitmap, pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS); /* store PMMIR register for sysfs */ if (is_pmuv3p4(pmuver)) cpu_pmu->reg_pmmir = read_pmmir(); else cpu_pmu->reg_pmmir = 0; brbe_probe(cpu_pmu); } static int branch_records_alloc(struct arm_pmu *armpmu) { size_t size = struct_size_t(struct perf_branch_stack, entries, brbe_num_branch_records(armpmu)); int cpu; for_each_cpu(cpu, &armpmu->supported_cpus) { struct pmu_hw_events *events_cpu; events_cpu = per_cpu_ptr(armpmu->hw_events, cpu); events_cpu->branch_stack = kmalloc(size, GFP_KERNEL); if (!events_cpu->branch_stack) return -ENOMEM; } return 0; } static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu) { struct armv8pmu_probe_info probe = { .pmu = cpu_pmu, .present = false, }; int ret; ret = smp_call_function_any(&cpu_pmu->supported_cpus, __armv8pmu_probe_pmu, &probe, 1); if (ret) return ret; if (!probe.present) return -ENODEV; if (brbe_num_branch_records(cpu_pmu)) { ret = branch_records_alloc(cpu_pmu); if (ret) return ret; } return 0; } static void armv8pmu_disable_user_access_ipi(void *unused) { armv8pmu_disable_user_access(); } static int armv8pmu_proc_user_access_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret || !write || sysctl_perf_user_access) return ret; on_each_cpu(armv8pmu_disable_user_access_ipi, NULL, 1); return 0; } static const struct ctl_table armv8_pmu_sysctl_table[] = { { .procname = "perf_user_access", .data = &sysctl_perf_user_access, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = armv8pmu_proc_user_access_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; static void armv8_pmu_register_sysctl_table(void) { static u32 tbl_registered = 0; if (!cmpxchg_relaxed(&tbl_registered, 0, 1)) register_sysctl("kernel", armv8_pmu_sysctl_table); } static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name, int (*map_event)(struct perf_event *event)) { int ret = armv8pmu_probe_pmu(cpu_pmu); if (ret) return ret; cpu_pmu->handle_irq = armv8pmu_handle_irq; cpu_pmu->enable = armv8pmu_enable_event; cpu_pmu->disable = armv8pmu_disable_event; cpu_pmu->read_counter = armv8pmu_read_counter; cpu_pmu->write_counter = armv8pmu_write_counter; cpu_pmu->get_event_idx = armv8pmu_get_event_idx; cpu_pmu->clear_event_idx = armv8pmu_clear_event_idx; cpu_pmu->start = armv8pmu_start; cpu_pmu->stop = armv8pmu_stop; cpu_pmu->reset = armv8pmu_reset; cpu_pmu->set_event_filter = armv8pmu_set_event_filter; cpu_pmu->pmu.event_idx = armv8pmu_user_event_idx; if (brbe_num_branch_records(cpu_pmu)) cpu_pmu->pmu.sched_task = armv8pmu_sched_task; cpu_pmu->name = name; cpu_pmu->map_event = map_event; cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = &armv8_pmuv3_events_attr_group; cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = &armv8_pmuv3_format_attr_group; cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = &armv8_pmuv3_caps_attr_group; armv8_pmu_register_sysctl_table(); return 0; } #define PMUV3_INIT_SIMPLE(name) \ static int name##_pmu_init(struct arm_pmu *cpu_pmu) \ { \ return armv8_pmu_init(cpu_pmu, #name, armv8_pmuv3_map_event); \ } #define PMUV3_INIT_MAP_EVENT(name, map_event) \ static int name##_pmu_init(struct arm_pmu *cpu_pmu) \ { \ return armv8_pmu_init(cpu_pmu, #name, map_event); \ } PMUV3_INIT_SIMPLE(armv8_pmuv3) PMUV3_INIT_SIMPLE(armv8_cortex_a34) PMUV3_INIT_SIMPLE(armv8_cortex_a55) PMUV3_INIT_SIMPLE(armv8_cortex_a65) PMUV3_INIT_SIMPLE(armv8_cortex_a75) PMUV3_INIT_SIMPLE(armv8_cortex_a76) PMUV3_INIT_SIMPLE(armv8_cortex_a77) PMUV3_INIT_SIMPLE(armv8_cortex_a78) PMUV3_INIT_SIMPLE(armv9_cortex_a510) PMUV3_INIT_SIMPLE(armv9_cortex_a520) PMUV3_INIT_SIMPLE(armv9_cortex_a710) PMUV3_INIT_SIMPLE(armv9_cortex_a715) PMUV3_INIT_SIMPLE(armv9_cortex_a720) PMUV3_INIT_SIMPLE(armv9_cortex_a725) PMUV3_INIT_SIMPLE(armv8_cortex_x1) PMUV3_INIT_SIMPLE(armv9_cortex_x2) PMUV3_INIT_SIMPLE(armv9_cortex_x3) PMUV3_INIT_SIMPLE(armv9_cortex_x4) PMUV3_INIT_SIMPLE(armv9_cortex_x925) PMUV3_INIT_SIMPLE(armv8_neoverse_e1) PMUV3_INIT_SIMPLE(armv8_neoverse_n1) PMUV3_INIT_SIMPLE(armv9_neoverse_n2) PMUV3_INIT_SIMPLE(armv9_neoverse_n3) PMUV3_INIT_SIMPLE(armv8_neoverse_v1) PMUV3_INIT_SIMPLE(armv8_neoverse_v2) PMUV3_INIT_SIMPLE(armv8_neoverse_v3) PMUV3_INIT_SIMPLE(armv8_neoverse_v3ae) PMUV3_INIT_SIMPLE(armv8_rainier) PMUV3_INIT_SIMPLE(armv8_nvidia_carmel) PMUV3_INIT_SIMPLE(armv8_nvidia_denver) PMUV3_INIT_SIMPLE(armv8_samsung_mongoose) PMUV3_INIT_MAP_EVENT(armv8_cortex_a35, armv8_a53_map_event) PMUV3_INIT_MAP_EVENT(armv8_cortex_a53, armv8_a53_map_event) PMUV3_INIT_MAP_EVENT(armv8_cortex_a57, armv8_a57_map_event) PMUV3_INIT_MAP_EVENT(armv8_cortex_a72, armv8_a57_map_event) PMUV3_INIT_MAP_EVENT(armv8_cortex_a73, armv8_a73_map_event) PMUV3_INIT_MAP_EVENT(armv8_cavium_thunder, armv8_thunder_map_event) PMUV3_INIT_MAP_EVENT(armv8_brcm_vulcan, armv8_vulcan_map_event) static const struct of_device_id armv8_pmu_of_device_ids[] = { {.compatible = "arm,armv8-pmuv3", .data = armv8_pmuv3_pmu_init}, {.compatible = "arm,cortex-a34-pmu", .data = armv8_cortex_a34_pmu_init}, {.compatible = "arm,cortex-a35-pmu", .data = armv8_cortex_a35_pmu_init}, {.compatible = "arm,cortex-a53-pmu", .data = armv8_cortex_a53_pmu_init}, {.compatible = "arm,cortex-a55-pmu", .data = armv8_cortex_a55_pmu_init}, {.compatible = "arm,cortex-a57-pmu", .data = armv8_cortex_a57_pmu_init}, {.compatible = "arm,cortex-a65-pmu", .data = armv8_cortex_a65_pmu_init}, {.compatible = "arm,cortex-a72-pmu", .data = armv8_cortex_a72_pmu_init}, {.compatible = "arm,cortex-a73-pmu", .data = armv8_cortex_a73_pmu_init}, {.compatible = "arm,cortex-a75-pmu", .data = armv8_cortex_a75_pmu_init}, {.compatible = "arm,cortex-a76-pmu", .data = armv8_cortex_a76_pmu_init}, {.compatible = "arm,cortex-a77-pmu", .data = armv8_cortex_a77_pmu_init}, {.compatible = "arm,cortex-a78-pmu", .data = armv8_cortex_a78_pmu_init}, {.compatible = "arm,cortex-a510-pmu", .data = armv9_cortex_a510_pmu_init}, {.compatible = "arm,cortex-a520-pmu", .data = armv9_cortex_a520_pmu_init}, {.compatible = "arm,cortex-a710-pmu", .data = armv9_cortex_a710_pmu_init}, {.compatible = "arm,cortex-a715-pmu", .data = armv9_cortex_a715_pmu_init}, {.compatible = "arm,cortex-a720-pmu", .data = armv9_cortex_a720_pmu_init}, {.compatible = "arm,cortex-a725-pmu", .data = armv9_cortex_a725_pmu_init}, {.compatible = "arm,cortex-x1-pmu", .data = armv8_cortex_x1_pmu_init}, {.compatible = "arm,cortex-x2-pmu", .data = armv9_cortex_x2_pmu_init}, {.compatible = "arm,cortex-x3-pmu", .data = armv9_cortex_x3_pmu_init}, {.compatible = "arm,cortex-x4-pmu", .data = armv9_cortex_x4_pmu_init}, {.compatible = "arm,cortex-x925-pmu", .data = armv9_cortex_x925_pmu_init}, {.compatible = "arm,neoverse-e1-pmu", .data = armv8_neoverse_e1_pmu_init}, {.compatible = "arm,neoverse-n1-pmu", .data = armv8_neoverse_n1_pmu_init}, {.compatible = "arm,neoverse-n2-pmu", .data = armv9_neoverse_n2_pmu_init}, {.compatible = "arm,neoverse-n3-pmu", .data = armv9_neoverse_n3_pmu_init}, {.compatible = "arm,neoverse-v1-pmu", .data = armv8_neoverse_v1_pmu_init}, {.compatible = "arm,neoverse-v2-pmu", .data = armv8_neoverse_v2_pmu_init}, {.compatible = "arm,neoverse-v3-pmu", .data = armv8_neoverse_v3_pmu_init}, {.compatible = "arm,neoverse-v3ae-pmu", .data = armv8_neoverse_v3ae_pmu_init}, {.compatible = "arm,rainier-pmu", .data = armv8_rainier_pmu_init}, {.compatible = "cavium,thunder-pmu", .data = armv8_cavium_thunder_pmu_init}, {.compatible = "brcm,vulcan-pmu", .data = armv8_brcm_vulcan_pmu_init}, {.compatible = "nvidia,carmel-pmu", .data = armv8_nvidia_carmel_pmu_init}, {.compatible = "nvidia,denver-pmu", .data = armv8_nvidia_denver_pmu_init}, {.compatible = "samsung,mongoose-pmu", .data = armv8_samsung_mongoose_pmu_init}, {}, }; static int armv8_pmu_device_probe(struct platform_device *pdev) { return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL); } static struct platform_driver armv8_pmu_driver = { .driver = { .name = ARMV8_PMU_PDEV_NAME, .of_match_table = armv8_pmu_of_device_ids, .suppress_bind_attrs = true, }, .probe = armv8_pmu_device_probe, }; static int __init armv8_pmu_driver_init(void) { int ret; if (acpi_disabled) ret = platform_driver_register(&armv8_pmu_driver); else ret = arm_pmu_acpi_probe(armv8_pmuv3_pmu_init); if (!ret) lockup_detector_retry_init(); return ret; } device_initcall(armv8_pmu_driver_init) void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) { struct clock_read_data *rd; unsigned int seq; u64 ns; userpg->cap_user_time = 0; userpg->cap_user_time_zero = 0; userpg->cap_user_time_short = 0; userpg->cap_user_rdpmc = armv8pmu_event_has_user_read(event); if (userpg->cap_user_rdpmc) { if (event->hw.flags & ARMPMU_EVT_64BIT) userpg->pmc_width = 64; else userpg->pmc_width = 32; } do { rd = sched_clock_read_begin(&seq); if (rd->read_sched_clock != arch_timer_read_counter) return; userpg->time_mult = rd->mult; userpg->time_shift = rd->shift; userpg->time_zero = rd->epoch_ns; userpg->time_cycles = rd->epoch_cyc; userpg->time_mask = rd->sched_clock_mask; /* * Subtract the cycle base, such that software that * doesn't know about cap_user_time_short still 'works' * assuming no wraps. */ ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift); userpg->time_zero -= ns; } while (sched_clock_read_retry(seq)); userpg->time_offset = userpg->time_zero - now; /* * time_shift is not expected to be greater than 31 due to * the original published conversion algorithm shifting a * 32-bit value (now specifies a 64-bit value) - refer * perf_event_mmap_page documentation in perf_event.h. */ if (userpg->time_shift == 32) { userpg->time_shift = 31; userpg->time_mult >>= 1; } /* * Internal timekeeping for enabled/running/stopped times * is always computed with the sched_clock. */ userpg->cap_user_time = 1; userpg->cap_user_time_zero = 1; userpg->cap_user_time_short = 1; } |
| 99 99 98 38 38 72 71 72 97 97 29 29 28 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the diskquota system for the LINUX operating system. QUOTA * is implemented using the BSD system call interface as the means of * communication with the user level. This file contains the generic routines * called by the different filesystems on allocation of an inode or block. * These routines take care of the administration needed to have a consistent * diskquota tracking system. The ideas of both user and group quotas are based * on the Melbourne quota system as used on BSD derived systems. The internal * implementation is based on one of the several variants of the LINUX * inode-subsystem with added complexity of the diskquota system. * * Author: Marco van Wieringen <mvw@planets.elm.net> * * Fixes: Dmitry Gorodchanin <pgmdsg@ibi.com>, 11 Feb 96 * * Revised list management to avoid races * -- Bill Hawes, <whawes@star.net>, 9/98 * * Fixed races in dquot_transfer(), dqget() and dquot_alloc_...(). * As the consequence the locking was moved from dquot_decr_...(), * dquot_incr_...() to calling functions. * invalidate_dquots() now writes modified dquots. * Serialized quota_off() and quota_on() for mount point. * Fixed a few bugs in grow_dquots(). * Fixed deadlock in write_dquot() - we no longer account quotas on * quota files * remove_dquot_ref() moved to inode.c - it now traverses through inodes * add_dquot_ref() restarts after blocking * Added check for bogus uid and fixed check for group in quotactl. * Jan Kara, <jack@suse.cz>, sponsored by SuSE CR, 10-11/99 * * Used struct list_head instead of own list struct * Invalidation of referenced dquots is no longer possible * Improved free_dquots list management * Quota and i_blocks are now updated in one place to avoid races * Warnings are now delayed so we won't block in critical section * Write updated not to require dquot lock * Jan Kara, <jack@suse.cz>, 9/2000 * * Added dynamic quota structure allocation * Jan Kara <jack@suse.cz> 12/2000 * * Rewritten quota interface. Implemented new quota format and * formats registering. * Jan Kara, <jack@suse.cz>, 2001,2002 * * New SMP locking. * Jan Kara, <jack@suse.cz>, 10/2002 * * Added journalled quota support, fix lock inversion problems * Jan Kara, <jack@suse.cz>, 2003,2004 * * (C) Copyright 1994 - 1997 Marco van Wieringen */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/mm.h> #include <linux/time.h> #include <linux/types.h> #include <linux/string.h> #include <linux/fcntl.h> #include <linux/stat.h> #include <linux/tty.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/sysctl.h> #include <linux/init.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/security.h> #include <linux/sched.h> #include <linux/cred.h> #include <linux/kmod.h> #include <linux/namei.h> #include <linux/capability.h> #include <linux/quotaops.h> #include <linux/blkdev.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> /* * There are five quota SMP locks: * * dq_list_lock protects all lists with quotas and quota formats. * * dquot->dq_dqb_lock protects data from dq_dqb * * inode->i_lock protects inode->i_blocks, i_bytes and also guards * consistency of dquot->dq_dqb with inode->i_blocks, i_bytes so that * dquot_transfer() can stabilize amount it transfers * * dq_data_lock protects mem_dqinfo structures and modifications of dquot * pointers in the inode * * dq_state_lock protects modifications of quota state (on quotaon and * quotaoff) and readers who care about latest values take it as well. * * The spinlock ordering is hence: * dq_data_lock > dq_list_lock > i_lock > dquot->dq_dqb_lock, * dq_list_lock > dq_state_lock * * Note that some things (eg. sb pointer, type, id) doesn't change during * the life of the dquot structure and so needn't to be protected by a lock * * Operation accessing dquots via inode pointers are protected by dquot_srcu. * Operation of reading pointer needs srcu_read_lock(&dquot_srcu), and * synchronize_srcu(&dquot_srcu) is called after clearing pointers from * inode and before dropping dquot references to avoid use of dquots after * they are freed. dq_data_lock is used to serialize the pointer setting and * clearing operations. * Special care needs to be taken about S_NOQUOTA inode flag (marking that * inode is a quota file). Functions adding pointers from inode to dquots have * to check this flag under dq_data_lock and then (if S_NOQUOTA is not set) they * have to do all pointer modifications before dropping dq_data_lock. This makes * sure they cannot race with quotaon which first sets S_NOQUOTA flag and * then drops all pointers to dquots from an inode. * * Each dquot has its dq_lock mutex. Dquot is locked when it is being read to * memory (or space for it is being allocated) on the first dqget(), when it is * being written out, and when it is being released on the last dqput(). The * allocation and release operations are serialized by the dq_lock and by * checking the use count in dquot_release(). * * Lock ordering (including related VFS locks) is the following: * s_umount > i_mutex > journal_lock > dquot->dq_lock > dqio_sem */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_list_lock); static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_state_lock); __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_data_lock); EXPORT_SYMBOL(dq_data_lock); DEFINE_STATIC_SRCU(dquot_srcu); static DECLARE_WAIT_QUEUE_HEAD(dquot_ref_wq); void __quota_error(struct super_block *sb, const char *func, const char *fmt, ...) { if (printk_ratelimit()) { va_list args; struct va_format vaf; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk(KERN_ERR "Quota error (device %s): %s: %pV\n", sb->s_id, func, &vaf); va_end(args); } } EXPORT_SYMBOL(__quota_error); #if defined(CONFIG_QUOTA_DEBUG) || defined(CONFIG_PRINT_QUOTA_WARNING) static char *quotatypes[] = INITQFNAMES; #endif static struct quota_format_type *quota_formats; /* List of registered formats */ static struct quota_module_name module_names[] = INIT_QUOTA_MODULE_NAMES; /* SLAB cache for dquot structures */ static struct kmem_cache *dquot_cachep; /* workqueue for work quota_release_work*/ static struct workqueue_struct *quota_unbound_wq; void register_quota_format(struct quota_format_type *fmt) { spin_lock(&dq_list_lock); fmt->qf_next = quota_formats; quota_formats = fmt; spin_unlock(&dq_list_lock); } EXPORT_SYMBOL(register_quota_format); void unregister_quota_format(struct quota_format_type *fmt) { struct quota_format_type **actqf; spin_lock(&dq_list_lock); for (actqf = "a_formats; *actqf && *actqf != fmt; actqf = &(*actqf)->qf_next) ; if (*actqf) *actqf = (*actqf)->qf_next; spin_unlock(&dq_list_lock); } EXPORT_SYMBOL(unregister_quota_format); static struct quota_format_type *find_quota_format(int id) { struct quota_format_type *actqf; spin_lock(&dq_list_lock); for (actqf = quota_formats; actqf && actqf->qf_fmt_id != id; actqf = actqf->qf_next) ; if (!actqf || !try_module_get(actqf->qf_owner)) { int qm; spin_unlock(&dq_list_lock); for (qm = 0; module_names[qm].qm_fmt_id && module_names[qm].qm_fmt_id != id; qm++) ; if (!module_names[qm].qm_fmt_id || request_module(module_names[qm].qm_mod_name)) return NULL; spin_lock(&dq_list_lock); for (actqf = quota_formats; actqf && actqf->qf_fmt_id != id; actqf = actqf->qf_next) ; if (actqf && !try_module_get(actqf->qf_owner)) actqf = NULL; } spin_unlock(&dq_list_lock); return actqf; } static void put_quota_format(struct quota_format_type *fmt) { module_put(fmt->qf_owner); } /* * Dquot List Management: * The quota code uses five lists for dquot management: the inuse_list, * releasing_dquots, free_dquots, dqi_dirty_list, and dquot_hash[] array. * A single dquot structure may be on some of those lists, depending on * its current state. * * All dquots are placed to the end of inuse_list when first created, and this * list is used for invalidate operation, which must look at every dquot. * * When the last reference of a dquot is dropped, the dquot is added to * releasing_dquots. We'll then queue work item which will call * synchronize_srcu() and after that perform the final cleanup of all the * dquots on the list. Each cleaned up dquot is moved to free_dquots list. * Both releasing_dquots and free_dquots use the dq_free list_head in the dquot * struct. * * Unused and cleaned up dquots are in the free_dquots list and this list is * searched whenever we need an available dquot. Dquots are removed from the * list as soon as they are used again and dqstats.free_dquots gives the number * of dquots on the list. When dquot is invalidated it's completely released * from memory. * * Dirty dquots are added to the dqi_dirty_list of quota_info when mark * dirtied, and this list is searched when writing dirty dquots back to * quota file. Note that some filesystems do dirty dquot tracking on their * own (e.g. in a journal) and thus don't use dqi_dirty_list. * * Dquots with a specific identity (device, type and id) are placed on * one of the dquot_hash[] hash chains. The provides an efficient search * mechanism to locate a specific dquot. */ static LIST_HEAD(inuse_list); static LIST_HEAD(free_dquots); static LIST_HEAD(releasing_dquots); static unsigned int dq_hash_bits, dq_hash_mask; static struct hlist_head *dquot_hash; struct dqstats dqstats; EXPORT_SYMBOL(dqstats); static qsize_t inode_get_rsv_space(struct inode *inode); static qsize_t __inode_get_rsv_space(struct inode *inode); static int __dquot_initialize(struct inode *inode, int type); static void quota_release_workfn(struct work_struct *work); static DECLARE_DELAYED_WORK(quota_release_work, quota_release_workfn); static inline unsigned int hashfn(const struct super_block *sb, struct kqid qid) { unsigned int id = from_kqid(&init_user_ns, qid); int type = qid.type; unsigned long tmp; tmp = (((unsigned long)sb>>L1_CACHE_SHIFT) ^ id) * (MAXQUOTAS - type); return (tmp + (tmp >> dq_hash_bits)) & dq_hash_mask; } /* * Following list functions expect dq_list_lock to be held */ static inline void insert_dquot_hash(struct dquot *dquot) { struct hlist_head *head; head = dquot_hash + hashfn(dquot->dq_sb, dquot->dq_id); hlist_add_head(&dquot->dq_hash, head); } static inline void remove_dquot_hash(struct dquot *dquot) { hlist_del_init(&dquot->dq_hash); } static struct dquot *find_dquot(unsigned int hashent, struct super_block *sb, struct kqid qid) { struct dquot *dquot; hlist_for_each_entry(dquot, dquot_hash+hashent, dq_hash) if (dquot->dq_sb == sb && qid_eq(dquot->dq_id, qid)) return dquot; return NULL; } /* Add a dquot to the tail of the free list */ static inline void put_dquot_last(struct dquot *dquot) { list_add_tail(&dquot->dq_free, &free_dquots); dqstats_inc(DQST_FREE_DQUOTS); } static inline void put_releasing_dquots(struct dquot *dquot) { list_add_tail(&dquot->dq_free, &releasing_dquots); set_bit(DQ_RELEASING_B, &dquot->dq_flags); } static inline void remove_free_dquot(struct dquot *dquot) { if (list_empty(&dquot->dq_free)) return; list_del_init(&dquot->dq_free); if (!test_bit(DQ_RELEASING_B, &dquot->dq_flags)) dqstats_dec(DQST_FREE_DQUOTS); else clear_bit(DQ_RELEASING_B, &dquot->dq_flags); } static inline void put_inuse(struct dquot *dquot) { /* We add to the back of inuse list so we don't have to restart * when traversing this list and we block */ list_add_tail(&dquot->dq_inuse, &inuse_list); dqstats_inc(DQST_ALLOC_DQUOTS); } static inline void remove_inuse(struct dquot *dquot) { dqstats_dec(DQST_ALLOC_DQUOTS); list_del(&dquot->dq_inuse); } /* * End of list functions needing dq_list_lock */ static void wait_on_dquot(struct dquot *dquot) { mutex_lock(&dquot->dq_lock); mutex_unlock(&dquot->dq_lock); } static inline int dquot_active(struct dquot *dquot) { return test_bit(DQ_ACTIVE_B, &dquot->dq_flags); } static inline int dquot_dirty(struct dquot *dquot) { return test_bit(DQ_MOD_B, &dquot->dq_flags); } static inline int mark_dquot_dirty(struct dquot *dquot) { return dquot->dq_sb->dq_op->mark_dirty(dquot); } /* Mark dquot dirty in atomic manner, and return it's old dirty flag state */ int dquot_mark_dquot_dirty(struct dquot *dquot) { int ret = 1; if (!dquot_active(dquot)) return 0; if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY) return test_and_set_bit(DQ_MOD_B, &dquot->dq_flags); /* If quota is dirty already, we don't have to acquire dq_list_lock */ if (dquot_dirty(dquot)) return 1; spin_lock(&dq_list_lock); if (!test_and_set_bit(DQ_MOD_B, &dquot->dq_flags)) { list_add(&dquot->dq_dirty, &sb_dqopt(dquot->dq_sb)-> info[dquot->dq_id.type].dqi_dirty_list); ret = 0; } spin_unlock(&dq_list_lock); return ret; } EXPORT_SYMBOL(dquot_mark_dquot_dirty); /* Dirtify all the dquots - this can block when journalling */ static inline int mark_all_dquot_dirty(struct dquot __rcu * const *dquots) { int ret, err, cnt; struct dquot *dquot; ret = err = 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (dquot) /* Even in case of error we have to continue */ ret = mark_dquot_dirty(dquot); if (!err && ret < 0) err = ret; } return err; } static inline void dqput_all(struct dquot **dquot) { unsigned int cnt; for (cnt = 0; cnt < MAXQUOTAS; cnt++) dqput(dquot[cnt]); } static inline int clear_dquot_dirty(struct dquot *dquot) { if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY) return test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags); spin_lock(&dq_list_lock); if (!test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags)) { spin_unlock(&dq_list_lock); return 0; } list_del_init(&dquot->dq_dirty); spin_unlock(&dq_list_lock); return 1; } void mark_info_dirty(struct super_block *sb, int type) { spin_lock(&dq_data_lock); sb_dqopt(sb)->info[type].dqi_flags |= DQF_INFO_DIRTY; spin_unlock(&dq_data_lock); } EXPORT_SYMBOL(mark_info_dirty); /* * Read dquot from disk and alloc space for it */ int dquot_acquire(struct dquot *dquot) { int ret = 0, ret2 = 0; unsigned int memalloc; struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); mutex_lock(&dquot->dq_lock); memalloc = memalloc_nofs_save(); if (!test_bit(DQ_READ_B, &dquot->dq_flags)) { ret = dqopt->ops[dquot->dq_id.type]->read_dqblk(dquot); if (ret < 0) goto out_iolock; } /* Make sure flags update is visible after dquot has been filled */ smp_mb__before_atomic(); set_bit(DQ_READ_B, &dquot->dq_flags); /* Instantiate dquot if needed */ if (!dquot_active(dquot) && !dquot->dq_off) { ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot); /* Write the info if needed */ if (info_dirty(&dqopt->info[dquot->dq_id.type])) { ret2 = dqopt->ops[dquot->dq_id.type]->write_file_info( dquot->dq_sb, dquot->dq_id.type); } if (ret < 0) goto out_iolock; if (ret2 < 0) { ret = ret2; goto out_iolock; } } /* * Make sure flags update is visible after on-disk struct has been * allocated. Paired with smp_rmb() in dqget(). */ smp_mb__before_atomic(); set_bit(DQ_ACTIVE_B, &dquot->dq_flags); out_iolock: memalloc_nofs_restore(memalloc); mutex_unlock(&dquot->dq_lock); return ret; } EXPORT_SYMBOL(dquot_acquire); /* * Write dquot to disk */ int dquot_commit(struct dquot *dquot) { int ret = 0; unsigned int memalloc; struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); mutex_lock(&dquot->dq_lock); memalloc = memalloc_nofs_save(); if (!clear_dquot_dirty(dquot)) goto out_lock; /* Inactive dquot can be only if there was error during read/init * => we have better not writing it */ if (dquot_active(dquot)) ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot); else ret = -EIO; out_lock: memalloc_nofs_restore(memalloc); mutex_unlock(&dquot->dq_lock); return ret; } EXPORT_SYMBOL(dquot_commit); /* * Release dquot */ int dquot_release(struct dquot *dquot) { int ret = 0, ret2 = 0; unsigned int memalloc; struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); mutex_lock(&dquot->dq_lock); memalloc = memalloc_nofs_save(); /* Check whether we are not racing with some other dqget() */ if (dquot_is_busy(dquot)) goto out_dqlock; if (dqopt->ops[dquot->dq_id.type]->release_dqblk) { ret = dqopt->ops[dquot->dq_id.type]->release_dqblk(dquot); /* Write the info */ if (info_dirty(&dqopt->info[dquot->dq_id.type])) { ret2 = dqopt->ops[dquot->dq_id.type]->write_file_info( dquot->dq_sb, dquot->dq_id.type); } if (ret >= 0) ret = ret2; } clear_bit(DQ_ACTIVE_B, &dquot->dq_flags); out_dqlock: memalloc_nofs_restore(memalloc); mutex_unlock(&dquot->dq_lock); return ret; } EXPORT_SYMBOL(dquot_release); void dquot_destroy(struct dquot *dquot) { kmem_cache_free(dquot_cachep, dquot); } EXPORT_SYMBOL(dquot_destroy); static inline void do_destroy_dquot(struct dquot *dquot) { dquot->dq_sb->dq_op->destroy_dquot(dquot); } /* Invalidate all dquots on the list. Note that this function is called after * quota is disabled and pointers from inodes removed so there cannot be new * quota users. There can still be some users of quotas due to inodes being * just deleted or pruned by prune_icache() (those are not attached to any * list) or parallel quotactl call. We have to wait for such users. */ static void invalidate_dquots(struct super_block *sb, int type) { struct dquot *dquot, *tmp; restart: flush_delayed_work("a_release_work); spin_lock(&dq_list_lock); list_for_each_entry_safe(dquot, tmp, &inuse_list, dq_inuse) { if (dquot->dq_sb != sb) continue; if (dquot->dq_id.type != type) continue; /* Wait for dquot users */ if (atomic_read(&dquot->dq_count)) { atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); /* * Once dqput() wakes us up, we know it's time to free * the dquot. * IMPORTANT: we rely on the fact that there is always * at most one process waiting for dquot to free. * Otherwise dq_count would be > 1 and we would never * wake up. */ wait_event(dquot_ref_wq, atomic_read(&dquot->dq_count) == 1); dqput(dquot); /* At this moment dquot() need not exist (it could be * reclaimed by prune_dqcache(). Hence we must * restart. */ goto restart; } /* * The last user already dropped its reference but dquot didn't * get fully cleaned up yet. Restart the scan which flushes the * work cleaning up released dquots. */ if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) { spin_unlock(&dq_list_lock); goto restart; } /* * Quota now has no users and it has been written on last * dqput() */ remove_dquot_hash(dquot); remove_free_dquot(dquot); remove_inuse(dquot); do_destroy_dquot(dquot); } spin_unlock(&dq_list_lock); } /* Call callback for every active dquot on given filesystem */ int dquot_scan_active(struct super_block *sb, int (*fn)(struct dquot *dquot, unsigned long priv), unsigned long priv) { struct dquot *dquot, *old_dquot = NULL; int ret = 0; WARN_ON_ONCE(!rwsem_is_locked(&sb->s_umount)); spin_lock(&dq_list_lock); list_for_each_entry(dquot, &inuse_list, dq_inuse) { if (!dquot_active(dquot)) continue; if (dquot->dq_sb != sb) continue; /* Now we have active dquot so we can just increase use count */ atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); dqput(old_dquot); old_dquot = dquot; /* * ->release_dquot() can be racing with us. Our reference * protects us from new calls to it so just wait for any * outstanding call and recheck the DQ_ACTIVE_B after that. */ wait_on_dquot(dquot); if (dquot_active(dquot)) { ret = fn(dquot, priv); if (ret < 0) goto out; } spin_lock(&dq_list_lock); /* We are safe to continue now because our dquot could not * be moved out of the inuse list while we hold the reference */ } spin_unlock(&dq_list_lock); out: dqput(old_dquot); return ret; } EXPORT_SYMBOL(dquot_scan_active); static inline int dquot_write_dquot(struct dquot *dquot) { int ret = dquot->dq_sb->dq_op->write_dquot(dquot); if (ret < 0) { quota_error(dquot->dq_sb, "Can't write quota structure " "(error %d). Quota may get out of sync!", ret); /* Clear dirty bit anyway to avoid infinite loop. */ clear_dquot_dirty(dquot); } return ret; } /* Write all dquot structures to quota files */ int dquot_writeback_dquots(struct super_block *sb, int type) { struct list_head dirty; struct dquot *dquot; struct quota_info *dqopt = sb_dqopt(sb); int cnt; int err, ret = 0; WARN_ON_ONCE(!rwsem_is_locked(&sb->s_umount)); flush_delayed_work("a_release_work); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; if (!sb_has_quota_active(sb, cnt)) continue; spin_lock(&dq_list_lock); /* Move list away to avoid livelock. */ list_replace_init(&dqopt->info[cnt].dqi_dirty_list, &dirty); while (!list_empty(&dirty)) { dquot = list_first_entry(&dirty, struct dquot, dq_dirty); WARN_ON(!dquot_active(dquot)); /* If the dquot is releasing we should not touch it */ if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) { spin_unlock(&dq_list_lock); flush_delayed_work("a_release_work); spin_lock(&dq_list_lock); continue; } /* Now we have active dquot from which someone is * holding reference so we can safely just increase * use count */ dqgrab(dquot); spin_unlock(&dq_list_lock); err = dquot_write_dquot(dquot); if (err && !ret) ret = err; dqput(dquot); spin_lock(&dq_list_lock); } spin_unlock(&dq_list_lock); } for (cnt = 0; cnt < MAXQUOTAS; cnt++) if ((cnt == type || type == -1) && sb_has_quota_active(sb, cnt) && info_dirty(&dqopt->info[cnt])) sb->dq_op->write_info(sb, cnt); dqstats_inc(DQST_SYNCS); return ret; } EXPORT_SYMBOL(dquot_writeback_dquots); /* Write all dquot structures to disk and make them visible from userspace */ int dquot_quota_sync(struct super_block *sb, int type) { struct quota_info *dqopt = sb_dqopt(sb); int cnt; int ret; ret = dquot_writeback_dquots(sb, type); if (ret) return ret; if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) return 0; /* This is not very clever (and fast) but currently I don't know about * any other simple way of getting quota data to disk and we must get * them there for userspace to be visible... */ if (sb->s_op->sync_fs) { ret = sb->s_op->sync_fs(sb, 1); if (ret) return ret; } ret = sync_blockdev(sb->s_bdev); if (ret) return ret; /* * Now when everything is written we can discard the pagecache so * that userspace sees the changes. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; if (!sb_has_quota_active(sb, cnt)) continue; inode_lock(dqopt->files[cnt]); truncate_inode_pages(&dqopt->files[cnt]->i_data, 0); inode_unlock(dqopt->files[cnt]); } return 0; } EXPORT_SYMBOL(dquot_quota_sync); static unsigned long dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { struct dquot *dquot; unsigned long freed = 0; spin_lock(&dq_list_lock); while (!list_empty(&free_dquots) && sc->nr_to_scan) { dquot = list_first_entry(&free_dquots, struct dquot, dq_free); remove_dquot_hash(dquot); remove_free_dquot(dquot); remove_inuse(dquot); do_destroy_dquot(dquot); sc->nr_to_scan--; freed++; } spin_unlock(&dq_list_lock); return freed; } static unsigned long dqcache_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { return vfs_pressure_ratio( percpu_counter_read_positive(&dqstats.counter[DQST_FREE_DQUOTS])); } /* * Safely release dquot and put reference to dquot. */ static void quota_release_workfn(struct work_struct *work) { struct dquot *dquot; struct list_head rls_head; spin_lock(&dq_list_lock); /* Exchange the list head to avoid livelock. */ list_replace_init(&releasing_dquots, &rls_head); spin_unlock(&dq_list_lock); synchronize_srcu(&dquot_srcu); restart: spin_lock(&dq_list_lock); while (!list_empty(&rls_head)) { dquot = list_first_entry(&rls_head, struct dquot, dq_free); WARN_ON_ONCE(atomic_read(&dquot->dq_count)); /* * Note that DQ_RELEASING_B protects us from racing with * invalidate_dquots() calls so we are safe to work with the * dquot even after we drop dq_list_lock. */ if (dquot_dirty(dquot)) { spin_unlock(&dq_list_lock); /* Commit dquot before releasing */ dquot_write_dquot(dquot); goto restart; } if (dquot_active(dquot)) { spin_unlock(&dq_list_lock); dquot->dq_sb->dq_op->release_dquot(dquot); goto restart; } /* Dquot is inactive and clean, now move it to free list */ remove_free_dquot(dquot); put_dquot_last(dquot); } spin_unlock(&dq_list_lock); } /* * Put reference to dquot */ void dqput(struct dquot *dquot) { if (!dquot) return; #ifdef CONFIG_QUOTA_DEBUG if (!atomic_read(&dquot->dq_count)) { quota_error(dquot->dq_sb, "trying to free free dquot of %s %d", quotatypes[dquot->dq_id.type], from_kqid(&init_user_ns, dquot->dq_id)); BUG(); } #endif dqstats_inc(DQST_DROPS); spin_lock(&dq_list_lock); if (atomic_read(&dquot->dq_count) > 1) { /* We have more than one user... nothing to do */ atomic_dec(&dquot->dq_count); /* Releasing dquot during quotaoff phase? */ if (!sb_has_quota_active(dquot->dq_sb, dquot->dq_id.type) && atomic_read(&dquot->dq_count) == 1) wake_up(&dquot_ref_wq); spin_unlock(&dq_list_lock); return; } /* Need to release dquot? */ WARN_ON_ONCE(!list_empty(&dquot->dq_free)); put_releasing_dquots(dquot); atomic_dec(&dquot->dq_count); spin_unlock(&dq_list_lock); queue_delayed_work(quota_unbound_wq, "a_release_work, 1); } EXPORT_SYMBOL(dqput); struct dquot *dquot_alloc(struct super_block *sb, int type) { return kmem_cache_zalloc(dquot_cachep, GFP_NOFS); } EXPORT_SYMBOL(dquot_alloc); static struct dquot *get_empty_dquot(struct super_block *sb, int type) { struct dquot *dquot; dquot = sb->dq_op->alloc_dquot(sb, type); if(!dquot) return NULL; mutex_init(&dquot->dq_lock); INIT_LIST_HEAD(&dquot->dq_free); INIT_LIST_HEAD(&dquot->dq_inuse); INIT_HLIST_NODE(&dquot->dq_hash); INIT_LIST_HEAD(&dquot->dq_dirty); dquot->dq_sb = sb; dquot->dq_id = make_kqid_invalid(type); atomic_set(&dquot->dq_count, 1); spin_lock_init(&dquot->dq_dqb_lock); return dquot; } /* * Get reference to dquot * * Locking is slightly tricky here. We are guarded from parallel quotaoff() * destroying our dquot by: * a) checking for quota flags under dq_list_lock and * b) getting a reference to dquot before we release dq_list_lock */ struct dquot *dqget(struct super_block *sb, struct kqid qid) { unsigned int hashent = hashfn(sb, qid); struct dquot *dquot, *empty = NULL; if (!qid_has_mapping(sb->s_user_ns, qid)) return ERR_PTR(-EINVAL); if (!sb_has_quota_active(sb, qid.type)) return ERR_PTR(-ESRCH); we_slept: spin_lock(&dq_list_lock); spin_lock(&dq_state_lock); if (!sb_has_quota_active(sb, qid.type)) { spin_unlock(&dq_state_lock); spin_unlock(&dq_list_lock); dquot = ERR_PTR(-ESRCH); goto out; } spin_unlock(&dq_state_lock); dquot = find_dquot(hashent, sb, qid); if (!dquot) { if (!empty) { spin_unlock(&dq_list_lock); empty = get_empty_dquot(sb, qid.type); if (!empty) schedule(); /* Try to wait for a moment... */ goto we_slept; } dquot = empty; empty = NULL; dquot->dq_id = qid; /* all dquots go on the inuse_list */ put_inuse(dquot); /* hash it first so it can be found */ insert_dquot_hash(dquot); spin_unlock(&dq_list_lock); dqstats_inc(DQST_LOOKUPS); } else { if (!atomic_read(&dquot->dq_count)) remove_free_dquot(dquot); atomic_inc(&dquot->dq_count); spin_unlock(&dq_list_lock); dqstats_inc(DQST_CACHE_HITS); dqstats_inc(DQST_LOOKUPS); } /* Wait for dq_lock - after this we know that either dquot_release() is * already finished or it will be canceled due to dq_count > 0 test */ wait_on_dquot(dquot); /* Read the dquot / allocate space in quota file */ if (!dquot_active(dquot)) { int err; err = sb->dq_op->acquire_dquot(dquot); if (err < 0) { dqput(dquot); dquot = ERR_PTR(err); goto out; } } /* * Make sure following reads see filled structure - paired with * smp_mb__before_atomic() in dquot_acquire(). */ smp_rmb(); /* Has somebody invalidated entry under us? */ WARN_ON_ONCE(hlist_unhashed(&dquot->dq_hash)); out: if (empty) do_destroy_dquot(empty); return dquot; } EXPORT_SYMBOL(dqget); static inline struct dquot __rcu **i_dquot(struct inode *inode) { return inode->i_sb->s_op->get_dquots(inode); } static int dqinit_needed(struct inode *inode, int type) { struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) return 0; dquots = i_dquot(inode); if (type != -1) return !dquots[type]; for (cnt = 0; cnt < MAXQUOTAS; cnt++) if (!dquots[cnt]) return 1; return 0; } /* This routine is guarded by s_umount semaphore */ static int add_dquot_ref(struct super_block *sb, int type) { struct inode *inode, *old_inode = NULL; #ifdef CONFIG_QUOTA_DEBUG int reserved = 0; #endif int err = 0; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || !atomic_read(&inode->i_writecount) || !dqinit_needed(inode, type)) { spin_unlock(&inode->i_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); #ifdef CONFIG_QUOTA_DEBUG if (unlikely(inode_get_rsv_space(inode) > 0)) reserved = 1; #endif iput(old_inode); err = __dquot_initialize(inode, type); if (err) { iput(inode); goto out; } /* * We hold a reference to 'inode' so it couldn't have been * removed from s_inodes list while we dropped the * s_inode_list_lock. We cannot iput the inode now as we can be * holding the last reference and we cannot iput it under * s_inode_list_lock. So we keep the reference and iput it * later. */ old_inode = inode; cond_resched(); spin_lock(&sb->s_inode_list_lock); } spin_unlock(&sb->s_inode_list_lock); iput(old_inode); out: #ifdef CONFIG_QUOTA_DEBUG if (reserved) { quota_error(sb, "Writes happened before quota was turned on " "thus quota information is probably inconsistent. " "Please run quotacheck(8)"); } #endif return err; } static void remove_dquot_ref(struct super_block *sb, int type) { struct inode *inode; #ifdef CONFIG_QUOTA_DEBUG int reserved = 0; #endif spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { /* * We have to scan also I_NEW inodes because they can already * have quota pointer initialized. Luckily, we need to touch * only quota pointers and these have separate locking * (dq_data_lock). */ spin_lock(&dq_data_lock); if (!IS_NOQUOTA(inode)) { struct dquot __rcu **dquots = i_dquot(inode); struct dquot *dquot = srcu_dereference_check( dquots[type], &dquot_srcu, lockdep_is_held(&dq_data_lock)); #ifdef CONFIG_QUOTA_DEBUG if (unlikely(inode_get_rsv_space(inode) > 0)) reserved = 1; #endif rcu_assign_pointer(dquots[type], NULL); if (dquot) dqput(dquot); } spin_unlock(&dq_data_lock); } spin_unlock(&sb->s_inode_list_lock); #ifdef CONFIG_QUOTA_DEBUG if (reserved) { printk(KERN_WARNING "VFS (%s): Writes happened after quota" " was disabled thus quota information is probably " "inconsistent. Please run quotacheck(8).\n", sb->s_id); } #endif } /* Gather all references from inodes and drop them */ static void drop_dquot_ref(struct super_block *sb, int type) { if (sb->dq_op) remove_dquot_ref(sb, type); } static inline void dquot_free_reserved_space(struct dquot *dquot, qsize_t number) { if (dquot->dq_dqb.dqb_rsvspace >= number) dquot->dq_dqb.dqb_rsvspace -= number; else { WARN_ON_ONCE(1); dquot->dq_dqb.dqb_rsvspace = 0; } if (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace <= dquot->dq_dqb.dqb_bsoftlimit) dquot->dq_dqb.dqb_btime = (time64_t) 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); } static void dquot_decr_inodes(struct dquot *dquot, qsize_t number) { if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NEGATIVE_USAGE || dquot->dq_dqb.dqb_curinodes >= number) dquot->dq_dqb.dqb_curinodes -= number; else dquot->dq_dqb.dqb_curinodes = 0; if (dquot->dq_dqb.dqb_curinodes <= dquot->dq_dqb.dqb_isoftlimit) dquot->dq_dqb.dqb_itime = (time64_t) 0; clear_bit(DQ_INODES_B, &dquot->dq_flags); } static void dquot_decr_space(struct dquot *dquot, qsize_t number) { if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NEGATIVE_USAGE || dquot->dq_dqb.dqb_curspace >= number) dquot->dq_dqb.dqb_curspace -= number; else dquot->dq_dqb.dqb_curspace = 0; if (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace <= dquot->dq_dqb.dqb_bsoftlimit) dquot->dq_dqb.dqb_btime = (time64_t) 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); } struct dquot_warn { struct super_block *w_sb; struct kqid w_dq_id; short w_type; }; static int warning_issued(struct dquot *dquot, const int warntype) { int flag = (warntype == QUOTA_NL_BHARDWARN || warntype == QUOTA_NL_BSOFTLONGWARN) ? DQ_BLKS_B : ((warntype == QUOTA_NL_IHARDWARN || warntype == QUOTA_NL_ISOFTLONGWARN) ? DQ_INODES_B : 0); if (!flag) return 0; return test_and_set_bit(flag, &dquot->dq_flags); } #ifdef CONFIG_PRINT_QUOTA_WARNING static int flag_print_warnings = 1; static int need_print_warning(struct dquot_warn *warn) { if (!flag_print_warnings) return 0; switch (warn->w_dq_id.type) { case USRQUOTA: return uid_eq(current_fsuid(), warn->w_dq_id.uid); case GRPQUOTA: return in_group_p(warn->w_dq_id.gid); case PRJQUOTA: return 1; } return 0; } /* Print warning to user which exceeded quota */ static void print_warning(struct dquot_warn *warn) { char *msg = NULL; struct tty_struct *tty; int warntype = warn->w_type; if (warntype == QUOTA_NL_IHARDBELOW || warntype == QUOTA_NL_ISOFTBELOW || warntype == QUOTA_NL_BHARDBELOW || warntype == QUOTA_NL_BSOFTBELOW || !need_print_warning(warn)) return; tty = get_current_tty(); if (!tty) return; tty_write_message(tty, warn->w_sb->s_id); if (warntype == QUOTA_NL_ISOFTWARN || warntype == QUOTA_NL_BSOFTWARN) tty_write_message(tty, ": warning, "); else tty_write_message(tty, ": write failed, "); tty_write_message(tty, quotatypes[warn->w_dq_id.type]); switch (warntype) { case QUOTA_NL_IHARDWARN: msg = " file limit reached.\r\n"; break; case QUOTA_NL_ISOFTLONGWARN: msg = " file quota exceeded too long.\r\n"; break; case QUOTA_NL_ISOFTWARN: msg = " file quota exceeded.\r\n"; break; case QUOTA_NL_BHARDWARN: msg = " block limit reached.\r\n"; break; case QUOTA_NL_BSOFTLONGWARN: msg = " block quota exceeded too long.\r\n"; break; case QUOTA_NL_BSOFTWARN: msg = " block quota exceeded.\r\n"; break; } tty_write_message(tty, msg); tty_kref_put(tty); } #endif static void prepare_warning(struct dquot_warn *warn, struct dquot *dquot, int warntype) { if (warning_issued(dquot, warntype)) return; warn->w_type = warntype; warn->w_sb = dquot->dq_sb; warn->w_dq_id = dquot->dq_id; } /* * Write warnings to the console and send warning messages over netlink. * * Note that this function can call into tty and networking code. */ static void flush_warnings(struct dquot_warn *warn) { int i; for (i = 0; i < MAXQUOTAS; i++) { if (warn[i].w_type == QUOTA_NL_NOWARN) continue; #ifdef CONFIG_PRINT_QUOTA_WARNING print_warning(&warn[i]); #endif quota_send_warning(warn[i].w_dq_id, warn[i].w_sb->s_dev, warn[i].w_type); } } static int ignore_hardlimit(struct dquot *dquot) { struct mem_dqinfo *info = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type]; return capable(CAP_SYS_RESOURCE) && (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD || !(info->dqi_flags & DQF_ROOT_SQUASH)); } static int dquot_add_inodes(struct dquot *dquot, qsize_t inodes, struct dquot_warn *warn) { qsize_t newinodes; int ret = 0; spin_lock(&dquot->dq_dqb_lock); newinodes = dquot->dq_dqb.dqb_curinodes + inodes; if (!sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_id.type) || test_bit(DQ_FAKE_B, &dquot->dq_flags)) goto add; if (dquot->dq_dqb.dqb_ihardlimit && newinodes > dquot->dq_dqb.dqb_ihardlimit && !ignore_hardlimit(dquot)) { prepare_warning(warn, dquot, QUOTA_NL_IHARDWARN); ret = -EDQUOT; goto out; } if (dquot->dq_dqb.dqb_isoftlimit && newinodes > dquot->dq_dqb.dqb_isoftlimit && dquot->dq_dqb.dqb_itime && ktime_get_real_seconds() >= dquot->dq_dqb.dqb_itime && !ignore_hardlimit(dquot)) { prepare_warning(warn, dquot, QUOTA_NL_ISOFTLONGWARN); ret = -EDQUOT; goto out; } if (dquot->dq_dqb.dqb_isoftlimit && newinodes > dquot->dq_dqb.dqb_isoftlimit && dquot->dq_dqb.dqb_itime == 0) { prepare_warning(warn, dquot, QUOTA_NL_ISOFTWARN); dquot->dq_dqb.dqb_itime = ktime_get_real_seconds() + sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type].dqi_igrace; } add: dquot->dq_dqb.dqb_curinodes = newinodes; out: spin_unlock(&dquot->dq_dqb_lock); return ret; } static int dquot_add_space(struct dquot *dquot, qsize_t space, qsize_t rsv_space, unsigned int flags, struct dquot_warn *warn) { qsize_t tspace; struct super_block *sb = dquot->dq_sb; int ret = 0; spin_lock(&dquot->dq_dqb_lock); if (!sb_has_quota_limits_enabled(sb, dquot->dq_id.type) || test_bit(DQ_FAKE_B, &dquot->dq_flags)) goto finish; tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace + space + rsv_space; if (dquot->dq_dqb.dqb_bhardlimit && tspace > dquot->dq_dqb.dqb_bhardlimit && !ignore_hardlimit(dquot)) { if (flags & DQUOT_SPACE_WARN) prepare_warning(warn, dquot, QUOTA_NL_BHARDWARN); ret = -EDQUOT; goto finish; } if (dquot->dq_dqb.dqb_bsoftlimit && tspace > dquot->dq_dqb.dqb_bsoftlimit && dquot->dq_dqb.dqb_btime && ktime_get_real_seconds() >= dquot->dq_dqb.dqb_btime && !ignore_hardlimit(dquot)) { if (flags & DQUOT_SPACE_WARN) prepare_warning(warn, dquot, QUOTA_NL_BSOFTLONGWARN); ret = -EDQUOT; goto finish; } if (dquot->dq_dqb.dqb_bsoftlimit && tspace > dquot->dq_dqb.dqb_bsoftlimit && dquot->dq_dqb.dqb_btime == 0) { if (flags & DQUOT_SPACE_WARN) { prepare_warning(warn, dquot, QUOTA_NL_BSOFTWARN); dquot->dq_dqb.dqb_btime = ktime_get_real_seconds() + sb_dqopt(sb)->info[dquot->dq_id.type].dqi_bgrace; } else { /* * We don't allow preallocation to exceed softlimit so exceeding will * be always printed */ ret = -EDQUOT; goto finish; } } finish: /* * We have to be careful and go through warning generation & grace time * setting even if DQUOT_SPACE_NOFAIL is set. That's why we check it * only here... */ if (flags & DQUOT_SPACE_NOFAIL) ret = 0; if (!ret) { dquot->dq_dqb.dqb_rsvspace += rsv_space; dquot->dq_dqb.dqb_curspace += space; } spin_unlock(&dquot->dq_dqb_lock); return ret; } static int info_idq_free(struct dquot *dquot, qsize_t inodes) { qsize_t newinodes; if (test_bit(DQ_FAKE_B, &dquot->dq_flags) || dquot->dq_dqb.dqb_curinodes <= dquot->dq_dqb.dqb_isoftlimit || !sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_id.type)) return QUOTA_NL_NOWARN; newinodes = dquot->dq_dqb.dqb_curinodes - inodes; if (newinodes <= dquot->dq_dqb.dqb_isoftlimit) return QUOTA_NL_ISOFTBELOW; if (dquot->dq_dqb.dqb_curinodes >= dquot->dq_dqb.dqb_ihardlimit && newinodes < dquot->dq_dqb.dqb_ihardlimit) return QUOTA_NL_IHARDBELOW; return QUOTA_NL_NOWARN; } static int info_bdq_free(struct dquot *dquot, qsize_t space) { qsize_t tspace; tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace; if (test_bit(DQ_FAKE_B, &dquot->dq_flags) || tspace <= dquot->dq_dqb.dqb_bsoftlimit) return QUOTA_NL_NOWARN; if (tspace - space <= dquot->dq_dqb.dqb_bsoftlimit) return QUOTA_NL_BSOFTBELOW; if (tspace >= dquot->dq_dqb.dqb_bhardlimit && tspace - space < dquot->dq_dqb.dqb_bhardlimit) return QUOTA_NL_BHARDBELOW; return QUOTA_NL_NOWARN; } static int inode_quota_active(const struct inode *inode) { struct super_block *sb = inode->i_sb; if (IS_NOQUOTA(inode)) return 0; return sb_any_quota_loaded(sb) & ~sb_any_quota_suspended(sb); } /* * Initialize quota pointers in inode * * It is better to call this function outside of any transaction as it * might need a lot of space in journal for dquot structure allocation. */ static int __dquot_initialize(struct inode *inode, int type) { int cnt, init_needed = 0; struct dquot __rcu **dquots; struct dquot *got[MAXQUOTAS] = {}; struct super_block *sb = inode->i_sb; qsize_t rsv; int ret = 0; if (!inode_quota_active(inode)) return 0; dquots = i_dquot(inode); /* First get references to structures we might need. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { struct kqid qid; kprojid_t projid; int rc; struct dquot *dquot; if (type != -1 && cnt != type) continue; /* * The i_dquot should have been initialized in most cases, * we check it without locking here to avoid unnecessary * dqget()/dqput() calls. */ if (dquots[cnt]) continue; if (!sb_has_quota_active(sb, cnt)) continue; init_needed = 1; switch (cnt) { case USRQUOTA: qid = make_kqid_uid(inode->i_uid); break; case GRPQUOTA: qid = make_kqid_gid(inode->i_gid); break; case PRJQUOTA: rc = inode->i_sb->dq_op->get_projid(inode, &projid); if (rc) continue; qid = make_kqid_projid(projid); break; } dquot = dqget(sb, qid); if (IS_ERR(dquot)) { /* We raced with somebody turning quotas off... */ if (PTR_ERR(dquot) != -ESRCH) { ret = PTR_ERR(dquot); goto out_put; } dquot = NULL; } got[cnt] = dquot; } /* All required i_dquot has been initialized */ if (!init_needed) return 0; spin_lock(&dq_data_lock); if (IS_NOQUOTA(inode)) goto out_lock; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; /* Avoid races with quotaoff() */ if (!sb_has_quota_active(sb, cnt)) continue; /* We could race with quotaon or dqget() could have failed */ if (!got[cnt]) continue; if (!dquots[cnt]) { rcu_assign_pointer(dquots[cnt], got[cnt]); got[cnt] = NULL; /* * Make quota reservation system happy if someone * did a write before quota was turned on */ rsv = inode_get_rsv_space(inode); if (unlikely(rsv)) { struct dquot *dquot = srcu_dereference_check( dquots[cnt], &dquot_srcu, lockdep_is_held(&dq_data_lock)); spin_lock(&inode->i_lock); /* Get reservation again under proper lock */ rsv = __inode_get_rsv_space(inode); spin_lock(&dquot->dq_dqb_lock); dquot->dq_dqb.dqb_rsvspace += rsv; spin_unlock(&dquot->dq_dqb_lock); spin_unlock(&inode->i_lock); } } } out_lock: spin_unlock(&dq_data_lock); out_put: /* Drop unused references */ dqput_all(got); return ret; } int dquot_initialize(struct inode *inode) { return __dquot_initialize(inode, -1); } EXPORT_SYMBOL(dquot_initialize); bool dquot_initialize_needed(struct inode *inode) { struct dquot __rcu **dquots; int i; if (!inode_quota_active(inode)) return false; dquots = i_dquot(inode); for (i = 0; i < MAXQUOTAS; i++) if (!dquots[i] && sb_has_quota_active(inode->i_sb, i)) return true; return false; } EXPORT_SYMBOL(dquot_initialize_needed); /* * Release all quotas referenced by inode. * * This function only be called on inode free or converting * a file to quota file, no other users for the i_dquot in * both cases, so we needn't call synchronize_srcu() after * clearing i_dquot. */ static void __dquot_drop(struct inode *inode) { int cnt; struct dquot __rcu **dquots = i_dquot(inode); struct dquot *put[MAXQUOTAS]; spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { put[cnt] = srcu_dereference_check(dquots[cnt], &dquot_srcu, lockdep_is_held(&dq_data_lock)); rcu_assign_pointer(dquots[cnt], NULL); } spin_unlock(&dq_data_lock); dqput_all(put); } void dquot_drop(struct inode *inode) { struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) return; /* * Test before calling to rule out calls from proc and such * where we are not allowed to block. Note that this is * actually reliable test even without the lock - the caller * must assure that nobody can come after the DQUOT_DROP and * add quota pointers back anyway. */ dquots = i_dquot(inode); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (dquots[cnt]) break; } if (cnt < MAXQUOTAS) __dquot_drop(inode); } EXPORT_SYMBOL(dquot_drop); /* * inode_reserved_space is managed internally by quota, and protected by * i_lock similar to i_blocks+i_bytes. */ static qsize_t *inode_reserved_space(struct inode * inode) { /* Filesystem must explicitly define it's own method in order to use * quota reservation interface */ BUG_ON(!inode->i_sb->dq_op->get_reserved_space); return inode->i_sb->dq_op->get_reserved_space(inode); } static qsize_t __inode_get_rsv_space(struct inode *inode) { if (!inode->i_sb->dq_op->get_reserved_space) return 0; return *inode_reserved_space(inode); } static qsize_t inode_get_rsv_space(struct inode *inode) { qsize_t ret; if (!inode->i_sb->dq_op->get_reserved_space) return 0; spin_lock(&inode->i_lock); ret = __inode_get_rsv_space(inode); spin_unlock(&inode->i_lock); return ret; } /* * This functions updates i_blocks+i_bytes fields and quota information * (together with appropriate checks). * * NOTE: We absolutely rely on the fact that caller dirties the inode * (usually helpers in quotaops.h care about this) and holds a handle for * the current transaction so that dquot write and inode write go into the * same transaction. */ /* * This operation can block, but only after everything is updated */ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; int reserve = flags & DQUOT_SPACE_RESERVE; struct dquot __rcu **dquots; struct dquot *dquot; if (!inode_quota_active(inode)) { if (reserve) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) += number; spin_unlock(&inode->i_lock); } else { inode_add_bytes(inode, number); } goto out; } for (cnt = 0; cnt < MAXQUOTAS; cnt++) warn[cnt].w_type = QUOTA_NL_NOWARN; dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot) continue; if (reserve) { ret = dquot_add_space(dquot, 0, number, flags, &warn[cnt]); } else { ret = dquot_add_space(dquot, number, 0, flags, &warn[cnt]); } if (ret) { /* Back out changes we already did */ for (cnt--; cnt >= 0; cnt--) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot) continue; spin_lock(&dquot->dq_dqb_lock); if (reserve) dquot_free_reserved_space(dquot, number); else dquot_decr_space(dquot, number); spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); goto out_flush_warn; } } if (reserve) *inode_reserved_space(inode) += number; else __inode_add_bytes(inode, number); spin_unlock(&inode->i_lock); if (reserve) goto out_flush_warn; ret = mark_all_dquot_dirty(dquots); out_flush_warn: srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn); out: return ret; } EXPORT_SYMBOL(__dquot_alloc_space); /* * This operation can block, but only after everything is updated */ int dquot_alloc_inode(struct inode *inode) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; struct dquot __rcu * const *dquots; struct dquot *dquot; if (!inode_quota_active(inode)) return 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) warn[cnt].w_type = QUOTA_NL_NOWARN; dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot) continue; ret = dquot_add_inodes(dquot, 1, &warn[cnt]); if (ret) { for (cnt--; cnt >= 0; cnt--) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot) continue; /* Back out changes we already did */ spin_lock(&dquot->dq_dqb_lock); dquot_decr_inodes(dquot, 1); spin_unlock(&dquot->dq_dqb_lock); } goto warn_put_all; } } warn_put_all: spin_unlock(&inode->i_lock); if (ret == 0) ret = mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn); return ret; } EXPORT_SYMBOL(dquot_alloc_inode); /* * Convert in-memory reserved quotas to real consumed quotas */ void dquot_claim_space_nodirty(struct inode *inode, qsize_t number) { struct dquot __rcu **dquots; struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) -= number; __inode_add_bytes(inode, number); spin_unlock(&inode->i_lock); return; } dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_rsvspace < number)) number = dquot->dq_dqb.dqb_rsvspace; dquot->dq_dqb.dqb_curspace += number; dquot->dq_dqb.dqb_rsvspace -= number; spin_unlock(&dquot->dq_dqb_lock); } } /* Update inode bytes */ *inode_reserved_space(inode) -= number; __inode_add_bytes(inode, number); spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); } EXPORT_SYMBOL(dquot_claim_space_nodirty); /* * Convert allocated space back to in-memory reserved quotas */ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) { struct dquot __rcu **dquots; struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) += number; __inode_sub_bytes(inode, number); spin_unlock(&inode->i_lock); return; } dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number)) number = dquot->dq_dqb.dqb_curspace; dquot->dq_dqb.dqb_rsvspace += number; dquot->dq_dqb.dqb_curspace -= number; spin_unlock(&dquot->dq_dqb_lock); } } /* Update inode bytes */ *inode_reserved_space(inode) += number; __inode_sub_bytes(inode, number); spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); } EXPORT_SYMBOL(dquot_reclaim_space_nodirty); /* * This operation can block, but only after everything is updated */ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; struct dquot __rcu **dquots; struct dquot *dquot; int reserve = flags & DQUOT_SPACE_RESERVE, index; if (!inode_quota_active(inode)) { if (reserve) { spin_lock(&inode->i_lock); *inode_reserved_space(inode) -= number; spin_unlock(&inode->i_lock); } else { inode_sub_bytes(inode, number); } return; } dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { int wtype; warn[cnt].w_type = QUOTA_NL_NOWARN; dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot) continue; spin_lock(&dquot->dq_dqb_lock); wtype = info_bdq_free(dquot, number); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn[cnt], dquot, wtype); if (reserve) dquot_free_reserved_space(dquot, number); else dquot_decr_space(dquot, number); spin_unlock(&dquot->dq_dqb_lock); } if (reserve) *inode_reserved_space(inode) -= number; else __inode_sub_bytes(inode, number); spin_unlock(&inode->i_lock); if (reserve) goto out_unlock; mark_all_dquot_dirty(dquots); out_unlock: srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn); } EXPORT_SYMBOL(__dquot_free_space); /* * This operation can block, but only after everything is updated */ void dquot_free_inode(struct inode *inode) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; struct dquot __rcu * const *dquots; struct dquot *dquot; int index; if (!inode_quota_active(inode)) return; dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { int wtype; warn[cnt].w_type = QUOTA_NL_NOWARN; dquot = srcu_dereference(dquots[cnt], &dquot_srcu); if (!dquot) continue; spin_lock(&dquot->dq_dqb_lock); wtype = info_idq_free(dquot, 1); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn[cnt], dquot, wtype); dquot_decr_inodes(dquot, 1); spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn); } EXPORT_SYMBOL(dquot_free_inode); /* * Transfer the number of inode and blocks from one diskquota to an other. * On success, dquot references in transfer_to are consumed and references * to original dquots that need to be released are placed there. On failure, * references are kept untouched. * * This operation can block, but only after everything is updated * A transaction must be started when entering this function. * * We are holding reference on transfer_from & transfer_to, no need to * protect them by srcu_read_lock(). */ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) { qsize_t cur_space; qsize_t rsv_space = 0; qsize_t inode_usage = 1; struct dquot __rcu **dquots; struct dquot *transfer_from[MAXQUOTAS] = {}; int cnt, index, ret = 0, err; char is_valid[MAXQUOTAS] = {}; struct dquot_warn warn_to[MAXQUOTAS]; struct dquot_warn warn_from_inodes[MAXQUOTAS]; struct dquot_warn warn_from_space[MAXQUOTAS]; if (IS_NOQUOTA(inode)) return 0; if (inode->i_sb->dq_op->get_inode_usage) { ret = inode->i_sb->dq_op->get_inode_usage(inode, &inode_usage); if (ret) return ret; } /* Initialize the arrays */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { warn_to[cnt].w_type = QUOTA_NL_NOWARN; warn_from_inodes[cnt].w_type = QUOTA_NL_NOWARN; warn_from_space[cnt].w_type = QUOTA_NL_NOWARN; } spin_lock(&dq_data_lock); spin_lock(&inode->i_lock); if (IS_NOQUOTA(inode)) { /* File without quota accounting? */ spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); return 0; } cur_space = __inode_get_bytes(inode); rsv_space = __inode_get_rsv_space(inode); dquots = i_dquot(inode); /* * Build the transfer_from list, check limits, and update usage in * the target structures. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { /* * Skip changes for same uid or gid or for turned off quota-type. */ if (!transfer_to[cnt]) continue; /* Avoid races with quotaoff() */ if (!sb_has_quota_active(inode->i_sb, cnt)) continue; is_valid[cnt] = 1; transfer_from[cnt] = srcu_dereference_check(dquots[cnt], &dquot_srcu, lockdep_is_held(&dq_data_lock)); ret = dquot_add_inodes(transfer_to[cnt], inode_usage, &warn_to[cnt]); if (ret) goto over_quota; ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space, DQUOT_SPACE_WARN, &warn_to[cnt]); if (ret) { spin_lock(&transfer_to[cnt]->dq_dqb_lock); dquot_decr_inodes(transfer_to[cnt], inode_usage); spin_unlock(&transfer_to[cnt]->dq_dqb_lock); goto over_quota; } } /* Decrease usage for source structures and update quota pointers */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (!is_valid[cnt]) continue; /* Due to IO error we might not have transfer_from[] structure */ if (transfer_from[cnt]) { int wtype; spin_lock(&transfer_from[cnt]->dq_dqb_lock); wtype = info_idq_free(transfer_from[cnt], inode_usage); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn_from_inodes[cnt], transfer_from[cnt], wtype); wtype = info_bdq_free(transfer_from[cnt], cur_space + rsv_space); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn_from_space[cnt], transfer_from[cnt], wtype); dquot_decr_inodes(transfer_from[cnt], inode_usage); dquot_decr_space(transfer_from[cnt], cur_space); dquot_free_reserved_space(transfer_from[cnt], rsv_space); spin_unlock(&transfer_from[cnt]->dq_dqb_lock); } rcu_assign_pointer(dquots[cnt], transfer_to[cnt]); } spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); /* * These arrays are local and we hold dquot references so we don't need * the srcu protection but still take dquot_srcu to avoid warning in * mark_all_dquot_dirty(). */ index = srcu_read_lock(&dquot_srcu); err = mark_all_dquot_dirty((struct dquot __rcu **)transfer_from); if (err < 0) ret = err; err = mark_all_dquot_dirty((struct dquot __rcu **)transfer_to); if (err < 0) ret = err; srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn_to); flush_warnings(warn_from_inodes); flush_warnings(warn_from_space); /* Pass back references to put */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) if (is_valid[cnt]) transfer_to[cnt] = transfer_from[cnt]; return ret; over_quota: /* Back out changes we already did */ for (cnt--; cnt >= 0; cnt--) { if (!is_valid[cnt]) continue; spin_lock(&transfer_to[cnt]->dq_dqb_lock); dquot_decr_inodes(transfer_to[cnt], inode_usage); dquot_decr_space(transfer_to[cnt], cur_space); dquot_free_reserved_space(transfer_to[cnt], rsv_space); spin_unlock(&transfer_to[cnt]->dq_dqb_lock); } spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); flush_warnings(warn_to); return ret; } EXPORT_SYMBOL(__dquot_transfer); /* Wrapper for transferring ownership of an inode for uid/gid only * Called from FSXXX_setattr() */ int dquot_transfer(struct mnt_idmap *idmap, struct inode *inode, struct iattr *iattr) { struct dquot *transfer_to[MAXQUOTAS] = {}; struct dquot *dquot; struct super_block *sb = inode->i_sb; int ret; if (!inode_quota_active(inode)) return 0; if (i_uid_needs_update(idmap, iattr, inode)) { kuid_t kuid = from_vfsuid(idmap, i_user_ns(inode), iattr->ia_vfsuid); dquot = dqget(sb, make_kqid_uid(kuid)); if (IS_ERR(dquot)) { if (PTR_ERR(dquot) != -ESRCH) { ret = PTR_ERR(dquot); goto out_put; } dquot = NULL; } transfer_to[USRQUOTA] = dquot; } if (i_gid_needs_update(idmap, iattr, inode)) { kgid_t kgid = from_vfsgid(idmap, i_user_ns(inode), iattr->ia_vfsgid); dquot = dqget(sb, make_kqid_gid(kgid)); if (IS_ERR(dquot)) { if (PTR_ERR(dquot) != -ESRCH) { ret = PTR_ERR(dquot); goto out_put; } dquot = NULL; } transfer_to[GRPQUOTA] = dquot; } ret = __dquot_transfer(inode, transfer_to); out_put: dqput_all(transfer_to); return ret; } EXPORT_SYMBOL(dquot_transfer); /* * Write info of quota file to disk */ int dquot_commit_info(struct super_block *sb, int type) { struct quota_info *dqopt = sb_dqopt(sb); return dqopt->ops[type]->write_file_info(sb, type); } EXPORT_SYMBOL(dquot_commit_info); int dquot_get_next_id(struct super_block *sb, struct kqid *qid) { struct quota_info *dqopt = sb_dqopt(sb); if (!sb_has_quota_active(sb, qid->type)) return -ESRCH; if (!dqopt->ops[qid->type]->get_next_id) return -ENOSYS; return dqopt->ops[qid->type]->get_next_id(sb, qid); } EXPORT_SYMBOL(dquot_get_next_id); /* * Definitions of diskquota operations. */ const struct dquot_operations dquot_operations = { .write_dquot = dquot_commit, .acquire_dquot = dquot_acquire, .release_dquot = dquot_release, .mark_dirty = dquot_mark_dquot_dirty, .write_info = dquot_commit_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, .get_next_id = dquot_get_next_id, }; EXPORT_SYMBOL(dquot_operations); /* * Generic helper for ->open on filesystems supporting disk quotas. */ int dquot_file_open(struct inode *inode, struct file *file) { int error; error = generic_file_open(inode, file); if (!error && (file->f_mode & FMODE_WRITE)) error = dquot_initialize(inode); return error; } EXPORT_SYMBOL(dquot_file_open); static void vfs_cleanup_quota_inode(struct super_block *sb, int type) { struct quota_info *dqopt = sb_dqopt(sb); struct inode *inode = dqopt->files[type]; if (!inode) return; if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { inode_lock(inode); inode->i_flags &= ~S_NOQUOTA; inode_unlock(inode); } dqopt->files[type] = NULL; iput(inode); } /* * Turn quota off on a device. type == -1 ==> quotaoff for all types (umount) */ int dquot_disable(struct super_block *sb, int type, unsigned int flags) { int cnt; struct quota_info *dqopt = sb_dqopt(sb); rwsem_assert_held_write(&sb->s_umount); /* Cannot turn off usage accounting without turning off limits, or * suspend quotas and simultaneously turn quotas off. */ if ((flags & DQUOT_USAGE_ENABLED && !(flags & DQUOT_LIMITS_ENABLED)) || (flags & DQUOT_SUSPENDED && flags & (DQUOT_LIMITS_ENABLED | DQUOT_USAGE_ENABLED))) return -EINVAL; /* * Skip everything if there's nothing to do. We have to do this because * sometimes we are called when fill_super() failed and calling * sync_fs() in such cases does no good. */ if (!sb_any_quota_loaded(sb)) return 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; if (!sb_has_quota_loaded(sb, cnt)) continue; if (flags & DQUOT_SUSPENDED) { spin_lock(&dq_state_lock); dqopt->flags |= dquot_state_flag(DQUOT_SUSPENDED, cnt); spin_unlock(&dq_state_lock); } else { spin_lock(&dq_state_lock); dqopt->flags &= ~dquot_state_flag(flags, cnt); /* Turning off suspended quotas? */ if (!sb_has_quota_loaded(sb, cnt) && sb_has_quota_suspended(sb, cnt)) { dqopt->flags &= ~dquot_state_flag( DQUOT_SUSPENDED, cnt); spin_unlock(&dq_state_lock); vfs_cleanup_quota_inode(sb, cnt); continue; } spin_unlock(&dq_state_lock); } /* We still have to keep quota loaded? */ if (sb_has_quota_loaded(sb, cnt) && !(flags & DQUOT_SUSPENDED)) continue; /* Note: these are blocking operations */ drop_dquot_ref(sb, cnt); invalidate_dquots(sb, cnt); /* * Now all dquots should be invalidated, all writes done so we * should be only users of the info. No locks needed. */ if (info_dirty(&dqopt->info[cnt])) sb->dq_op->write_info(sb, cnt); if (dqopt->ops[cnt]->free_file_info) dqopt->ops[cnt]->free_file_info(sb, cnt); put_quota_format(dqopt->info[cnt].dqi_format); dqopt->info[cnt].dqi_flags = 0; dqopt->info[cnt].dqi_igrace = 0; dqopt->info[cnt].dqi_bgrace = 0; dqopt->ops[cnt] = NULL; } /* Skip syncing and setting flags if quota files are hidden */ if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) goto put_inodes; /* Sync the superblock so that buffers with quota data are written to * disk (and so userspace sees correct data afterwards). */ if (sb->s_op->sync_fs) sb->s_op->sync_fs(sb, 1); sync_blockdev(sb->s_bdev); /* Now the quota files are just ordinary files and we can set the * inode flags back. Moreover we discard the pagecache so that * userspace sees the writes we did bypassing the pagecache. We * must also discard the blockdev buffers so that we see the * changes done by userspace on the next quotaon() */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) if (!sb_has_quota_loaded(sb, cnt) && dqopt->files[cnt]) { inode_lock(dqopt->files[cnt]); truncate_inode_pages(&dqopt->files[cnt]->i_data, 0); inode_unlock(dqopt->files[cnt]); } if (sb->s_bdev) invalidate_bdev(sb->s_bdev); put_inodes: /* We are done when suspending quotas */ if (flags & DQUOT_SUSPENDED) return 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) if (!sb_has_quota_loaded(sb, cnt)) vfs_cleanup_quota_inode(sb, cnt); return 0; } EXPORT_SYMBOL(dquot_disable); int dquot_quota_off(struct super_block *sb, int type) { return dquot_disable(sb, type, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); } EXPORT_SYMBOL(dquot_quota_off); /* * Turn quotas on on a device */ static int vfs_setup_quota_inode(struct inode *inode, int type) { struct super_block *sb = inode->i_sb; struct quota_info *dqopt = sb_dqopt(sb); if (is_bad_inode(inode)) return -EUCLEAN; if (!S_ISREG(inode->i_mode)) return -EACCES; if (IS_RDONLY(inode)) return -EROFS; if (sb_has_quota_loaded(sb, type)) return -EBUSY; /* * Quota files should never be encrypted. They should be thought of as * filesystem metadata, not user data. New-style internal quota files * cannot be encrypted by users anyway, but old-style external quota * files could potentially be incorrectly created in an encrypted * directory, hence this explicit check. Some reasons why encrypted * quota files don't work include: (1) some filesystems that support * encryption don't handle it in their quota_read and quota_write, and * (2) cleaning up encrypted quota files at unmount would need special * consideration, as quota files are cleaned up later than user files. */ if (IS_ENCRYPTED(inode)) return -EINVAL; dqopt->files[type] = igrab(inode); if (!dqopt->files[type]) return -EIO; if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { /* We don't want quota and atime on quota files (deadlocks * possible) Also nobody should write to the file - we use * special IO operations which ignore the immutable bit. */ inode_lock(inode); inode->i_flags |= S_NOQUOTA; inode_unlock(inode); /* * When S_NOQUOTA is set, remove dquot references as no more * references can be added */ __dquot_drop(inode); } return 0; } int dquot_load_quota_sb(struct super_block *sb, int type, int format_id, unsigned int flags) { struct quota_format_type *fmt; struct quota_info *dqopt = sb_dqopt(sb); int error; lockdep_assert_held_write(&sb->s_umount); /* Just unsuspend quotas? */ if (WARN_ON_ONCE(flags & DQUOT_SUSPENDED)) return -EINVAL; fmt = find_quota_format(format_id); if (!fmt) return -ESRCH; if (!sb->dq_op || !sb->s_qcop || (type == PRJQUOTA && sb->dq_op->get_projid == NULL)) { error = -EINVAL; goto out_fmt; } /* Filesystems outside of init_user_ns not yet supported */ if (sb->s_user_ns != &init_user_ns) { error = -EINVAL; goto out_fmt; } /* Usage always has to be set... */ if (!(flags & DQUOT_USAGE_ENABLED)) { error = -EINVAL; goto out_fmt; } if (sb_has_quota_loaded(sb, type)) { error = -EBUSY; goto out_fmt; } if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) { /* As we bypass the pagecache we must now flush all the * dirty data and invalidate caches so that kernel sees * changes from userspace. It is not enough to just flush * the quota file since if blocksize < pagesize, invalidation * of the cache could fail because of other unrelated dirty * data */ sync_filesystem(sb); invalidate_bdev(sb->s_bdev); } error = -EINVAL; if (!fmt->qf_ops->check_quota_file(sb, type)) goto out_fmt; dqopt->ops[type] = fmt->qf_ops; dqopt->info[type].dqi_format = fmt; dqopt->info[type].dqi_fmt_id = format_id; INIT_LIST_HEAD(&dqopt->info[type].dqi_dirty_list); error = dqopt->ops[type]->read_file_info(sb, type); if (error < 0) goto out_fmt; if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) { spin_lock(&dq_data_lock); dqopt->info[type].dqi_flags |= DQF_SYS_FILE; spin_unlock(&dq_data_lock); } spin_lock(&dq_state_lock); dqopt->flags |= dquot_state_flag(flags, type); spin_unlock(&dq_state_lock); error = add_dquot_ref(sb, type); if (error) dquot_disable(sb, type, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); return error; out_fmt: put_quota_format(fmt); return error; } EXPORT_SYMBOL(dquot_load_quota_sb); /* * More powerful function for turning on quotas on given quota inode allowing * setting of individual quota flags */ int dquot_load_quota_inode(struct inode *inode, int type, int format_id, unsigned int flags) { int err; err = vfs_setup_quota_inode(inode, type); if (err < 0) return err; err = dquot_load_quota_sb(inode->i_sb, type, format_id, flags); if (err < 0) vfs_cleanup_quota_inode(inode->i_sb, type); return err; } EXPORT_SYMBOL(dquot_load_quota_inode); /* Reenable quotas on remount RW */ int dquot_resume(struct super_block *sb, int type) { struct quota_info *dqopt = sb_dqopt(sb); int ret = 0, cnt; unsigned int flags; rwsem_assert_held_write(&sb->s_umount); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; if (!sb_has_quota_suspended(sb, cnt)) continue; spin_lock(&dq_state_lock); flags = dqopt->flags & dquot_state_flag(DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED, cnt); dqopt->flags &= ~dquot_state_flag(DQUOT_STATE_FLAGS, cnt); spin_unlock(&dq_state_lock); flags = dquot_generic_flag(flags, cnt); ret = dquot_load_quota_sb(sb, cnt, dqopt->info[cnt].dqi_fmt_id, flags); if (ret < 0) vfs_cleanup_quota_inode(sb, cnt); } return ret; } EXPORT_SYMBOL(dquot_resume); int dquot_quota_on(struct super_block *sb, int type, int format_id, const struct path *path) { int error = security_quota_on(path->dentry); if (error) return error; /* Quota file not on the same filesystem? */ if (path->dentry->d_sb != sb) error = -EXDEV; else error = dquot_load_quota_inode(d_inode(path->dentry), type, format_id, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); return error; } EXPORT_SYMBOL(dquot_quota_on); /* * This function is used when filesystem needs to initialize quotas * during mount time. */ int dquot_quota_on_mount(struct super_block *sb, char *qf_name, int format_id, int type) { struct dentry *dentry; int error; dentry = lookup_noperm_positive_unlocked(&QSTR(qf_name), sb->s_root); if (IS_ERR(dentry)) return PTR_ERR(dentry); error = security_quota_on(dentry); if (!error) error = dquot_load_quota_inode(d_inode(dentry), type, format_id, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); dput(dentry); return error; } EXPORT_SYMBOL(dquot_quota_on_mount); static int dquot_quota_enable(struct super_block *sb, unsigned int flags) { int ret; int type; struct quota_info *dqopt = sb_dqopt(sb); if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) return -ENOSYS; /* Accounting cannot be turned on while fs is mounted */ flags &= ~(FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT); if (!flags) return -EINVAL; for (type = 0; type < MAXQUOTAS; type++) { if (!(flags & qtype_enforce_flag(type))) continue; /* Can't enforce without accounting */ if (!sb_has_quota_usage_enabled(sb, type)) { ret = -EINVAL; goto out_err; } if (sb_has_quota_limits_enabled(sb, type)) { /* compatible with XFS */ ret = -EEXIST; goto out_err; } spin_lock(&dq_state_lock); dqopt->flags |= dquot_state_flag(DQUOT_LIMITS_ENABLED, type); spin_unlock(&dq_state_lock); } return 0; out_err: /* Backout enforcement enablement we already did */ for (type--; type >= 0; type--) { if (flags & qtype_enforce_flag(type)) dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); } return ret; } static int dquot_quota_disable(struct super_block *sb, unsigned int flags) { int ret; int type; struct quota_info *dqopt = sb_dqopt(sb); if (!(dqopt->flags & DQUOT_QUOTA_SYS_FILE)) return -ENOSYS; /* * We don't support turning off accounting via quotactl. In principle * quota infrastructure can do this but filesystems don't expect * userspace to be able to do it. */ if (flags & (FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT | FS_QUOTA_PDQ_ACCT)) return -EOPNOTSUPP; /* Filter out limits not enabled */ for (type = 0; type < MAXQUOTAS; type++) if (!sb_has_quota_limits_enabled(sb, type)) flags &= ~qtype_enforce_flag(type); /* Nothing left? */ if (!flags) return -EEXIST; for (type = 0; type < MAXQUOTAS; type++) { if (flags & qtype_enforce_flag(type)) { ret = dquot_disable(sb, type, DQUOT_LIMITS_ENABLED); if (ret < 0) goto out_err; } } return 0; out_err: /* Backout enforcement disabling we already did */ for (type--; type >= 0; type--) { if (flags & qtype_enforce_flag(type)) { spin_lock(&dq_state_lock); dqopt->flags |= dquot_state_flag(DQUOT_LIMITS_ENABLED, type); spin_unlock(&dq_state_lock); } } return ret; } /* Generic routine for getting common part of quota structure */ static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di) { struct mem_dqblk *dm = &dquot->dq_dqb; memset(di, 0, sizeof(*di)); spin_lock(&dquot->dq_dqb_lock); di->d_spc_hardlimit = dm->dqb_bhardlimit; di->d_spc_softlimit = dm->dqb_bsoftlimit; di->d_ino_hardlimit = dm->dqb_ihardlimit; di->d_ino_softlimit = dm->dqb_isoftlimit; di->d_space = dm->dqb_curspace + dm->dqb_rsvspace; di->d_ino_count = dm->dqb_curinodes; di->d_spc_timer = dm->dqb_btime; di->d_ino_timer = dm->dqb_itime; spin_unlock(&dquot->dq_dqb_lock); } int dquot_get_dqblk(struct super_block *sb, struct kqid qid, struct qc_dqblk *di) { struct dquot *dquot; dquot = dqget(sb, qid); if (IS_ERR(dquot)) return PTR_ERR(dquot); do_get_dqblk(dquot, di); dqput(dquot); return 0; } EXPORT_SYMBOL(dquot_get_dqblk); int dquot_get_next_dqblk(struct super_block *sb, struct kqid *qid, struct qc_dqblk *di) { struct dquot *dquot; int err; if (!sb->dq_op->get_next_id) return -ENOSYS; err = sb->dq_op->get_next_id(sb, qid); if (err < 0) return err; dquot = dqget(sb, *qid); if (IS_ERR(dquot)) return PTR_ERR(dquot); do_get_dqblk(dquot, di); dqput(dquot); return 0; } EXPORT_SYMBOL(dquot_get_next_dqblk); #define VFS_QC_MASK \ (QC_SPACE | QC_SPC_SOFT | QC_SPC_HARD | \ QC_INO_COUNT | QC_INO_SOFT | QC_INO_HARD | \ QC_SPC_TIMER | QC_INO_TIMER) /* Generic routine for setting common part of quota structure */ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di) { struct mem_dqblk *dm = &dquot->dq_dqb; int check_blim = 0, check_ilim = 0; struct mem_dqinfo *dqi = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type]; int ret; if (di->d_fieldmask & ~VFS_QC_MASK) return -EINVAL; if (((di->d_fieldmask & QC_SPC_SOFT) && di->d_spc_softlimit > dqi->dqi_max_spc_limit) || ((di->d_fieldmask & QC_SPC_HARD) && di->d_spc_hardlimit > dqi->dqi_max_spc_limit) || ((di->d_fieldmask & QC_INO_SOFT) && (di->d_ino_softlimit > dqi->dqi_max_ino_limit)) || ((di->d_fieldmask & QC_INO_HARD) && (di->d_ino_hardlimit > dqi->dqi_max_ino_limit))) return -ERANGE; spin_lock(&dquot->dq_dqb_lock); if (di->d_fieldmask & QC_SPACE) { dm->dqb_curspace = di->d_space - dm->dqb_rsvspace; check_blim = 1; set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags); } if (di->d_fieldmask & QC_SPC_SOFT) dm->dqb_bsoftlimit = di->d_spc_softlimit; if (di->d_fieldmask & QC_SPC_HARD) dm->dqb_bhardlimit = di->d_spc_hardlimit; if (di->d_fieldmask & (QC_SPC_SOFT | QC_SPC_HARD)) { check_blim = 1; set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags); } if (di->d_fieldmask & QC_INO_COUNT) { dm->dqb_curinodes = di->d_ino_count; check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags); } if (di->d_fieldmask & QC_INO_SOFT) dm->dqb_isoftlimit = di->d_ino_softlimit; if (di->d_fieldmask & QC_INO_HARD) dm->dqb_ihardlimit = di->d_ino_hardlimit; if (di->d_fieldmask & (QC_INO_SOFT | QC_INO_HARD)) { check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags); } if (di->d_fieldmask & QC_SPC_TIMER) { dm->dqb_btime = di->d_spc_timer; check_blim = 1; set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags); } if (di->d_fieldmask & QC_INO_TIMER) { dm->dqb_itime = di->d_ino_timer; check_ilim = 1; set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags); } if (check_blim) { if (!dm->dqb_bsoftlimit || dm->dqb_curspace + dm->dqb_rsvspace <= dm->dqb_bsoftlimit) { dm->dqb_btime = 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); } else if (!(di->d_fieldmask & QC_SPC_TIMER)) /* Set grace only if user hasn't provided his own... */ dm->dqb_btime = ktime_get_real_seconds() + dqi->dqi_bgrace; } if (check_ilim) { if (!dm->dqb_isoftlimit || dm->dqb_curinodes <= dm->dqb_isoftlimit) { dm->dqb_itime = 0; clear_bit(DQ_INODES_B, &dquot->dq_flags); } else if (!(di->d_fieldmask & QC_INO_TIMER)) /* Set grace only if user hasn't provided his own... */ dm->dqb_itime = ktime_get_real_seconds() + dqi->dqi_igrace; } if (dm->dqb_bhardlimit || dm->dqb_bsoftlimit || dm->dqb_ihardlimit || dm->dqb_isoftlimit) clear_bit(DQ_FAKE_B, &dquot->dq_flags); else set_bit(DQ_FAKE_B, &dquot->dq_flags); spin_unlock(&dquot->dq_dqb_lock); ret = mark_dquot_dirty(dquot); if (ret < 0) return ret; return 0; } int dquot_set_dqblk(struct super_block *sb, struct kqid qid, struct qc_dqblk *di) { struct dquot *dquot; int rc; dquot = dqget(sb, qid); if (IS_ERR(dquot)) { rc = PTR_ERR(dquot); goto out; } rc = do_set_dqblk(dquot, di); dqput(dquot); out: return rc; } EXPORT_SYMBOL(dquot_set_dqblk); /* Generic routine for getting common part of quota file information */ int dquot_get_state(struct super_block *sb, struct qc_state *state) { struct mem_dqinfo *mi; struct qc_type_state *tstate; struct quota_info *dqopt = sb_dqopt(sb); int type; memset(state, 0, sizeof(*state)); for (type = 0; type < MAXQUOTAS; type++) { if (!sb_has_quota_active(sb, type)) continue; tstate = state->s_state + type; mi = sb_dqopt(sb)->info + type; tstate->flags = QCI_ACCT_ENABLED; spin_lock(&dq_data_lock); if (mi->dqi_flags & DQF_SYS_FILE) tstate->flags |= QCI_SYSFILE; if (mi->dqi_flags & DQF_ROOT_SQUASH) tstate->flags |= QCI_ROOT_SQUASH; if (sb_has_quota_limits_enabled(sb, type)) tstate->flags |= QCI_LIMITS_ENFORCED; tstate->spc_timelimit = mi->dqi_bgrace; tstate->ino_timelimit = mi->dqi_igrace; if (dqopt->files[type]) { tstate->ino = dqopt->files[type]->i_ino; tstate->blocks = dqopt->files[type]->i_blocks; } tstate->nextents = 1; /* We don't know... */ spin_unlock(&dq_data_lock); } return 0; } EXPORT_SYMBOL(dquot_get_state); /* Generic routine for setting common part of quota file information */ int dquot_set_dqinfo(struct super_block *sb, int type, struct qc_info *ii) { struct mem_dqinfo *mi; if ((ii->i_fieldmask & QC_WARNS_MASK) || (ii->i_fieldmask & QC_RT_SPC_TIMER)) return -EINVAL; if (!sb_has_quota_active(sb, type)) return -ESRCH; mi = sb_dqopt(sb)->info + type; if (ii->i_fieldmask & QC_FLAGS) { if ((ii->i_flags & QCI_ROOT_SQUASH && mi->dqi_format->qf_fmt_id != QFMT_VFS_OLD)) return -EINVAL; } spin_lock(&dq_data_lock); if (ii->i_fieldmask & QC_SPC_TIMER) mi->dqi_bgrace = ii->i_spc_timelimit; if (ii->i_fieldmask & QC_INO_TIMER) mi->dqi_igrace = ii->i_ino_timelimit; if (ii->i_fieldmask & QC_FLAGS) { if (ii->i_flags & QCI_ROOT_SQUASH) mi->dqi_flags |= DQF_ROOT_SQUASH; else mi->dqi_flags &= ~DQF_ROOT_SQUASH; } spin_unlock(&dq_data_lock); mark_info_dirty(sb, type); /* Force write to disk */ return sb->dq_op->write_info(sb, type); } EXPORT_SYMBOL(dquot_set_dqinfo); const struct quotactl_ops dquot_quotactl_sysfile_ops = { .quota_enable = dquot_quota_enable, .quota_disable = dquot_quota_disable, .quota_sync = dquot_quota_sync, .get_state = dquot_get_state, .set_info = dquot_set_dqinfo, .get_dqblk = dquot_get_dqblk, .get_nextdqblk = dquot_get_next_dqblk, .set_dqblk = dquot_set_dqblk }; EXPORT_SYMBOL(dquot_quotactl_sysfile_ops); static int do_proc_dqstats(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned int type = (unsigned long *)table->data - dqstats.stat; s64 value = percpu_counter_sum(&dqstats.counter[type]); /* Filter negative values for non-monotonic counters */ if (value < 0 && (type == DQST_ALLOC_DQUOTS || type == DQST_FREE_DQUOTS)) value = 0; /* Update global table */ dqstats.stat[type] = value; return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } static const struct ctl_table fs_dqstats_table[] = { { .procname = "lookups", .data = &dqstats.stat[DQST_LOOKUPS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "drops", .data = &dqstats.stat[DQST_DROPS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "reads", .data = &dqstats.stat[DQST_READS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "writes", .data = &dqstats.stat[DQST_WRITES], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "cache_hits", .data = &dqstats.stat[DQST_CACHE_HITS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "allocated_dquots", .data = &dqstats.stat[DQST_ALLOC_DQUOTS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "free_dquots", .data = &dqstats.stat[DQST_FREE_DQUOTS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, { .procname = "syncs", .data = &dqstats.stat[DQST_SYNCS], .maxlen = sizeof(unsigned long), .mode = 0444, .proc_handler = do_proc_dqstats, }, #ifdef CONFIG_PRINT_QUOTA_WARNING { .procname = "warnings", .data = &flag_print_warnings, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif }; static int __init dquot_init(void) { int i, ret; unsigned long nr_hash, order; struct shrinker *dqcache_shrinker; printk(KERN_NOTICE "VFS: Disk quotas %s\n", __DQUOT_VERSION__); register_sysctl_init("fs/quota", fs_dqstats_table); dquot_cachep = kmem_cache_create("dquot", sizeof(struct dquot), sizeof(unsigned long) * 4, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| SLAB_PANIC), NULL); order = 0; dquot_hash = (struct hlist_head *)__get_free_pages(GFP_KERNEL, order); if (!dquot_hash) panic("Cannot create dquot hash table"); ret = percpu_counter_init_many(dqstats.counter, 0, GFP_KERNEL, _DQST_DQSTAT_LAST); if (ret) panic("Cannot create dquot stat counters"); /* Find power-of-two hlist_heads which can fit into allocation */ nr_hash = (1UL << order) * PAGE_SIZE / sizeof(struct hlist_head); dq_hash_bits = ilog2(nr_hash); nr_hash = 1UL << dq_hash_bits; dq_hash_mask = nr_hash - 1; for (i = 0; i < nr_hash; i++) INIT_HLIST_HEAD(dquot_hash + i); pr_info("VFS: Dquot-cache hash table entries: %ld (order %ld," " %ld bytes)\n", nr_hash, order, (PAGE_SIZE << order)); dqcache_shrinker = shrinker_alloc(0, "dquota-cache"); if (!dqcache_shrinker) panic("Cannot allocate dquot shrinker"); dqcache_shrinker->count_objects = dqcache_shrink_count; dqcache_shrinker->scan_objects = dqcache_shrink_scan; shrinker_register(dqcache_shrinker); quota_unbound_wq = alloc_workqueue("quota_events_unbound", WQ_UNBOUND | WQ_MEM_RECLAIM, WQ_MAX_ACTIVE); if (!quota_unbound_wq) panic("Cannot create quota_unbound_wq\n"); return 0; } fs_initcall(dquot_init); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * device.h - generic, centralized driver model * * Copyright (c) 2001-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2004-2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2008-2009 Novell Inc. * * See Documentation/driver-api/driver-model/ for more information. */ #ifndef _DEVICE_H_ #define _DEVICE_H_ #include <linux/dev_printk.h> #include <linux/energy_model.h> #include <linux/ioport.h> #include <linux/kobject.h> #include <linux/klist.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/compiler.h> #include <linux/types.h> #include <linux/mutex.h> #include <linux/pm.h> #include <linux/atomic.h> #include <linux/uidgid.h> #include <linux/gfp.h> #include <linux/device/bus.h> #include <linux/device/class.h> #include <linux/device/devres.h> #include <linux/device/driver.h> #include <linux/cleanup.h> #include <asm/device.h> struct device; struct device_private; struct device_driver; struct driver_private; struct module; struct class; struct subsys_private; struct device_node; struct fwnode_handle; struct iommu_group; struct dev_pin_info; struct dev_iommu; struct msi_device_data; /** * struct subsys_interface - interfaces to device functions * @name: name of the device function * @subsys: subsystem of the devices to attach to * @node: the list of functions registered at the subsystem * @add_dev: device hookup to device function handler * @remove_dev: device hookup to device function handler * * Simple interfaces attached to a subsystem. Multiple interfaces can * attach to a subsystem and its devices. Unlike drivers, they do not * exclusively claim or control devices. Interfaces usually represent * a specific functionality of a subsystem/class of devices. */ struct subsys_interface { const char *name; const struct bus_type *subsys; struct list_head node; int (*add_dev)(struct device *dev, struct subsys_interface *sif); void (*remove_dev)(struct device *dev, struct subsys_interface *sif); }; int subsys_interface_register(struct subsys_interface *sif); void subsys_interface_unregister(struct subsys_interface *sif); int subsys_system_register(const struct bus_type *subsys, const struct attribute_group **groups); int subsys_virtual_register(const struct bus_type *subsys, const struct attribute_group **groups); /* * The type of device, "struct device" is embedded in. A class * or bus can contain devices of different types * like "partitions" and "disks", "mouse" and "event". * This identifies the device type and carries type-specific * information, equivalent to the kobj_type of a kobject. * If "name" is specified, the uevent will contain it in * the DEVTYPE variable. */ struct device_type { const char *name; const struct attribute_group **groups; int (*uevent)(const struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(const struct device *dev, umode_t *mode, kuid_t *uid, kgid_t *gid); void (*release)(struct device *dev); const struct dev_pm_ops *pm; }; /** * struct device_attribute - Interface for exporting device attributes. * @attr: sysfs attribute definition. * @show: Show handler. * @store: Store handler. */ struct device_attribute { struct attribute attr; ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf); ssize_t (*store)(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); }; /** * struct dev_ext_attribute - Exported device attribute with extra context. * @attr: Exported device attribute. * @var: Pointer to context. */ struct dev_ext_attribute { struct device_attribute attr; void *var; }; ssize_t device_show_ulong(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_ulong(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_int(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_int(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_bool(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); ssize_t device_show_string(struct device *dev, struct device_attribute *attr, char *buf); /** * DEVICE_ATTR - Define a device attribute. * @_name: Attribute name. * @_mode: File mode. * @_show: Show handler. Optional, but mandatory if attribute is readable. * @_store: Store handler. Optional, but mandatory if attribute is writable. * * Convenience macro for defining a struct device_attribute. * * For example, ``DEVICE_ATTR(foo, 0644, foo_show, foo_store);`` expands to: * * .. code-block:: c * * struct device_attribute dev_attr_foo = { * .attr = { .name = "foo", .mode = 0644 }, * .show = foo_show, * .store = foo_store, * }; */ #define DEVICE_ATTR(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store) /** * DEVICE_ATTR_PREALLOC - Define a preallocated device attribute. * @_name: Attribute name. * @_mode: File mode. * @_show: Show handler. Optional, but mandatory if attribute is readable. * @_store: Store handler. Optional, but mandatory if attribute is writable. * * Like DEVICE_ATTR(), but ``SYSFS_PREALLOC`` is set on @_mode. */ #define DEVICE_ATTR_PREALLOC(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_PREALLOC(_name, _mode, _show, _store) /** * DEVICE_ATTR_RW - Define a read-write device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0644, @_show is <_name>_show, * and @_store is <_name>_store. */ #define DEVICE_ATTR_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW(_name) /** * DEVICE_ATTR_ADMIN_RW - Define an admin-only read-write device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR_RW(), but @_mode is 0600. */ #define DEVICE_ATTR_ADMIN_RW(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600) /** * DEVICE_ATTR_RO - Define a readable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0444 and @_show is <_name>_show. */ #define DEVICE_ATTR_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO(_name) /** * DEVICE_ATTR_ADMIN_RO - Define an admin-only readable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR_RO(), but @_mode is 0400. */ #define DEVICE_ATTR_ADMIN_RO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400) /** * DEVICE_ATTR_WO - Define an admin-only writable device attribute. * @_name: Attribute name. * * Like DEVICE_ATTR(), but @_mode is 0200 and @_store is <_name>_store. */ #define DEVICE_ATTR_WO(_name) \ struct device_attribute dev_attr_##_name = __ATTR_WO(_name) /** * DEVICE_ULONG_ATTR - Define a device attribute backed by an unsigned long. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of unsigned long. * * Like DEVICE_ATTR(), but @_show and @_store are automatically provided * such that reads and writes to the attribute from userspace affect @_var. */ #define DEVICE_ULONG_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) } /** * DEVICE_INT_ATTR - Define a device attribute backed by an int. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of int. * * Like DEVICE_ULONG_ATTR(), but @_var is an int. */ #define DEVICE_INT_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_int, device_store_int), &(_var) } /** * DEVICE_BOOL_ATTR - Define a device attribute backed by a bool. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of bool. * * Like DEVICE_ULONG_ATTR(), but @_var is a bool. */ #define DEVICE_BOOL_ATTR(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_bool, device_store_bool), &(_var) } /** * DEVICE_STRING_ATTR_RO - Define a device attribute backed by a r/o string. * @_name: Attribute name. * @_mode: File mode. * @_var: Identifier of string. * * Like DEVICE_ULONG_ATTR(), but @_var is a string. Because the length of the * string allocation is unknown, the attribute must be read-only. */ #define DEVICE_STRING_ATTR_RO(_name, _mode, _var) \ struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, (_mode) & ~0222, device_show_string, NULL), (_var) } #define DEVICE_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) int device_create_file(struct device *device, const struct device_attribute *entry); void device_remove_file(struct device *dev, const struct device_attribute *attr); bool device_remove_file_self(struct device *dev, const struct device_attribute *attr); int __must_check device_create_bin_file(struct device *dev, const struct bin_attribute *attr); void device_remove_bin_file(struct device *dev, const struct bin_attribute *attr); /** * devm_alloc_percpu - Resource-managed alloc_percpu * @dev: Device to allocate per-cpu memory for * @type: Type to allocate per-cpu memory for * * Managed alloc_percpu. Per-cpu memory allocated with this function is * automatically freed on driver detach. * * RETURNS: * Pointer to allocated memory on success, NULL on failure. */ #define devm_alloc_percpu(dev, type) \ ((typeof(type) __percpu *)__devm_alloc_percpu((dev), sizeof(type), \ __alignof__(type))) void __percpu *__devm_alloc_percpu(struct device *dev, size_t size, size_t align); void devm_free_percpu(struct device *dev, void __percpu *pdata); struct device_dma_parameters { /* * a low level driver may set these to teach IOMMU code about * sg limitations. */ unsigned int max_segment_size; unsigned int min_align_mask; unsigned long segment_boundary_mask; }; /** * enum device_link_state - Device link states. * @DL_STATE_NONE: The presence of the drivers is not being tracked. * @DL_STATE_DORMANT: None of the supplier/consumer drivers is present. * @DL_STATE_AVAILABLE: The supplier driver is present, but the consumer is not. * @DL_STATE_CONSUMER_PROBE: The consumer is probing (supplier driver present). * @DL_STATE_ACTIVE: Both the supplier and consumer drivers are present. * @DL_STATE_SUPPLIER_UNBIND: The supplier driver is unbinding. */ enum device_link_state { DL_STATE_NONE = -1, DL_STATE_DORMANT = 0, DL_STATE_AVAILABLE, DL_STATE_CONSUMER_PROBE, DL_STATE_ACTIVE, DL_STATE_SUPPLIER_UNBIND, }; /* * Device link flags. * * STATELESS: The core will not remove this link automatically. * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind. * PM_RUNTIME: If set, the runtime PM framework will use this link. * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation. * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind. * AUTOPROBE_CONSUMER: Probe consumer driver automatically after supplier binds. * MANAGED: The core tracks presence of supplier/consumer drivers (internal). * SYNC_STATE_ONLY: Link only affects sync_state() behavior. * INFERRED: Inferred from data (eg: firmware) and not from driver actions. */ #define DL_FLAG_STATELESS BIT(0) #define DL_FLAG_AUTOREMOVE_CONSUMER BIT(1) #define DL_FLAG_PM_RUNTIME BIT(2) #define DL_FLAG_RPM_ACTIVE BIT(3) #define DL_FLAG_AUTOREMOVE_SUPPLIER BIT(4) #define DL_FLAG_AUTOPROBE_CONSUMER BIT(5) #define DL_FLAG_MANAGED BIT(6) #define DL_FLAG_SYNC_STATE_ONLY BIT(7) #define DL_FLAG_INFERRED BIT(8) #define DL_FLAG_CYCLE BIT(9) /** * enum dl_dev_state - Device driver presence tracking information. * @DL_DEV_NO_DRIVER: There is no driver attached to the device. * @DL_DEV_PROBING: A driver is probing. * @DL_DEV_DRIVER_BOUND: The driver has been bound to the device. * @DL_DEV_UNBINDING: The driver is unbinding from the device. */ enum dl_dev_state { DL_DEV_NO_DRIVER = 0, DL_DEV_PROBING, DL_DEV_DRIVER_BOUND, DL_DEV_UNBINDING, }; /** * enum device_removable - Whether the device is removable. The criteria for a * device to be classified as removable is determined by its subsystem or bus. * @DEVICE_REMOVABLE_NOT_SUPPORTED: This attribute is not supported for this * device (default). * @DEVICE_REMOVABLE_UNKNOWN: Device location is Unknown. * @DEVICE_FIXED: Device is not removable by the user. * @DEVICE_REMOVABLE: Device is removable by the user. */ enum device_removable { DEVICE_REMOVABLE_NOT_SUPPORTED = 0, /* must be 0 */ DEVICE_REMOVABLE_UNKNOWN, DEVICE_FIXED, DEVICE_REMOVABLE, }; /** * struct dev_links_info - Device data related to device links. * @suppliers: List of links to supplier devices. * @consumers: List of links to consumer devices. * @defer_sync: Hook to global list of devices that have deferred sync_state. * @status: Driver status information. */ struct dev_links_info { struct list_head suppliers; struct list_head consumers; struct list_head defer_sync; enum dl_dev_state status; }; /** * struct dev_msi_info - Device data related to MSI * @domain: The MSI interrupt domain associated to the device * @data: Pointer to MSI device data */ struct dev_msi_info { #ifdef CONFIG_GENERIC_MSI_IRQ struct irq_domain *domain; struct msi_device_data *data; #endif }; /** * enum device_physical_location_panel - Describes which panel surface of the * system's housing the device connection point resides on. * @DEVICE_PANEL_TOP: Device connection point is on the top panel. * @DEVICE_PANEL_BOTTOM: Device connection point is on the bottom panel. * @DEVICE_PANEL_LEFT: Device connection point is on the left panel. * @DEVICE_PANEL_RIGHT: Device connection point is on the right panel. * @DEVICE_PANEL_FRONT: Device connection point is on the front panel. * @DEVICE_PANEL_BACK: Device connection point is on the back panel. * @DEVICE_PANEL_UNKNOWN: The panel with device connection point is unknown. */ enum device_physical_location_panel { DEVICE_PANEL_TOP, DEVICE_PANEL_BOTTOM, DEVICE_PANEL_LEFT, DEVICE_PANEL_RIGHT, DEVICE_PANEL_FRONT, DEVICE_PANEL_BACK, DEVICE_PANEL_UNKNOWN, }; /** * enum device_physical_location_vertical_position - Describes vertical * position of the device connection point on the panel surface. * @DEVICE_VERT_POS_UPPER: Device connection point is at upper part of panel. * @DEVICE_VERT_POS_CENTER: Device connection point is at center part of panel. * @DEVICE_VERT_POS_LOWER: Device connection point is at lower part of panel. */ enum device_physical_location_vertical_position { DEVICE_VERT_POS_UPPER, DEVICE_VERT_POS_CENTER, DEVICE_VERT_POS_LOWER, }; /** * enum device_physical_location_horizontal_position - Describes horizontal * position of the device connection point on the panel surface. * @DEVICE_HORI_POS_LEFT: Device connection point is at left part of panel. * @DEVICE_HORI_POS_CENTER: Device connection point is at center part of panel. * @DEVICE_HORI_POS_RIGHT: Device connection point is at right part of panel. */ enum device_physical_location_horizontal_position { DEVICE_HORI_POS_LEFT, DEVICE_HORI_POS_CENTER, DEVICE_HORI_POS_RIGHT, }; /** * struct device_physical_location - Device data related to physical location * of the device connection point. * @panel: Panel surface of the system's housing that the device connection * point resides on. * @vertical_position: Vertical position of the device connection point within * the panel. * @horizontal_position: Horizontal position of the device connection point * within the panel. * @dock: Set if the device connection point resides in a docking station or * port replicator. * @lid: Set if this device connection point resides on the lid of laptop * system. */ struct device_physical_location { enum device_physical_location_panel panel; enum device_physical_location_vertical_position vertical_position; enum device_physical_location_horizontal_position horizontal_position; bool dock; bool lid; }; /** * struct device - The basic device structure * @parent: The device's "parent" device, the device to which it is attached. * In most cases, a parent device is some sort of bus or host * controller. If parent is NULL, the device, is a top-level device, * which is not usually what you want. * @p: Holds the private data of the driver core portions of the device. * See the comment of the struct device_private for detail. * @kobj: A top-level, abstract class from which other classes are derived. * @init_name: Initial name of the device. * @type: The type of device. * This identifies the device type and carries type-specific * information. * @mutex: Mutex to synchronize calls to its driver. * @bus: Type of bus device is on. * @driver: Which driver has allocated this * @platform_data: Platform data specific to the device. * Example: For devices on custom boards, as typical of embedded * and SOC based hardware, Linux often uses platform_data to point * to board-specific structures describing devices and how they * are wired. That can include what ports are available, chip * variants, which GPIO pins act in what additional roles, and so * on. This shrinks the "Board Support Packages" (BSPs) and * minimizes board-specific #ifdefs in drivers. * @driver_data: Private pointer for driver specific info. * @links: Links to suppliers and consumers of this device. * @power: For device power management. * See Documentation/driver-api/pm/devices.rst for details. * @pm_domain: Provide callbacks that are executed during system suspend, * hibernation, system resume and during runtime PM transitions * along with subsystem-level and driver-level callbacks. * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. * @msi: MSI related data * @numa_node: NUMA node this device is close to. * @dma_ops: DMA mapping operations for this device. * @dma_mask: Dma mask (if dma'ble device). * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all * hardware supports 64-bit addresses for consistent allocations * such descriptors. * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller * DMA limit than the device itself supports. * @dma_range_map: map for DMA memory ranges relative to that of RAM * @dma_parms: A low level driver may set these to teach IOMMU code about * segment limitations. * @dma_pools: Dma pools (if dma'ble device). * @dma_mem: Internal for coherent mem override. * @cma_area: Contiguous memory area for dma allocations * @dma_io_tlb_mem: Software IO TLB allocator. Not for driver use. * @dma_io_tlb_pools: List of transient swiotlb memory pools. * @dma_io_tlb_lock: Protects changes to the list of active pools. * @dma_uses_io_tlb: %true if device has used the software IO TLB. * @archdata: For arch-specific additions. * @of_node: Associated device tree node. * @fwnode: Associated device node supplied by platform firmware. * @devt: For creating the sysfs "dev". * @id: device instance * @devres_lock: Spinlock to protect the resource of the device. * @devres_head: The resources list of the device. * @class: The class of the device. * @groups: Optional attribute groups. * @release: Callback to free the device after all references have * gone away. This should be set by the allocator of the * device (i.e. the bus driver that discovered the device). * @iommu_group: IOMMU group the device belongs to. * @iommu: Per device generic IOMMU runtime data * @physical_location: Describes physical location of the device connection * point in the system housing. * @removable: Whether the device can be removed from the system. This * should be set by the subsystem / bus driver that discovered * the device. * * @offline_disabled: If set, the device is permanently online. * @offline: Set after successful invocation of bus type's .offline(). * @of_node_reused: Set if the device-tree node is shared with an ancestor * device. * @state_synced: The hardware state of this device has been synced to match * the software state of this device by calling the driver/bus * sync_state() callback. * @can_match: The device has matched with a driver at least once or it is in * a bus (like AMBA) which can't check for matching drivers until * other devices probe successfully. * @dma_coherent: this particular device is dma coherent, even if the * architecture supports non-coherent devices. * @dma_ops_bypass: If set to %true then the dma_ops are bypassed for the * streaming DMA operations (->map_* / ->unmap_* / ->sync_*), * and optionall (if the coherent mask is large enough) also * for dma allocations. This flag is managed by the dma ops * instance from ->dma_supported. * @dma_skip_sync: DMA sync operations can be skipped for coherent buffers. * @dma_iommu: Device is using default IOMMU implementation for DMA and * doesn't rely on dma_ops structure. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information * that the device model core needs to model the system. Most subsystems, * however, track additional information about the devices they host. As a * result, it is rare for devices to be represented by bare device structures; * instead, that structure, like kobject structures, is usually embedded within * a higher-level representation of the device. */ struct device { struct kobject kobj; struct device *parent; struct device_private *p; const char *init_name; /* initial name of the device */ const struct device_type *type; const struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *platform_data; /* Platform specific data, device core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set_drvdata/dev_get_drvdata */ struct mutex mutex; /* mutex to synchronize calls to * its driver. */ struct dev_links_info links; struct dev_pm_info power; struct dev_pm_domain *pm_domain; #ifdef CONFIG_ENERGY_MODEL struct em_perf_domain *em_pd; #endif #ifdef CONFIG_PINCTRL struct dev_pin_info *pins; #endif struct dev_msi_info msi; #ifdef CONFIG_ARCH_HAS_DMA_OPS const struct dma_map_ops *dma_ops; #endif u64 *dma_mask; /* dma mask (if dma'able device) */ u64 coherent_dma_mask;/* Like dma_mask, but for alloc_coherent mappings as not all hardware supports 64 bit addresses for consistent allocations such descriptors. */ u64 bus_dma_limit; /* upstream dma constraint */ const struct bus_dma_region *dma_range_map; struct device_dma_parameters *dma_parms; struct list_head dma_pools; /* dma pools (if dma'ble) */ #ifdef CONFIG_DMA_DECLARE_COHERENT struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ #endif #ifdef CONFIG_DMA_CMA struct cma *cma_area; /* contiguous memory area for dma allocations */ #endif #ifdef CONFIG_SWIOTLB struct io_tlb_mem *dma_io_tlb_mem; #endif #ifdef CONFIG_SWIOTLB_DYNAMIC struct list_head dma_io_tlb_pools; spinlock_t dma_io_tlb_lock; bool dma_uses_io_tlb; #endif /* arch specific additions */ struct dev_archdata archdata; struct device_node *of_node; /* associated device tree node */ struct fwnode_handle *fwnode; /* firmware device node */ #ifdef CONFIG_NUMA int numa_node; /* NUMA node this device is close to */ #endif dev_t devt; /* dev_t, creates the sysfs "dev" */ u32 id; /* device instance */ spinlock_t devres_lock; struct list_head devres_head; const struct class *class; const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); struct iommu_group *iommu_group; struct dev_iommu *iommu; struct device_physical_location *physical_location; enum device_removable removable; bool offline_disabled:1; bool offline:1; bool of_node_reused:1; bool state_synced:1; bool can_match:1; #if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) bool dma_coherent:1; #endif #ifdef CONFIG_DMA_OPS_BYPASS bool dma_ops_bypass : 1; #endif #ifdef CONFIG_DMA_NEED_SYNC bool dma_skip_sync:1; #endif #ifdef CONFIG_IOMMU_DMA bool dma_iommu:1; #endif }; /** * struct device_link - Device link representation. * @supplier: The device on the supplier end of the link. * @s_node: Hook to the supplier device's list of links to consumers. * @consumer: The device on the consumer end of the link. * @c_node: Hook to the consumer device's list of links to suppliers. * @link_dev: device used to expose link details in sysfs * @status: The state of the link (with respect to the presence of drivers). * @flags: Link flags. * @rpm_active: Whether or not the consumer device is runtime-PM-active. * @kref: Count repeated addition of the same link. * @rm_work: Work structure used for removing the link. * @supplier_preactivated: Supplier has been made active before consumer probe. */ struct device_link { struct device *supplier; struct list_head s_node; struct device *consumer; struct list_head c_node; struct device link_dev; enum device_link_state status; u32 flags; refcount_t rpm_active; struct kref kref; struct work_struct rm_work; bool supplier_preactivated; /* Owned by consumer probe. */ }; #define kobj_to_dev(__kobj) container_of_const(__kobj, struct device, kobj) /** * device_iommu_mapped - Returns true when the device DMA is translated * by an IOMMU * @dev: Device to perform the check on */ static inline bool device_iommu_mapped(struct device *dev) { return (dev->iommu_group != NULL); } /* Get the wakeup routines, which depend on struct device */ #include <linux/pm_wakeup.h> /** * dev_name - Return a device's name. * @dev: Device with name to get. * Return: The kobject name of the device, or its initial name if unavailable. */ static inline const char *dev_name(const struct device *dev) { /* Use the init name until the kobject becomes available */ if (dev->init_name) return dev->init_name; return kobject_name(&dev->kobj); } /** * dev_bus_name - Return a device's bus/class name, if at all possible * @dev: struct device to get the bus/class name of * * Will return the name of the bus/class the device is attached to. If it is * not attached to a bus/class, an empty string will be returned. */ static inline const char *dev_bus_name(const struct device *dev) { return dev->bus ? dev->bus->name : (dev->class ? dev->class->name : ""); } __printf(2, 3) int dev_set_name(struct device *dev, const char *name, ...); #ifdef CONFIG_NUMA static inline int dev_to_node(struct device *dev) { return dev->numa_node; } static inline void set_dev_node(struct device *dev, int node) { dev->numa_node = node; } #else static inline int dev_to_node(struct device *dev) { return NUMA_NO_NODE; } static inline void set_dev_node(struct device *dev, int node) { } #endif static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) { #ifdef CONFIG_GENERIC_MSI_IRQ return dev->msi.domain; #else return NULL; #endif } static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) { #ifdef CONFIG_GENERIC_MSI_IRQ dev->msi.domain = d; #endif } static inline void *dev_get_drvdata(const struct device *dev) { return dev->driver_data; } static inline void dev_set_drvdata(struct device *dev, void *data) { dev->driver_data = data; } static inline struct pm_subsys_data *dev_to_psd(struct device *dev) { return dev ? dev->power.subsys_data : NULL; } static inline unsigned int dev_get_uevent_suppress(const struct device *dev) { return dev->kobj.uevent_suppress; } static inline void dev_set_uevent_suppress(struct device *dev, int val) { dev->kobj.uevent_suppress = val; } static inline int device_is_registered(struct device *dev) { return dev->kobj.state_in_sysfs; } static inline void device_enable_async_suspend(struct device *dev) { if (!dev->power.is_prepared) dev->power.async_suspend = true; } static inline void device_disable_async_suspend(struct device *dev) { if (!dev->power.is_prepared) dev->power.async_suspend = false; } static inline bool device_async_suspend_enabled(struct device *dev) { return !!dev->power.async_suspend; } static inline bool device_pm_not_required(struct device *dev) { return dev->power.no_pm; } static inline void device_set_pm_not_required(struct device *dev) { dev->power.no_pm = true; #ifdef CONFIG_PM dev->power.no_callbacks = true; #endif } static inline void dev_pm_syscore_device(struct device *dev, bool val) { #ifdef CONFIG_PM_SLEEP dev->power.syscore = val; #endif } static inline void dev_pm_set_driver_flags(struct device *dev, u32 flags) { dev->power.driver_flags = flags; } static inline bool dev_pm_test_driver_flags(struct device *dev, u32 flags) { return !!(dev->power.driver_flags & flags); } static inline bool dev_pm_smart_suspend(struct device *dev) { #ifdef CONFIG_PM_SLEEP return dev->power.smart_suspend; #else return false; #endif } /* * dev_pm_set_strict_midlayer - Update the device's power.strict_midlayer flag * @dev: Target device. * @val: New flag value. * * When set, power.strict_midlayer means that the middle layer power management * code (typically, a bus type or a PM domain) does not expect its runtime PM * suspend callback to be invoked at all during system-wide PM transitions and * it does not expect its runtime PM resume callback to be invoked at any point * when runtime PM is disabled for the device during system-wide PM transitions. */ static inline void dev_pm_set_strict_midlayer(struct device *dev, bool val) { #ifdef CONFIG_PM_SLEEP dev->power.strict_midlayer = val; #endif } static inline bool dev_pm_strict_midlayer_is_set(struct device *dev) { #ifdef CONFIG_PM_SLEEP return dev->power.strict_midlayer; #else return false; #endif } static inline void device_lock(struct device *dev) { mutex_lock(&dev->mutex); } static inline int device_lock_interruptible(struct device *dev) { return mutex_lock_interruptible(&dev->mutex); } static inline int device_trylock(struct device *dev) { return mutex_trylock(&dev->mutex); } static inline void device_unlock(struct device *dev) { mutex_unlock(&dev->mutex); } DEFINE_GUARD(device, struct device *, device_lock(_T), device_unlock(_T)) static inline void device_lock_assert(struct device *dev) { lockdep_assert_held(&dev->mutex); } static inline bool dev_has_sync_state(struct device *dev) { if (!dev) return false; if (dev->driver && dev->driver->sync_state) return true; if (dev->bus && dev->bus->sync_state) return true; return false; } static inline int dev_set_drv_sync_state(struct device *dev, void (*fn)(struct device *dev)) { if (!dev || !dev->driver) return 0; if (dev->driver->sync_state && dev->driver->sync_state != fn) return -EBUSY; if (!dev->driver->sync_state) dev->driver->sync_state = fn; return 0; } static inline void dev_set_removable(struct device *dev, enum device_removable removable) { dev->removable = removable; } static inline bool dev_is_removable(struct device *dev) { return dev->removable == DEVICE_REMOVABLE; } static inline bool dev_removable_is_valid(struct device *dev) { return dev->removable != DEVICE_REMOVABLE_NOT_SUPPORTED; } /* * High level routines for use by the bus drivers */ int __must_check device_register(struct device *dev); void device_unregister(struct device *dev); void device_initialize(struct device *dev); int __must_check device_add(struct device *dev); void device_del(struct device *dev); DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T)) int device_for_each_child(struct device *parent, void *data, device_iter_t fn); int device_for_each_child_reverse(struct device *parent, void *data, device_iter_t fn); int device_for_each_child_reverse_from(struct device *parent, struct device *from, void *data, device_iter_t fn); struct device *device_find_child(struct device *parent, const void *data, device_match_t match); /** * device_find_child_by_name - device iterator for locating a child device. * @parent: parent struct device * @name: name of the child device * * This is similar to the device_find_child() function above, but it * returns a reference to a device that has the name @name. * * NOTE: you will need to drop the reference with put_device() after use. */ static inline struct device *device_find_child_by_name(struct device *parent, const char *name) { return device_find_child(parent, name, device_match_name); } /** * device_find_any_child - device iterator for locating a child device, if any. * @parent: parent struct device * * This is similar to the device_find_child() function above, but it * returns a reference to a child device, if any. * * NOTE: you will need to drop the reference with put_device() after use. */ static inline struct device *device_find_any_child(struct device *parent) { return device_find_child(parent, NULL, device_match_any); } int device_rename(struct device *dev, const char *new_name); int device_move(struct device *dev, struct device *new_parent, enum dpm_order dpm_order); int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid); static inline bool device_supports_offline(struct device *dev) { return dev->bus && dev->bus->offline && dev->bus->online; } #define __device_lock_set_class(dev, name, key) \ do { \ struct device *__d2 __maybe_unused = dev; \ lock_set_class(&__d2->mutex.dep_map, name, key, 0, _THIS_IP_); \ } while (0) /** * device_lock_set_class - Specify a temporary lock class while a device * is attached to a driver * @dev: device to modify * @key: lock class key data * * This must be called with the device_lock() already held, for example * from driver ->probe(). Take care to only override the default * lockdep_no_validate class. */ #ifdef CONFIG_LOCKDEP #define device_lock_set_class(dev, key) \ do { \ struct device *__d = dev; \ dev_WARN_ONCE(__d, !lockdep_match_class(&__d->mutex, \ &__lockdep_no_validate__), \ "overriding existing custom lock class\n"); \ __device_lock_set_class(__d, #key, key); \ } while (0) #else #define device_lock_set_class(dev, key) __device_lock_set_class(dev, #key, key) #endif /** * device_lock_reset_class - Return a device to the default lockdep novalidate state * @dev: device to modify * * This must be called with the device_lock() already held, for example * from driver ->remove(). */ #define device_lock_reset_class(dev) \ do { \ struct device *__d __maybe_unused = dev; \ lock_set_novalidate_class(&__d->mutex.dep_map, "&dev->mutex", \ _THIS_IP_); \ } while (0) void lock_device_hotplug(void); void unlock_device_hotplug(void); int lock_device_hotplug_sysfs(void); int device_offline(struct device *dev); int device_online(struct device *dev); void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void device_set_node(struct device *dev, struct fwnode_handle *fwnode); int device_add_of_node(struct device *dev, struct device_node *of_node); void device_remove_of_node(struct device *dev); void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); struct device *get_dev_from_fwnode(struct fwnode_handle *fwnode); static inline struct device_node *dev_of_node(struct device *dev) { if (!IS_ENABLED(CONFIG_OF) || !dev) return NULL; return dev->of_node; } static inline int dev_num_vf(struct device *dev) { if (dev->bus && dev->bus->num_vf) return dev->bus->num_vf(dev); return 0; } /* * Root device objects for grouping under /sys/devices */ struct device *__root_device_register(const char *name, struct module *owner); /* This is a macro to avoid include problems with THIS_MODULE */ #define root_device_register(name) \ __root_device_register(name, THIS_MODULE) void root_device_unregister(struct device *root); static inline void *dev_get_platdata(const struct device *dev) { return dev->platform_data; } /* * Manual binding of a device to driver. See drivers/base/bus.c * for information on use. */ int __must_check device_driver_attach(const struct device_driver *drv, struct device *dev); int __must_check device_bind_driver(struct device *dev); void device_release_driver(struct device *dev); int __must_check device_attach(struct device *dev); int __must_check driver_attach(const struct device_driver *drv); void device_initial_probe(struct device *dev); int __must_check device_reprobe(struct device *dev); bool device_is_bound(struct device *dev); /* * Easy functions for dynamically creating devices on the fly */ __printf(5, 6) struct device * device_create(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...); __printf(6, 7) struct device * device_create_with_groups(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); void device_destroy(const struct class *cls, dev_t devt); int __must_check device_add_groups(struct device *dev, const struct attribute_group **groups); void device_remove_groups(struct device *dev, const struct attribute_group **groups); static inline int __must_check device_add_group(struct device *dev, const struct attribute_group *grp) { const struct attribute_group *groups[] = { grp, NULL }; return device_add_groups(dev, groups); } static inline void device_remove_group(struct device *dev, const struct attribute_group *grp) { const struct attribute_group *groups[] = { grp, NULL }; device_remove_groups(dev, groups); } int __must_check devm_device_add_group(struct device *dev, const struct attribute_group *grp); /* * get_device - atomically increment the reference count for the device. * */ struct device *get_device(struct device *dev); void put_device(struct device *dev); DEFINE_FREE(put_device, struct device *, if (_T) put_device(_T)) bool kill_device(struct device *dev); #ifdef CONFIG_DEVTMPFS int devtmpfs_mount(void); #else static inline int devtmpfs_mount(void) { return 0; } #endif /* drivers/base/power/shutdown.c */ void device_shutdown(void); /* debugging and troubleshooting/diagnostic helpers. */ const char *dev_driver_string(const struct device *dev); /* Device links interface. */ struct device_link *device_link_add(struct device *consumer, struct device *supplier, u32 flags); void device_link_del(struct device_link *link); void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); void device_link_wait_removal(void); static inline bool device_link_test(const struct device_link *link, u32 flags) { return !!(link->flags & flags); } /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_CHARDEV_MAJOR(major) \ MODULE_ALIAS("char-major-" __stringify(major) "-*") #endif /* _DEVICE_H_ */ |
| 14 995 995 993 995 997 995 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * printk_safe.c - Safe printk for printk-deadlock-prone contexts */ #include <linux/preempt.h> #include <linux/kdb.h> #include <linux/smp.h> #include <linux/cpumask.h> #include <linux/printk.h> #include <linux/kprobes.h> #include "internal.h" /* Context where printk messages are never suppressed */ static atomic_t force_con; void printk_force_console_enter(void) { atomic_inc(&force_con); } void printk_force_console_exit(void) { atomic_dec(&force_con); } bool is_printk_force_console(void) { return atomic_read(&force_con); } static DEFINE_PER_CPU(int, printk_context); /* Can be preempted by NMI. */ void __printk_safe_enter(void) { this_cpu_inc(printk_context); } /* Can be preempted by NMI. */ void __printk_safe_exit(void) { this_cpu_dec(printk_context); } void __printk_deferred_enter(void) { cant_migrate(); __printk_safe_enter(); } void __printk_deferred_exit(void) { cant_migrate(); __printk_safe_exit(); } bool is_printk_legacy_deferred(void) { /* * The per-CPU variable @printk_context can be read safely in any * context. CPU migration is always disabled when set. * * A context holding the printk_cpu_sync must not spin waiting for * another CPU. For legacy printing, it could be the console_lock * or the port lock. */ return (force_legacy_kthread() || this_cpu_read(printk_context) || in_nmi() || is_printk_cpu_sync_owner()); } asmlinkage int vprintk(const char *fmt, va_list args) { #ifdef CONFIG_KGDB_KDB /* Allow to pass printk() to kdb but avoid a recursion. */ if (unlikely(kdb_trap_printk && kdb_printf_cpu < 0)) return vkdb_printf(KDB_MSGSRC_PRINTK, fmt, args); #endif return vprintk_default(fmt, args); } EXPORT_SYMBOL(vprintk); |
| 4 4 1 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 | // 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. * * IPv4 Forwarding Information Base: FIB frontend. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <net/flow.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/arp.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/rtnetlink.h> #include <net/xfrm.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> #include <trace/events/fib.h> #ifndef CONFIG_IP_MULTIPLE_TABLES static int __net_init fib4_rules_init(struct net *net) { struct fib_table *local_table, *main_table; main_table = fib_trie_table(RT_TABLE_MAIN, NULL); if (!main_table) return -ENOMEM; local_table = fib_trie_table(RT_TABLE_LOCAL, main_table); if (!local_table) goto fail; hlist_add_head_rcu(&local_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]); hlist_add_head_rcu(&main_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]); return 0; fail: fib_free_table(main_table); return -ENOMEM; } #else struct fib_table *fib_new_table(struct net *net, u32 id) { struct fib_table *tb, *alias = NULL; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; tb = fib_get_table(net, id); if (tb) return tb; if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules) alias = fib_new_table(net, RT_TABLE_MAIN); tb = fib_trie_table(id, alias); if (!tb) return NULL; switch (id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, tb); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, tb); break; default: break; } h = id & (FIB_TABLE_HASHSZ - 1); hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]); return tb; } EXPORT_SYMBOL_GPL(fib_new_table); /* caller must hold either rtnl or rcu read lock */ struct fib_table *fib_get_table(struct net *net, u32 id) { struct fib_table *tb; struct hlist_head *head; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; h = id & (FIB_TABLE_HASHSZ - 1); head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist, lockdep_rtnl_is_held()) { if (tb->tb_id == id) return tb; } return NULL; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ static void fib_replace_table(struct net *net, struct fib_table *old, struct fib_table *new) { #ifdef CONFIG_IP_MULTIPLE_TABLES switch (new->tb_id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, new); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, new); break; default: break; } #endif /* replace the old table in the hlist */ hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist); } int fib_unmerge(struct net *net) { struct fib_table *old, *new, *main_table; /* attempt to fetch local table if it has been allocated */ old = fib_get_table(net, RT_TABLE_LOCAL); if (!old) return 0; new = fib_trie_unmerge(old); if (!new) return -ENOMEM; /* table is already unmerged */ if (new == old) return 0; /* replace merged table with clean table */ fib_replace_table(net, old, new); fib_free_table(old); /* attempt to fetch main table if it has been allocated */ main_table = fib_get_table(net, RT_TABLE_MAIN); if (!main_table) return 0; /* flush local entries from main table */ fib_table_flush_external(main_table); return 0; } void fib_flush(struct net *net) { int flushed = 0; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct hlist_node *tmp; struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) flushed += fib_table_flush(net, tb, false); } if (flushed) rt_cache_flush(net); } /* * Find address type as if only "dev" was present in the system. If * on_dev is NULL then all interfaces are taken into consideration. */ static inline unsigned int __inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr, u32 tb_id) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res; unsigned int ret = RTN_BROADCAST; struct fib_table *table; if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) return RTN_BROADCAST; if (ipv4_is_multicast(addr)) return RTN_MULTICAST; rcu_read_lock(); table = fib_get_table(net, tb_id); if (table) { ret = RTN_UNICAST; if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) { struct fib_nh_common *nhc = fib_info_nhc(res.fi, 0); if (!dev || dev == nhc->nhc_dev) ret = res.type; } } rcu_read_unlock(); return ret; } unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id) { return __inet_dev_addr_type(net, NULL, addr, tb_id); } EXPORT_SYMBOL(inet_addr_type_table); unsigned int inet_addr_type(struct net *net, __be32 addr) { return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL); } EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, dev, addr, rt_table); } EXPORT_SYMBOL(inet_dev_addr_type); /* inet_addr_type with dev == NULL but using the table from a dev * if one is associated */ unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, NULL, addr, rt_table); } EXPORT_SYMBOL(inet_addr_type_dev_table); __be32 fib_compute_spec_dst(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev; struct fib_result res; struct rtable *rt; struct net *net; int scope; rt = skb_rtable(skb); if ((rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL)) == RTCF_LOCAL) return ip_hdr(skb)->daddr; in_dev = __in_dev_get_rcu(dev); net = dev_net(dev); scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev); struct flowi4 fl4 = { .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, .flowi4_dscp = ip4h_dscp(ip_hdr(skb)), .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; if (!fib_lookup(net, &fl4, &res, 0)) return fib_result_prefsrc(net, &res); } else { scope = RT_SCOPE_LINK; } return inet_select_addr(dev, ip_hdr(skb)->saddr, scope); } bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev) { bool dev_match = false; #ifdef CONFIG_IP_ROUTE_MULTIPATH if (unlikely(fi->nh)) { dev_match = nexthop_uses_dev(fi->nh, dev); } else { int ret; for (ret = 0; ret < fib_info_num_path(fi); ret++) { const struct fib_nh_common *nhc = fib_info_nhc(fi, ret); if (nhc_l3mdev_matches_dev(nhc, dev)) { dev_match = true; break; } } } #else if (fib_info_nhc(fi, 0)->nhc_dev == dev) dev_match = true; #endif return dev_match; } EXPORT_SYMBOL_GPL(fib_info_nh_uses_dev); /* Given (packet source, input interface) and optional (dst, oif, tos): * - (main) check, that source is valid i.e. not broadcast or our local * address. * - figure out what "logical" interface this packet arrived * and calculate "specific destination" address. * - check, that packet arrived from expected physical interface. * called with rcu_read_lock() */ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, int rpf, struct in_device *idev, u32 *itag) { struct net *net = dev_net(dev); enum skb_drop_reason reason; struct flow_keys flkeys; int ret, no_addr; struct fib_result res; struct flowi4 fl4; bool dev_match; fl4.flowi4_oif = 0; fl4.flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev); fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_dscp = dscp; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_flags = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_multipath_hash = 0; no_addr = idev->ifa_list == NULL; fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0; if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) { fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; } else { swap(fl4.fl4_sport, fl4.fl4_dport); } if (fib_lookup(net, &fl4, &res, 0)) goto last_resort; if (res.type != RTN_UNICAST) { if (res.type != RTN_LOCAL) { reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto e_inval; } else if (!IN_DEV_ACCEPT_LOCAL(idev)) { reason = SKB_DROP_REASON_IP_LOCAL_SOURCE; goto e_inval; } } fib_combine_itag(itag, &res); dev_match = fib_info_nh_uses_dev(res.fi, dev); /* This is not common, loopback packets retain skb_dst so normally they * would not even hit this slow path. */ dev_match = dev_match || (res.type == RTN_LOCAL && dev == net->loopback_dev); if (dev_match) { ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; return ret; } if (no_addr) goto last_resort; if (rpf == 1) goto e_rpf; fl4.flowi4_oif = dev->ifindex; ret = 0; if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) { if (res.type == RTN_UNICAST) ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; } return ret; last_resort: if (rpf) goto e_rpf; *itag = 0; return 0; e_inval: return -reason; e_rpf: return -SKB_DROP_REASON_IP_RPFILTER; } /* Ignore rp_filter for packets protected by IPsec. */ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, struct in_device *idev, u32 *itag) { int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev); struct net *net = dev_net(dev); if (!r && !fib_num_tclassid_users(net) && (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) { if (IN_DEV_ACCEPT_LOCAL(idev)) goto ok; /* with custom local routes in place, checking local addresses * only will be too optimistic, with custom rules, checking * local addresses only can be too strict, e.g. due to vrf */ if (net->ipv4.fib_has_custom_local_routes || fib4_has_custom_rules(net)) goto full_check; /* Within the same container, it is regarded as a martian source, * and the same host but different containers are not. */ if (inet_lookup_ifaddr_rcu(net, src)) return -SKB_DROP_REASON_IP_LOCAL_SOURCE; ok: *itag = 0; return 0; } full_check: return __fib_validate_source(skb, src, dst, dscp, oif, dev, r, idev, itag); } static inline __be32 sk_extract_addr(struct sockaddr *addr) { return ((struct sockaddr_in *) addr)->sin_addr.s_addr; } static int put_rtax(struct nlattr *mx, int len, int type, u32 value) { struct nlattr *nla; nla = (struct nlattr *) ((char *) mx + len); nla->nla_type = type; nla->nla_len = nla_attr_size(4); *(u32 *) nla_data(nla) = value; return len + nla_total_size(4); } static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, struct fib_config *cfg) { __be32 addr; int plen; memset(cfg, 0, sizeof(*cfg)); cfg->fc_nlinfo.nl_net = net; if (rt->rt_dst.sa_family != AF_INET) return -EAFNOSUPPORT; /* * Check mask for validity: * a) it must be contiguous. * b) destination must have all host bits clear. * c) if application forgot to set correct family (AF_INET), * reject request unless it is absolutely clear i.e. * both family and mask are zero. */ plen = 32; addr = sk_extract_addr(&rt->rt_dst); if (!(rt->rt_flags & RTF_HOST)) { __be32 mask = sk_extract_addr(&rt->rt_genmask); if (rt->rt_genmask.sa_family != AF_INET) { if (mask || rt->rt_genmask.sa_family) return -EAFNOSUPPORT; } if (bad_mask(mask, addr)) return -EINVAL; plen = inet_mask_len(mask); } cfg->fc_dst_len = plen; cfg->fc_dst = addr; if (cmd != SIOCDELRT) { cfg->fc_nlflags = NLM_F_CREATE; cfg->fc_protocol = RTPROT_BOOT; } if (rt->rt_metric) cfg->fc_priority = rt->rt_metric - 1; if (rt->rt_flags & RTF_REJECT) { cfg->fc_scope = RT_SCOPE_HOST; cfg->fc_type = RTN_UNREACHABLE; return 0; } cfg->fc_scope = RT_SCOPE_NOWHERE; cfg->fc_type = RTN_UNICAST; if (rt->rt_dev) { char *colon; struct net_device *dev; char devname[IFNAMSIZ]; if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1)) return -EFAULT; devname[IFNAMSIZ-1] = 0; colon = strchr(devname, ':'); if (colon) *colon = 0; dev = __dev_get_by_name(net, devname); if (!dev) return -ENODEV; cfg->fc_oif = dev->ifindex; cfg->fc_table = l3mdev_fib_table(dev); if (colon) { const struct in_ifaddr *ifa; struct in_device *in_dev; in_dev = __in_dev_get_rtnl_net(dev); if (!in_dev) return -ENODEV; *colon = ':'; in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) { if (strcmp(ifa->ifa_label, devname) == 0) break; } if (!ifa) return -ENODEV; cfg->fc_prefsrc = ifa->ifa_local; } } addr = sk_extract_addr(&rt->rt_gateway); if (rt->rt_gateway.sa_family == AF_INET && addr) { unsigned int addr_type; cfg->fc_gw4 = addr; cfg->fc_gw_family = AF_INET; addr_type = inet_addr_type_table(net, addr, cfg->fc_table); if (rt->rt_flags & RTF_GATEWAY && addr_type == RTN_UNICAST) cfg->fc_scope = RT_SCOPE_UNIVERSE; } if (!cfg->fc_table) cfg->fc_table = RT_TABLE_MAIN; if (cmd == SIOCDELRT) return 0; if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw_family) return -EINVAL; if (cfg->fc_scope == RT_SCOPE_NOWHERE) cfg->fc_scope = RT_SCOPE_LINK; if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) { struct nlattr *mx; int len = 0; mx = kcalloc(3, nla_total_size(4), GFP_KERNEL); if (!mx) return -ENOMEM; if (rt->rt_flags & RTF_MTU) len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40); if (rt->rt_flags & RTF_WINDOW) len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window); if (rt->rt_flags & RTF_IRTT) len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3); cfg->fc_mx = mx; cfg->fc_mx_len = len; } return 0; } /* * Handle IP routing ioctl calls. * These are used to manipulate the routing tables */ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt) { struct fib_config cfg; int err; switch (cmd) { case SIOCADDRT: /* Add a route */ case SIOCDELRT: /* Delete a route */ if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtnl_net_lock(net); err = rtentry_to_fib_config(net, cmd, rt, &cfg); if (err == 0) { struct fib_table *tb; if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) err = fib_table_delete(net, tb, &cfg, NULL); else err = -ESRCH; } else { tb = fib_new_table(net, cfg.fc_table); if (tb) err = fib_table_insert(net, tb, &cfg, NULL); else err = -ENOBUFS; } /* allocated by rtentry_to_fib_config() */ kfree(cfg.fc_mx); } rtnl_net_unlock(net); return err; } return -EINVAL; } const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_DST] = { .type = NLA_U32 }, [RTA_SRC] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_GATEWAY] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_PREFSRC] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_FLOW] = { .type = NLA_U32 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_IP_PROTO] = { .type = NLA_U8 }, [RTA_SPORT] = { .type = NLA_U16 }, [RTA_DPORT] = { .type = NLA_U16 }, [RTA_NH_ID] = { .type = NLA_U32 }, }; int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, struct netlink_ext_ack *extack) { struct rtvia *via; int alen; if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) { NL_SET_ERR_MSG(extack, "Invalid attribute length for RTA_VIA"); return -EINVAL; } via = nla_data(nla); alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr); switch (via->rtvia_family) { case AF_INET: if (alen != sizeof(__be32)) { NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_VIA"); return -EINVAL; } cfg->fc_gw_family = AF_INET; cfg->fc_gw4 = *((__be32 *)via->rtvia_addr); break; case AF_INET6: #if IS_ENABLED(CONFIG_IPV6) if (alen != sizeof(struct in6_addr)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA"); return -EINVAL; } cfg->fc_gw_family = AF_INET6; cfg->fc_gw6 = *((struct in6_addr *)via->rtvia_addr); #else NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel"); return -EINVAL; #endif break; default: NL_SET_ERR_MSG(extack, "Unsupported address family in RTA_VIA"); return -EINVAL; } return 0; } static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_config *cfg, struct netlink_ext_ack *extack) { bool has_gw = false, has_via = false; struct nlattr *attr; int err, remaining; struct rtmsg *rtm; err = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy, extack); if (err < 0) goto errout; memset(cfg, 0, sizeof(*cfg)); rtm = nlmsg_data(nlh); if (!inet_validate_dscp(rtm->rtm_tos)) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): ECN bits must be 0"); err = -EINVAL; goto errout; } cfg->fc_dscp = inet_dsfield_to_dscp(rtm->rtm_tos); cfg->fc_dst_len = rtm->rtm_dst_len; cfg->fc_table = rtm->rtm_table; cfg->fc_protocol = rtm->rtm_protocol; cfg->fc_scope = rtm->rtm_scope; cfg->fc_type = rtm->rtm_type; cfg->fc_flags = rtm->rtm_flags; cfg->fc_nlflags = nlh->nlmsg_flags; cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->fc_nlinfo.nlh = nlh; cfg->fc_nlinfo.nl_net = net; if (cfg->fc_type > RTN_MAX) { NL_SET_ERR_MSG(extack, "Invalid route type"); err = -EINVAL; goto errout; } nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) { switch (nla_type(attr)) { case RTA_DST: cfg->fc_dst = nla_get_be32(attr); break; case RTA_OIF: cfg->fc_oif = nla_get_u32(attr); break; case RTA_GATEWAY: has_gw = true; cfg->fc_gw4 = nla_get_be32(attr); if (cfg->fc_gw4) cfg->fc_gw_family = AF_INET; break; case RTA_VIA: has_via = true; err = fib_gw_from_via(cfg, attr, extack); if (err) goto errout; break; case RTA_PRIORITY: cfg->fc_priority = nla_get_u32(attr); break; case RTA_PREFSRC: cfg->fc_prefsrc = nla_get_be32(attr); break; case RTA_METRICS: cfg->fc_mx = nla_data(attr); cfg->fc_mx_len = nla_len(attr); break; case RTA_MULTIPATH: err = lwtunnel_valid_encap_type_attr(nla_data(attr), nla_len(attr), extack); if (err < 0) goto errout; cfg->fc_mp = nla_data(attr); cfg->fc_mp_len = nla_len(attr); break; case RTA_FLOW: cfg->fc_flow = nla_get_u32(attr); break; case RTA_TABLE: cfg->fc_table = nla_get_u32(attr); break; case RTA_ENCAP: cfg->fc_encap = attr; break; case RTA_ENCAP_TYPE: cfg->fc_encap_type = nla_get_u16(attr); err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; break; case RTA_NH_ID: cfg->fc_nh_id = nla_get_u32(attr); break; } } if (cfg->fc_dst_len > 32) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); err = -EINVAL; goto errout; } if (cfg->fc_dst_len < 32 && (ntohl(cfg->fc_dst) << cfg->fc_dst_len)) { NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length"); err = -EINVAL; goto errout; } if (cfg->fc_nh_id) { if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_encap || cfg->fc_mp) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); err = -EINVAL; goto errout; } } if (has_gw && has_via) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); err = -EINVAL; goto errout; } if (!cfg->fc_table) cfg->fc_table = RT_TABLE_MAIN; return 0; errout: return err; } static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; rtnl_net_lock(net); if (cfg.fc_nh_id && !nexthop_find_by_id(net, cfg.fc_nh_id)) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); err = -EINVAL; goto unlock; } tb = fib_get_table(net, cfg.fc_table); if (!tb) { NL_SET_ERR_MSG(extack, "FIB table does not exist"); err = -ESRCH; goto unlock; } err = fib_table_delete(net, tb, &cfg, extack); unlock: rtnl_net_unlock(net); errout: return err; } static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; err = rtm_to_fib_config(net, skb, nlh, &cfg, extack); if (err < 0) goto errout; rtnl_net_lock(net); tb = fib_new_table(net, cfg.fc_table); if (!tb) { err = -ENOBUFS; goto unlock; } err = fib_table_insert(net, tb, &cfg, extack); if (!err && cfg.fc_type == RTN_LOCAL) net->ipv4.fib_has_custom_local_routes = true; unlock: rtnl_net_unlock(net); errout: return err; } int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[RTA_MAX + 1]; struct rtmsg *rtm; int err, i; if (filter->rtnl_held) ASSERT_RTNL(); rtm = nlmsg_payload(nlh, sizeof(*rtm)); if (!rtm) { NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request"); return -EINVAL; } if (rtm->rtm_dst_len || rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_scope) { NL_SET_ERR_MSG(extack, "Invalid values in header for FIB dump request"); return -EINVAL; } if (rtm->rtm_flags & ~(RTM_F_CLONED | RTM_F_PREFIX)) { NL_SET_ERR_MSG(extack, "Invalid flags for FIB dump request"); return -EINVAL; } if (rtm->rtm_flags & RTM_F_CLONED) filter->dump_routes = false; else filter->dump_exceptions = false; filter->flags = rtm->rtm_flags; filter->protocol = rtm->rtm_protocol; filter->rt_type = rtm->rtm_type; filter->table_id = rtm->rtm_table; err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err < 0) return err; for (i = 0; i <= RTA_MAX; ++i) { int ifindex; if (!tb[i]) continue; switch (i) { case RTA_TABLE: filter->table_id = nla_get_u32(tb[i]); break; case RTA_OIF: ifindex = nla_get_u32(tb[i]); if (filter->rtnl_held) filter->dev = __dev_get_by_index(net, ifindex); else filter->dev = dev_get_by_index_rcu(net, ifindex); if (!filter->dev) return -ENODEV; break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); return -EINVAL; } } if (filter->flags || filter->protocol || filter->rt_type || filter->table_id || filter->dev) { filter->filter_set = 1; cb->answer_flags = NLM_F_DUMP_FILTERED; } return 0; } EXPORT_SYMBOL_GPL(ip_valid_fib_dump_req); static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { struct fib_dump_filter filter = { .dump_routes = true, .dump_exceptions = true, .rtnl_held = false, }; const struct nlmsghdr *nlh = cb->nlh; struct net *net = sock_net(skb->sk); unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; struct hlist_head *head; int dumped = 0, err = 0; rcu_read_lock(); if (cb->strict_check) { err = ip_valid_fib_dump_req(net, nlh, &filter, cb); if (err < 0) goto unlock; } else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) { struct rtmsg *rtm = nlmsg_data(nlh); filter.flags = rtm->rtm_flags & (RTM_F_PREFIX | RTM_F_CLONED); } /* ipv4 does not use prefix flag */ if (filter.flags & RTM_F_PREFIX) goto unlock; if (filter.table_id) { tb = fib_get_table(net, filter.table_id); if (!tb) { if (rtnl_msg_family(cb->nlh) != PF_INET) goto unlock; NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist"); err = -ENOENT; goto unlock; } err = fib_table_dump(tb, skb, cb, &filter); goto unlock; } s_h = cb->args[0]; s_e = cb->args[1]; err = 0; for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { e = 0; head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist) { if (e < s_e) goto next; if (dumped) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); err = fib_table_dump(tb, skb, cb, &filter); if (err < 0) goto out; dumped = 1; next: e++; } } out: cb->args[1] = e; cb->args[0] = h; unlock: rcu_read_unlock(); return err; } /* Prepare and feed intra-kernel routing request. * Really, it should be netlink message, but :-( netlink * can be not configured, so that we feed it directly * to fib engine. It is legal, because all events occur * only when netlink is already locked. */ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa, u32 rt_priority) { struct net *net = dev_net(ifa->ifa_dev->dev); u32 tb_id = l3mdev_fib_table(ifa->ifa_dev->dev); struct fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, .fc_type = type, .fc_dst = dst, .fc_dst_len = dst_len, .fc_priority = rt_priority, .fc_prefsrc = ifa->ifa_local, .fc_oif = ifa->ifa_dev->dev->ifindex, .fc_nlflags = NLM_F_CREATE | NLM_F_APPEND, .fc_nlinfo = { .nl_net = net, }, }; if (!tb_id) tb_id = (type == RTN_UNICAST) ? RT_TABLE_MAIN : RT_TABLE_LOCAL; tb = fib_new_table(net, tb_id); if (!tb) return; cfg.fc_table = tb->tb_id; if (type != RTN_LOCAL) cfg.fc_scope = RT_SCOPE_LINK; else cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) fib_table_insert(net, tb, &cfg, NULL); else fib_table_delete(net, tb, &cfg, NULL); } void fib_add_ifaddr(struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; struct in_ifaddr *prim = ifa; __be32 mask = ifa->ifa_mask; __be32 addr = ifa->ifa_local; __be32 prefix = ifa->ifa_address & mask; if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, prefix, mask); if (!prim) { pr_warn("%s: bug: prim == NULL\n", __func__); return; } } fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim, 0); if (!(dev->flags & IFF_UP)) return; /* Add broadcast address, if it is explicitly assigned. */ if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) { fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim, 0); arp_invalidate(dev, ifa->ifa_broadcast, false); } if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) && (prefix != addr || ifa->ifa_prefixlen < 32)) { if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE)) fib_magic(RTM_NEWROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, prim, ifa->ifa_rt_priority); /* Add the network broadcast address, when it makes sense */ if (ifa->ifa_prefixlen < 31) { fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask, 32, prim, 0); arp_invalidate(dev, prefix | ~mask, false); } } } void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric) { __be32 prefix = ifa->ifa_address & ifa->ifa_mask; struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; if (!(dev->flags & IFF_UP) || ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) || ipv4_is_zeronet(prefix) || (prefix == ifa->ifa_local && ifa->ifa_prefixlen == 32)) return; /* add the new */ fib_magic(RTM_NEWROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, ifa, new_metric); /* delete the old */ fib_magic(RTM_DELROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, prefix, ifa->ifa_prefixlen, ifa, ifa->ifa_rt_priority); } /* Delete primary or secondary address. * Optionally, on secondary address promotion consider the addresses * from subnet iprim as deleted, even if they are in device list. * In this case the secondary ifa can be in device list. */ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) { struct in_device *in_dev = ifa->ifa_dev; struct net_device *dev = in_dev->dev; struct in_ifaddr *ifa1; struct in_ifaddr *prim = ifa, *prim1 = NULL; __be32 brd = ifa->ifa_address | ~ifa->ifa_mask; __be32 any = ifa->ifa_address & ifa->ifa_mask; #define LOCAL_OK 1 #define BRD_OK 2 #define BRD0_OK 4 #define BRD1_OK 8 unsigned int ok = 0; int subnet = 0; /* Primary network */ int gone = 1; /* Address is missing */ int same_prefsrc = 0; /* Another primary with same IP */ if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (!prim) { /* if the device has been deleted, we don't perform * address promotion */ if (!in_dev->dead) pr_warn("%s: bug: prim == NULL\n", __func__); return; } if (iprim && iprim != prim) { pr_warn("%s: bug: iprim != prim\n", __func__); return; } } else if (!ipv4_is_zeronet(any) && (any != ifa->ifa_local || ifa->ifa_prefixlen < 32)) { if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE)) fib_magic(RTM_DELROUTE, dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, any, ifa->ifa_prefixlen, prim, 0); subnet = 1; } if (in_dev->dead) goto no_promotions; /* Deletion is more complicated than add. * We should take care of not to delete too much :-) * * Scan address list to be sure that addresses are really gone. */ rcu_read_lock(); in_dev_for_each_ifa_rcu(ifa1, in_dev) { if (ifa1 == ifa) { /* promotion, keep the IP */ gone = 0; continue; } /* Ignore IFAs from our subnet */ if (iprim && ifa1->ifa_mask == iprim->ifa_mask && inet_ifa_match(ifa1->ifa_address, iprim)) continue; /* Ignore ifa1 if it uses different primary IP (prefsrc) */ if (ifa1->ifa_flags & IFA_F_SECONDARY) { /* Another address from our subnet? */ if (ifa1->ifa_mask == prim->ifa_mask && inet_ifa_match(ifa1->ifa_address, prim)) prim1 = prim; else { /* We reached the secondaries, so * same_prefsrc should be determined. */ if (!same_prefsrc) continue; /* Search new prim1 if ifa1 is not * using the current prim1 */ if (!prim1 || ifa1->ifa_mask != prim1->ifa_mask || !inet_ifa_match(ifa1->ifa_address, prim1)) prim1 = inet_ifa_byprefix(in_dev, ifa1->ifa_address, ifa1->ifa_mask); if (!prim1) continue; if (prim1->ifa_local != prim->ifa_local) continue; } } else { if (prim->ifa_local != ifa1->ifa_local) continue; prim1 = ifa1; if (prim != prim1) same_prefsrc = 1; } if (ifa->ifa_local == ifa1->ifa_local) ok |= LOCAL_OK; if (ifa->ifa_broadcast == ifa1->ifa_broadcast) ok |= BRD_OK; if (brd == ifa1->ifa_broadcast) ok |= BRD1_OK; if (any == ifa1->ifa_broadcast) ok |= BRD0_OK; /* primary has network specific broadcasts */ if (prim1 == ifa1 && ifa1->ifa_prefixlen < 31) { __be32 brd1 = ifa1->ifa_address | ~ifa1->ifa_mask; __be32 any1 = ifa1->ifa_address & ifa1->ifa_mask; if (!ipv4_is_zeronet(any1)) { if (ifa->ifa_broadcast == brd1 || ifa->ifa_broadcast == any1) ok |= BRD_OK; if (brd == brd1 || brd == any1) ok |= BRD1_OK; if (any == brd1 || any == any1) ok |= BRD0_OK; } } } rcu_read_unlock(); no_promotions: if (!(ok & BRD_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim, 0); if (subnet && ifa->ifa_prefixlen < 31) { if (!(ok & BRD1_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim, 0); if (!(ok & BRD0_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim, 0); } if (!(ok & LOCAL_OK)) { unsigned int addr_type; fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim, 0); /* Check, that this local address finally disappeared. */ addr_type = inet_addr_type_dev_table(dev_net(dev), dev, ifa->ifa_local); if (gone && addr_type != RTN_LOCAL) { /* And the last, but not the least thing. * We must flush stray FIB entries. * * First of all, we scan fib_info list searching * for stray nexthop entries, then ignite fib_flush. */ if (fib_sync_down_addr(dev, ifa->ifa_local)) fib_flush(dev_net(dev)); } } #undef LOCAL_OK #undef BRD_OK #undef BRD0_OK #undef BRD1_OK } static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn) { struct fib_result res; struct flowi4 fl4 = { .flowi4_mark = frn->fl_mark, .daddr = frn->fl_addr, .flowi4_dscp = inet_dsfield_to_dscp(frn->fl_tos), .flowi4_scope = frn->fl_scope, }; struct fib_table *tb; rcu_read_lock(); tb = fib_get_table(net, frn->tb_id_in); frn->err = -ENOENT; if (tb) { local_bh_disable(); frn->tb_id = tb->tb_id; frn->err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); if (!frn->err) { frn->prefixlen = res.prefixlen; frn->nh_sel = res.nh_sel; frn->type = res.type; frn->scope = res.scope; } local_bh_enable(); } rcu_read_unlock(); } static void nl_fib_input(struct sk_buff *skb) { struct net *net; struct fib_result_nl *frn; struct nlmsghdr *nlh; u32 portid; net = sock_net(skb->sk); nlh = nlmsg_hdr(skb); if (skb->len < nlmsg_total_size(sizeof(*frn)) || skb->len < nlh->nlmsg_len || nlmsg_len(nlh) < sizeof(*frn)) return; skb = netlink_skb_clone(skb, GFP_KERNEL); if (!skb) return; nlh = nlmsg_hdr(skb); frn = nlmsg_data(nlh); nl_fib_lookup(net, frn); portid = NETLINK_CB(skb).portid; /* netlink portid */ NETLINK_CB(skb).portid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ nlmsg_unicast(net->ipv4.fibnl, skb, portid); } static int __net_init nl_fib_lookup_init(struct net *net) { struct sock *sk; struct netlink_kernel_cfg cfg = { .input = nl_fib_input, }; sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, &cfg); if (!sk) return -EAFNOSUPPORT; net->ipv4.fibnl = sk; return 0; } static void nl_fib_lookup_exit(struct net *net) { netlink_kernel_release(net->ipv4.fibnl); net->ipv4.fibnl = NULL; } static void fib_disable_ip(struct net_device *dev, unsigned long event, bool force) { if (fib_sync_down_dev(dev, event, force)) fib_flush(dev_net(dev)); else rt_cache_flush(dev_net(dev)); arp_ifdown(dev); } static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct in_ifaddr *ifa = ptr; struct net_device *dev = ifa->ifa_dev->dev; struct net *net = dev_net(dev); switch (event) { case NETDEV_UP: fib_add_ifaddr(ifa); #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev, RTNH_F_DEAD); #endif atomic_inc(&net->ipv4.dev_addr_genid); rt_cache_flush(net); break; case NETDEV_DOWN: fib_del_ifaddr(ifa, NULL); atomic_inc(&net->ipv4.dev_addr_genid); if (!ifa->ifa_dev->ifa_list) { /* Last address was deleted from this interface. * Disable IP. */ fib_disable_ip(dev, event, true); } else { rt_cache_flush(net); } break; } return NOTIFY_DONE; } static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_changeupper_info *upper_info = ptr; struct netdev_notifier_info_ext *info_ext = ptr; struct in_device *in_dev; struct net *net = dev_net(dev); struct in_ifaddr *ifa; unsigned int flags; if (event == NETDEV_UNREGISTER) { fib_disable_ip(dev, event, true); rt_flush_dev(dev); return NOTIFY_DONE; } in_dev = __in_dev_get_rtnl(dev); if (!in_dev) return NOTIFY_DONE; switch (event) { case NETDEV_UP: in_dev_for_each_ifa_rtnl(ifa, in_dev) { fib_add_ifaddr(ifa); } #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev, RTNH_F_DEAD); #endif atomic_inc(&net->ipv4.dev_addr_genid); rt_cache_flush(net); break; case NETDEV_DOWN: fib_disable_ip(dev, event, false); break; case NETDEV_CHANGE: flags = netif_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) fib_sync_up(dev, RTNH_F_LINKDOWN); else fib_sync_down_dev(dev, event, false); rt_cache_flush(net); break; case NETDEV_CHANGEMTU: fib_sync_mtu(dev, info_ext->ext.mtu); rt_cache_flush(net); break; case NETDEV_CHANGEUPPER: upper_info = ptr; /* flush all routes if dev is linked to or unlinked from * an L3 master device (e.g., VRF) */ if (upper_info->upper_dev && netif_is_l3_master(upper_info->upper_dev)) fib_disable_ip(dev, NETDEV_DOWN, true); break; } return NOTIFY_DONE; } static struct notifier_block fib_inetaddr_notifier = { .notifier_call = fib_inetaddr_event, }; static struct notifier_block fib_netdev_notifier = { .notifier_call = fib_netdev_event, }; static int __net_init ip_fib_net_init(struct net *net) { int err; size_t size = sizeof(struct hlist_head) * FIB_TABLE_HASHSZ; err = fib4_notifier_init(net); if (err) return err; #ifdef CONFIG_IP_ROUTE_MULTIPATH /* Default to 3-tuple */ net->ipv4.sysctl_fib_multipath_hash_fields = FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; #endif /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL); if (!net->ipv4.fib_table_hash) { err = -ENOMEM; goto err_table_hash_alloc; } err = fib4_rules_init(net); if (err < 0) goto err_rules_init; return 0; err_rules_init: kfree(net->ipv4.fib_table_hash); err_table_hash_alloc: fib4_notifier_exit(net); return err; } static void ip_fib_net_exit(struct net *net) { int i; ASSERT_RTNL_NET(net); #ifdef CONFIG_IP_MULTIPLE_TABLES RCU_INIT_POINTER(net->ipv4.fib_main, NULL); RCU_INIT_POINTER(net->ipv4.fib_default, NULL); #endif /* Destroy the tables in reverse order to guarantee that the * local table, ID 255, is destroyed before the main table, ID * 254. This is necessary as the local table may contain * references to data contained in the main table. */ for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) { struct hlist_head *head = &net->ipv4.fib_table_hash[i]; struct hlist_node *tmp; struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { hlist_del(&tb->tb_hlist); fib_table_flush(net, tb, true); fib_free_table(tb); } } #ifdef CONFIG_IP_MULTIPLE_TABLES fib4_rules_exit(net); #endif kfree(net->ipv4.fib_table_hash); fib4_notifier_exit(net); } static int __net_init fib_net_init(struct net *net) { int error; #ifdef CONFIG_IP_ROUTE_CLASSID atomic_set(&net->ipv4.fib_num_tclassid_users, 0); #endif error = ip_fib_net_init(net); if (error < 0) goto out; error = fib4_semantics_init(net); if (error) goto out_semantics; error = nl_fib_lookup_init(net); if (error < 0) goto out_nlfl; error = fib_proc_init(net); if (error < 0) goto out_proc; out: return error; out_proc: nl_fib_lookup_exit(net); out_nlfl: fib4_semantics_exit(net); out_semantics: rtnl_net_lock(net); ip_fib_net_exit(net); rtnl_net_unlock(net); goto out; } static void __net_exit fib_net_exit(struct net *net) { fib_proc_exit(net); nl_fib_lookup_exit(net); } static void __net_exit fib_net_exit_batch(struct list_head *net_list) { struct net *net; rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { __rtnl_net_lock(net); ip_fib_net_exit(net); __rtnl_net_unlock(net); } rtnl_unlock(); list_for_each_entry(net, net_list, exit_list) fib4_semantics_exit(net); } static struct pernet_operations fib_net_ops = { .init = fib_net_init, .exit = fib_net_exit, .exit_batch = fib_net_exit_batch, }; static const struct rtnl_msg_handler fib_rtnl_msg_handlers[] __initconst = { {.protocol = PF_INET, .msgtype = RTM_NEWROUTE, .doit = inet_rtm_newroute, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_DELROUTE, .doit = inet_rtm_delroute, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_GETROUTE, .dumpit = inet_dump_fib, .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE}, }; void __init ip_fib_init(void) { fib_trie_init(); register_pernet_subsys(&fib_net_ops); register_netdevice_notifier(&fib_netdev_notifier); register_inetaddr_notifier(&fib_inetaddr_notifier); rtnl_register_many(fib_rtnl_msg_handlers); } |
| 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 | // 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. * * IPv4 Forwarding Information Base: semantics. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/netlink.h> #include <linux/hash.h> #include <linux/nospec.h> #include <net/arp.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/nexthop.h> #include <net/netlink.h> #include <net/rtnh.h> #include <net/lwtunnel.h> #include <net/fib_notifier.h> #include <net/addrconf.h> #include "fib_lookup.h" /* for_nexthops and change_nexthops only used when nexthop object * is not set in a fib_info. The logic within can reference fib_nh. */ #ifdef CONFIG_IP_ROUTE_MULTIPATH #define for_nexthops(fi) { \ int nhsel; const struct fib_nh *nh; \ for (nhsel = 0, nh = (fi)->fib_nh; \ nhsel < fib_info_num_path((fi)); \ nh++, nhsel++) #define change_nexthops(fi) { \ int nhsel; struct fib_nh *nexthop_nh; \ for (nhsel = 0, nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \ nhsel < fib_info_num_path((fi)); \ nexthop_nh++, nhsel++) #else /* CONFIG_IP_ROUTE_MULTIPATH */ /* Hope, that gcc will optimize it to get rid of dummy loop */ #define for_nexthops(fi) { \ int nhsel; const struct fib_nh *nh = (fi)->fib_nh; \ for (nhsel = 0; nhsel < 1; nhsel++) #define change_nexthops(fi) { \ int nhsel; \ struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \ for (nhsel = 0; nhsel < 1; nhsel++) #endif /* CONFIG_IP_ROUTE_MULTIPATH */ #define endfor_nexthops(fi) } const struct fib_prop fib_props[RTN_MAX + 1] = { [RTN_UNSPEC] = { .error = 0, .scope = RT_SCOPE_NOWHERE, }, [RTN_UNICAST] = { .error = 0, .scope = RT_SCOPE_UNIVERSE, }, [RTN_LOCAL] = { .error = 0, .scope = RT_SCOPE_HOST, }, [RTN_BROADCAST] = { .error = 0, .scope = RT_SCOPE_LINK, }, [RTN_ANYCAST] = { .error = 0, .scope = RT_SCOPE_LINK, }, [RTN_MULTICAST] = { .error = 0, .scope = RT_SCOPE_UNIVERSE, }, [RTN_BLACKHOLE] = { .error = -EINVAL, .scope = RT_SCOPE_UNIVERSE, }, [RTN_UNREACHABLE] = { .error = -EHOSTUNREACH, .scope = RT_SCOPE_UNIVERSE, }, [RTN_PROHIBIT] = { .error = -EACCES, .scope = RT_SCOPE_UNIVERSE, }, [RTN_THROW] = { .error = -EAGAIN, .scope = RT_SCOPE_UNIVERSE, }, [RTN_NAT] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE, }, [RTN_XRESOLVE] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE, }, }; static void rt_fibinfo_free(struct rtable __rcu **rtp) { struct rtable *rt = rcu_dereference_protected(*rtp, 1); if (!rt) return; /* Not even needed : RCU_INIT_POINTER(*rtp, NULL); * because we waited an RCU grace period before calling * free_fib_info_rcu() */ dst_dev_put(&rt->dst); dst_release_immediate(&rt->dst); } static void free_nh_exceptions(struct fib_nh_common *nhc) { struct fnhe_hash_bucket *hash; int i; hash = rcu_dereference_protected(nhc->nhc_exceptions, 1); if (!hash) return; for (i = 0; i < FNHE_HASH_SIZE; i++) { struct fib_nh_exception *fnhe; fnhe = rcu_dereference_protected(hash[i].chain, 1); while (fnhe) { struct fib_nh_exception *next; next = rcu_dereference_protected(fnhe->fnhe_next, 1); rt_fibinfo_free(&fnhe->fnhe_rth_input); rt_fibinfo_free(&fnhe->fnhe_rth_output); kfree(fnhe); fnhe = next; } } kfree(hash); } static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) { int cpu; if (!rtp) return; for_each_possible_cpu(cpu) { struct rtable *rt; rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1); if (rt) { dst_dev_put(&rt->dst); dst_release_immediate(&rt->dst); } } free_percpu(rtp); } void fib_nh_common_release(struct fib_nh_common *nhc) { netdev_put(nhc->nhc_dev, &nhc->nhc_dev_tracker); lwtstate_put(nhc->nhc_lwtstate); rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output); rt_fibinfo_free(&nhc->nhc_rth_input); free_nh_exceptions(nhc); } EXPORT_SYMBOL_GPL(fib_nh_common_release); void fib_nh_release(struct net *net, struct fib_nh *fib_nh) { #ifdef CONFIG_IP_ROUTE_CLASSID if (fib_nh->nh_tclassid) atomic_dec(&net->ipv4.fib_num_tclassid_users); #endif fib_nh_common_release(&fib_nh->nh_common); } /* Release a nexthop info record */ static void free_fib_info_rcu(struct rcu_head *head) { struct fib_info *fi = container_of(head, struct fib_info, rcu); if (fi->nh) { nexthop_put(fi->nh); } else { change_nexthops(fi) { fib_nh_release(fi->fib_net, nexthop_nh); } endfor_nexthops(fi); } ip_fib_metrics_put(fi->fib_metrics); kfree(fi); } void free_fib_info(struct fib_info *fi) { if (fi->fib_dead == 0) { pr_warn("Freeing alive fib_info %p\n", fi); return; } call_rcu_hurry(&fi->rcu, free_fib_info_rcu); } EXPORT_SYMBOL_GPL(free_fib_info); void fib_release_info(struct fib_info *fi) { ASSERT_RTNL(); if (fi && refcount_dec_and_test(&fi->fib_treeref)) { hlist_del(&fi->fib_hash); fi->fib_net->ipv4.fib_info_cnt--; if (fi->fib_prefsrc) hlist_del(&fi->fib_lhash); if (fi->nh) { list_del(&fi->nh_list); } else { change_nexthops(fi) { if (!nexthop_nh->fib_nh_dev) continue; hlist_del_rcu(&nexthop_nh->nh_hash); } endfor_nexthops(fi) } /* Paired with READ_ONCE() from fib_table_lookup() */ WRITE_ONCE(fi->fib_dead, 1); fib_info_put(fi); } } static inline int nh_comp(struct fib_info *fi, struct fib_info *ofi) { const struct fib_nh *onh; if (fi->nh || ofi->nh) return nexthop_cmp(fi->nh, ofi->nh) ? 0 : -1; if (ofi->fib_nhs == 0) return 0; for_nexthops(fi) { onh = fib_info_nh(ofi, nhsel); if (nh->fib_nh_oif != onh->fib_nh_oif || nh->fib_nh_gw_family != onh->fib_nh_gw_family || nh->fib_nh_scope != onh->fib_nh_scope || #ifdef CONFIG_IP_ROUTE_MULTIPATH nh->fib_nh_weight != onh->fib_nh_weight || #endif #ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid != onh->nh_tclassid || #endif lwtunnel_cmp_encap(nh->fib_nh_lws, onh->fib_nh_lws) || ((nh->fib_nh_flags ^ onh->fib_nh_flags) & ~RTNH_COMPARE_MASK)) return -1; if (nh->fib_nh_gw_family == AF_INET && nh->fib_nh_gw4 != onh->fib_nh_gw4) return -1; if (nh->fib_nh_gw_family == AF_INET6 && ipv6_addr_cmp(&nh->fib_nh_gw6, &onh->fib_nh_gw6)) return -1; } endfor_nexthops(fi); return 0; } static struct hlist_head *fib_nh_head(struct net_device *dev) { return &dev->fib_nh_head; } static unsigned int fib_info_hashfn_1(int init_val, u8 protocol, u8 scope, u32 prefsrc, u32 priority) { unsigned int val = init_val; val ^= (protocol << 8) | scope; val ^= prefsrc; val ^= priority; return val; } static unsigned int fib_info_hashfn_result(const struct net *net, unsigned int val) { return hash_32(val ^ net_hash_mix(net), net->ipv4.fib_info_hash_bits); } static struct hlist_head *fib_info_hash_bucket(struct fib_info *fi) { struct net *net = fi->fib_net; unsigned int val; val = fib_info_hashfn_1(fi->fib_nhs, fi->fib_protocol, fi->fib_scope, (__force u32)fi->fib_prefsrc, fi->fib_priority); if (fi->nh) { val ^= fi->nh->id; } else { for_nexthops(fi) { val ^= nh->fib_nh_oif; } endfor_nexthops(fi) } return &net->ipv4.fib_info_hash[fib_info_hashfn_result(net, val)]; } static struct hlist_head *fib_info_laddrhash_bucket(const struct net *net, __be32 val) { unsigned int hash_bits = net->ipv4.fib_info_hash_bits; u32 slot; slot = hash_32(net_hash_mix(net) ^ (__force u32)val, hash_bits); return &net->ipv4.fib_info_hash[(1 << hash_bits) + slot]; } static struct hlist_head *fib_info_hash_alloc(unsigned int hash_bits) { /* The second half is used for prefsrc */ return kvcalloc((1 << hash_bits) * 2, sizeof(struct hlist_head), GFP_KERNEL); } static void fib_info_hash_free(struct hlist_head *head) { kvfree(head); } static void fib_info_hash_grow(struct net *net) { unsigned int old_size = 1 << net->ipv4.fib_info_hash_bits; struct hlist_head *new_info_hash, *old_info_hash; unsigned int i; if (net->ipv4.fib_info_cnt < old_size) return; new_info_hash = fib_info_hash_alloc(net->ipv4.fib_info_hash_bits + 1); if (!new_info_hash) return; old_info_hash = net->ipv4.fib_info_hash; net->ipv4.fib_info_hash = new_info_hash; net->ipv4.fib_info_hash_bits += 1; for (i = 0; i < old_size; i++) { struct hlist_head *head = &old_info_hash[i]; struct hlist_node *n; struct fib_info *fi; hlist_for_each_entry_safe(fi, n, head, fib_hash) hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi)); } for (i = 0; i < old_size; i++) { struct hlist_head *lhead = &old_info_hash[old_size + i]; struct hlist_node *n; struct fib_info *fi; hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) hlist_add_head(&fi->fib_lhash, fib_info_laddrhash_bucket(fi->fib_net, fi->fib_prefsrc)); } fib_info_hash_free(old_info_hash); } /* no metrics, only nexthop id */ static struct fib_info *fib_find_info_nh(struct net *net, const struct fib_config *cfg) { struct hlist_head *head; struct fib_info *fi; unsigned int hash; hash = fib_info_hashfn_1(cfg->fc_nh_id, cfg->fc_protocol, cfg->fc_scope, (__force u32)cfg->fc_prefsrc, cfg->fc_priority); hash = fib_info_hashfn_result(net, hash); head = &net->ipv4.fib_info_hash[hash]; hlist_for_each_entry(fi, head, fib_hash) { if (!fi->nh || fi->nh->id != cfg->fc_nh_id) continue; if (cfg->fc_protocol == fi->fib_protocol && cfg->fc_scope == fi->fib_scope && cfg->fc_prefsrc == fi->fib_prefsrc && cfg->fc_priority == fi->fib_priority && cfg->fc_type == fi->fib_type && cfg->fc_table == fi->fib_tb_id && !((cfg->fc_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK)) return fi; } return NULL; } static struct fib_info *fib_find_info(struct fib_info *nfi) { struct hlist_head *head = fib_info_hash_bucket(nfi); struct fib_info *fi; hlist_for_each_entry(fi, head, fib_hash) { if (fi->fib_nhs != nfi->fib_nhs) continue; if (nfi->fib_protocol == fi->fib_protocol && nfi->fib_scope == fi->fib_scope && nfi->fib_prefsrc == fi->fib_prefsrc && nfi->fib_priority == fi->fib_priority && nfi->fib_type == fi->fib_type && nfi->fib_tb_id == fi->fib_tb_id && memcmp(nfi->fib_metrics, fi->fib_metrics, sizeof(u32) * RTAX_MAX) == 0 && !((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK) && nh_comp(fi, nfi) == 0) return fi; } return NULL; } /* Check, that the gateway is already configured. * Used only by redirect accept routine, under rcu_read_lock(); */ int ip_fib_check_default(__be32 gw, struct net_device *dev) { struct hlist_head *head; struct fib_nh *nh; head = fib_nh_head(dev); hlist_for_each_entry_rcu(nh, head, nh_hash) { DEBUG_NET_WARN_ON_ONCE(nh->fib_nh_dev != dev); if (nh->fib_nh_gw4 == gw && !(nh->fib_nh_flags & RTNH_F_DEAD)) { return 0; } } return -1; } size_t fib_nlmsg_size(struct fib_info *fi) { size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(4) /* RTA_DST */ + nla_total_size(4) /* RTA_PRIORITY */ + nla_total_size(4) /* RTA_PREFSRC */ + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */ unsigned int nhs = fib_info_num_path(fi); /* space for nested metrics */ payload += nla_total_size((RTAX_MAX * nla_total_size(4))); if (fi->nh) payload += nla_total_size(4); /* RTA_NH_ID */ if (nhs) { size_t nh_encapsize = 0; /* Also handles the special case nhs == 1 */ /* each nexthop is packed in an attribute */ size_t nhsize = nla_total_size(sizeof(struct rtnexthop)); unsigned int i; /* may contain flow and gateway attribute */ nhsize += 2 * nla_total_size(4); /* grab encap info */ for (i = 0; i < fib_info_num_path(fi); i++) { struct fib_nh_common *nhc = fib_info_nhc(fi, i); if (nhc->nhc_lwtstate) { /* RTA_ENCAP_TYPE */ nh_encapsize += lwtunnel_get_encap_size( nhc->nhc_lwtstate); /* RTA_ENCAP */ nh_encapsize += nla_total_size(2); } } /* all nexthops are packed in a nested attribute */ payload += nla_total_size((nhs * nhsize) + nh_encapsize); } return payload; } void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, const struct nl_info *info, unsigned int nlm_flags) { struct fib_rt_info fri; struct sk_buff *skb; u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; int err = -ENOBUFS; skb = nlmsg_new(fib_nlmsg_size(fa->fa_info), GFP_KERNEL); if (!skb) goto errout; fri.fi = fa->fa_info; fri.tb_id = tb_id; fri.dst = key; fri.dst_len = dst_len; fri.dscp = fa->fa_dscp; fri.type = fa->fa_type; fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); fri.offload_failed = READ_ONCE(fa->offload_failed); err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_IPV4_ROUTE, info->nlh, GFP_KERNEL); return; errout: rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err); } static int fib_detect_death(struct fib_info *fi, int order, struct fib_info **last_resort, int *last_idx, int dflt) { const struct fib_nh_common *nhc = fib_info_nhc(fi, 0); struct neighbour *n; int state = NUD_NONE; if (likely(nhc->nhc_gw_family == AF_INET)) n = neigh_lookup(&arp_tbl, &nhc->nhc_gw.ipv4, nhc->nhc_dev); else if (nhc->nhc_gw_family == AF_INET6) n = neigh_lookup(ipv6_stub->nd_tbl, &nhc->nhc_gw.ipv6, nhc->nhc_dev); else n = NULL; if (n) { state = READ_ONCE(n->nud_state); neigh_release(n); } else { return 0; } if (state == NUD_REACHABLE) return 0; if ((state & NUD_VALID) && order != dflt) return 0; if ((state & NUD_VALID) || (*last_idx < 0 && order > dflt && state != NUD_INCOMPLETE)) { *last_resort = fi; *last_idx = order; } return 1; } int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc, struct nlattr *encap, u16 encap_type, void *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { int err; nhc->nhc_pcpu_rth_output = alloc_percpu_gfp(struct rtable __rcu *, gfp_flags); if (!nhc->nhc_pcpu_rth_output) return -ENOMEM; if (encap) { struct lwtunnel_state *lwtstate; err = lwtunnel_build_state(net, encap_type, encap, nhc->nhc_family, cfg, &lwtstate, extack); if (err) goto lwt_failure; nhc->nhc_lwtstate = lwtstate_get(lwtstate); } return 0; lwt_failure: rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output); nhc->nhc_pcpu_rth_output = NULL; return err; } EXPORT_SYMBOL_GPL(fib_nh_common_init); int fib_nh_init(struct net *net, struct fib_nh *nh, struct fib_config *cfg, int nh_weight, struct netlink_ext_ack *extack) { int err; nh->fib_nh_family = AF_INET; err = fib_nh_common_init(net, &nh->nh_common, cfg->fc_encap, cfg->fc_encap_type, cfg, GFP_KERNEL, extack); if (err) return err; nh->fib_nh_oif = cfg->fc_oif; nh->fib_nh_gw_family = cfg->fc_gw_family; if (cfg->fc_gw_family == AF_INET) nh->fib_nh_gw4 = cfg->fc_gw4; else if (cfg->fc_gw_family == AF_INET6) nh->fib_nh_gw6 = cfg->fc_gw6; nh->fib_nh_flags = cfg->fc_flags; #ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid = cfg->fc_flow; if (nh->nh_tclassid) atomic_inc(&net->ipv4.fib_num_tclassid_users); #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH nh->fib_nh_weight = nh_weight; #endif return 0; } #ifdef CONFIG_IP_ROUTE_MULTIPATH static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining, struct netlink_ext_ack *extack) { int nhs = 0; while (rtnh_ok(rtnh, remaining)) { nhs++; rtnh = rtnh_next(rtnh, &remaining); } /* leftover implies invalid nexthop configuration, discard it */ if (remaining > 0) { NL_SET_ERR_MSG(extack, "Invalid nexthop configuration - extra data after nexthops"); nhs = 0; } return nhs; } static int fib_gw_from_attr(__be32 *gw, struct nlattr *nla, struct netlink_ext_ack *extack) { if (nla_len(nla) < sizeof(*gw)) { NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_GATEWAY"); return -EINVAL; } *gw = nla_get_in_addr(nla); return 0; } /* only called when fib_nh is integrated into fib_info */ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, int remaining, struct fib_config *cfg, struct netlink_ext_ack *extack) { struct net *net = fi->fib_net; struct fib_config fib_cfg; struct fib_nh *nh; int ret; change_nexthops(fi) { int attrlen; memset(&fib_cfg, 0, sizeof(fib_cfg)); if (!rtnh_ok(rtnh, remaining)) { NL_SET_ERR_MSG(extack, "Invalid nexthop configuration - extra data after nexthop"); return -EINVAL; } if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) { NL_SET_ERR_MSG(extack, "Invalid flags for nexthop - can not contain DEAD or LINKDOWN"); return -EINVAL; } fib_cfg.fc_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; fib_cfg.fc_oif = rtnh->rtnh_ifindex; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); nlav = nla_find(attrs, attrlen, RTA_VIA); if (nla && nlav) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); return -EINVAL; } if (nla) { ret = fib_gw_from_attr(&fib_cfg.fc_gw4, nla, extack); if (ret) goto errout; if (fib_cfg.fc_gw4) fib_cfg.fc_gw_family = AF_INET; } else if (nlav) { ret = fib_gw_from_via(&fib_cfg, nlav, extack); if (ret) goto errout; } nla = nla_find(attrs, attrlen, RTA_FLOW); if (nla) { if (nla_len(nla) < sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW"); return -EINVAL; } fib_cfg.fc_flow = nla_get_u32(nla); } fib_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); /* RTA_ENCAP_TYPE length checked in * lwtunnel_valid_encap_type_attr */ nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla) fib_cfg.fc_encap_type = nla_get_u16(nla); } ret = fib_nh_init(net, nexthop_nh, &fib_cfg, rtnh->rtnh_hops + 1, extack); if (ret) goto errout; rtnh = rtnh_next(rtnh, &remaining); } endfor_nexthops(fi); ret = -EINVAL; nh = fib_info_nh(fi, 0); if (cfg->fc_oif && nh->fib_nh_oif != cfg->fc_oif) { NL_SET_ERR_MSG(extack, "Nexthop device index does not match RTA_OIF"); goto errout; } if (cfg->fc_gw_family) { if (cfg->fc_gw_family != nh->fib_nh_gw_family || (cfg->fc_gw_family == AF_INET && nh->fib_nh_gw4 != cfg->fc_gw4) || (cfg->fc_gw_family == AF_INET6 && ipv6_addr_cmp(&nh->fib_nh_gw6, &cfg->fc_gw6))) { NL_SET_ERR_MSG(extack, "Nexthop gateway does not match RTA_GATEWAY or RTA_VIA"); goto errout; } } #ifdef CONFIG_IP_ROUTE_CLASSID if (cfg->fc_flow && nh->nh_tclassid != cfg->fc_flow) { NL_SET_ERR_MSG(extack, "Nexthop class id does not match RTA_FLOW"); goto errout; } #endif ret = 0; errout: return ret; } /* only called when fib_nh is integrated into fib_info */ static void fib_rebalance(struct fib_info *fi) { int total; int w; if (fib_info_num_path(fi) < 2) return; total = 0; for_nexthops(fi) { if (nh->fib_nh_flags & RTNH_F_DEAD) continue; if (ip_ignore_linkdown(nh->fib_nh_dev) && nh->fib_nh_flags & RTNH_F_LINKDOWN) continue; total += nh->fib_nh_weight; } endfor_nexthops(fi); w = 0; change_nexthops(fi) { int upper_bound; if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD) { upper_bound = -1; } else if (ip_ignore_linkdown(nexthop_nh->fib_nh_dev) && nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN) { upper_bound = -1; } else { w += nexthop_nh->fib_nh_weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1; } atomic_set(&nexthop_nh->fib_nh_upper_bound, upper_bound); } endfor_nexthops(fi); } #else /* CONFIG_IP_ROUTE_MULTIPATH */ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, int remaining, struct fib_config *cfg, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "Multipath support not enabled in kernel"); return -EINVAL; } #define fib_rebalance(fi) do { } while (0) #endif /* CONFIG_IP_ROUTE_MULTIPATH */ static int fib_encap_match(struct net *net, u16 encap_type, struct nlattr *encap, const struct fib_nh *nh, const struct fib_config *cfg, struct netlink_ext_ack *extack) { struct lwtunnel_state *lwtstate; int ret, result = 0; if (encap_type == LWTUNNEL_ENCAP_NONE) return 0; ret = lwtunnel_build_state(net, encap_type, encap, AF_INET, cfg, &lwtstate, extack); if (!ret) { result = lwtunnel_cmp_encap(lwtstate, nh->fib_nh_lws); lwtstate_free(lwtstate); } return result; } int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, struct netlink_ext_ack *extack) { #ifdef CONFIG_IP_ROUTE_MULTIPATH struct rtnexthop *rtnh; int remaining; #endif if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority) return 1; if (cfg->fc_nh_id) { if (fi->nh && cfg->fc_nh_id == fi->nh->id) return 0; return 1; } if (fi->nh) { if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_mp) return 1; return 0; } if (cfg->fc_oif || cfg->fc_gw_family) { struct fib_nh *nh; nh = fib_info_nh(fi, 0); if (cfg->fc_encap) { if (fib_encap_match(net, cfg->fc_encap_type, cfg->fc_encap, nh, cfg, extack)) return 1; } #ifdef CONFIG_IP_ROUTE_CLASSID if (cfg->fc_flow && cfg->fc_flow != nh->nh_tclassid) return 1; #endif if ((cfg->fc_oif && cfg->fc_oif != nh->fib_nh_oif) || (cfg->fc_gw_family && cfg->fc_gw_family != nh->fib_nh_gw_family)) return 1; if (cfg->fc_gw_family == AF_INET && cfg->fc_gw4 != nh->fib_nh_gw4) return 1; if (cfg->fc_gw_family == AF_INET6 && ipv6_addr_cmp(&cfg->fc_gw6, &nh->fib_nh_gw6)) return 1; return 0; } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (!cfg->fc_mp) return 0; rtnh = cfg->fc_mp; remaining = cfg->fc_mp_len; for_nexthops(fi) { int attrlen; if (!rtnh_ok(rtnh, remaining)) return -EINVAL; if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->fib_nh_oif) return 1; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh); int err; nla = nla_find(attrs, attrlen, RTA_GATEWAY); nlav = nla_find(attrs, attrlen, RTA_VIA); if (nla && nlav) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); return -EINVAL; } if (nla) { __be32 gw; err = fib_gw_from_attr(&gw, nla, extack); if (err) return err; if (nh->fib_nh_gw_family != AF_INET || gw != nh->fib_nh_gw4) return 1; } else if (nlav) { struct fib_config cfg2; err = fib_gw_from_via(&cfg2, nlav, extack); if (err) return err; switch (nh->fib_nh_gw_family) { case AF_INET: if (cfg2.fc_gw_family != AF_INET || cfg2.fc_gw4 != nh->fib_nh_gw4) return 1; break; case AF_INET6: if (cfg2.fc_gw_family != AF_INET6 || ipv6_addr_cmp(&cfg2.fc_gw6, &nh->fib_nh_gw6)) return 1; break; } } #ifdef CONFIG_IP_ROUTE_CLASSID nla = nla_find(attrs, attrlen, RTA_FLOW); if (nla) { if (nla_len(nla) < sizeof(u32)) { NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW"); return -EINVAL; } if (nla_get_u32(nla) != nh->nh_tclassid) return 1; } #endif } rtnh = rtnh_next(rtnh, &remaining); } endfor_nexthops(fi); #endif return 0; } bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) { struct nlattr *nla; int remaining; if (!cfg->fc_mx) return true; nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { int type = nla_type(nla); u32 fi_val, val; if (!type) continue; if (type > RTAX_MAX) return false; type = array_index_nospec(type, RTAX_MAX + 1); if (type == RTAX_CC_ALGO) { char tmp[TCP_CA_NAME_MAX]; bool ecn_ca = false; nla_strscpy(tmp, nla, sizeof(tmp)); val = tcp_ca_get_key_by_name(tmp, &ecn_ca); } else { if (nla_len(nla) != sizeof(u32)) return false; val = nla_get_u32(nla); } fi_val = fi->fib_metrics->metrics[type - 1]; if (type == RTAX_FEATURES) fi_val &= ~DST_FEATURE_ECN_CA; if (fi_val != val) return false; } return true; } static int fib_check_nh_v6_gw(struct net *net, struct fib_nh *nh, u32 table, struct netlink_ext_ack *extack) { struct fib6_config cfg = { .fc_table = table, .fc_flags = nh->fib_nh_flags | RTF_GATEWAY, .fc_ifindex = nh->fib_nh_oif, .fc_gateway = nh->fib_nh_gw6, }; struct fib6_nh fib6_nh = {}; int err; err = ipv6_stub->fib6_nh_init(net, &fib6_nh, &cfg, GFP_KERNEL, extack); if (!err) { nh->fib_nh_dev = fib6_nh.fib_nh_dev; netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_KERNEL); nh->fib_nh_oif = nh->fib_nh_dev->ifindex; nh->fib_nh_scope = RT_SCOPE_LINK; ipv6_stub->fib6_nh_release(&fib6_nh); } return err; } /* * Picture * ------- * * Semantics of nexthop is very messy by historical reasons. * We have to take into account, that: * a) gateway can be actually local interface address, * so that gatewayed route is direct. * b) gateway must be on-link address, possibly * described not by an ifaddr, but also by a direct route. * c) If both gateway and interface are specified, they should not * contradict. * d) If we use tunnel routes, gateway could be not on-link. * * Attempt to reconcile all of these (alas, self-contradictory) conditions * results in pretty ugly and hairy code with obscure logic. * * I chose to generalized it instead, so that the size * of code does not increase practically, but it becomes * much more general. * Every prefix is assigned a "scope" value: "host" is local address, * "link" is direct route, * [ ... "site" ... "interior" ... ] * and "universe" is true gateway route with global meaning. * * Every prefix refers to a set of "nexthop"s (gw, oif), * where gw must have narrower scope. This recursion stops * when gw has LOCAL scope or if "nexthop" is declared ONLINK, * which means that gw is forced to be on link. * * Code is still hairy, but now it is apparently logically * consistent and very flexible. F.e. as by-product it allows * to co-exists in peace independent exterior and interior * routing processes. * * Normally it looks as following. * * {universe prefix} -> (gw, oif) [scope link] * | * |-> {link prefix} -> (gw, oif) [scope local] * | * |-> {local prefix} (terminal node) */ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table, u8 scope, struct netlink_ext_ack *extack) { struct net_device *dev; struct fib_result res; int err = 0; if (nh->fib_nh_flags & RTNH_F_ONLINK) { unsigned int addr_type; if (scope >= RT_SCOPE_LINK) { NL_SET_ERR_MSG(extack, "Nexthop has invalid scope"); return -EINVAL; } dev = __dev_get_by_index(net, nh->fib_nh_oif); if (!dev) { NL_SET_ERR_MSG(extack, "Nexthop device required for onlink"); return -ENODEV; } if (!(dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); return -ENETDOWN; } addr_type = inet_addr_type_dev_table(net, dev, nh->fib_nh_gw4); if (addr_type != RTN_UNICAST) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway"); return -EINVAL; } if (!netif_carrier_ok(dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; nh->fib_nh_dev = dev; netdev_hold(dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); nh->fib_nh_scope = RT_SCOPE_LINK; return 0; } rcu_read_lock(); { struct fib_table *tbl = NULL; struct flowi4 fl4 = { .daddr = nh->fib_nh_gw4, .flowi4_scope = scope + 1, .flowi4_oif = nh->fib_nh_oif, .flowi4_iif = LOOPBACK_IFINDEX, }; /* It is not necessary, but requires a bit of thinking */ if (fl4.flowi4_scope < RT_SCOPE_LINK) fl4.flowi4_scope = RT_SCOPE_LINK; if (table && table != RT_TABLE_MAIN) tbl = fib_get_table(net, table); if (tbl) err = fib_table_lookup(tbl, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE | FIB_LOOKUP_NOREF); /* on error or if no table given do full lookup. This * is needed for example when nexthops are in the local * table rather than the given table */ if (!tbl || err) { err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE); } if (err) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway"); goto out; } } err = -EINVAL; if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway"); goto out; } nh->fib_nh_scope = res.scope; nh->fib_nh_oif = FIB_RES_OIF(res); nh->fib_nh_dev = dev = FIB_RES_DEV(res); if (!dev) { NL_SET_ERR_MSG(extack, "No egress device for nexthop gateway"); goto out; } netdev_hold(dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); if (!netif_carrier_ok(dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN; out: rcu_read_unlock(); return err; } static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh, struct netlink_ext_ack *extack) { struct in_device *in_dev; int err; if (nh->fib_nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) { NL_SET_ERR_MSG(extack, "Invalid flags for nexthop - PERVASIVE and ONLINK can not be set"); return -EINVAL; } rcu_read_lock(); err = -ENODEV; in_dev = inetdev_by_index(net, nh->fib_nh_oif); if (!in_dev) goto out; err = -ENETDOWN; if (!(in_dev->dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Device for nexthop is not up"); goto out; } nh->fib_nh_dev = in_dev->dev; netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); nh->fib_nh_scope = RT_SCOPE_HOST; if (!netif_carrier_ok(nh->fib_nh_dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = 0; out: rcu_read_unlock(); return err; } int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, struct netlink_ext_ack *extack) { int err; if (nh->fib_nh_gw_family == AF_INET) err = fib_check_nh_v4_gw(net, nh, table, scope, extack); else if (nh->fib_nh_gw_family == AF_INET6) err = fib_check_nh_v6_gw(net, nh, table, extack); else err = fib_check_nh_nongw(net, nh, extack); return err; } __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, unsigned char scope) { struct fib_nh *nh; __be32 saddr; if (nhc->nhc_family != AF_INET) return inet_select_addr(nhc->nhc_dev, 0, scope); nh = container_of(nhc, struct fib_nh, nh_common); saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope); WRITE_ONCE(nh->nh_saddr, saddr); WRITE_ONCE(nh->nh_saddr_genid, atomic_read(&net->ipv4.dev_addr_genid)); return saddr; } __be32 fib_result_prefsrc(struct net *net, struct fib_result *res) { struct fib_nh_common *nhc = res->nhc; if (res->fi->fib_prefsrc) return res->fi->fib_prefsrc; if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); if (READ_ONCE(nh->nh_saddr_genid) == atomic_read(&net->ipv4.dev_addr_genid)) return READ_ONCE(nh->nh_saddr); } return fib_info_update_nhc_saddr(net, nhc, res->fi->fib_scope); } static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc) { if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst || fib_prefsrc != cfg->fc_dst) { u32 tb_id = cfg->fc_table; int rc; if (tb_id == RT_TABLE_MAIN) tb_id = RT_TABLE_LOCAL; rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net, fib_prefsrc, tb_id); if (rc != RTN_LOCAL && tb_id != RT_TABLE_LOCAL) { rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net, fib_prefsrc, RT_TABLE_LOCAL); } if (rc != RTN_LOCAL) return false; } return true; } struct fib_info *fib_create_info(struct fib_config *cfg, struct netlink_ext_ack *extack) { int err; struct fib_info *fi = NULL; struct nexthop *nh = NULL; struct fib_info *ofi; int nhs = 1; struct net *net = cfg->fc_nlinfo.nl_net; ASSERT_RTNL(); if (cfg->fc_type > RTN_MAX) goto err_inval; /* Fast check to catch the most weird cases */ if (fib_props[cfg->fc_type].scope > cfg->fc_scope) { NL_SET_ERR_MSG(extack, "Invalid scope"); goto err_inval; } if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) { NL_SET_ERR_MSG(extack, "Invalid rtm_flags - can not contain DEAD or LINKDOWN"); goto err_inval; } if (cfg->fc_nh_id) { if (!cfg->fc_mx) { fi = fib_find_info_nh(net, cfg); if (fi) { refcount_inc(&fi->fib_treeref); return fi; } } nh = nexthop_find_by_id(net, cfg->fc_nh_id); if (!nh) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); goto err_inval; } nhs = 0; } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (cfg->fc_mp) { nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len, extack); if (nhs == 0) goto err_inval; } #endif fib_info_hash_grow(net); fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL); if (!fi) { err = -ENOBUFS; goto failure; } fi->fib_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack); if (IS_ERR(fi->fib_metrics)) { err = PTR_ERR(fi->fib_metrics); kfree(fi); return ERR_PTR(err); } fi->fib_net = net; fi->fib_protocol = cfg->fc_protocol; fi->fib_scope = cfg->fc_scope; fi->fib_flags = cfg->fc_flags; fi->fib_priority = cfg->fc_priority; fi->fib_prefsrc = cfg->fc_prefsrc; fi->fib_type = cfg->fc_type; fi->fib_tb_id = cfg->fc_table; fi->fib_nhs = nhs; if (nh) { if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); err = -EINVAL; } else { err = 0; fi->nh = nh; } } else { change_nexthops(fi) { nexthop_nh->nh_parent = fi; } endfor_nexthops(fi) if (cfg->fc_mp) err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, extack); else err = fib_nh_init(net, fi->fib_nh, cfg, 1, extack); } if (err != 0) goto failure; if (fib_props[cfg->fc_type].error) { if (cfg->fc_gw_family || cfg->fc_oif || cfg->fc_mp) { NL_SET_ERR_MSG(extack, "Gateway, device and multipath can not be specified for this route type"); goto err_inval; } goto link_it; } else { switch (cfg->fc_type) { case RTN_UNICAST: case RTN_LOCAL: case RTN_BROADCAST: case RTN_ANYCAST: case RTN_MULTICAST: break; default: NL_SET_ERR_MSG(extack, "Invalid route type"); goto err_inval; } } if (cfg->fc_scope > RT_SCOPE_HOST) { NL_SET_ERR_MSG(extack, "Invalid scope"); goto err_inval; } if (fi->nh) { err = fib_check_nexthop(fi->nh, cfg->fc_scope, extack); if (err) goto failure; } else if (cfg->fc_scope == RT_SCOPE_HOST) { struct fib_nh *nh = fi->fib_nh; /* Local address is added. */ if (nhs != 1) { NL_SET_ERR_MSG(extack, "Route with host scope can not have multiple nexthops"); goto err_inval; } if (nh->fib_nh_gw_family) { NL_SET_ERR_MSG(extack, "Route with host scope can not have a gateway"); goto err_inval; } nh->fib_nh_scope = RT_SCOPE_NOWHERE; nh->fib_nh_dev = dev_get_by_index(net, nh->fib_nh_oif); err = -ENODEV; if (!nh->fib_nh_dev) goto failure; netdev_tracker_alloc(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_KERNEL); } else { int linkdown = 0; change_nexthops(fi) { err = fib_check_nh(cfg->fc_nlinfo.nl_net, nexthop_nh, cfg->fc_table, cfg->fc_scope, extack); if (err != 0) goto failure; if (nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN) linkdown++; } endfor_nexthops(fi) if (linkdown == fi->fib_nhs) fi->fib_flags |= RTNH_F_LINKDOWN; } if (fi->fib_prefsrc && !fib_valid_prefsrc(cfg, fi->fib_prefsrc)) { NL_SET_ERR_MSG(extack, "Invalid prefsrc address"); goto err_inval; } if (!fi->nh) { change_nexthops(fi) { fib_info_update_nhc_saddr(net, &nexthop_nh->nh_common, fi->fib_scope); if (nexthop_nh->fib_nh_gw_family == AF_INET6) fi->fib_nh_is_v6 = true; } endfor_nexthops(fi) fib_rebalance(fi); } link_it: ofi = fib_find_info(fi); if (ofi) { /* fib_table_lookup() should not see @fi yet. */ fi->fib_dead = 1; free_fib_info(fi); refcount_inc(&ofi->fib_treeref); return ofi; } refcount_set(&fi->fib_treeref, 1); refcount_set(&fi->fib_clntref, 1); net->ipv4.fib_info_cnt++; hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi)); if (fi->fib_prefsrc) { struct hlist_head *head; head = fib_info_laddrhash_bucket(net, fi->fib_prefsrc); hlist_add_head(&fi->fib_lhash, head); } if (fi->nh) { list_add(&fi->nh_list, &nh->fi_list); } else { change_nexthops(fi) { struct hlist_head *head; if (!nexthop_nh->fib_nh_dev) continue; head = fib_nh_head(nexthop_nh->fib_nh_dev); hlist_add_head_rcu(&nexthop_nh->nh_hash, head); } endfor_nexthops(fi) } return fi; err_inval: err = -EINVAL; failure: if (fi) { /* fib_table_lookup() should not see @fi yet. */ fi->fib_dead = 1; free_fib_info(fi); } return ERR_PTR(err); } int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc, u8 rt_family, unsigned char *flags, bool skip_oif) { if (nhc->nhc_flags & RTNH_F_DEAD) *flags |= RTNH_F_DEAD; if (nhc->nhc_flags & RTNH_F_LINKDOWN) { *flags |= RTNH_F_LINKDOWN; rcu_read_lock(); switch (nhc->nhc_family) { case AF_INET: if (ip_ignore_linkdown(nhc->nhc_dev)) *flags |= RTNH_F_DEAD; break; case AF_INET6: if (ip6_ignore_linkdown(nhc->nhc_dev)) *flags |= RTNH_F_DEAD; break; } rcu_read_unlock(); } switch (nhc->nhc_gw_family) { case AF_INET: if (nla_put_in_addr(skb, RTA_GATEWAY, nhc->nhc_gw.ipv4)) goto nla_put_failure; break; case AF_INET6: /* if gateway family does not match nexthop family * gateway is encoded as RTA_VIA */ if (rt_family != nhc->nhc_gw_family) { int alen = sizeof(struct in6_addr); struct nlattr *nla; struct rtvia *via; nla = nla_reserve(skb, RTA_VIA, alen + 2); if (!nla) goto nla_put_failure; via = nla_data(nla); via->rtvia_family = AF_INET6; memcpy(via->rtvia_addr, &nhc->nhc_gw.ipv6, alen); } else if (nla_put_in6_addr(skb, RTA_GATEWAY, &nhc->nhc_gw.ipv6) < 0) { goto nla_put_failure; } break; } *flags |= (nhc->nhc_flags & (RTNH_F_ONLINK | RTNH_F_OFFLOAD | RTNH_F_TRAP)); if (!skip_oif && nhc->nhc_dev && nla_put_u32(skb, RTA_OIF, nhc->nhc_dev->ifindex)) goto nla_put_failure; if (lwtunnel_fill_encap(skb, nhc->nhc_lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } EXPORT_SYMBOL_GPL(fib_nexthop_info); #if IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) || IS_ENABLED(CONFIG_IPV6) int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc, int nh_weight, u8 rt_family, u32 nh_tclassid) { const struct net_device *dev = nhc->nhc_dev; struct rtnexthop *rtnh; unsigned char flags = 0; rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh)); if (!rtnh) goto nla_put_failure; rtnh->rtnh_hops = nh_weight - 1; rtnh->rtnh_ifindex = dev ? dev->ifindex : 0; if (fib_nexthop_info(skb, nhc, rt_family, &flags, true) < 0) goto nla_put_failure; rtnh->rtnh_flags = flags; if (nh_tclassid && nla_put_u32(skb, RTA_FLOW, nh_tclassid)) goto nla_put_failure; /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh; return 0; nla_put_failure: return -EMSGSIZE; } EXPORT_SYMBOL_GPL(fib_add_nexthop); #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) { struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; if (unlikely(fi->nh)) { if (nexthop_mpath_fill_node(skb, fi->nh, AF_INET) < 0) goto nla_put_failure; goto mp_end; } for_nexthops(fi) { u32 nh_tclassid = 0; #ifdef CONFIG_IP_ROUTE_CLASSID nh_tclassid = nh->nh_tclassid; #endif if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight, AF_INET, nh_tclassid) < 0) goto nla_put_failure; } endfor_nexthops(fi); mp_end: nla_nest_end(skb, mp); return 0; nla_put_failure: return -EMSGSIZE; } #else static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) { return 0; } #endif int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, const struct fib_rt_info *fri, unsigned int flags) { unsigned int nhs = fib_info_num_path(fri->fi); struct fib_info *fi = fri->fi; u32 tb_id = fri->tb_id; struct nlmsghdr *nlh; struct rtmsg *rtm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET; rtm->rtm_dst_len = fri->dst_len; rtm->rtm_src_len = 0; rtm->rtm_tos = inet_dscp_to_dsfield(fri->dscp); if (tb_id < 256) rtm->rtm_table = tb_id; else rtm->rtm_table = RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, tb_id)) goto nla_put_failure; rtm->rtm_type = fri->type; rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = fi->fib_scope; rtm->rtm_protocol = fi->fib_protocol; if (rtm->rtm_dst_len && nla_put_in_addr(skb, RTA_DST, fri->dst)) goto nla_put_failure; if (fi->fib_priority && nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority)) goto nla_put_failure; if (rtnetlink_put_metrics(skb, fi->fib_metrics->metrics) < 0) goto nla_put_failure; if (fi->fib_prefsrc && nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc)) goto nla_put_failure; if (fi->nh) { if (nla_put_u32(skb, RTA_NH_ID, fi->nh->id)) goto nla_put_failure; if (nexthop_is_blackhole(fi->nh)) rtm->rtm_type = RTN_BLACKHOLE; if (!READ_ONCE(fi->fib_net->ipv4.sysctl_nexthop_compat_mode)) goto offload; } if (nhs == 1) { const struct fib_nh_common *nhc = fib_info_nhc(fi, 0); unsigned char flags = 0; if (fib_nexthop_info(skb, nhc, AF_INET, &flags, false) < 0) goto nla_put_failure; rtm->rtm_flags = flags; #ifdef CONFIG_IP_ROUTE_CLASSID if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); if (nh->nh_tclassid && nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) goto nla_put_failure; } #endif } else { if (fib_add_multipath(skb, fi) < 0) goto nla_put_failure; } offload: if (fri->offload) rtm->rtm_flags |= RTM_F_OFFLOAD; if (fri->trap) rtm->rtm_flags |= RTM_F_TRAP; if (fri->offload_failed) rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } /* * Update FIB if: * - local address disappeared -> we must delete all the entries * referring to it. * - device went down -> we must shutdown all nexthops going via it. */ int fib_sync_down_addr(struct net_device *dev, __be32 local) { int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; struct net *net = dev_net(dev); struct hlist_head *head; struct fib_info *fi; int ret = 0; if (!local) return 0; head = fib_info_laddrhash_bucket(net, local); hlist_for_each_entry(fi, head, fib_lhash) { if (!net_eq(fi->fib_net, net) || fi->fib_tb_id != tb_id) continue; if (fi->fib_prefsrc == local) { fi->fib_flags |= RTNH_F_DEAD; fi->pfsrc_removed = true; ret++; } } return ret; } static int call_fib_nh_notifiers(struct fib_nh *nh, enum fib_event_type event_type) { bool ignore_link_down = ip_ignore_linkdown(nh->fib_nh_dev); struct fib_nh_notifier_info info = { .fib_nh = nh, }; switch (event_type) { case FIB_EVENT_NH_ADD: if (nh->fib_nh_flags & RTNH_F_DEAD) break; if (ignore_link_down && nh->fib_nh_flags & RTNH_F_LINKDOWN) break; return call_fib4_notifiers(dev_net(nh->fib_nh_dev), event_type, &info.info); case FIB_EVENT_NH_DEL: if ((ignore_link_down && nh->fib_nh_flags & RTNH_F_LINKDOWN) || (nh->fib_nh_flags & RTNH_F_DEAD)) return call_fib4_notifiers(dev_net(nh->fib_nh_dev), event_type, &info.info); break; default: break; } return NOTIFY_DONE; } /* Update the PMTU of exceptions when: * - the new MTU of the first hop becomes smaller than the PMTU * - the old MTU was the same as the PMTU, and it limited discovery of * larger MTUs on the path. With that limit raised, we can now * discover larger MTUs * A special case is locked exceptions, for which the PMTU is smaller * than the minimal accepted PMTU: * - if the new MTU is greater than the PMTU, don't make any change * - otherwise, unlock and set PMTU */ void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig) { struct fnhe_hash_bucket *bucket; int i; bucket = rcu_dereference_protected(nhc->nhc_exceptions, 1); if (!bucket) return; for (i = 0; i < FNHE_HASH_SIZE; i++) { struct fib_nh_exception *fnhe; for (fnhe = rcu_dereference_protected(bucket[i].chain, 1); fnhe; fnhe = rcu_dereference_protected(fnhe->fnhe_next, 1)) { if (fnhe->fnhe_mtu_locked) { if (new <= fnhe->fnhe_pmtu) { fnhe->fnhe_pmtu = new; fnhe->fnhe_mtu_locked = false; } } else if (new < fnhe->fnhe_pmtu || orig == fnhe->fnhe_pmtu) { fnhe->fnhe_pmtu = new; } } } } void fib_sync_mtu(struct net_device *dev, u32 orig_mtu) { struct hlist_head *head = fib_nh_head(dev); struct fib_nh *nh; hlist_for_each_entry(nh, head, nh_hash) { DEBUG_NET_WARN_ON_ONCE(nh->fib_nh_dev != dev); fib_nhc_update_mtu(&nh->nh_common, dev->mtu, orig_mtu); } } /* Event force Flags Description * NETDEV_CHANGE 0 LINKDOWN Carrier OFF, not for scope host * NETDEV_DOWN 0 LINKDOWN|DEAD Link down, not for scope host * NETDEV_DOWN 1 LINKDOWN|DEAD Last address removed * NETDEV_UNREGISTER 1 LINKDOWN|DEAD Device removed * * only used when fib_nh is built into fib_info */ int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force) { struct hlist_head *head = fib_nh_head(dev); struct fib_info *prev_fi = NULL; int scope = RT_SCOPE_NOWHERE; struct fib_nh *nh; int ret = 0; if (force) scope = -1; hlist_for_each_entry(nh, head, nh_hash) { struct fib_info *fi = nh->nh_parent; int dead; BUG_ON(!fi->fib_nhs); DEBUG_NET_WARN_ON_ONCE(nh->fib_nh_dev != dev); if (fi == prev_fi) continue; prev_fi = fi; dead = 0; change_nexthops(fi) { if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD) dead++; else if (nexthop_nh->fib_nh_dev == dev && nexthop_nh->fib_nh_scope != scope) { switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: nexthop_nh->fib_nh_flags |= RTNH_F_DEAD; fallthrough; case NETDEV_CHANGE: nexthop_nh->fib_nh_flags |= RTNH_F_LINKDOWN; break; } call_fib_nh_notifiers(nexthop_nh, FIB_EVENT_NH_DEL); dead++; } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (event == NETDEV_UNREGISTER && nexthop_nh->fib_nh_dev == dev) { dead = fi->fib_nhs; break; } #endif } endfor_nexthops(fi) if (dead == fi->fib_nhs) { switch (event) { case NETDEV_DOWN: case NETDEV_UNREGISTER: fi->fib_flags |= RTNH_F_DEAD; fallthrough; case NETDEV_CHANGE: fi->fib_flags |= RTNH_F_LINKDOWN; break; } ret++; } fib_rebalance(fi); } return ret; } /* Must be invoked inside of an RCU protected region. */ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) { struct fib_info *fi = NULL, *last_resort = NULL; struct hlist_head *fa_head = res->fa_head; struct fib_table *tb = res->table; u8 slen = 32 - res->prefixlen; int order = -1, last_idx = -1; struct fib_alias *fa, *fa1 = NULL; u32 last_prio = res->fi->fib_priority; dscp_t last_dscp = 0; hlist_for_each_entry_rcu(fa, fa_head, fa_list) { struct fib_info *next_fi = fa->fa_info; struct fib_nh_common *nhc; if (fa->fa_slen != slen) continue; if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp)) continue; if (fa->tb_id != tb->tb_id) continue; if (next_fi->fib_priority > last_prio && fa->fa_dscp == last_dscp) { if (last_dscp) continue; break; } if (next_fi->fib_flags & RTNH_F_DEAD) continue; last_dscp = fa->fa_dscp; last_prio = next_fi->fib_priority; if (next_fi->fib_scope != res->scope || fa->fa_type != RTN_UNICAST) continue; nhc = fib_info_nhc(next_fi, 0); if (!nhc->nhc_gw_family || nhc->nhc_scope != RT_SCOPE_LINK) continue; fib_alias_accessed(fa); if (!fi) { if (next_fi != res->fi) break; fa1 = fa; } else if (!fib_detect_death(fi, order, &last_resort, &last_idx, fa1->fa_default)) { fib_result_assign(res, fi); fa1->fa_default = order; goto out; } fi = next_fi; order++; } if (order <= 0 || !fi) { if (fa1) fa1->fa_default = -1; goto out; } if (!fib_detect_death(fi, order, &last_resort, &last_idx, fa1->fa_default)) { fib_result_assign(res, fi); fa1->fa_default = order; goto out; } if (last_idx >= 0) fib_result_assign(res, last_resort); fa1->fa_default = last_idx; out: return; } /* * Dead device goes up. We wake up dead nexthops. * It takes sense only on multipath routes. * * only used when fib_nh is built into fib_info */ int fib_sync_up(struct net_device *dev, unsigned char nh_flags) { struct fib_info *prev_fi; struct hlist_head *head; struct fib_nh *nh; int ret; if (!(dev->flags & IFF_UP)) return 0; if (nh_flags & RTNH_F_DEAD) { unsigned int flags = netif_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) nh_flags |= RTNH_F_LINKDOWN; } prev_fi = NULL; head = fib_nh_head(dev); ret = 0; hlist_for_each_entry(nh, head, nh_hash) { struct fib_info *fi = nh->nh_parent; int alive; BUG_ON(!fi->fib_nhs); DEBUG_NET_WARN_ON_ONCE(nh->fib_nh_dev != dev); if (fi == prev_fi) continue; prev_fi = fi; alive = 0; change_nexthops(fi) { if (!(nexthop_nh->fib_nh_flags & nh_flags)) { alive++; continue; } if (!nexthop_nh->fib_nh_dev || !(nexthop_nh->fib_nh_dev->flags & IFF_UP)) continue; if (nexthop_nh->fib_nh_dev != dev || !__in_dev_get_rtnl(dev)) continue; alive++; nexthop_nh->fib_nh_flags &= ~nh_flags; call_fib_nh_notifiers(nexthop_nh, FIB_EVENT_NH_ADD); } endfor_nexthops(fi) if (alive > 0) { fi->fib_flags &= ~nh_flags; ret++; } fib_rebalance(fi); } return ret; } #ifdef CONFIG_IP_ROUTE_MULTIPATH static bool fib_good_nh(const struct fib_nh *nh) { int state = NUD_REACHABLE; if (nh->fib_nh_scope == RT_SCOPE_LINK) { struct neighbour *n; rcu_read_lock(); if (likely(nh->fib_nh_gw_family == AF_INET)) n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev, (__force u32)nh->fib_nh_gw4); else if (nh->fib_nh_gw_family == AF_INET6) n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev, &nh->fib_nh_gw6); else n = NULL; if (n) state = READ_ONCE(n->nud_state); rcu_read_unlock(); } return !!(state & NUD_VALID); } void fib_select_multipath(struct fib_result *res, int hash, const struct flowi4 *fl4) { struct fib_info *fi = res->fi; struct net *net = fi->fib_net; bool found = false; bool use_neigh; __be32 saddr; if (unlikely(res->fi->nh)) { nexthop_path_fib_result(res, hash); return; } use_neigh = READ_ONCE(net->ipv4.sysctl_fib_multipath_use_neigh); saddr = fl4 ? fl4->saddr : 0; change_nexthops(fi) { int nh_upper_bound; /* Nexthops without a carrier are assigned an upper bound of * minus one when "ignore_routes_with_linkdown" is set. */ nh_upper_bound = atomic_read(&nexthop_nh->fib_nh_upper_bound); if (nh_upper_bound == -1 || (use_neigh && !fib_good_nh(nexthop_nh))) continue; if (!found) { res->nh_sel = nhsel; res->nhc = &nexthop_nh->nh_common; found = !saddr || nexthop_nh->nh_saddr == saddr; } if (hash > nh_upper_bound) continue; if (!saddr || nexthop_nh->nh_saddr == saddr) { res->nh_sel = nhsel; res->nhc = &nexthop_nh->nh_common; return; } if (found) return; } endfor_nexthops(fi); } #endif void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb) { if (fl4->flowi4_oif) goto check_saddr; #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fib_info_num_path(res->fi) > 1) { int h = fib_multipath_hash(net, fl4, skb, NULL); fib_select_multipath(res, h, fl4); } else #endif if (!res->prefixlen && res->table->tb_num_default > 1 && res->type == RTN_UNICAST) fib_select_default(fl4, res); check_saddr: if (!fl4->saddr) { struct net_device *l3mdev; l3mdev = dev_get_by_index_rcu(net, fl4->flowi4_l3mdev); if (!l3mdev || l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) == l3mdev) fl4->saddr = fib_result_prefsrc(net, res); else fl4->saddr = inet_select_addr(l3mdev, 0, RT_SCOPE_LINK); } } int __net_init fib4_semantics_init(struct net *net) { unsigned int hash_bits = 4; net->ipv4.fib_info_hash = fib_info_hash_alloc(hash_bits); if (!net->ipv4.fib_info_hash) return -ENOMEM; net->ipv4.fib_info_hash_bits = hash_bits; net->ipv4.fib_info_cnt = 0; return 0; } void __net_exit fib4_semantics_exit(struct net *net) { fib_info_hash_free(net->ipv4.fib_info_hash); } |
| 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 | /* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ /* Copyright (c) 2002-2007 Volkswagen Group Electronic Research * Copyright (c) 2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de> * * 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. * */ #ifndef CAN_ML_H #define CAN_ML_H #include <linux/can.h> #include <linux/list.h> #include <linux/netdevice.h> #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS) #define CAN_EFF_RCV_HASH_BITS 10 #define CAN_EFF_RCV_ARRAY_SZ (1 << CAN_EFF_RCV_HASH_BITS) enum { RX_ERR, RX_ALL, RX_FIL, RX_INV, RX_MAX }; struct can_dev_rcv_lists { struct hlist_head rx[RX_MAX]; struct hlist_head rx_sff[CAN_SFF_RCV_ARRAY_SZ]; struct hlist_head rx_eff[CAN_EFF_RCV_ARRAY_SZ]; int entries; }; struct can_ml_priv { struct can_dev_rcv_lists dev_rcv_lists; #ifdef CAN_J1939 struct j1939_priv *j1939_priv; #endif }; static inline struct can_ml_priv *can_get_ml_priv(struct net_device *dev) { return netdev_get_ml_priv(dev, ML_PRIV_CAN); } static inline void can_set_ml_priv(struct net_device *dev, struct can_ml_priv *ml_priv) { netdev_set_ml_priv(dev, ml_priv, ML_PRIV_CAN); } #endif /* CAN_ML_H */ |
| 1240 1242 | 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); } } |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_COMPAT_H #define __ASM_COMPAT_H #define compat_mode_t compat_mode_t typedef u16 compat_mode_t; #define __compat_uid_t __compat_uid_t typedef u16 __compat_uid_t; typedef u16 __compat_gid_t; #define compat_ipc_pid_t compat_ipc_pid_t typedef u16 compat_ipc_pid_t; #define compat_statfs compat_statfs #include <asm-generic/compat.h> #ifdef CONFIG_COMPAT /* * Architecture specific compatibility types */ #include <linux/types.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #ifdef __AARCH64EB__ #define COMPAT_UTS_MACHINE "armv8b\0\0" #else #define COMPAT_UTS_MACHINE "armv8l\0\0" #endif typedef u16 __compat_uid16_t; typedef u16 __compat_gid16_t; typedef s32 compat_nlink_t; struct compat_stat { #ifdef __AARCH64EB__ short st_dev; short __pad1; #else compat_dev_t st_dev; #endif compat_ino_t st_ino; compat_mode_t st_mode; compat_ushort_t st_nlink; __compat_uid16_t st_uid; __compat_gid16_t st_gid; #ifdef __AARCH64EB__ short st_rdev; short __pad2; #else compat_dev_t st_rdev; #endif compat_off_t st_size; compat_off_t st_blksize; compat_off_t st_blocks; old_time32_t st_atime; compat_ulong_t st_atime_nsec; old_time32_t st_mtime; compat_ulong_t st_mtime_nsec; old_time32_t st_ctime; compat_ulong_t st_ctime_nsec; compat_ulong_t __unused4[2]; }; struct compat_statfs { int f_type; int f_bsize; int f_blocks; int f_bfree; int f_bavail; int f_files; int f_ffree; compat_fsid_t f_fsid; int f_namelen; /* SunOS ignores this field. */ int f_frsize; int f_flags; int f_spare[4]; }; #define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current))) #define COMPAT_MINSIGSTKSZ 2048 static inline int is_compat_task(void) { return test_thread_flag(TIF_32BIT); } static inline int is_compat_thread(struct thread_info *thread) { return test_ti_thread_flag(thread, TIF_32BIT); } long compat_arm_syscall(struct pt_regs *regs, int scno); #else /* !CONFIG_COMPAT */ static inline int is_compat_thread(struct thread_info *thread) { return 0; } #endif /* CONFIG_COMPAT */ #endif /* __ASM_COMPAT_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/neon.h> #include <asm/simd.h> // The minimum input length to consider the 4-way interleaved code path static const size_t min_len = 1024; asmlinkage u32 crc32_le_arm64(u32 crc, unsigned char const *p, size_t len); asmlinkage u32 crc32c_le_arm64(u32 crc, unsigned char const *p, size_t len); asmlinkage u32 crc32_be_arm64(u32 crc, unsigned char const *p, size_t len); asmlinkage u32 crc32_le_arm64_4way(u32 crc, unsigned char const *p, size_t len); asmlinkage u32 crc32c_le_arm64_4way(u32 crc, unsigned char const *p, size_t len); asmlinkage u32 crc32_be_arm64_4way(u32 crc, unsigned char const *p, size_t len); static inline u32 crc32_le_arch(u32 crc, const u8 *p, size_t len) { if (!alternative_has_cap_likely(ARM64_HAS_CRC32)) return crc32_le_base(crc, p, len); if (len >= min_len && cpu_have_named_feature(PMULL) && likely(may_use_simd())) { kernel_neon_begin(); crc = crc32_le_arm64_4way(crc, p, len); kernel_neon_end(); p += round_down(len, 64); len %= 64; if (!len) return crc; } return crc32_le_arm64(crc, p, len); } static inline u32 crc32c_arch(u32 crc, const u8 *p, size_t len) { if (!alternative_has_cap_likely(ARM64_HAS_CRC32)) return crc32c_base(crc, p, len); if (len >= min_len && cpu_have_named_feature(PMULL) && likely(may_use_simd())) { kernel_neon_begin(); crc = crc32c_le_arm64_4way(crc, p, len); kernel_neon_end(); p += round_down(len, 64); len %= 64; if (!len) return crc; } return crc32c_le_arm64(crc, p, len); } static inline u32 crc32_be_arch(u32 crc, const u8 *p, size_t len) { if (!alternative_has_cap_likely(ARM64_HAS_CRC32)) return crc32_be_base(crc, p, len); if (len >= min_len && cpu_have_named_feature(PMULL) && likely(may_use_simd())) { kernel_neon_begin(); crc = crc32_be_arm64_4way(crc, p, len); kernel_neon_end(); p += round_down(len, 64); len %= 64; if (!len) return crc; } return crc32_be_arm64(crc, p, len); } static inline u32 crc32_optimizations_arch(void) { if (alternative_has_cap_likely(ARM64_HAS_CRC32)) return CRC32_LE_OPTIMIZATION | CRC32_BE_OPTIMIZATION | CRC32C_OPTIMIZATION; return 0; } |
| 333 355 78 355 355 | 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 |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * arch/arm64/include/asm/arch_gicv3.h * * Copyright (C) 2015 ARM Ltd. */ #ifndef __ASM_ARCH_GICV3_H #define __ASM_ARCH_GICV3_H #include <asm/sysreg.h> #ifndef __ASSEMBLY__ #include <linux/irqchip/arm-gic-common.h> #include <linux/stringify.h> #include <asm/barrier.h> #include <asm/cacheflush.h> #define read_gicreg(r) read_sysreg_s(SYS_ ## r) #define write_gicreg(v, r) write_sysreg_s(v, SYS_ ## r) /* * Low-level accessors * * These system registers are 32 bits, but we make sure that the compiler * sets the GP register's most significant bits to 0 with an explicit cast. */ static __always_inline void gic_write_dir(u32 irq) { write_sysreg_s(irq, SYS_ICC_DIR_EL1); isb(); } static inline u64 gic_read_iar_common(void) { u64 irqstat; irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1); dsb(sy); return irqstat; } /* * Cavium ThunderX erratum 23154 * * The gicv3 of ThunderX requires a modified version for reading the * IAR status to ensure data synchronization (access to icc_iar1_el1 * is not sync'ed before and after). * * Erratum 38545 * * When a IAR register read races with a GIC interrupt RELEASE event, * GIC-CPU interface could wrongly return a valid INTID to the CPU * for an interrupt that is already released(non activated) instead of 0x3ff. * * To workaround this, return a valid interrupt ID only if there is a change * in the active priority list after the IAR read. * * Common function used for both the workarounds since, * 1. On Thunderx 88xx 1.x both erratas are applicable. * 2. Having extra nops doesn't add any side effects for Silicons where * erratum 23154 is not applicable. */ static inline u64 gic_read_iar_cavium_thunderx(void) { u64 irqstat, apr; apr = read_sysreg_s(SYS_ICC_AP1R0_EL1); nops(8); irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1); nops(4); mb(); /* Max priority groups implemented is only 32 */ if (likely(apr != read_sysreg_s(SYS_ICC_AP1R0_EL1))) return irqstat; return 0x3ff; } static u64 __maybe_unused gic_read_iar(void) { if (alternative_has_cap_unlikely(ARM64_WORKAROUND_CAVIUM_23154)) return gic_read_iar_cavium_thunderx(); else return gic_read_iar_common(); } static inline void gic_write_ctlr(u32 val) { write_sysreg_s(val, SYS_ICC_CTLR_EL1); isb(); } static inline u32 gic_read_ctlr(void) { return read_sysreg_s(SYS_ICC_CTLR_EL1); } static inline void gic_write_grpen1(u32 val) { write_sysreg_s(val, SYS_ICC_IGRPEN1_EL1); isb(); } static inline void gic_write_sgi1r(u64 val) { write_sysreg_s(val, SYS_ICC_SGI1R_EL1); } static inline u32 gic_read_sre(void) { return read_sysreg_s(SYS_ICC_SRE_EL1); } static inline void gic_write_sre(u32 val) { write_sysreg_s(val, SYS_ICC_SRE_EL1); isb(); } static inline void gic_write_bpr1(u32 val) { write_sysreg_s(val, SYS_ICC_BPR1_EL1); } static inline u32 gic_read_pmr(void) { return read_sysreg_s(SYS_ICC_PMR_EL1); } static __always_inline void gic_write_pmr(u32 val) { write_sysreg_s(val, SYS_ICC_PMR_EL1); } static inline u32 gic_read_rpr(void) { return read_sysreg_s(SYS_ICC_RPR_EL1); } #define gic_read_typer(c) readq_relaxed(c) #define gic_write_irouter(v, c) writeq_relaxed(v, c) #define gic_read_lpir(c) readq_relaxed(c) #define gic_write_lpir(v, c) writeq_relaxed(v, c) #define gic_flush_dcache_to_poc(a,l) \ dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l)) #define gits_read_baser(c) readq_relaxed(c) #define gits_write_baser(v, c) writeq_relaxed(v, c) #define gits_read_cbaser(c) readq_relaxed(c) #define gits_write_cbaser(v, c) writeq_relaxed(v, c) #define gits_write_cwriter(v, c) writeq_relaxed(v, c) #define gicr_read_propbaser(c) readq_relaxed(c) #define gicr_write_propbaser(v, c) writeq_relaxed(v, c) #define gicr_write_pendbaser(v, c) writeq_relaxed(v, c) #define gicr_read_pendbaser(c) readq_relaxed(c) #define gicr_write_vpropbaser(v, c) writeq_relaxed(v, c) #define gicr_read_vpropbaser(c) readq_relaxed(c) #define gicr_write_vpendbaser(v, c) writeq_relaxed(v, c) #define gicr_read_vpendbaser(c) readq_relaxed(c) static inline bool gic_prio_masking_enabled(void) { return system_uses_irq_prio_masking(); } static inline void gic_pmr_mask_irqs(void) { gic_write_pmr(GIC_PRIO_IRQOFF); } static inline void gic_arch_enable_irqs(void) { asm volatile ("msr daifclr, #3" : : : "memory"); } static inline bool gic_has_relaxed_pmr_sync(void) { return cpus_have_cap(ARM64_HAS_GIC_PRIO_RELAXED_SYNC); } #endif /* __ASSEMBLY__ */ #endif /* __ASM_ARCH_GICV3_H */ |
| 1856 352 103 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2013 Huawei Ltd. * Author: Jiang Liu <liuj97@gmail.com> * * Based on arch/arm/include/asm/jump_label.h */ #ifndef __ASM_JUMP_LABEL_H #define __ASM_JUMP_LABEL_H #ifndef __ASSEMBLY__ #include <linux/types.h> #include <asm/insn.h> #define HAVE_JUMP_LABEL_BATCH #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE #define JUMP_TABLE_ENTRY(key, label) \ ".pushsection __jump_table, \"aw\"\n\t" \ ".align 3\n\t" \ ".long 1b - ., " label " - .\n\t" \ ".quad " key " - .\n\t" \ ".popsection\n\t" /* This macro is also expanded on the Rust side. */ #define ARCH_STATIC_BRANCH_ASM(key, label) \ "1: nop\n\t" \ JUMP_TABLE_ENTRY(key, label) static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) { char *k = &((char *)key)[branch]; asm goto( ARCH_STATIC_BRANCH_ASM("%c0", "%l[l_yes]") : : "i"(k) : : l_yes ); return false; l_yes: return true; } static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) { char *k = &((char *)key)[branch]; asm goto( "1: b %l[l_yes] \n\t" JUMP_TABLE_ENTRY("%c0", "%l[l_yes]") : : "i"(k) : : l_yes ); return false; l_yes: return true; } #endif /* __ASSEMBLY__ */ #endif /* __ASM_JUMP_LABEL_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * A policy database (policydb) specifies the * configuration data for the security policy. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * Support for enhanced MLS infrastructure. * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. * * Updated: Frank Mayer <mayerf@tresys.com> and * Karl MacMillan <kmacmillan@tresys.com> * Added conditional policy language extensions * Copyright (C) 2003-2004 Tresys Technology, LLC */ #ifndef _SS_POLICYDB_H_ #define _SS_POLICYDB_H_ #include "symtab.h" #include "avtab.h" #include "sidtab.h" #include "ebitmap.h" #include "mls_types.h" #include "context.h" #include "constraint.h" /* * A datum type is defined for each kind of symbol * in the configuration data: individual permissions, * common prefixes for access vectors, classes, * users, roles, types, sensitivities, categories, etc. */ /* Permission attributes */ struct perm_datum { u32 value; /* permission bit + 1 */ }; /* Attributes of a common prefix for access vectors */ struct common_datum { u32 value; /* internal common value */ struct symtab permissions; /* common permissions */ }; /* Class attributes */ struct class_datum { u32 value; /* class value */ char *comkey; /* common name */ struct common_datum *comdatum; /* common datum */ struct symtab permissions; /* class-specific permission symbol table */ struct constraint_node *constraints; /* constraints on class perms */ struct constraint_node *validatetrans; /* special transition rules */ /* Options how a new object user, role, and type should be decided */ #define DEFAULT_SOURCE 1 #define DEFAULT_TARGET 2 char default_user; char default_role; char default_type; /* Options how a new object range should be decided */ #define DEFAULT_SOURCE_LOW 1 #define DEFAULT_SOURCE_HIGH 2 #define DEFAULT_SOURCE_LOW_HIGH 3 #define DEFAULT_TARGET_LOW 4 #define DEFAULT_TARGET_HIGH 5 #define DEFAULT_TARGET_LOW_HIGH 6 #define DEFAULT_GLBLUB 7 char default_range; }; /* Role attributes */ struct role_datum { u32 value; /* internal role value */ u32 bounds; /* boundary of role */ struct ebitmap dominates; /* set of roles dominated by this role */ struct ebitmap types; /* set of authorized types for role */ }; struct role_trans_key { u32 role; /* current role */ u32 type; /* program executable type, or new object type */ u32 tclass; /* process class, or new object class */ }; struct role_trans_datum { u32 new_role; /* new role */ }; struct filename_trans_key { u32 ttype; /* parent dir context */ u16 tclass; /* class of new object */ const char *name; /* last path component */ }; struct filename_trans_datum { struct ebitmap stypes; /* bitmap of source types for this otype */ u32 otype; /* resulting type of new object */ struct filename_trans_datum *next; /* record for next otype*/ }; struct role_allow { u32 role; /* current role */ u32 new_role; /* new role */ struct role_allow *next; }; /* Type attributes */ struct type_datum { u32 value; /* internal type value */ u32 bounds; /* boundary of type */ unsigned char primary; /* primary name? */ unsigned char attribute; /* attribute ?*/ }; /* User attributes */ struct user_datum { u32 value; /* internal user value */ u32 bounds; /* bounds of user */ struct ebitmap roles; /* set of authorized roles for user */ struct mls_range range; /* MLS range (min - max) for user */ struct mls_level dfltlevel; /* default login MLS level for user */ }; /* Sensitivity attributes */ struct level_datum { struct mls_level level; /* sensitivity and associated categories */ unsigned char isalias; /* is this sensitivity an alias for another? */ }; /* Category attributes */ struct cat_datum { u32 value; /* internal category bit + 1 */ unsigned char isalias; /* is this category an alias for another? */ }; struct range_trans { u32 source_type; u32 target_type; u32 target_class; }; /* Boolean data type */ struct cond_bool_datum { u32 value; /* internal type value */ int state; }; struct cond_node; /* * type set preserves data needed to determine constraint info from * policy source. This is not used by the kernel policy but allows * utilities such as audit2allow to determine constraint denials. */ struct type_set { struct ebitmap types; struct ebitmap negset; u32 flags; }; /* * The configuration data includes security contexts for * initial SIDs, unlabeled file systems, TCP and UDP port numbers, * network interfaces, and nodes. This structure stores the * relevant data for one such entry. Entries of the same kind * (e.g. all initial SIDs) are linked together into a list. */ struct ocontext { union { char *name; /* name of initial SID, fs, netif, fstype, path */ struct { u8 protocol; u16 low_port; u16 high_port; } port; /* TCP or UDP port information */ struct { u32 addr; u32 mask; } node; /* node information */ struct { u32 addr[4]; u32 mask[4]; } node6; /* IPv6 node information */ struct { u64 subnet_prefix; u16 low_pkey; u16 high_pkey; } ibpkey; struct { char *dev_name; u8 port; } ibendport; } u; union { u32 sclass; /* security class for genfs */ u32 behavior; /* labeling behavior for fs_use */ } v; struct context context[2]; /* security context(s) */ u32 sid[2]; /* SID(s) */ struct ocontext *next; }; struct genfs { char *fstype; struct ocontext *head; struct genfs *next; }; /* symbol table array indices */ #define SYM_COMMONS 0 #define SYM_CLASSES 1 #define SYM_ROLES 2 #define SYM_TYPES 3 #define SYM_USERS 4 #define SYM_BOOLS 5 #define SYM_LEVELS 6 #define SYM_CATS 7 #define SYM_NUM 8 /* object context array indices */ #define OCON_ISID 0 /* initial SIDs */ #define OCON_FS 1 /* unlabeled file systems (deprecated) */ #define OCON_PORT 2 /* TCP and UDP port numbers */ #define OCON_NETIF 3 /* network interfaces */ #define OCON_NODE 4 /* nodes */ #define OCON_FSUSE 5 /* fs_use */ #define OCON_NODE6 6 /* IPv6 nodes */ #define OCON_IBPKEY 7 /* Infiniband PKeys */ #define OCON_IBENDPORT 8 /* Infiniband end ports */ #define OCON_NUM 9 /* The policy database */ struct policydb { int mls_enabled; /* symbol tables */ struct symtab symtab[SYM_NUM]; #define p_commons symtab[SYM_COMMONS] #define p_classes symtab[SYM_CLASSES] #define p_roles symtab[SYM_ROLES] #define p_types symtab[SYM_TYPES] #define p_users symtab[SYM_USERS] #define p_bools symtab[SYM_BOOLS] #define p_levels symtab[SYM_LEVELS] #define p_cats symtab[SYM_CATS] /* symbol names indexed by (value - 1) */ char **sym_val_to_name[SYM_NUM]; /* class, role, and user attributes indexed by (value - 1) */ struct class_datum **class_val_to_struct; struct role_datum **role_val_to_struct; struct user_datum **user_val_to_struct; struct type_datum **type_val_to_struct; /* type enforcement access vectors and transitions */ struct avtab te_avtab; /* role transitions */ struct hashtab role_tr; /* file transitions with the last path component */ /* quickly exclude lookups when parent ttype has no rules */ struct ebitmap filename_trans_ttypes; /* actual set of filename_trans rules */ struct hashtab filename_trans; /* only used if policyvers < POLICYDB_VERSION_COMP_FTRANS */ u32 compat_filename_trans_count; /* bools indexed by (value - 1) */ struct cond_bool_datum **bool_val_to_struct; /* type enforcement conditional access vectors and transitions */ struct avtab te_cond_avtab; /* array indexing te_cond_avtab by conditional */ struct cond_node *cond_list; u32 cond_list_len; /* role allows */ struct role_allow *role_allow; /* security contexts of initial SIDs, unlabeled file systems, TCP or UDP port numbers, network interfaces and nodes */ struct ocontext *ocontexts[OCON_NUM]; /* security contexts for files in filesystems that cannot support a persistent label mapping or use another fixed labeling behavior. */ struct genfs *genfs; /* range transitions table (range_trans_key -> mls_range) */ struct hashtab range_tr; /* type -> attribute reverse mapping */ struct ebitmap *type_attr_map_array; struct ebitmap policycaps; struct ebitmap permissive_map; struct ebitmap neveraudit_map; /* length of this policy when it was loaded */ size_t len; unsigned int policyvers; unsigned int reject_unknown : 1; unsigned int allow_unknown : 1; u16 process_class; u32 process_trans_perms; } __randomize_layout; struct policy_file { char *data; size_t len; }; extern void policydb_destroy(struct policydb *p); extern int policydb_load_isids(struct policydb *p, struct sidtab *s); extern int policydb_context_isvalid(struct policydb *p, struct context *c); extern int policydb_class_isvalid(struct policydb *p, unsigned int class); extern int policydb_type_isvalid(struct policydb *p, unsigned int type); extern int policydb_role_isvalid(struct policydb *p, unsigned int role); extern int policydb_read(struct policydb *p, struct policy_file *fp); extern int policydb_write(struct policydb *p, struct policy_file *fp); extern struct filename_trans_datum * policydb_filenametr_search(struct policydb *p, struct filename_trans_key *key); extern struct mls_range *policydb_rangetr_search(struct policydb *p, struct range_trans *key); extern struct role_trans_datum * policydb_roletr_search(struct policydb *p, struct role_trans_key *key); #define POLICYDB_CONFIG_MLS 1 /* the config flags related to unknown classes/perms are bits 2 and 3 */ #define REJECT_UNKNOWN 0x00000002 #define ALLOW_UNKNOWN 0x00000004 #define OBJECT_R "object_r" #define OBJECT_R_VAL 1 #define POLICYDB_MAGIC SELINUX_MAGIC #define POLICYDB_STRING "SE Linux" struct policy_data { struct policydb *p; struct policy_file *fp; }; static inline int next_entry(void *buf, struct policy_file *fp, size_t bytes) { if (bytes > fp->len) return -EINVAL; memcpy(buf, fp->data, bytes); fp->data += bytes; fp->len -= bytes; return 0; } static inline int put_entry(const void *buf, size_t bytes, size_t num, struct policy_file *fp) { size_t len; if (unlikely(check_mul_overflow(bytes, num, &len))) return -EINVAL; if (len > fp->len) return -EINVAL; memcpy(fp->data, buf, len); fp->data += len; fp->len -= len; return 0; } static inline char *sym_name(struct policydb *p, unsigned int sym_num, unsigned int element_nr) { return p->sym_val_to_name[sym_num][element_nr]; } extern int str_read(char **strp, gfp_t flags, struct policy_file *fp, u32 len); extern u16 string_to_security_class(struct policydb *p, const char *name); extern u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name); #endif /* _SS_POLICYDB_H_ */ |
| 454 | 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_ */ |
| 10 127 127 126 127 127 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Implementation of the access vector table type. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* Updated: Frank Mayer <mayerf@tresys.com> and * Karl MacMillan <kmacmillan@tresys.com> * Added conditional policy language extensions * Copyright (C) 2003 Tresys Technology, LLC * * Updated: Yuichi Nakamura <ynakam@hitachisoft.jp> * Tuned number of hash slots for avtab to reduce memory usage */ #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include "avtab.h" #include "policydb.h" static struct kmem_cache *avtab_node_cachep __ro_after_init; static struct kmem_cache *avtab_xperms_cachep __ro_after_init; /* Based on MurmurHash3, written by Austin Appleby and placed in the * public domain. */ static inline u32 avtab_hash(const struct avtab_key *keyp, u32 mask) { static const u32 c1 = 0xcc9e2d51; static const u32 c2 = 0x1b873593; static const u32 r1 = 15; static const u32 r2 = 13; static const u32 m = 5; static const u32 n = 0xe6546b64; u32 hash = 0; #define mix(input) \ do { \ u32 v = input; \ v *= c1; \ v = (v << r1) | (v >> (32 - r1)); \ v *= c2; \ hash ^= v; \ hash = (hash << r2) | (hash >> (32 - r2)); \ hash = hash * m + n; \ } while (0) mix(keyp->target_class); mix(keyp->target_type); mix(keyp->source_type); #undef mix hash ^= hash >> 16; hash *= 0x85ebca6b; hash ^= hash >> 13; hash *= 0xc2b2ae35; hash ^= hash >> 16; return hash & mask; } static struct avtab_node *avtab_insert_node(struct avtab *h, struct avtab_node **dst, const struct avtab_key *key, const struct avtab_datum *datum) { struct avtab_node *newnode; struct avtab_extended_perms *xperms; newnode = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL); if (newnode == NULL) return NULL; newnode->key = *key; if (key->specified & AVTAB_XPERMS) { xperms = kmem_cache_zalloc(avtab_xperms_cachep, GFP_KERNEL); if (xperms == NULL) { kmem_cache_free(avtab_node_cachep, newnode); return NULL; } *xperms = *(datum->u.xperms); newnode->datum.u.xperms = xperms; } else { newnode->datum.u.data = datum->u.data; } newnode->next = *dst; *dst = newnode; h->nel++; return newnode; } static int avtab_node_cmp(const struct avtab_key *key1, const struct avtab_key *key2) { u16 specified = key1->specified & ~(AVTAB_ENABLED | AVTAB_ENABLED_OLD); if (key1->source_type == key2->source_type && key1->target_type == key2->target_type && key1->target_class == key2->target_class && (specified & key2->specified)) return 0; if (key1->source_type < key2->source_type) return -1; if (key1->source_type == key2->source_type && key1->target_type < key2->target_type) return -1; if (key1->source_type == key2->source_type && key1->target_type == key2->target_type && key1->target_class < key2->target_class) return -1; return 1; } static int avtab_insert(struct avtab *h, const struct avtab_key *key, const struct avtab_datum *datum) { u32 hvalue; struct avtab_node *prev, *cur, *newnode; int cmp; if (!h || !h->nslot || h->nel == U32_MAX) return -EINVAL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { cmp = avtab_node_cmp(key, &cur->key); /* extended perms may not be unique */ if (cmp == 0 && !(key->specified & AVTAB_XPERMS)) return -EEXIST; if (cmp <= 0) break; } newnode = avtab_insert_node(h, prev ? &prev->next : &h->htable[hvalue], key, datum); if (!newnode) return -ENOMEM; return 0; } /* Unlike avtab_insert(), this function allow multiple insertions of the same * key/specified mask into the table, as needed by the conditional avtab. * It also returns a pointer to the node inserted. */ struct avtab_node *avtab_insert_nonunique(struct avtab *h, const struct avtab_key *key, const struct avtab_datum *datum) { u32 hvalue; struct avtab_node *prev, *cur; int cmp; if (!h || !h->nslot || h->nel == U32_MAX) return NULL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { cmp = avtab_node_cmp(key, &cur->key); if (cmp <= 0) break; } return avtab_insert_node(h, prev ? &prev->next : &h->htable[hvalue], key, datum); } /* This search function returns a node pointer, and can be used in * conjunction with avtab_search_next_node() */ struct avtab_node *avtab_search_node(struct avtab *h, const struct avtab_key *key) { u32 hvalue; struct avtab_node *cur; int cmp; if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (cur = h->htable[hvalue]; cur; cur = cur->next) { cmp = avtab_node_cmp(key, &cur->key); if (cmp == 0) return cur; if (cmp < 0) break; } return NULL; } struct avtab_node *avtab_search_node_next(struct avtab_node *node, u16 specified) { struct avtab_key tmp_key; struct avtab_node *cur; int cmp; if (!node) return NULL; tmp_key = node->key; tmp_key.specified = specified; for (cur = node->next; cur; cur = cur->next) { cmp = avtab_node_cmp(&tmp_key, &cur->key); if (cmp == 0) return cur; if (cmp < 0) break; } return NULL; } void avtab_destroy(struct avtab *h) { u32 i; struct avtab_node *cur, *temp; if (!h) return; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; while (cur) { temp = cur; cur = cur->next; if (temp->key.specified & AVTAB_XPERMS) kmem_cache_free(avtab_xperms_cachep, temp->datum.u.xperms); kmem_cache_free(avtab_node_cachep, temp); } } kvfree(h->htable); h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } void avtab_init(struct avtab *h) { h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } static int avtab_alloc_common(struct avtab *h, u32 nslot) { if (!nslot) return 0; h->htable = kvcalloc(nslot, sizeof(void *), GFP_KERNEL); if (!h->htable) return -ENOMEM; h->nslot = nslot; h->mask = nslot - 1; return 0; } int avtab_alloc(struct avtab *h, u32 nrules) { int rc; u32 nslot = 0; if (nrules != 0) { nslot = nrules > 3 ? rounddown_pow_of_two(nrules / 2) : 2; if (nslot > MAX_AVTAB_HASH_BUCKETS) nslot = MAX_AVTAB_HASH_BUCKETS; rc = avtab_alloc_common(h, nslot); if (rc) return rc; } pr_debug("SELinux: %d avtab hash slots, %d rules.\n", nslot, nrules); return 0; } int avtab_alloc_dup(struct avtab *new, const struct avtab *orig) { return avtab_alloc_common(new, orig->nslot); } #ifdef CONFIG_SECURITY_SELINUX_DEBUG void avtab_hash_eval(struct avtab *h, const char *tag) { u32 i, chain_len, slots_used, max_chain_len; unsigned long long chain2_len_sum; struct avtab_node *cur; slots_used = 0; max_chain_len = 0; chain2_len_sum = 0; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; if (cur) { slots_used++; chain_len = 0; while (cur) { chain_len++; cur = cur->next; } if (chain_len > max_chain_len) max_chain_len = chain_len; chain2_len_sum += (unsigned long long)chain_len * chain_len; } } pr_debug("SELinux: %s: %d entries and %d/%d buckets used, " "longest chain length %d, sum of chain length^2 %llu\n", tag, h->nel, slots_used, h->nslot, max_chain_len, chain2_len_sum); } #endif /* CONFIG_SECURITY_SELINUX_DEBUG */ /* clang-format off */ static const uint16_t spec_order[] = { AVTAB_ALLOWED, AVTAB_AUDITDENY, AVTAB_AUDITALLOW, AVTAB_TRANSITION, AVTAB_CHANGE, AVTAB_MEMBER, AVTAB_XPERMS_ALLOWED, AVTAB_XPERMS_AUDITALLOW, AVTAB_XPERMS_DONTAUDIT }; /* clang-format on */ int avtab_read_item(struct avtab *a, struct policy_file *fp, struct policydb *pol, int (*insertf)(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *p), void *p, bool conditional) { __le16 buf16[4]; u16 enabled; u32 items, items2, val, i; struct avtab_key key; struct avtab_datum datum; struct avtab_extended_perms xperms; __le32 buf32[ARRAY_SIZE(xperms.perms.p)]; int rc; unsigned int set, vers = pol->policyvers; memset(&key, 0, sizeof(struct avtab_key)); memset(&datum, 0, sizeof(struct avtab_datum)); if (vers < POLICYDB_VERSION_AVTAB) { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items2 = le32_to_cpu(buf32[0]); if (items2 > ARRAY_SIZE(buf32)) { pr_err("SELinux: avtab: entry overflow\n"); return -EINVAL; } rc = next_entry(buf32, fp, sizeof(u32) * items2); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; val = le32_to_cpu(buf32[items++]); key.source_type = (u16)val; if (key.source_type != val) { pr_err("SELinux: avtab: truncated source type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_type = (u16)val; if (key.target_type != val) { pr_err("SELinux: avtab: truncated target type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_class = (u16)val; if (key.target_class != val) { pr_err("SELinux: avtab: truncated target class\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); enabled = (val & AVTAB_ENABLED_OLD) ? AVTAB_ENABLED : 0; if (!(val & (AVTAB_AV | AVTAB_TYPE))) { pr_err("SELinux: avtab: null entry\n"); return -EINVAL; } if ((val & AVTAB_AV) && (val & AVTAB_TYPE)) { pr_err("SELinux: avtab: entry has both access vectors and types\n"); return -EINVAL; } if (val & AVTAB_XPERMS) { pr_err("SELinux: avtab: entry has extended permissions\n"); return -EINVAL; } for (i = 0; i < ARRAY_SIZE(spec_order); i++) { if (val & spec_order[i]) { key.specified = spec_order[i] | enabled; datum.u.data = le32_to_cpu(buf32[items++]); rc = insertf(a, &key, &datum, p); if (rc) return rc; } } if (items != items2) { pr_err("SELinux: avtab: entry only had %d items, expected %d\n", items2, items); return -EINVAL; } return 0; } rc = next_entry(buf16, fp, sizeof(u16) * 4); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; key.source_type = le16_to_cpu(buf16[items++]); key.target_type = le16_to_cpu(buf16[items++]); key.target_class = le16_to_cpu(buf16[items++]); key.specified = le16_to_cpu(buf16[items++]); if (!policydb_type_isvalid(pol, key.source_type) || !policydb_type_isvalid(pol, key.target_type) || !policydb_class_isvalid(pol, key.target_class)) { pr_err("SELinux: avtab: invalid type or class\n"); return -EINVAL; } set = hweight16(key.specified & (AVTAB_XPERMS | AVTAB_TYPE | AVTAB_AV)); if (!set || set > 1) { pr_err("SELinux: avtab: more than one specifier\n"); return -EINVAL; } if ((vers < POLICYDB_VERSION_XPERMS_IOCTL) && (key.specified & AVTAB_XPERMS)) { pr_err("SELinux: avtab: policy version %u does not " "support extended permissions rules and one " "was specified\n", vers); return -EINVAL; } else if ((vers < POLICYDB_VERSION_COND_XPERMS) && (key.specified & AVTAB_XPERMS) && conditional) { pr_err("SELinux: avtab: policy version %u does not " "support extended permissions rules in conditional " "policies and one was specified\n", vers); return -EINVAL; } else if (key.specified & AVTAB_XPERMS) { memset(&xperms, 0, sizeof(struct avtab_extended_perms)); rc = next_entry(&xperms.specified, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(&xperms.driver, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(buf32, fp, sizeof(u32) * ARRAY_SIZE(xperms.perms.p)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } for (i = 0; i < ARRAY_SIZE(xperms.perms.p); i++) xperms.perms.p[i] = le32_to_cpu(buf32[i]); datum.u.xperms = &xperms; } else { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } datum.u.data = le32_to_cpu(*buf32); } if ((key.specified & AVTAB_TYPE) && !policydb_type_isvalid(pol, datum.u.data)) { pr_err("SELinux: avtab: invalid type\n"); return -EINVAL; } return insertf(a, &key, &datum, p); } static int avtab_insertf(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *p) { return avtab_insert(a, k, d); } int avtab_read(struct avtab *a, struct policy_file *fp, struct policydb *pol) { int rc; __le32 buf[1]; u32 nel, i; rc = next_entry(buf, fp, sizeof(u32)); if (rc < 0) { pr_err("SELinux: avtab: truncated table\n"); goto bad; } nel = le32_to_cpu(buf[0]); if (!nel) { pr_err("SELinux: avtab: table is empty\n"); rc = -EINVAL; goto bad; } rc = avtab_alloc(a, nel); if (rc) goto bad; for (i = 0; i < nel; i++) { rc = avtab_read_item(a, fp, pol, avtab_insertf, NULL, false); if (rc) { if (rc == -ENOMEM) pr_err("SELinux: avtab: out of memory\n"); else if (rc == -EEXIST) pr_err("SELinux: avtab: duplicate entry\n"); goto bad; } } rc = 0; out: return rc; bad: avtab_destroy(a); goto out; } int avtab_write_item(struct policydb *p, const struct avtab_node *cur, struct policy_file *fp) { __le16 buf16[4]; __le32 buf32[ARRAY_SIZE(cur->datum.u.xperms->perms.p)]; int rc; unsigned int i; buf16[0] = cpu_to_le16(cur->key.source_type); buf16[1] = cpu_to_le16(cur->key.target_type); buf16[2] = cpu_to_le16(cur->key.target_class); buf16[3] = cpu_to_le16(cur->key.specified); rc = put_entry(buf16, sizeof(u16), 4, fp); if (rc) return rc; if (cur->key.specified & AVTAB_XPERMS) { rc = put_entry(&cur->datum.u.xperms->specified, sizeof(u8), 1, fp); if (rc) return rc; rc = put_entry(&cur->datum.u.xperms->driver, sizeof(u8), 1, fp); if (rc) return rc; for (i = 0; i < ARRAY_SIZE(cur->datum.u.xperms->perms.p); i++) buf32[i] = cpu_to_le32(cur->datum.u.xperms->perms.p[i]); rc = put_entry(buf32, sizeof(u32), ARRAY_SIZE(cur->datum.u.xperms->perms.p), fp); } else { buf32[0] = cpu_to_le32(cur->datum.u.data); rc = put_entry(buf32, sizeof(u32), 1, fp); } if (rc) return rc; return 0; } int avtab_write(struct policydb *p, struct avtab *a, struct policy_file *fp) { u32 i; int rc = 0; struct avtab_node *cur; __le32 buf[1]; buf[0] = cpu_to_le32(a->nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (i = 0; i < a->nslot; i++) { for (cur = a->htable[i]; cur; cur = cur->next) { rc = avtab_write_item(p, cur, fp); if (rc) return rc; } } return rc; } void __init avtab_cache_init(void) { avtab_node_cachep = KMEM_CACHE(avtab_node, SLAB_PANIC); avtab_xperms_cachep = KMEM_CACHE(avtab_extended_perms, SLAB_PANIC); } |
| 285 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM percpu #if !defined(_TRACE_PERCPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PERCPU_H #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(percpu_alloc_percpu, TP_PROTO(unsigned long call_site, bool reserved, bool is_atomic, size_t size, size_t align, void *base_addr, int off, void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off, ptr, bytes_alloc, gfp_flags), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", (void *)__entry->call_site, __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, __entry->base_addr, __entry->off, __entry->ptr, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); TRACE_EVENT(percpu_free_percpu, TP_PROTO(void *base_addr, int off, void __percpu *ptr), TP_ARGS(base_addr, off, ptr), TP_STRUCT__entry( __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) ), TP_fast_assign( __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; ), TP_printk("base_addr=%p off=%d ptr=%p", __entry->base_addr, __entry->off, __entry->ptr) ); TRACE_EVENT(percpu_alloc_percpu_fail, TP_PROTO(bool reserved, bool is_atomic, size_t size, size_t align), TP_ARGS(reserved, is_atomic, size, align), TP_STRUCT__entry( __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) ), TP_fast_assign( __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; ), TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu", __entry->reserved, __entry->is_atomic, __entry->size, __entry->align) ); TRACE_EVENT(percpu_create_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); TRACE_EVENT(percpu_destroy_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); #endif /* _TRACE_PERCPU_H */ #include <trace/define_trace.h> |
| 2 5 5 3 2 3 5 5 5 5 5 1 2 2 2 5 1 1 3 5 2 2 2 2 4 4 1 2 10 6 1 1 2 6 3 3 5 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 | // SPDX-License-Identifier: GPL-2.0 #include <linux/backing-dev.h> #include <linux/falloc.h> #include <linux/kvm_host.h> #include <linux/pagemap.h> #include <linux/anon_inodes.h> #include "kvm_mm.h" struct kvm_gmem { struct kvm *kvm; struct xarray bindings; struct list_head entry; }; /** * folio_file_pfn - like folio_file_page, but return a pfn. * @folio: The folio which contains this index. * @index: The index we want to look up. * * Return: The pfn for this index. */ static inline kvm_pfn_t folio_file_pfn(struct folio *folio, pgoff_t index) { return folio_pfn(folio) + (index & (folio_nr_pages(folio) - 1)); } static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot, pgoff_t index, struct folio *folio) { #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE kvm_pfn_t pfn = folio_file_pfn(folio, index); gfn_t gfn = slot->base_gfn + index - slot->gmem.pgoff; int rc = kvm_arch_gmem_prepare(kvm, gfn, pfn, folio_order(folio)); if (rc) { pr_warn_ratelimited("gmem: Failed to prepare folio for index %lx GFN %llx PFN %llx error %d.\n", index, gfn, pfn, rc); return rc; } #endif return 0; } static inline void kvm_gmem_mark_prepared(struct folio *folio) { folio_mark_uptodate(folio); } /* * Process @folio, which contains @gfn, so that the guest can use it. * The folio must be locked and the gfn must be contained in @slot. * On successful return the guest sees a zero page so as to avoid * leaking host data and the up-to-date flag is set. */ static int kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, struct folio *folio) { unsigned long nr_pages, i; pgoff_t index; int r; nr_pages = folio_nr_pages(folio); for (i = 0; i < nr_pages; i++) clear_highpage(folio_page(folio, i)); /* * Preparing huge folios should always be safe, since it should * be possible to split them later if needed. * * Right now the folio order is always going to be zero, but the * code is ready for huge folios. The only assumption is that * the base pgoff of memslots is naturally aligned with the * requested page order, ensuring that huge folios can also use * huge page table entries for GPA->HPA mapping. * * The order will be passed when creating the guest_memfd, and * checked when creating memslots. */ WARN_ON(!IS_ALIGNED(slot->gmem.pgoff, 1 << folio_order(folio))); index = gfn - slot->base_gfn + slot->gmem.pgoff; index = ALIGN_DOWN(index, 1 << folio_order(folio)); r = __kvm_gmem_prepare_folio(kvm, slot, index, folio); if (!r) kvm_gmem_mark_prepared(folio); return r; } /* * Returns a locked folio on success. The caller is responsible for * setting the up-to-date flag before the memory is mapped into the guest. * There is no backing storage for the memory, so the folio will remain * up-to-date until it's removed. * * Ignore accessed, referenced, and dirty flags. The memory is * unevictable and there is no storage to write back to. */ static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index) { /* TODO: Support huge pages. */ return filemap_grab_folio(inode->i_mapping, index); } static enum kvm_gfn_range_filter kvm_gmem_get_invalidate_filter(struct inode *inode) { if ((u64)inode->i_private & GUEST_MEMFD_FLAG_INIT_SHARED) return KVM_FILTER_SHARED; return KVM_FILTER_PRIVATE; } static void __kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start, pgoff_t end, enum kvm_gfn_range_filter attr_filter) { bool flush = false, found_memslot = false; struct kvm_memory_slot *slot; struct kvm *kvm = gmem->kvm; unsigned long index; xa_for_each_range(&gmem->bindings, index, slot, start, end - 1) { pgoff_t pgoff = slot->gmem.pgoff; struct kvm_gfn_range gfn_range = { .start = slot->base_gfn + max(pgoff, start) - pgoff, .end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff, .slot = slot, .may_block = true, .attr_filter = attr_filter, }; if (!found_memslot) { found_memslot = true; KVM_MMU_LOCK(kvm); kvm_mmu_invalidate_begin(kvm); } flush |= kvm_mmu_unmap_gfn_range(kvm, &gfn_range); } if (flush) kvm_flush_remote_tlbs(kvm); if (found_memslot) KVM_MMU_UNLOCK(kvm); } static void kvm_gmem_invalidate_begin(struct inode *inode, pgoff_t start, pgoff_t end) { struct list_head *gmem_list = &inode->i_mapping->i_private_list; enum kvm_gfn_range_filter attr_filter; struct kvm_gmem *gmem; attr_filter = kvm_gmem_get_invalidate_filter(inode); list_for_each_entry(gmem, gmem_list, entry) __kvm_gmem_invalidate_begin(gmem, start, end, attr_filter); } static void __kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start, pgoff_t end) { struct kvm *kvm = gmem->kvm; if (xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) { KVM_MMU_LOCK(kvm); kvm_mmu_invalidate_end(kvm); KVM_MMU_UNLOCK(kvm); } } static void kvm_gmem_invalidate_end(struct inode *inode, pgoff_t start, pgoff_t end) { struct list_head *gmem_list = &inode->i_mapping->i_private_list; struct kvm_gmem *gmem; list_for_each_entry(gmem, gmem_list, entry) __kvm_gmem_invalidate_end(gmem, start, end); } static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len) { pgoff_t start = offset >> PAGE_SHIFT; pgoff_t end = (offset + len) >> PAGE_SHIFT; /* * Bindings must be stable across invalidation to ensure the start+end * are balanced. */ filemap_invalidate_lock(inode->i_mapping); kvm_gmem_invalidate_begin(inode, start, end); truncate_inode_pages_range(inode->i_mapping, offset, offset + len - 1); kvm_gmem_invalidate_end(inode, start, end); filemap_invalidate_unlock(inode->i_mapping); return 0; } static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len) { struct address_space *mapping = inode->i_mapping; pgoff_t start, index, end; int r; /* Dedicated guest is immutable by default. */ if (offset + len > i_size_read(inode)) return -EINVAL; filemap_invalidate_lock_shared(mapping); start = offset >> PAGE_SHIFT; end = (offset + len) >> PAGE_SHIFT; r = 0; for (index = start; index < end; ) { struct folio *folio; if (signal_pending(current)) { r = -EINTR; break; } folio = kvm_gmem_get_folio(inode, index); if (IS_ERR(folio)) { r = PTR_ERR(folio); break; } index = folio_next_index(folio); folio_unlock(folio); folio_put(folio); /* 64-bit only, wrapping the index should be impossible. */ if (WARN_ON_ONCE(!index)) break; cond_resched(); } filemap_invalidate_unlock_shared(mapping); return r; } static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { int ret; if (!(mode & FALLOC_FL_KEEP_SIZE)) return -EOPNOTSUPP; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; if (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len)) return -EINVAL; if (mode & FALLOC_FL_PUNCH_HOLE) ret = kvm_gmem_punch_hole(file_inode(file), offset, len); else ret = kvm_gmem_allocate(file_inode(file), offset, len); if (!ret) file_modified(file); return ret; } static int kvm_gmem_release(struct inode *inode, struct file *file) { struct kvm_gmem *gmem = file->private_data; struct kvm_memory_slot *slot; struct kvm *kvm = gmem->kvm; unsigned long index; /* * Prevent concurrent attempts to *unbind* a memslot. This is the last * reference to the file and thus no new bindings can be created, but * dereferencing the slot for existing bindings needs to be protected * against memslot updates, specifically so that unbind doesn't race * and free the memslot (kvm_gmem_get_file() will return NULL). * * Since .release is called only when the reference count is zero, * after which file_ref_get() and get_file_active() fail, * kvm_gmem_get_pfn() cannot be using the file concurrently. * file_ref_put() provides a full barrier, and get_file_active() the * matching acquire barrier. */ mutex_lock(&kvm->slots_lock); filemap_invalidate_lock(inode->i_mapping); xa_for_each(&gmem->bindings, index, slot) WRITE_ONCE(slot->gmem.file, NULL); /* * All in-flight operations are gone and new bindings can be created. * Zap all SPTEs pointed at by this file. Do not free the backing * memory, as its lifetime is associated with the inode, not the file. */ __kvm_gmem_invalidate_begin(gmem, 0, -1ul, kvm_gmem_get_invalidate_filter(inode)); __kvm_gmem_invalidate_end(gmem, 0, -1ul); list_del(&gmem->entry); filemap_invalidate_unlock(inode->i_mapping); mutex_unlock(&kvm->slots_lock); xa_destroy(&gmem->bindings); kfree(gmem); kvm_put_kvm(kvm); return 0; } static inline struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot) { /* * Do not return slot->gmem.file if it has already been closed; * there might be some time between the last fput() and when * kvm_gmem_release() clears slot->gmem.file. */ return get_file_active(&slot->gmem.file); } static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn) { return gfn - slot->base_gfn + slot->gmem.pgoff; } static bool kvm_gmem_supports_mmap(struct inode *inode) { const u64 flags = (u64)inode->i_private; return flags & GUEST_MEMFD_FLAG_MMAP; } static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); struct folio *folio; vm_fault_t ret = VM_FAULT_LOCKED; if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode)) return VM_FAULT_SIGBUS; if (!((u64)inode->i_private & GUEST_MEMFD_FLAG_INIT_SHARED)) return VM_FAULT_SIGBUS; folio = kvm_gmem_get_folio(inode, vmf->pgoff); if (IS_ERR(folio)) { int err = PTR_ERR(folio); if (err == -EAGAIN) return VM_FAULT_RETRY; return vmf_error(err); } if (WARN_ON_ONCE(folio_test_large(folio))) { ret = VM_FAULT_SIGBUS; goto out_folio; } if (!folio_test_uptodate(folio)) { clear_highpage(folio_page(folio, 0)); kvm_gmem_mark_prepared(folio); } vmf->page = folio_file_page(folio, vmf->pgoff); out_folio: if (ret != VM_FAULT_LOCKED) { folio_unlock(folio); folio_put(folio); } return ret; } static const struct vm_operations_struct kvm_gmem_vm_ops = { .fault = kvm_gmem_fault_user_mapping, }; static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma) { if (!kvm_gmem_supports_mmap(file_inode(file))) return -ENODEV; if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) != (VM_SHARED | VM_MAYSHARE)) { return -EINVAL; } vma->vm_ops = &kvm_gmem_vm_ops; return 0; } static struct file_operations kvm_gmem_fops = { .mmap = kvm_gmem_mmap, .open = generic_file_open, .release = kvm_gmem_release, .fallocate = kvm_gmem_fallocate, }; void kvm_gmem_init(struct module *module) { kvm_gmem_fops.owner = module; } static int kvm_gmem_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { WARN_ON_ONCE(1); return -EINVAL; } static int kvm_gmem_error_folio(struct address_space *mapping, struct folio *folio) { pgoff_t start, end; filemap_invalidate_lock_shared(mapping); start = folio->index; end = start + folio_nr_pages(folio); kvm_gmem_invalidate_begin(mapping->host, start, end); /* * Do not truncate the range, what action is taken in response to the * error is userspace's decision (assuming the architecture supports * gracefully handling memory errors). If/when the guest attempts to * access a poisoned page, kvm_gmem_get_pfn() will return -EHWPOISON, * at which point KVM can either terminate the VM or propagate the * error to userspace. */ kvm_gmem_invalidate_end(mapping->host, start, end); filemap_invalidate_unlock_shared(mapping); return MF_DELAYED; } #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE static void kvm_gmem_free_folio(struct folio *folio) { struct page *page = folio_page(folio, 0); kvm_pfn_t pfn = page_to_pfn(page); int order = folio_order(folio); kvm_arch_gmem_invalidate(pfn, pfn + (1ul << order)); } #endif static const struct address_space_operations kvm_gmem_aops = { .dirty_folio = noop_dirty_folio, .migrate_folio = kvm_gmem_migrate_folio, .error_remove_folio = kvm_gmem_error_folio, #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE .free_folio = kvm_gmem_free_folio, #endif }; static int kvm_gmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { return -EINVAL; } static const struct inode_operations kvm_gmem_iops = { .setattr = kvm_gmem_setattr, }; bool __weak kvm_arch_supports_gmem_init_shared(struct kvm *kvm) { return true; } static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) { const char *anon_name = "[kvm-gmem]"; struct kvm_gmem *gmem; struct inode *inode; struct file *file; int fd, err; fd = get_unused_fd_flags(0); if (fd < 0) return fd; gmem = kzalloc(sizeof(*gmem), GFP_KERNEL); if (!gmem) { err = -ENOMEM; goto err_fd; } file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, gmem, O_RDWR, NULL); if (IS_ERR(file)) { err = PTR_ERR(file); goto err_gmem; } file->f_flags |= O_LARGEFILE; inode = file->f_inode; WARN_ON(file->f_mapping != inode->i_mapping); inode->i_private = (void *)(unsigned long)flags; inode->i_op = &kvm_gmem_iops; inode->i_mapping->a_ops = &kvm_gmem_aops; inode->i_mode |= S_IFREG; inode->i_size = size; mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); mapping_set_inaccessible(inode->i_mapping); /* Unmovable mappings are supposed to be marked unevictable as well. */ WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping)); kvm_get_kvm(kvm); gmem->kvm = kvm; xa_init(&gmem->bindings); list_add(&gmem->entry, &inode->i_mapping->i_private_list); fd_install(fd, file); return fd; err_gmem: kfree(gmem); err_fd: put_unused_fd(fd); return err; } int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args) { loff_t size = args->size; u64 flags = args->flags; if (flags & ~kvm_gmem_get_supported_flags(kvm)) return -EINVAL; if (size <= 0 || !PAGE_ALIGNED(size)) return -EINVAL; return __kvm_gmem_create(kvm, size, flags); } int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, unsigned int fd, loff_t offset) { loff_t size = slot->npages << PAGE_SHIFT; unsigned long start, end; struct kvm_gmem *gmem; struct inode *inode; struct file *file; int r = -EINVAL; BUILD_BUG_ON(sizeof(gfn_t) != sizeof(slot->gmem.pgoff)); file = fget(fd); if (!file) return -EBADF; if (file->f_op != &kvm_gmem_fops) goto err; gmem = file->private_data; if (gmem->kvm != kvm) goto err; inode = file_inode(file); if (offset < 0 || !PAGE_ALIGNED(offset) || offset + size > i_size_read(inode)) goto err; filemap_invalidate_lock(inode->i_mapping); start = offset >> PAGE_SHIFT; end = start + slot->npages; if (!xa_empty(&gmem->bindings) && xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) { filemap_invalidate_unlock(inode->i_mapping); goto err; } /* * memslots of flag KVM_MEM_GUEST_MEMFD are immutable to change, so * kvm_gmem_bind() must occur on a new memslot. Because the memslot * is not visible yet, kvm_gmem_get_pfn() is guaranteed to see the file. */ WRITE_ONCE(slot->gmem.file, file); slot->gmem.pgoff = start; if (kvm_gmem_supports_mmap(inode)) slot->flags |= KVM_MEMSLOT_GMEM_ONLY; xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL); filemap_invalidate_unlock(inode->i_mapping); /* * Drop the reference to the file, even on success. The file pins KVM, * not the other way 'round. Active bindings are invalidated if the * file is closed before memslots are destroyed. */ r = 0; err: fput(file); return r; } void kvm_gmem_unbind(struct kvm_memory_slot *slot) { unsigned long start = slot->gmem.pgoff; unsigned long end = start + slot->npages; struct kvm_gmem *gmem; struct file *file; /* * Nothing to do if the underlying file was already closed (or is being * closed right now), kvm_gmem_release() invalidates all bindings. */ file = kvm_gmem_get_file(slot); if (!file) return; gmem = file->private_data; filemap_invalidate_lock(file->f_mapping); xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL); /* * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn() * cannot see this memslot. */ WRITE_ONCE(slot->gmem.file, NULL); filemap_invalidate_unlock(file->f_mapping); fput(file); } /* Returns a locked folio on success. */ static struct folio *__kvm_gmem_get_pfn(struct file *file, struct kvm_memory_slot *slot, pgoff_t index, kvm_pfn_t *pfn, bool *is_prepared, int *max_order) { struct file *gmem_file = READ_ONCE(slot->gmem.file); struct kvm_gmem *gmem = file->private_data; struct folio *folio; if (file != gmem_file) { WARN_ON_ONCE(gmem_file); return ERR_PTR(-EFAULT); } gmem = file->private_data; if (xa_load(&gmem->bindings, index) != slot) { WARN_ON_ONCE(xa_load(&gmem->bindings, index)); return ERR_PTR(-EIO); } folio = kvm_gmem_get_folio(file_inode(file), index); if (IS_ERR(folio)) return folio; if (folio_test_hwpoison(folio)) { folio_unlock(folio); folio_put(folio); return ERR_PTR(-EHWPOISON); } *pfn = folio_file_pfn(folio, index); if (max_order) *max_order = 0; *is_prepared = folio_test_uptodate(folio); return folio; } int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, kvm_pfn_t *pfn, struct page **page, int *max_order) { pgoff_t index = kvm_gmem_get_index(slot, gfn); struct file *file = kvm_gmem_get_file(slot); struct folio *folio; bool is_prepared = false; int r = 0; if (!file) return -EFAULT; folio = __kvm_gmem_get_pfn(file, slot, index, pfn, &is_prepared, max_order); if (IS_ERR(folio)) { r = PTR_ERR(folio); goto out; } if (!is_prepared) r = kvm_gmem_prepare_folio(kvm, slot, gfn, folio); folio_unlock(folio); if (!r) *page = folio_file_page(folio, index); else folio_put(folio); out: fput(file); return r; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn); #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_POPULATE long kvm_gmem_populate(struct kvm *kvm, gfn_t start_gfn, void __user *src, long npages, kvm_gmem_populate_cb post_populate, void *opaque) { struct file *file; struct kvm_memory_slot *slot; void __user *p; int ret = 0, max_order; long i; lockdep_assert_held(&kvm->slots_lock); if (WARN_ON_ONCE(npages <= 0)) return -EINVAL; slot = gfn_to_memslot(kvm, start_gfn); if (!kvm_slot_has_gmem(slot)) return -EINVAL; file = kvm_gmem_get_file(slot); if (!file) return -EFAULT; filemap_invalidate_lock(file->f_mapping); npages = min_t(ulong, slot->npages - (start_gfn - slot->base_gfn), npages); for (i = 0; i < npages; i += (1 << max_order)) { struct folio *folio; gfn_t gfn = start_gfn + i; pgoff_t index = kvm_gmem_get_index(slot, gfn); bool is_prepared = false; kvm_pfn_t pfn; if (signal_pending(current)) { ret = -EINTR; break; } folio = __kvm_gmem_get_pfn(file, slot, index, &pfn, &is_prepared, &max_order); if (IS_ERR(folio)) { ret = PTR_ERR(folio); break; } if (is_prepared) { folio_unlock(folio); folio_put(folio); ret = -EEXIST; break; } folio_unlock(folio); WARN_ON(!IS_ALIGNED(gfn, 1 << max_order) || (npages - i) < (1 << max_order)); ret = -EINVAL; while (!kvm_range_has_memory_attributes(kvm, gfn, gfn + (1 << max_order), KVM_MEMORY_ATTRIBUTE_PRIVATE, KVM_MEMORY_ATTRIBUTE_PRIVATE)) { if (!max_order) goto put_folio_and_exit; max_order--; } p = src ? src + i * PAGE_SIZE : NULL; ret = post_populate(kvm, gfn, pfn, p, max_order, opaque); if (!ret) kvm_gmem_mark_prepared(folio); put_folio_and_exit: folio_put(folio); if (ret) break; } filemap_invalidate_unlock(file->f_mapping); fput(file); return ret && !i ? ret : i; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_populate); #endif |
| 1178 717 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CGROUP_H #define _LINUX_CGROUP_H /* * cgroup interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/nodemask.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/cgroupstats.h> #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/kernfs.h> #include <linux/jump_label.h> #include <linux/types.h> #include <linux/notifier.h> #include <linux/ns_common.h> #include <linux/nsproxy.h> #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/kernel_stat.h> #include <linux/cgroup-defs.h> #include <linux/cgroup_namespace.h> struct kernel_clone_args; /* * All weight knobs on the default hierarchy should use the following min, * default and max values. The default value is the logarithmic center of * MIN and MAX and allows 100x to be expressed in both directions. */ #define CGROUP_WEIGHT_MIN 1 #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 #ifdef CONFIG_CGROUPS enum css_task_iter_flags { CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */ }; /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { struct cgroup_subsys *ss; unsigned int flags; struct list_head *cset_pos; struct list_head *cset_head; struct list_head *tcset_pos; struct list_head *tcset_head; struct list_head *task_pos; struct list_head *cur_tasks_head; struct css_set *cur_cset; struct css_set *cur_dcset; struct task_struct *cur_task; struct list_head iters_node; /* css_set->task_iters */ }; enum cgroup_lifetime_events { CGROUP_LIFETIME_ONLINE, CGROUP_LIFETIME_OFFLINE, }; extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; extern spinlock_t css_set_lock; extern struct blocking_notifier_head cgroup_lifetime_notifier; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; #include <linux/cgroup_subsys.h> #undef SUBSYS #define SUBSYS(_x) \ extern struct static_key_true _x ## _cgrp_subsys_enabled_key; \ extern struct static_key_true _x ## _cgrp_subsys_on_dfl_key; #include <linux/cgroup_subsys.h> #undef SUBSYS /** * cgroup_subsys_enabled - fast test on whether a subsys is enabled * @ss: subsystem in question */ #define cgroup_subsys_enabled(ss) \ static_branch_likely(&ss ## _enabled_key) /** * cgroup_subsys_on_dfl - fast test on whether a subsys is on default hierarchy * @ss: subsystem in question */ #define cgroup_subsys_on_dfl(ss) \ static_branch_likely(&ss ## _on_dfl_key) bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss); struct cgroup *cgroup_get_from_path(const char *path); struct cgroup *cgroup_get_from_fd(int fd); struct cgroup *cgroup_v1v2_get_from_fd(int fd); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); void cgroup_file_notify(struct cgroup_file *cfile); void cgroup_file_show(struct cgroup_file *cfile, bool show); int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); void cgroup_fork(struct task_struct *p); extern int cgroup_can_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void cgroup_cancel_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void cgroup_post_fork(struct task_struct *p, struct kernel_clone_args *kargs); void cgroup_exit(struct task_struct *p); void cgroup_release(struct task_struct *p); void cgroup_free(struct task_struct *p); int cgroup_init_early(void); int cgroup_init(void); int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v); /* * Iteration helpers and macros. */ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent); struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos); struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it); struct task_struct *css_task_iter_next(struct css_task_iter *it); void css_task_iter_end(struct css_task_iter *it); /** * css_for_each_child - iterate through children of a css * @pos: the css * to use as the loop cursor * @parent: css whose children to walk * * Walk @parent's children. Must be called under rcu_read_lock(). * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ #define css_for_each_child(pos, parent) \ for ((pos) = css_next_child(NULL, (parent)); (pos); \ (pos) = css_next_child((pos), (parent))) /** * css_for_each_descendant_pre - pre-order walk of a css's descendants * @pos: the css * to use as the loop cursor * @root: css whose descendants to walk * * Walk @root's descendants. @root is included in the iteration and the * first node to be visited. Must be called under rcu_read_lock(). * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * For example, the following guarantees that a descendant can't escape * state updates of its ancestors. * * my_online(@css) * { * Lock @css's parent and @css; * Inherit state from the parent; * Unlock both. * } * * my_update_state(@css) * { * css_for_each_descendant_pre(@pos, @css) { * Lock @pos; * if (@pos == @css) * Update @css's state; * else * Verify @pos is alive and inherit state from its parent; * Unlock @pos; * } * } * * As long as the inheriting step, including checking the parent state, is * enclosed inside @pos locking, double-locking the parent isn't necessary * while inheriting. The state update to the parent is guaranteed to be * visible by walking order and, as long as inheriting operations to the * same @pos are atomic to each other, multiple updates racing each other * still result in the correct state. It's guaranateed that at least one * inheritance happens for any css after the latest update to its parent. * * If checking parent's state requires locking the parent, each inheriting * iteration should lock and unlock both @pos->parent and @pos. * * Alternatively, a subsystem may choose to use a single global lock to * synchronize ->css_online() and ->css_offline() against tree-walking * operations. * * It is allowed to temporarily drop RCU read lock during iteration. The * caller is responsible for ensuring that @pos remains accessible until * the start of the next iteration by, for example, bumping the css refcnt. */ #define css_for_each_descendant_pre(pos, css) \ for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ (pos) = css_next_descendant_pre((pos), (css))) /** * css_for_each_descendant_post - post-order walk of a css's descendants * @pos: the css * to use as the loop cursor * @css: css whose descendants to walk * * Similar to css_for_each_descendant_pre() but performs post-order * traversal instead. @root is included in the iteration and the last * node to be visited. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. * * Note that the walk visibility guarantee example described in pre-order * walk doesn't apply the same to post-order walks. */ #define css_for_each_descendant_post(pos, css) \ for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ (pos) = css_next_descendant_post((pos), (css))) /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor * @dst_css: the destination css * @tset: taskset to iterate * * @tset may contain multiple tasks and they may belong to multiple * processes. * * On the v2 hierarchy, there may be tasks from multiple processes and they * may not share the source or destination csses. * * On traditional hierarchies, when there are multiple tasks in @tset, if a * task of a process is in @tset, all tasks of the process are in @tset. * Also, all are guaranteed to share the same source and destination csses. * * Iteration is not in any specific order. */ #define cgroup_taskset_for_each(task, dst_css, tset) \ for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ (task); \ (task) = cgroup_taskset_next((tset), &(dst_css))) /** * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor * @dst_css: the destination css * @tset: taskset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. */ #define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ (leader); \ (leader) = cgroup_taskset_next((tset), &(dst_css))) \ if ((leader) != (leader)->group_leader) \ ; \ else /* * Inline functions. */ #ifdef CONFIG_DEBUG_CGROUP_REF void css_get(struct cgroup_subsys_state *css); void css_get_many(struct cgroup_subsys_state *css, unsigned int n); bool css_tryget(struct cgroup_subsys_state *css); bool css_tryget_online(struct cgroup_subsys_state *css); void css_put(struct cgroup_subsys_state *css); void css_put_many(struct cgroup_subsys_state *css, unsigned int n); #else #define CGROUP_REF_FN_ATTRS static inline #define CGROUP_REF_EXPORT(fn) #include <linux/cgroup_refcnt.h> #endif static inline u64 cgroup_id(const struct cgroup *cgrp) { return cgrp->kn->id; } /** * css_is_dying - test whether the specified css is dying * @css: target css * * Test whether @css is in the process of offlining or already offline. In * most cases, ->css_online() and ->css_offline() callbacks should be * enough; however, the actual offline operations are RCU delayed and this * test returns %true also when @css is scheduled to be offlined. * * This is useful, for example, when the use case requires synchronous * behavior with respect to cgroup removal. cgroup removal schedules css * offlining but the css can seem alive while the operation is being * delayed. If the delay affects user visible semantics, this test can be * used to resolve the situation. */ static inline bool css_is_dying(struct cgroup_subsys_state *css) { return css->flags & CSS_DYING; } static inline bool css_is_online(struct cgroup_subsys_state *css) { return css->flags & CSS_ONLINE; } static inline bool css_is_self(struct cgroup_subsys_state *css) { if (css == &css->cgroup->self) { /* cgroup::self should not have subsystem association */ WARN_ON(css->ss != NULL); return true; } return false; } static inline void cgroup_get(struct cgroup *cgrp) { css_get(&cgrp->self); } static inline bool cgroup_tryget(struct cgroup *cgrp) { return css_tryget(&cgrp->self); } static inline void cgroup_put(struct cgroup *cgrp) { css_put(&cgrp->self); } extern struct mutex cgroup_mutex; static inline void cgroup_lock(void) { mutex_lock(&cgroup_mutex); } static inline void cgroup_unlock(void) { mutex_unlock(&cgroup_mutex); } /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for * @__c: extra condition expression to be passed to rcu_dereference_check() * * A task's css_set is RCU protected, initialized and exited while holding * task_lock(), and can only be modified while holding both cgroup_mutex * and task_lock() while the task is alive. This macro verifies that the * caller is inside proper critical section and returns @task's css_set. * * The caller can also specify additional allowed conditions via @__c, such * as locks used during the cgroup_subsys::attach() methods. */ #ifdef CONFIG_PROVE_RCU #define task_css_set_check(task, __c) \ rcu_dereference_check((task)->cgroups, \ rcu_read_lock_sched_held() || \ lockdep_is_held(&cgroup_mutex) || \ lockdep_is_held(&css_set_lock) || \ ((task)->flags & PF_EXITING) || (__c)) #else #define task_css_set_check(task, __c) \ rcu_dereference((task)->cgroups) #endif /** * task_css_check - obtain css for (task, subsys) w/ extra access conds * @task: the target task * @subsys_id: the target subsystem ID * @__c: extra condition expression to be passed to rcu_dereference_check() * * Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The * synchronization rules are the same as task_css_set_check(). */ #define task_css_check(task, subsys_id, __c) \ task_css_set_check((task), (__c))->subsys[(subsys_id)] /** * task_css_set - obtain a task's css_set * @task: the task to obtain css_set for * * See task_css_set_check(). */ static inline struct css_set *task_css_set(struct task_struct *task) { return task_css_set_check(task, false); } /** * task_css - obtain css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * * See task_css_check(). */ static inline struct cgroup_subsys_state *task_css(struct task_struct *task, int subsys_id) { return task_css_check(task, subsys_id, false); } /** * task_get_css - find and get the css for (task, subsys) * @task: the target task * @subsys_id: the target subsystem ID * * Find the css for the (@task, @subsys_id) combination, increment a * reference on and return it. This function is guaranteed to return a * valid css. The returned css may already have been offlined. */ static inline struct cgroup_subsys_state * task_get_css(struct task_struct *task, int subsys_id) { struct cgroup_subsys_state *css; rcu_read_lock(); while (true) { css = task_css(task, subsys_id); /* * Can't use css_tryget_online() here. A task which has * PF_EXITING set may stay associated with an offline css. * If such task calls this function, css_tryget_online() * will keep failing. */ if (likely(css_tryget(css))) break; cpu_relax(); } rcu_read_unlock(); return css; } /** * task_css_is_root - test whether a task belongs to the root css * @task: the target task * @subsys_id: the target subsystem ID * * Test whether @task belongs to the root css on the specified subsystem. * May be invoked in any context. */ static inline bool task_css_is_root(struct task_struct *task, int subsys_id) { return task_css_check(task, subsys_id, true) == init_css_set.subsys[subsys_id]; } static inline struct cgroup *task_cgroup(struct task_struct *task, int subsys_id) { return task_css(task, subsys_id)->cgroup; } static inline struct cgroup *task_dfl_cgroup(struct task_struct *task) { return task_css_set(task)->dfl_cgrp; } static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { struct cgroup_subsys_state *parent_css = cgrp->self.parent; if (parent_css) return container_of(parent_css, struct cgroup, self); return NULL; } /** * cgroup_is_descendant - test ancestry * @cgrp: the cgroup to be tested * @ancestor: possible ancestor of @cgrp * * Test whether @cgrp is a descendant of @ancestor. It also returns %true * if @cgrp == @ancestor. This function is safe to call as long as @cgrp * and @ancestor are accessible. */ static inline bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor) { if (cgrp->root != ancestor->root || cgrp->level < ancestor->level) return false; return cgrp->ancestors[ancestor->level] == ancestor; } /** * cgroup_ancestor - find ancestor of cgroup * @cgrp: cgroup to find ancestor of * @ancestor_level: level of ancestor to find starting from root * * Find ancestor of cgroup at specified level starting from root if it exists * and return pointer to it. Return NULL if @cgrp doesn't have ancestor at * @ancestor_level. * * This function is safe to call as long as @cgrp is accessible. */ static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp, int ancestor_level) { if (ancestor_level < 0 || ancestor_level > cgrp->level) return NULL; return cgrp->ancestors[ancestor_level]; } /** * task_under_cgroup_hierarchy - test task's membership of cgroup ancestry * @task: the task to be tested * @ancestor: possible ancestor of @task's cgroup * * Tests whether @task's default cgroup hierarchy is a descendant of @ancestor. * It follows all the same rules as cgroup_is_descendant, and only applies * to the default hierarchy. */ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { struct css_set *cset = task_css_set(task); return cgroup_is_descendant(cset->dfl_cgrp, ancestor); } /* no synchronization, the result can only be used as a hint */ static inline bool cgroup_is_populated(struct cgroup *cgrp) { return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children + cgrp->nr_populated_threaded_children; } /* returns ino associated with a cgroup */ static inline ino_t cgroup_ino(struct cgroup *cgrp) { return kernfs_ino(cgrp->kn); } /* cft/css accessors for cftype->write() operation */ static inline struct cftype *of_cft(struct kernfs_open_file *of) { return of->kn->priv; } struct cgroup_subsys_state *of_css(struct kernfs_open_file *of); /* cft/css accessors for cftype->seq_*() operations */ static inline struct cftype *seq_cft(struct seq_file *seq) { return of_cft(seq->private); } static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq) { return of_css(seq->private); } /* * Name / path handling functions. All are thin wrappers around the kernfs * counterparts and can be called under any context. */ static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen) { return kernfs_name(cgrp->kn, buf, buflen); } static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen) { return kernfs_path(cgrp->kn, buf, buflen); } static inline void pr_cont_cgroup_name(struct cgroup *cgrp) { pr_cont_kernfs_name(cgrp->kn); } static inline void pr_cont_cgroup_path(struct cgroup *cgrp) { pr_cont_kernfs_path(cgrp->kn); } bool cgroup_psi_enabled(void); static inline void cgroup_init_kthreadd(void) { /* * kthreadd is inherited by all kthreads, keep it in the root so * that the new kthreads are guaranteed to stay in the root until * initialization is finished. */ current->no_cgroup_migration = 1; } static inline void cgroup_kthread_ready(void) { /* * This kthread finished initialization. The creator should have * set PF_NO_SETAFFINITY if this kthread should stay in the root. */ current->no_cgroup_migration = 0; } void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); struct cgroup *__cgroup_get_from_id(u64 id); struct cgroup *cgroup_get_from_id(u64 id); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; struct cgroup; static inline u64 cgroup_id(const struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} static inline void cgroup_lock(void) {} static inline void cgroup_unlock(void) {} static inline int cgroup_attach_task_all(struct task_struct *from, struct task_struct *t) { return 0; } static inline int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { return -EINVAL; } static inline void cgroup_fork(struct task_struct *p) {} static inline int cgroup_can_fork(struct task_struct *p, struct kernel_clone_args *kargs) { return 0; } static inline void cgroup_cancel_fork(struct task_struct *p, struct kernel_clone_args *kargs) {} static inline void cgroup_post_fork(struct task_struct *p, struct kernel_clone_args *kargs) {} static inline void cgroup_exit(struct task_struct *p) {} static inline void cgroup_release(struct task_struct *p) {} static inline void cgroup_free(struct task_struct *p) {} static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { return NULL; } static inline bool cgroup_psi_enabled(void) { return false; } static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { return true; } static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) {} #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS /* * cgroup scalable recursive statistics. */ void css_rstat_updated(struct cgroup_subsys_state *css, int cpu); void css_rstat_flush(struct cgroup_subsys_state *css); /* * Basic resource stats. */ #ifdef CONFIG_CGROUP_CPUACCT void cpuacct_charge(struct task_struct *tsk, u64 cputime); void cpuacct_account_field(struct task_struct *tsk, int index, u64 val); #else static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} static inline void cpuacct_account_field(struct task_struct *tsk, int index, u64 val) {} #endif void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec); void __cgroup_account_cputime_field(struct cgroup *cgrp, enum cpu_usage_stat index, u64 delta_exec); static inline void cgroup_account_cputime(struct task_struct *task, u64 delta_exec) { struct cgroup *cgrp; cpuacct_charge(task, delta_exec); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime(cgrp, delta_exec); } static inline void cgroup_account_cputime_field(struct task_struct *task, enum cpu_usage_stat index, u64 delta_exec) { struct cgroup *cgrp; cpuacct_account_field(task, index, delta_exec); cgrp = task_dfl_cgroup(task); if (cgroup_parent(cgrp)) __cgroup_account_cputime_field(cgrp, index, delta_exec); } #else /* CONFIG_CGROUPS */ static inline void cgroup_account_cputime(struct task_struct *task, u64 delta_exec) {} static inline void cgroup_account_cputime_field(struct task_struct *task, enum cpu_usage_stat index, u64 delta_exec) {} #endif /* CONFIG_CGROUPS */ /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA void cgroup_sk_alloc(struct sock_cgroup_data *skcd); void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) { return skcd->cgroup; } #else /* CONFIG_CGROUP_DATA */ static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {} static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {} #endif /* CONFIG_CGROUP_DATA */ #ifdef CONFIG_CGROUPS void cgroup_enter_frozen(void); void cgroup_leave_frozen(bool always_leave); void cgroup_update_frozen(struct cgroup *cgrp); void cgroup_freeze(struct cgroup *cgrp, bool freeze); void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src, struct cgroup *dst); static inline bool cgroup_task_frozen(struct task_struct *task) { return task->frozen; } #else /* !CONFIG_CGROUPS */ static inline void cgroup_enter_frozen(void) { } static inline void cgroup_leave_frozen(bool always_leave) { } static inline bool cgroup_task_frozen(struct task_struct *task) { return false; } #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUP_BPF static inline void cgroup_bpf_get(struct cgroup *cgrp) { percpu_ref_get(&cgrp->bpf.refcnt); } static inline void cgroup_bpf_put(struct cgroup *cgrp) { percpu_ref_put(&cgrp->bpf.refcnt); } #else /* CONFIG_CGROUP_BPF */ static inline void cgroup_bpf_get(struct cgroup *cgrp) {} static inline void cgroup_bpf_put(struct cgroup *cgrp) {} #endif /* CONFIG_CGROUP_BPF */ struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id); struct cgroup_of_peak *of_peak(struct kernfs_open_file *of); #endif /* _LINUX_CGROUP_H */ |
| 303 302 102 19 459 459 303 303 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #ifndef __ARM64_KVM_MMU_H__ #define __ARM64_KVM_MMU_H__ #include <asm/page.h> #include <asm/memory.h> #include <asm/mmu.h> #include <asm/cpufeature.h> /* * As ARMv8.0 only has the TTBR0_EL2 register, we cannot express * "negative" addresses. This makes it impossible to directly share * mappings with the kernel. * * Instead, give the HYP mode its own VA region at a fixed offset from * the kernel by just masking the top bits (which are all ones for a * kernel address). We need to find out how many bits to mask. * * We want to build a set of page tables that cover both parts of the * idmap (the trampoline page used to initialize EL2), and our normal * runtime VA space, at the same time. * * Given that the kernel uses VA_BITS for its entire address space, * and that half of that space (VA_BITS - 1) is used for the linear * mapping, we can also limit the EL2 space to (VA_BITS - 1). * * The main question is "Within the VA_BITS space, does EL2 use the * top or the bottom half of that space to shadow the kernel's linear * mapping?". As we need to idmap the trampoline page, this is * determined by the range in which this page lives. * * If the page is in the bottom half, we have to use the top half. If * the page is in the top half, we have to use the bottom half: * * T = __pa_symbol(__hyp_idmap_text_start) * if (T & BIT(VA_BITS - 1)) * HYP_VA_MIN = 0 //idmap in upper half * else * HYP_VA_MIN = 1 << (VA_BITS - 1) * HYP_VA_MAX = HYP_VA_MIN + (1 << (VA_BITS - 1)) - 1 * * When using VHE, there are no separate hyp mappings and all KVM * functionality is already mapped as part of the main kernel * mappings, and none of this applies in that case. */ #ifdef __ASSEMBLY__ #include <asm/alternative.h> /* * Convert a hypervisor VA to a PA * reg: hypervisor address to be converted in place * tmp: temporary register */ .macro hyp_pa reg, tmp ldr_l \tmp, hyp_physvirt_offset add \reg, \reg, \tmp .endm /* * Convert a hypervisor VA to a kernel image address * reg: hypervisor address to be converted in place * tmp: temporary register * * The actual code generation takes place in kvm_get_kimage_voffset, and * the instructions below are only there to reserve the space and * perform the register allocation (kvm_get_kimage_voffset uses the * specific registers encoded in the instructions). */ .macro hyp_kimg_va reg, tmp /* Convert hyp VA -> PA. */ hyp_pa \reg, \tmp /* Load kimage_voffset. */ alternative_cb ARM64_ALWAYS_SYSTEM, kvm_get_kimage_voffset movz \tmp, #0 movk \tmp, #0, lsl #16 movk \tmp, #0, lsl #32 movk \tmp, #0, lsl #48 alternative_cb_end /* Convert PA -> kimg VA. */ add \reg, \reg, \tmp .endm #else #include <linux/pgtable.h> #include <asm/pgalloc.h> #include <asm/cache.h> #include <asm/cacheflush.h> #include <asm/mmu_context.h> #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> #include <asm/kvm_nested.h> void kvm_update_va_mask(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst); void kvm_compute_layout(void); void kvm_apply_hyp_relocations(void); #define __hyp_pa(x) (((phys_addr_t)(x)) + hyp_physvirt_offset) /* * Convert a kernel VA into a HYP VA. * * Can be called from hyp or non-hyp context. * * The actual code generation takes place in kvm_update_va_mask(), and * the instructions below are only there to reserve the space and * perform the register allocation (kvm_update_va_mask() uses the * specific registers encoded in the instructions). */ static __always_inline unsigned long __kern_hyp_va(unsigned long v) { /* * This #ifndef is an optimisation for when this is called from VHE hyp * context. When called from a VHE non-hyp context, kvm_update_va_mask() will * replace the instructions with `nop`s. */ #ifndef __KVM_VHE_HYPERVISOR__ asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n" /* mask with va_mask */ "ror %0, %0, #1\n" /* rotate to the first tag bit */ "add %0, %0, #0\n" /* insert the low 12 bits of the tag */ "add %0, %0, #0, lsl 12\n" /* insert the top 12 bits of the tag */ "ror %0, %0, #63\n", /* rotate back */ ARM64_ALWAYS_SYSTEM, kvm_update_va_mask) : "+r" (v)); #endif return v; } #define kern_hyp_va(v) ((typeof(v))(__kern_hyp_va((unsigned long)(v)))) extern u32 __hyp_va_bits; /* * We currently support using a VM-specified IPA size. For backward * compatibility, the default IPA size is fixed to 40bits. */ #define KVM_PHYS_SHIFT (40) #define kvm_phys_shift(mmu) VTCR_EL2_IPA((mmu)->vtcr) #define kvm_phys_size(mmu) (_AC(1, ULL) << kvm_phys_shift(mmu)) #define kvm_phys_mask(mmu) (kvm_phys_size(mmu) - _AC(1, ULL)) #include <asm/kvm_pgtable.h> #include <asm/stage2_pgtable.h> int kvm_share_hyp(void *from, void *to); void kvm_unshare_hyp(void *from, void *to); int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot); int __create_hyp_mappings(unsigned long start, unsigned long size, unsigned long phys, enum kvm_pgtable_prot prot); int hyp_alloc_private_va_range(size_t size, unsigned long *haddr); int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, void __iomem **kaddr, void __iomem **haddr); int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, void **haddr); int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr); void __init free_hyp_pgds(void); void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size, bool may_block); void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end); void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end); void stage2_unmap_vm(struct kvm *kvm); int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type); void kvm_uninit_stage2_mmu(struct kvm *kvm); void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu); int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, phys_addr_t pa, unsigned long size, bool writable); int kvm_handle_guest_sea(struct kvm_vcpu *vcpu); int kvm_handle_guest_abort(struct kvm_vcpu *vcpu); phys_addr_t kvm_mmu_get_httbr(void); phys_addr_t kvm_get_idmap_vector(void); int __init kvm_mmu_init(u32 *hyp_va_bits); static inline void *__kvm_vector_slot2addr(void *base, enum arm64_hyp_spectre_vector slot) { int idx = slot - (slot != HYP_VECTOR_DIRECT); return base + (idx * SZ_2K); } struct kvm; #define kvm_flush_dcache_to_poc(a,l) \ dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l)) static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) { u64 cache_bits = SCTLR_ELx_M | SCTLR_ELx_C; int reg; if (vcpu_is_el2(vcpu)) reg = SCTLR_EL2; else reg = SCTLR_EL1; return (vcpu_read_sys_reg(vcpu, reg) & cache_bits) == cache_bits; } static inline void __clean_dcache_guest_page(void *va, size_t size) { /* * With FWB, we ensure that the guest always accesses memory using * cacheable attributes, and we don't have to clean to PoC when * faulting in pages. Furthermore, FWB implies IDC, so cleaning to * PoU is not required either in this case. */ if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) return; kvm_flush_dcache_to_poc(va, size); } static inline size_t __invalidate_icache_max_range(void) { u8 iminline; u64 ctr; asm volatile(ALTERNATIVE_CB("movz %0, #0\n" "movk %0, #0, lsl #16\n" "movk %0, #0, lsl #32\n" "movk %0, #0, lsl #48\n", ARM64_ALWAYS_SYSTEM, kvm_compute_final_ctr_el0) : "=r" (ctr)); iminline = SYS_FIELD_GET(CTR_EL0, IminLine, ctr) + 2; return MAX_DVM_OPS << iminline; } static inline void __invalidate_icache_guest_page(void *va, size_t size) { /* * Blow the whole I-cache if it is aliasing (i.e. VIPT) or the * invalidation range exceeds our arbitrary limit on invadations by * cache line. */ if (icache_is_aliasing() || size > __invalidate_icache_max_range()) icache_inval_all_pou(); else icache_inval_pou((unsigned long)va, (unsigned long)va + size); } void kvm_set_way_flush(struct kvm_vcpu *vcpu); void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled); static inline unsigned int kvm_get_vmid_bits(void) { int reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); return get_vmid_bits(reg); } /* * We are not in the kvm->srcu critical section most of the time, so we take * the SRCU read lock here. Since we copy the data from the user page, we * can immediately drop the lock again. */ static inline int kvm_read_guest_lock(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len) { int srcu_idx = srcu_read_lock(&kvm->srcu); int ret = kvm_read_guest(kvm, gpa, data, len); srcu_read_unlock(&kvm->srcu, srcu_idx); return ret; } static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len) { int srcu_idx = srcu_read_lock(&kvm->srcu); int ret = kvm_write_guest(kvm, gpa, data, len); srcu_read_unlock(&kvm->srcu, srcu_idx); return ret; } #define kvm_phys_to_vttbr(addr) phys_to_ttbr(addr) /* * When this is (directly or indirectly) used on the TLB invalidation * path, we rely on a previously issued DSB so that page table updates * and VMID reads are correctly ordered. */ static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu) { struct kvm_vmid *vmid = &mmu->vmid; u64 vmid_field, baddr; u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0; baddr = mmu->pgd_phys; vmid_field = atomic64_read(&vmid->id) << VTTBR_VMID_SHIFT; vmid_field &= VTTBR_VMID_MASK(kvm_arm_vmid_bits); return kvm_phys_to_vttbr(baddr) | vmid_field | cnp; } /* * Must be called from hyp code running at EL2 with an updated VTTBR * and interrupts disabled. */ static __always_inline void __load_stage2(struct kvm_s2_mmu *mmu, struct kvm_arch *arch) { write_sysreg(mmu->vtcr, vtcr_el2); write_sysreg(kvm_get_vttbr(mmu), vttbr_el2); /* * ARM errata 1165522 and 1530923 require the actual execution of the * above before we can switch to the EL1/EL0 translation regime used by * the guest. */ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); } static inline struct kvm *kvm_s2_mmu_to_kvm(struct kvm_s2_mmu *mmu) { return container_of(mmu->arch, struct kvm, arch); } static inline u64 get_vmid(u64 vttbr) { return (vttbr & VTTBR_VMID_MASK(kvm_get_vmid_bits())) >> VTTBR_VMID_SHIFT; } static inline bool kvm_s2_mmu_valid(struct kvm_s2_mmu *mmu) { return !(mmu->tlb_vttbr & VTTBR_CNP_BIT); } static inline bool kvm_is_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu) { /* * Be careful, mmu may not be fully initialised so do look at * *any* of its fields. */ return &kvm->arch.mmu != mmu; } static inline void kvm_fault_lock(struct kvm *kvm) { if (is_protected_kvm_enabled()) write_lock(&kvm->mmu_lock); else read_lock(&kvm->mmu_lock); } static inline void kvm_fault_unlock(struct kvm *kvm) { if (is_protected_kvm_enabled()) write_unlock(&kvm->mmu_lock); else read_unlock(&kvm->mmu_lock); } /* * ARM64 KVM relies on a simple conversion from physaddr to a kernel * virtual address (KVA) when it does cache maintenance as the CMO * instructions work on virtual addresses. This is incompatible with * VM_PFNMAP VMAs which may not have a kernel direct mapping to a * virtual address. * * With S2FWB and CACHE DIC features, KVM need not do cache flushing * and CMOs are NOP'd. This has the effect of no longer requiring a * KVA for addresses mapped into the S2. The presence of these features * are thus necessary to support cacheable S2 mapping of VM_PFNMAP. */ static inline bool kvm_supports_cacheable_pfnmap(void) { return cpus_have_final_cap(ARM64_HAS_STAGE2_FWB) && cpus_have_final_cap(ARM64_HAS_CACHE_DIC); } #ifdef CONFIG_PTDUMP_STAGE2_DEBUGFS void kvm_s2_ptdump_create_debugfs(struct kvm *kvm); #else static inline void kvm_s2_ptdump_create_debugfs(struct kvm *kvm) {} #endif /* CONFIG_PTDUMP_STAGE2_DEBUGFS */ #endif /* __ASSEMBLY__ */ #endif /* __ARM64_KVM_MMU_H__ */ |
| 435 435 346 324 96 48 224 224 5 257 118 257 4 60 4 56 291 96 324 324 30 279 279 39 222 118 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_NOTIFY_H #define _LINUX_FS_NOTIFY_H /* * include/linux/fsnotify.h - generic hooks for filesystem notification, to * reduce in-source duplication from both dnotify and inotify. * * We don't compile any of this away in some complicated menagerie of ifdefs. * Instead, we rely on the code inside to optimize away as needed. * * (C) Copyright 2005 Robert Love */ #include <linux/fsnotify_backend.h> #include <linux/audit.h> #include <linux/slab.h> #include <linux/bug.h> /* Are there any inode/mount/sb objects watched with priority prio or above? */ static inline bool fsnotify_sb_has_priority_watchers(struct super_block *sb, int prio) { struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); /* Were any marks ever added to any object on this sb? */ if (!sbinfo) return false; return atomic_long_read(&sbinfo->watched_objects[prio]); } /* Are there any inode/mount/sb objects that are being watched at all? */ static inline bool fsnotify_sb_has_watchers(struct super_block *sb) { return fsnotify_sb_has_priority_watchers(sb, 0); } /* * Notify this @dir inode about a change in a child directory entry. * The directory entry may have turned positive or negative or its inode may * have changed (i.e. renamed over). * * Unlike fsnotify_parent(), the event will be reported regardless of the * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ static inline int fsnotify_name(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, u32 cookie) { if (!fsnotify_sb_has_watchers(dir->i_sb)) return 0; return fsnotify(mask, data, data_type, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) { if (!fsnotify_sb_has_watchers(inode->i_sb)) return; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify(mask, inode, FSNOTIFY_EVENT_INODE, NULL, NULL, inode, 0); } /* Notify this dentry's parent about a child's events. */ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { struct inode *inode = d_inode(dentry); if (!fsnotify_sb_has_watchers(inode->i_sb)) return 0; if (S_ISDIR(inode->i_mode)) { mask |= FS_ISDIR; /* sb/mount marks are not interested in name of directory */ if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED)) goto notify_child; } /* disconnected dentry cannot notify parent */ if (IS_ROOT(dentry)) goto notify_child; return __fsnotify_parent(dentry, mask, data, data_type); notify_child: return fsnotify(mask, data, data_type, NULL, NULL, inode, 0); } /* * Simple wrappers to consolidate calls to fsnotify_parent() when an event * is on a file/dentry. */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } static inline int fsnotify_path(const struct path *path, __u32 mask) { return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } static inline int fsnotify_file(struct file *file, __u32 mask) { /* * FMODE_NONOTIFY are fds generated by fanotify itself which should not * generate new events. We also don't want to generate events for * FMODE_PATH fds (involves open & close events) as they are just * handle creation / destruction events and not "real" file events. */ if (FMODE_FSNOTIFY_NONE(file->f_mode)) return 0; return fsnotify_path(&file->f_path, mask); } #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS int fsnotify_open_perm_and_set_mode(struct file *file); /* * fsnotify_file_area_perm - permission hook before access to file range */ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { /* * filesystem may be modified in the context of permission events * (e.g. by HSM filling a file on access), so sb freeze protection * must not be held. */ lockdep_assert_once(file_write_not_started(file)); if (!(perm_mask & (MAY_READ | MAY_WRITE | MAY_ACCESS))) return 0; /* * read()/write() and other types of access generate pre-content events. */ if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) { int ret = fsnotify_pre_content(&file->f_path, ppos, count); if (ret) return ret; } if (!(perm_mask & MAY_READ) || likely(!FMODE_FSNOTIFY_ACCESS_PERM(file->f_mode))) return 0; /* * read() also generates the legacy FS_ACCESS_PERM event, so content * scanners can inspect the content filled by pre-content event. */ return fsnotify_path(&file->f_path, FS_ACCESS_PERM); } /* * fsnotify_mmap_perm - permission hook before mmap of file range */ static inline int fsnotify_mmap_perm(struct file *file, int prot, const loff_t off, size_t len) { /* * mmap() generates only pre-content events. */ if (!file || likely(!FMODE_FSNOTIFY_HSM(file->f_mode))) return 0; return fsnotify_pre_content(&file->f_path, &off, len); } /* * fsnotify_truncate_perm - permission hook before file truncate */ static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) { struct inode *inode = d_inode(path->dentry); if (!(inode->i_sb->s_iflags & SB_I_ALLOW_HSM) || !fsnotify_sb_has_priority_watchers(inode->i_sb, FSNOTIFY_PRIO_PRE_CONTENT)) return 0; return fsnotify_pre_content(path, &length, 0); } /* * fsnotify_file_perm - permission hook before file access (unknown range) */ static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return fsnotify_file_area_perm(file, perm_mask, NULL, 0); } #else static inline int fsnotify_open_perm_and_set_mode(struct file *file) { return 0; } static inline int fsnotify_file_area_perm(struct file *file, int perm_mask, const loff_t *ppos, size_t count) { return 0; } static inline int fsnotify_mmap_perm(struct file *file, int prot, const loff_t off, size_t len) { return 0; } static inline int fsnotify_truncate_perm(const struct path *path, loff_t length) { return 0; } static inline int fsnotify_file_perm(struct file *file, int perm_mask) { return 0; } #endif /* * fsnotify_link_count - inode's link count changed */ static inline void fsnotify_link_count(struct inode *inode) { fsnotify_inode(inode, FS_ATTRIB); } /* * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir */ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, const struct qstr *old_name, int isdir, struct inode *target, struct dentry *moved) { struct inode *source = moved->d_inode; u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; __u32 rename_mask = FS_RENAME; const struct qstr *new_name = &moved->d_name; if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; rename_mask |= FS_ISDIR; } /* Event with information about both old and new parent+name */ fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY, old_dir, old_name, 0); fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_dir, old_name, fs_cookie); fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_dir, new_name, fs_cookie); if (target) fsnotify_link_count(target); fsnotify_inode(source, FS_MOVE_SELF); audit_inode_child(new_dir, moved, AUDIT_TYPE_CHILD_CREATE); } /* * fsnotify_inode_delete - and inode is being evicted from cache, clean up is needed */ static inline void fsnotify_inode_delete(struct inode *inode) { __fsnotify_inode_delete(inode); } /* * fsnotify_vfsmount_delete - a vfsmount is being destroyed, clean up is needed */ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt) { __fsnotify_vfsmount_delete(mnt); } static inline void fsnotify_mntns_delete(struct mnt_namespace *mntns) { __fsnotify_mntns_delete(mntns); } /* * fsnotify_inoderemove - an inode is going away */ static inline void fsnotify_inoderemove(struct inode *inode) { fsnotify_inode(inode, FS_DELETE_SELF); __fsnotify_inode_delete(inode); } /* * fsnotify_create - 'name' was linked in * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_create(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory * * Caller must make sure that new_dentry->d_name is stable. * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry) { fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE, dir, &new_dentry->d_name, 0); } /* * fsnotify_delete - @dentry was unlinked and unhashed * * Caller must make sure that dentry->d_name is stable. * * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode * as this may be called after d_delete() and old_dentry may be negative. */ static inline void fsnotify_delete(struct inode *dir, struct inode *inode, struct dentry *dentry) { __u32 mask = FS_DELETE; if (S_ISDIR(inode->i_mode)) mask |= FS_ISDIR; fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, 0); } /** * d_delete_notify - delete a dentry and call fsnotify_delete() * @dentry: The dentry to delete * * This helper is used to guaranty that the unlinked inode cannot be found * by lookup of this name after fsnotify_delete() event has been delivered. */ static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); ihold(inode); d_delete(dentry); fsnotify_delete(dir, inode, dentry); iput(inode); } /* * fsnotify_unlink - 'name' was unlinked * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_mkdir - directory 'name' was created * * Caller must make sure that dentry->d_name is stable. * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate * ->d_inode later */ static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) { audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR); } /* * fsnotify_rmdir - directory 'name' was removed * * Caller must make sure that dentry->d_name is stable. */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { if (WARN_ON_ONCE(d_is_negative(dentry))) return; fsnotify_delete(dir, d_inode(dentry), dentry); } /* * fsnotify_access - file was read */ static inline void fsnotify_access(struct file *file) { fsnotify_file(file, FS_ACCESS); } /* * fsnotify_modify - file was modified */ static inline void fsnotify_modify(struct file *file) { fsnotify_file(file, FS_MODIFY); } /* * fsnotify_open - file was opened */ static inline void fsnotify_open(struct file *file) { __u32 mask = FS_OPEN; if (file->f_flags & __FMODE_EXEC) mask |= FS_OPEN_EXEC; fsnotify_file(file, mask); } /* * fsnotify_close - file was closed */ static inline void fsnotify_close(struct file *file) { __u32 mask = (file->f_mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE; fsnotify_file(file, mask); } /* * fsnotify_xattr - extended attributes were changed */ static inline void fsnotify_xattr(struct dentry *dentry) { fsnotify_dentry(dentry, FS_ATTRIB); } /* * fsnotify_change - notify_change event. file was modified and/or metadata * was changed. */ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) { __u32 mask = 0; if (ia_valid & ATTR_UID) mask |= FS_ATTRIB; if (ia_valid & ATTR_GID) mask |= FS_ATTRIB; if (ia_valid & ATTR_SIZE) mask |= FS_MODIFY; /* both times implies a utime(s) call */ if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME)) mask |= FS_ATTRIB; else if (ia_valid & ATTR_ATIME) mask |= FS_ACCESS; else if (ia_valid & ATTR_MTIME) mask |= FS_MODIFY; if (ia_valid & ATTR_MODE) mask |= FS_ATTRIB; if (mask) fsnotify_dentry(dentry, mask); } static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, int error) { struct fs_error_report report = { .error = error, .inode = inode, .sb = sb, }; return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, NULL, NULL, NULL, 0); } static inline void fsnotify_mnt_attach(struct mnt_namespace *ns, struct vfsmount *mnt) { fsnotify_mnt(FS_MNT_ATTACH, ns, mnt); } static inline void fsnotify_mnt_detach(struct mnt_namespace *ns, struct vfsmount *mnt) { fsnotify_mnt(FS_MNT_DETACH, ns, mnt); } static inline void fsnotify_mnt_move(struct mnt_namespace *ns, struct vfsmount *mnt) { fsnotify_mnt(FS_MNT_MOVE, ns, mnt); } #endif /* _LINUX_FS_NOTIFY_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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> */ #ifndef __IPVLAN_H #define __IPVLAN_H #include <linux/kernel.h> #include <linux/types.h> #include <linux/module.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/if_link.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <linux/inetdevice.h> #include <linux/netfilter.h> #include <net/ip.h> #include <net/ip6_route.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/route.h> #include <net/addrconf.h> #include <net/l3mdev.h> #define IPVLAN_DRV "ipvlan" #define IPV_DRV_VER "0.1" #define IPVLAN_HASH_SIZE (1 << BITS_PER_BYTE) #define IPVLAN_HASH_MASK (IPVLAN_HASH_SIZE - 1) #define IPVLAN_MAC_FILTER_BITS 8 #define IPVLAN_MAC_FILTER_SIZE (1 << IPVLAN_MAC_FILTER_BITS) #define IPVLAN_MAC_FILTER_MASK (IPVLAN_MAC_FILTER_SIZE - 1) #define IPVLAN_QBACKLOG_LIMIT 1000 typedef enum { IPVL_IPV6 = 0, IPVL_ICMPV6, IPVL_IPV4, IPVL_ARP, } ipvl_hdr_type; struct ipvl_pcpu_stats { u64_stats_t rx_pkts; u64_stats_t rx_bytes; u64_stats_t rx_mcast; u64_stats_t tx_pkts; u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errs; u32 tx_drps; }; struct ipvl_port; struct ipvl_dev { struct net_device *dev; struct list_head pnode; struct ipvl_port *port; struct net_device *phy_dev; struct list_head addrs; struct ipvl_pcpu_stats __percpu *pcpu_stats; DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE); netdev_features_t sfeatures; u32 msg_enable; spinlock_t addrs_lock; }; struct ipvl_addr { struct ipvl_dev *master; /* Back pointer to master */ union { struct in6_addr ip6; /* IPv6 address on logical interface */ struct in_addr ip4; /* IPv4 address on logical interface */ } ipu; #define ip6addr ipu.ip6 #define ip4addr ipu.ip4 struct hlist_node hlnode; /* Hash-table linkage */ struct list_head anode; /* logical-interface linkage */ ipvl_hdr_type atype; struct rcu_head rcu; }; struct ipvl_port { struct net_device *dev; possible_net_t pnet; struct hlist_head hlhead[IPVLAN_HASH_SIZE]; struct list_head ipvlans; u16 mode; u16 flags; u16 dev_id_start; struct work_struct wq; struct sk_buff_head backlog; int count; struct ida ida; netdevice_tracker dev_tracker; }; struct ipvl_skb_cb { bool tx_pkt; }; #define IPVL_SKB_CB(_skb) ((struct ipvl_skb_cb *)&((_skb)->cb[0])) static inline struct ipvl_port *ipvlan_port_get_rcu(const struct net_device *d) { return rcu_dereference(d->rx_handler_data); } static inline struct ipvl_port *ipvlan_port_get_rcu_bh(const struct net_device *d) { return rcu_dereference_bh(d->rx_handler_data); } static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d) { return rtnl_dereference(d->rx_handler_data); } static inline bool ipvlan_is_private(const struct ipvl_port *port) { return !!(port->flags & IPVLAN_F_PRIVATE); } static inline void ipvlan_mark_private(struct ipvl_port *port) { port->flags |= IPVLAN_F_PRIVATE; } static inline void ipvlan_clear_private(struct ipvl_port *port) { port->flags &= ~IPVLAN_F_PRIVATE; } static inline bool ipvlan_is_vepa(const struct ipvl_port *port) { return !!(port->flags & IPVLAN_F_VEPA); } static inline void ipvlan_mark_vepa(struct ipvl_port *port) { port->flags |= IPVLAN_F_VEPA; } static inline void ipvlan_clear_vepa(struct ipvl_port *port) { port->flags &= ~IPVLAN_F_VEPA; } void ipvlan_init_secret(void); unsigned int ipvlan_mac_hash(const unsigned char *addr); rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb); void ipvlan_process_multicast(struct work_struct *work); int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev); void ipvlan_ht_addr_add(struct ipvl_dev *ipvlan, struct ipvl_addr *addr); struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, const void *iaddr, bool is_v6); bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6); void ipvlan_ht_addr_del(struct ipvl_addr *addr); struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, int addr_type, bool use_dest); void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type); void ipvlan_count_rx(const struct ipvl_dev *ipvlan, unsigned int len, bool success, bool mcast); int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack); void ipvlan_link_delete(struct net_device *dev, struct list_head *head); void ipvlan_link_setup(struct net_device *dev); int ipvlan_link_register(struct rtnl_link_ops *ops); #ifdef CONFIG_IPVLAN_L3S int ipvlan_l3s_register(struct ipvl_port *port); void ipvlan_l3s_unregister(struct ipvl_port *port); void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet); int ipvlan_l3s_init(void); void ipvlan_l3s_cleanup(void); #else static inline int ipvlan_l3s_register(struct ipvl_port *port) { return -ENOTSUPP; } static inline void ipvlan_l3s_unregister(struct ipvl_port *port) { } static inline void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet) { } static inline int ipvlan_l3s_init(void) { return 0; } static inline void ipvlan_l3s_cleanup(void) { } #endif /* CONFIG_IPVLAN_L3S */ static inline bool netif_is_ipvlan_port(const struct net_device *dev) { return rcu_access_pointer(dev->rx_handler) == ipvlan_handle_frame; } #endif /* __IPVLAN_H */ |
| 65 65 4 62 4 65 65 65 65 | 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); |
| 1839 1837 14 14 1839 1838 1838 418 1838 4 4 1085 1084 1083 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 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <dipankar@in.ibm.com> * * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) * * For detailed explanation of Read-Copy Update mechanism see - * http://lse.sourceforge.net/locking/rcupdate.html * */ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/processor.h> #include <linux/context_tracking_irq.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define RCU_SEQ_CTR_SHIFT 2 #define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void synchronize_rcu(void); struct rcu_gp_oldstate; unsigned long get_completed_synchronize_rcu(void); void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); // Maximum number of unsigned long values corresponding to // not-yet-completed RCU grace periods. #define NUM_ACTIVE_RCU_POLL_OLDSTATE 2 /** * same_state_synchronize_rcu - Are two old-state values identical? * @oldstate1: First old-state value. * @oldstate2: Second old-state value. * * The two old-state values must have been obtained from either * get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or * get_completed_synchronize_rcu(). Returns @true if the two values are * identical and @false otherwise. This allows structures whose lifetimes * are tracked by old-state values to push these values to a list header, * allowing those structures to be slightly smaller. */ static inline bool same_state_synchronize_rcu(unsigned long oldstate1, unsigned long oldstate2) { return oldstate1 == oldstate2; } #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from * areas that don't even know about current. This gives the rcu_read_lock() * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() READ_ONCE(current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TINY_RCU #define rcu_read_unlock_strict() do { } while (0) #else void rcu_read_unlock_strict(void); #endif static inline void __rcu_read_lock(void) { preempt_disable(); } static inline void __rcu_read_unlock(void) { if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) rcu_read_unlock_strict(); preempt_enable(); } static inline int rcu_preempt_depth(void) { return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_RCU_LAZY void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func); #else static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) { call_rcu(head, func); } #endif /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_VIRT_XFER_TO_GUEST_WORK)) void rcu_irq_work_resched(void); #else static __always_inline void rcu_irq_work_resched(void) { } #endif #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); int rcu_nocb_cpu_offload(int cpu); int rcu_nocb_cpu_deoffload(int cpu); void rcu_nocb_flush_deferred_wakeup(void); #define RCU_NOCB_LOCKDEP_WARN(c, s) RCU_LOCKDEP_WARN(c, s) #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; } static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #define RCU_NOCB_LOCKDEP_WARN(c, s) #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU_GENERIC # ifdef CONFIG_TASKS_RCU # define rcu_tasks_classic_qs(t, preempt) \ do { \ if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void rcu_tasks_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu # define synchronize_rcu_tasks synchronize_rcu # endif # ifdef CONFIG_TASKS_TRACE_RCU // Bits for ->trc_reader_special.b.need_qs field. #define TRC_NEED_QS 0x1 // Task needs a quiescent state. #define TRC_NEED_QS_CHECKED 0x2 // Task has been checked for needing quiescent state. u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new); void rcu_tasks_trace_qs_blkd(struct task_struct *t); # define rcu_tasks_trace_qs(t) \ do { \ int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ \ if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \ likely(!___rttq_nesting)) { \ rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \ } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \ !READ_ONCE((t)->trc_reader_special.b.blocked)) { \ rcu_tasks_trace_qs_blkd(t); \ } \ } while (0) void rcu_tasks_trace_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_trace_qs(t) do { } while (0) # endif #define rcu_tasks_qs(t, preempt) \ do { \ rcu_tasks_classic_qs((t), (preempt)); \ rcu_tasks_trace_qs(t); \ } while (0) # ifdef CONFIG_TASKS_RUDE_RCU void synchronize_rcu_tasks_rude(void); void rcu_tasks_rude_torture_stats_print(char *tt, char *tf); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** * rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period? * * As an accident of implementation, an RCU Tasks Trace grace period also * acts as an RCU grace period. However, this could change at any time. * Code relying on this accident must call this function to verify that * this accident is still happening. * * You have been warned! */ static inline bool rcu_trace_implies_rcu_gp(void) { return true; } /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPTION kernels. */ #define cond_resched_tasks_rcu_qs() \ do { \ rcu_tasks_qs(current, false); \ cond_resched(); \ } while (0) /** * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states * @old_ts: jiffies at start of processing. * * This helper is for long-running softirq handlers, such as NAPI threads in * networking. The caller should initialize the variable passed in as @old_ts * at the beginning of the softirq handler. When invoked frequently, this macro * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will * provide both RCU and RCU-Tasks quiescent states. Note that this macro * modifies its old_ts argument. * * Because regions of code that have disabled softirq act as RCU read-side * critical sections, this macro should be invoked with softirq (and * preemption) enabled. * * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would * have more chance to invoke schedule() calls and provide necessary quiescent * states. As a contrast, calling cond_resched() only won't achieve the same * effect because cond_resched() does not provide RCU-Tasks quiescent states. */ #define rcu_softirq_qs_periodic(old_ts) \ do { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ time_after(jiffies, (old_ts) + HZ / 10)) { \ preempt_disable(); \ rcu_softirq_qs(); \ preempt_enable(); \ (old_ts) = jiffies; \ } \ } while (0) /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ #if defined(CONFIG_TREE_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif /* * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls * are needed for dynamic initialization and destruction of rcu_head * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for * dynamic initialization and destruction of statically allocated rcu_head * structures. However, rcu_head structures allocated dynamically in the * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head(struct rcu_head *head) { } static inline void destroy_rcu_head(struct rcu_head *head) { } static inline void init_rcu_head_on_stack(struct rcu_head *head) { } static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ extern struct lockdep_map rcu_lock_map; extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } static inline void rcu_try_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); } int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) # define rcu_try_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) { return 1; } static inline int rcu_read_lock_bh_held(void) { return 1; } static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } static inline int rcu_read_lock_any_held(void) { return !preemptible(); } static inline int debug_lockdep_rcu_enabled(void) { return 0; } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU /** * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message * * This checks debug_lockdep_rcu_enabled() before checking (c) to * prevent early boot splats due to lockdep not yet being initialized, * and rechecks it after checking (c) to prevent false-positive splats * due to races with lockdep being disabled. See commit 3066820034b5dd * ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail. */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(".data..unlikely") __warned; \ if (debug_lockdep_rcu_enabled() && (c) && \ debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } #else // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { } #endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) // See RCU_LOCKDEP_WARN() for an explanation of the double call to // debug_lockdep_rcu_enabled(). static inline bool lockdep_assert_rcu_helper(bool c) { return debug_lockdep_rcu_enabled() && (c || !rcu_is_watching() || !rcu_lockdep_current_cpu_online()) && debug_lockdep_rcu_enabled(); } /** * lockdep_assert_in_rcu_read_lock - WARN if not protected by rcu_read_lock() * * Splats if lockdep is enabled and there is no rcu_read_lock() in effect. */ #define lockdep_assert_in_rcu_read_lock() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map))) /** * lockdep_assert_in_rcu_read_lock_bh - WARN if not protected by rcu_read_lock_bh() * * Splats if lockdep is enabled and there is no rcu_read_lock_bh() in effect. * Note that local_bh_disable() and friends do not suffice here, instead an * actual rcu_read_lock_bh() is required. */ #define lockdep_assert_in_rcu_read_lock_bh() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_bh_lock_map))) /** * lockdep_assert_in_rcu_read_lock_sched - WARN if not protected by rcu_read_lock_sched() * * Splats if lockdep is enabled and there is no rcu_read_lock_sched() * in effect. Note that preempt_disable() and friends do not suffice here, * instead an actual rcu_read_lock_sched() is required. */ #define lockdep_assert_in_rcu_read_lock_sched() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_sched_lock_map))) /** * lockdep_assert_in_rcu_reader - WARN if not within some type of RCU reader * * Splats if lockdep is enabled and there is no RCU reader of any * type in effect. Note that regions of code protected by things like * preempt_disable, local_bh_disable(), and local_irq_disable() all qualify * as RCU readers. * * Note that this will never trigger in PREEMPT_NONE or PREEMPT_VOLUNTARY * kernels that are not also built with PREEMPT_COUNT. But if you have * lockdep enabled, you might as well also enable PREEMPT_COUNT. */ #define lockdep_assert_in_rcu_reader() \ WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map) && \ !lock_is_held(&rcu_bh_lock_map) && \ !lock_is_held(&rcu_sched_lock_map) && \ preemptible())) #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0 && (c)) #define rcu_sleep_check() do { } while (0) #define lockdep_assert_in_rcu_read_lock() do { } while (0) #define lockdep_assert_in_rcu_read_lock_bh() do { } while (0) #define lockdep_assert_in_rcu_read_lock_sched() do { } while (0) #define lockdep_assert_in_rcu_reader() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple pointers markings to match different RCU implementations * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ #define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ #define __unrcu_pointer(p, local) \ ({ \ typeof(*p) *local = (typeof(*p) *__force)(p); \ rcu_check_sparse(p, __rcu); \ ((typeof(*p) __force __kernel *)(local)); \ }) /** * unrcu_pointer - mark a pointer as not being RCU protected * @p: pointer needing to lose its __rcu property * * Converts @p from an __rcu pointer to a __kernel pointer. * This allows an __rcu pointer to be used with xchg() and friends. */ #define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu)) #define __rcu_access_pointer(p, local, space) \ ({ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_check(p, local, c, space) \ ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define __rcu_dereference_protected(p, local, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) #define __rcu_dereference_raw(p, local) \ ({ \ /* Dependency order vs. p above. */ \ typeof(p) local = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(local)); \ }) #define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu)) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. */ #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from * reordering the code that initializes the structure after the pointer * assignment. More importantly, this call documents which pointers * will be dereferenced by RCU read-side code. * * In some special cases, you may use RCU_INIT_POINTER() instead * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due * to the fact that it does not constrain either the CPU or the compiler. * That said, using RCU_INIT_POINTER() when you should have used * rcu_assign_pointer() is a very bad thing that results in * impossible-to-diagnose memory corruption. So please be careful. * See the RCU_INIT_POINTER() comment header for details. * * Note that rcu_assign_pointer() evaluates each of its arguments only * once, appearances notwithstanding. One of the "extra" evaluations * is in typeof() and the other visible only to sparse (__CHECKER__), * neither of which actually execute the argument. As with most cpp * macros, this execute-arguments-only-once property is important, so * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ #define rcu_assign_pointer(p, v) \ do { \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ else \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ } while (0) /** * rcu_replace_pointer() - replace an RCU pointer, returning its old value * @rcu_ptr: RCU pointer, whose old value is returned * @ptr: regular pointer * @c: the lockdep conditions under which the dereference will take place * * Perform a replacement, where @rcu_ptr is an RCU-annotated * pointer and @c is the lockdep argument that is passed to the * rcu_dereference_protected() call used to read that pointer. The old * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. */ #define rcu_replace_pointer(rcu_ptr, ptr, c) \ ({ \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ __tmp; \ }) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the * lockdep checks for being in an RCU read-side critical section. This is * useful when the value of this pointer is accessed, but the pointer is * not dereferenced, for example, when testing an RCU-protected pointer * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. * Within an RCU read-side critical section, there is little reason to * use rcu_access_pointer(). * * It is usually best to test the rcu_access_pointer() return value * directly in order to avoid accidental dereferences being introduced * by later inattentive changes. In other words, assigning the * rcu_access_pointer() return value to a local variable results in an * accident waiting to happen. * * It is also permissible to use rcu_access_pointer() when read-side * access to the pointer was removed at least one grace period ago, as is * the case in the context of the RCU callback that is freeing up the data, * or after a synchronize_rcu() returns. This can be useful when tearing * down multi-linked structures after a grace period has elapsed. However, * rcu_dereference_protected() is normally preferred for this use case. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the * dereference will take place are correct. Typically the conditions * indicate the various locking conditions that should be held at that * point. The check should return true if the conditions are satisfied. * An implicit check for being in an RCU read-side critical section * (rcu_read_lock()) is included. * * For example: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); * * Inserts memory barriers on architectures that require them * (currently only the Alpha), prevents the compiler from refetching * (and from merging fetches), and, more importantly, documents exactly * which pointers are protected by RCU and checks that the pointer is * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-bh counterpart to rcu_dereference_check(). However, * please note that starting in v5.0 kernels, vanilla RCU grace periods * wait for local_bh_disable() regions of code in addition to regions of * code demarked by rcu_read_lock() and rcu_read_unlock(). This means * that synchronize_rcu(), call_rcu, and friends all take not only * rcu_read_lock() but also rcu_read_lock_bh() into account. */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). * However, please note that starting in v5.0 kernels, vanilla RCU grace * periods wait for preempt_disable() regions of code in addition to * regions of code demarked by rcu_read_lock() and rcu_read_unlock(). * This means that synchronize_rcu(), call_rcu, and friends all take not * only rcu_read_lock() but also rcu_read_lock_sched() into account. */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_sched_held(), \ __rcu) /** * rcu_dereference_all_check() - rcu_dereference_all with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is similar to rcu_dereference_check(), but allows protection * by all forms of vanilla RCU readers, including preemption disabled, * bh-disabled, and interrupt-disabled regions of code. Note that "vanilla * RCU" excludes SRCU and the various Tasks RCU flavors. Please note * that this macro should not be backported to any Linux-kernel version * preceding v5.0 due to changes in synchronize_rcu() semantics prior * to that version. */ #define rcu_dereference_all_check(p, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || rcu_read_lock_any_held(), \ __rcu) /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_check(p) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(). This is useful in cases where update-side locks * prevent the value of the pointer from changing. Please note that this * primitive does *not* prevent the compiler from repeating this reference * or combining it with other references, so it should not be used without * protection of appropriate locks. * * This function is only for update-side use. Using this function * when protected only by rcu_read_lock() will result in infrequent * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu) /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * This is a simple wrapper around rcu_dereference_check(). */ #define rcu_dereference(p) rcu_dereference_check(p, 0) /** * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0) /** * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** * rcu_dereference_all() - fetch RCU-all-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_all(p) rcu_dereference_all_check(p, 0) /** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows:: * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); * if (long_lived) { * if (!atomic_inc_not_zero(p->refcnt)) * long_lived = false; * else * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); */ #define rcu_pointer_handoff(p) (p) /** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the * synchronize_rcu() is guaranteed to block until after all the other * CPUs exit their critical sections. Similarly, if call_rcu() is invoked * on one CPU while other CPUs are within RCU read-side critical * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * * Both synchronize_rcu() and call_rcu() also wait for regions of code * with preemption disabled, including regions of code with interrupts or * softirqs disabled. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU * callback is invoked. This is legal, because the RCU read-side critical * section that was running concurrently with the call_rcu() (and which * therefore might be referencing something that the corresponding RCU * callback would free up) has completed before the corresponding * RCU callback is invoked. * * RCU read-side critical sections may be nested. Any deferred actions * will be deferred until the outermost RCU read-side critical section * completes. * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU * read-side critical section that would block in a !PREEMPTION kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock() used illegally while idle"); } /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not * a bug -- this property is what provides RCU's performance benefits. * Of course, writers must coordinate with each other. The normal * spinlock primitives work well for this, but any other technique may be * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In almost all situations, rcu_read_unlock() is immune from deadlock. * This deadlock immunity also extends to the scheduler's runqueue * and priority-inheritance spinlocks, courtesy of the quiescent-state * deferral that is carried out when rcu_read_unlock() is invoked with * interrupts disabled. * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ __release(RCU); __rcu_read_unlock(); } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent to rcu_read_lock(), but also disables softirqs. * Note that anything else that disables softirqs can also serve as an RCU * read-side critical section. However, please note that this equivalence * applies only to v5.0 and later. Before v5.0, rcu_read_lock() and * rcu_read_lock_bh() were unrelated. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) { local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_bh() used illegally while idle"); } /** * rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ static inline void rcu_read_unlock_bh(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * This is equivalent to rcu_read_lock(), but also disables preemption. * Read-side critical sections can also be introduced by anything else that * disables preemption, including local_irq_disable() and friends. However, * please note that the equivalence to rcu_read_lock() applies only to * v5.0 and later. Before v5.0, rcu_read_lock() and rcu_read_lock_sched() * were unrelated. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_sched() from process context if the matching * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) { preempt_disable_notrace(); __acquire(RCU_SCHED); } /** * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section * * See rcu_read_lock_sched() for more information. */ static inline void rcu_read_unlock_sched(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) { __release(RCU_SCHED); preempt_enable_notrace(); } static __always_inline void rcu_read_lock_dont_migrate(void) { if (IS_ENABLED(CONFIG_PREEMPT_RCU)) migrate_disable(); rcu_read_lock(); } static inline void rcu_read_unlock_migrate(void) { rcu_read_unlock(); if (IS_ENABLED(CONFIG_PREEMPT_RCU)) migrate_enable(); } /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to * readers either at compile time or via rcu_assign_pointer() *and* * * a. You have not made *any* reader-visible changes to * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to * other state where exact synchronization is not required.) * * Failure to follow these rules governing use of RCU_INIT_POINTER() will * result in impossible-to-diagnose memory corruption. As in the structures * will look OK in crash dumps, but any concurrent RCU readers might * see pre-initialized values of the referenced data structure. So * please be very careful how you use RCU_INIT_POINTER()!!! * * If you are creating an RCU-protected linked structure that is accessed * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) \ do { \ rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree for double-argument invocations. * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * * The kfree_rcu() function handles this issue. In order to have a universal * callback function handling different offsets of rcu_head, the callback needs * to determine the starting address of the freed object, which can be a large * kmalloc or vmalloc allocation. To allow simply aligning the pointer down to * page boundary for those, only offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in kvfree_rcu_arg_2(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * * The object to be freed can be allocated either by kmalloc() or * kmem_cache_alloc(). * * Note that the allowable offset might decrease in the future. * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ #define kfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) #define kvfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) /** * kfree_rcu_mightsleep() - kfree an object after a grace period. * @ptr: pointer to kfree for single-argument invocations. * * When it comes to head-less variant, only one argument * is passed and that is just a pointer which has to be * freed after a grace period. Therefore the semantic is * * kfree_rcu_mightsleep(ptr); * * where @ptr is the pointer to be freed by kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() * annotation. Otherwise, please switch and embed the * rcu_head structure within the type of @ptr. */ #define kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) /* * In mm/slab_common.c, no suitable header to include here. */ void kvfree_call_rcu(struct rcu_head *head, void *ptr); /* * The BUILD_BUG_ON() makes sure the rcu_head offset can be handled. See the * comment of kfree_rcu() for details. */ #define kvfree_rcu_arg_2(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) { \ BUILD_BUG_ON(offsetof(typeof(*(ptr)), rhf) >= 4096); \ kvfree_call_rcu(&((___p)->rhf), (void *) (___p)); \ } \ } while (0) #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ \ if (___p) \ kvfree_call_rcu(NULL, (void *) (___p)); \ } while (0) /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies * if the UNLOCK and LOCK are executed by the same CPU or if the * UNLOCK and LOCK operate on the same lock variable. */ #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE #define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ #else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #define smp_mb__after_unlock_lock() do { } while (0) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ /* Has the specified rcu_head structure been handed to call_rcu()? */ /** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * * If you intend to invoke rcu_head_after_call_rcu() to test whether a * given rcu_head structure has already been passed to call_rcu(), then * you must also invoke this rcu_head_init() function on it just after * allocating that structure. Calls to this function must not race with * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. */ static inline void rcu_head_init(struct rcu_head *rhp) { rhp->func = (rcu_callback_t)~0L; } /** * rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including * the case where @rhp has already been invoked after a grace period. * Calls to this function must not race with callback invocation. One way * to avoid such races is to enclose the call to rcu_head_after_call_rcu() * in an RCU read-side critical section that includes a read-side fetch * of the pointer to the structure containing @rhp. */ static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { rcu_callback_t func = READ_ONCE(rhp->func); if (func == f) return true; WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } /* kernel/ksysfs.c definitions */ extern int rcu_expedited; extern int rcu_normal; DEFINE_LOCK_GUARD_0(rcu, do { rcu_read_lock(); /* * sparse doesn't call the cleanup function, * so just release immediately and don't track * the context. We don't need to anyway, since * the whole point of the guard is to not need * the explicit unlock. */ __release(RCU); } while (0), rcu_read_unlock()) #endif /* __LINUX_RCUPDATE_H */ |
| 9 9 471 312 130 131 46 1 1 1 371 208 471 8 263 284 472 7 471 320 41 208 1 207 29 190 194 24 130 24 24 225 224 2 225 371 123 45 6 39 468 468 464 1 471 471 475 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/fault.c * * Copyright (C) 1995 Linus Torvalds * Copyright (C) 1995-2004 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/acpi.h> #include <linux/bitfield.h> #include <linux/extable.h> #include <linux/kfence.h> #include <linux/signal.h> #include <linux/mm.h> #include <linux/hardirq.h> #include <linux/init.h> #include <linux/kasan.h> #include <linux/kprobes.h> #include <linux/uaccess.h> #include <linux/page-flags.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> #include <linux/highmem.h> #include <linux/perf_event.h> #include <linux/pkeys.h> #include <linux/preempt.h> #include <linux/hugetlb.h> #include <asm/acpi.h> #include <asm/bug.h> #include <asm/cmpxchg.h> #include <asm/cpufeature.h> #include <asm/efi.h> #include <asm/exception.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/kprobes.h> #include <asm/mte.h> #include <asm/processor.h> #include <asm/sysreg.h> #include <asm/system_misc.h> #include <asm/tlbflush.h> #include <asm/traps.h> struct fault_info { int (*fn)(unsigned long far, unsigned long esr, struct pt_regs *regs); int sig; int code; const char *name; }; static const struct fault_info fault_info[]; static inline const struct fault_info *esr_to_fault_info(unsigned long esr) { return fault_info + (esr & ESR_ELx_FSC); } static void data_abort_decode(unsigned long esr) { unsigned long iss2 = ESR_ELx_ISS2(esr); pr_alert("Data abort info:\n"); if (esr & ESR_ELx_ISV) { pr_alert(" Access size = %u byte(s)\n", 1U << ((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT)); pr_alert(" SSE = %lu, SRT = %lu\n", (esr & ESR_ELx_SSE) >> ESR_ELx_SSE_SHIFT, (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT); pr_alert(" SF = %lu, AR = %lu\n", (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT, (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT); } else { pr_alert(" ISV = 0, ISS = 0x%08lx, ISS2 = 0x%08lx\n", esr & ESR_ELx_ISS_MASK, iss2); } pr_alert(" CM = %lu, WnR = %lu, TnD = %lu, TagAccess = %lu\n", (esr & ESR_ELx_CM) >> ESR_ELx_CM_SHIFT, (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT, (iss2 & ESR_ELx_TnD) >> ESR_ELx_TnD_SHIFT, (iss2 & ESR_ELx_TagAccess) >> ESR_ELx_TagAccess_SHIFT); pr_alert(" GCS = %ld, Overlay = %lu, DirtyBit = %lu, Xs = %llu\n", (iss2 & ESR_ELx_GCS) >> ESR_ELx_GCS_SHIFT, (iss2 & ESR_ELx_Overlay) >> ESR_ELx_Overlay_SHIFT, (iss2 & ESR_ELx_DirtyBit) >> ESR_ELx_DirtyBit_SHIFT, (iss2 & ESR_ELx_Xs_MASK) >> ESR_ELx_Xs_SHIFT); } static void mem_abort_decode(unsigned long esr) { pr_alert("Mem abort info:\n"); pr_alert(" ESR = 0x%016lx\n", esr); pr_alert(" EC = 0x%02lx: %s, IL = %u bits\n", ESR_ELx_EC(esr), esr_get_class_string(esr), (esr & ESR_ELx_IL) ? 32 : 16); pr_alert(" SET = %lu, FnV = %lu\n", (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT, (esr & ESR_ELx_FnV) >> ESR_ELx_FnV_SHIFT); pr_alert(" EA = %lu, S1PTW = %lu\n", (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT, (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT); pr_alert(" FSC = 0x%02lx: %s\n", (esr & ESR_ELx_FSC), esr_to_fault_info(esr)->name); if (esr_is_data_abort(esr)) data_abort_decode(esr); } static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm) { /* Either init_pg_dir or swapper_pg_dir */ if (mm == &init_mm) return __pa_symbol(mm->pgd); return (unsigned long)virt_to_phys(mm->pgd); } /* * Dump out the page tables associated with 'addr' in the currently active mm. */ static void show_pte(unsigned long addr) { struct mm_struct *mm; pgd_t *pgdp; pgd_t pgd; if (is_ttbr0_addr(addr)) { /* TTBR0 */ mm = current->active_mm; if (mm == &init_mm) { pr_alert("[%016lx] user address but active_mm is swapper\n", addr); return; } } else if (is_ttbr1_addr(addr)) { /* TTBR1 */ mm = &init_mm; } else { pr_alert("[%016lx] address between user and kernel address ranges\n", addr); return; } pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, vabits_actual, mm_to_pgd_phys(mm)); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); do { p4d_t *p4dp, p4d; pud_t *pudp, pud; pmd_t *pmdp, pmd; pte_t *ptep, pte; if (pgd_none(pgd) || pgd_bad(pgd)) break; p4dp = p4d_offset(pgdp, addr); p4d = READ_ONCE(*p4dp); pr_cont(", p4d=%016llx", p4d_val(p4d)); if (p4d_none(p4d) || p4d_bad(p4d)) break; pudp = pud_offset(p4dp, addr); pud = READ_ONCE(*pudp); pr_cont(", pud=%016llx", pud_val(pud)); if (pud_none(pud) || pud_bad(pud)) break; pmdp = pmd_offset(pudp, addr); pmd = READ_ONCE(*pmdp); pr_cont(", pmd=%016llx", pmd_val(pmd)); if (pmd_none(pmd) || pmd_bad(pmd)) break; ptep = pte_offset_map(pmdp, addr); if (!ptep) break; pte = __ptep_get(ptep); pr_cont(", pte=%016llx", pte_val(pte)); pte_unmap(ptep); } while(0); pr_cont("\n"); } /* * This function sets the access flags (dirty, accessed), as well as write * permission, and only to a more permissive setting. * * It needs to cope with hardware update of the accessed/dirty state by other * agents in the system and can safely skip the __sync_icache_dcache() call as, * like __set_ptes(), the PTE is never changed from no-exec to exec here. * * Returns whether or not the PTE actually changed. */ int __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { pteval_t old_pteval, pteval; pte_t pte = __ptep_get(ptep); if (pte_same(pte, entry)) return 0; /* only preserve the access flags and write permission */ pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY; /* * Setting the flags must be done atomically to avoid racing with the * hardware update of the access/dirty state. The PTE_RDONLY bit must * be set to the most permissive (lowest value) of *ptep and entry * (calculated as: a & b == ~(~a | ~b)). */ pte_val(entry) ^= PTE_RDONLY; pteval = pte_val(pte); do { old_pteval = pteval; pteval ^= PTE_RDONLY; pteval |= pte_val(entry); pteval ^= PTE_RDONLY; pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval); } while (pteval != old_pteval); /* Invalidate a stale read-only entry */ if (dirty) flush_tlb_page(vma, address); return 1; } static bool is_el1_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR; } static bool is_el1_data_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_DABT_CUR; } static inline bool is_el1_permission_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { if (!is_el1_data_abort(esr) && !is_el1_instruction_abort(esr)) return false; if (esr_fsc_is_permission_fault(esr)) return true; if (is_ttbr0_addr(addr) && system_uses_ttbr0_pan()) return esr_fsc_is_translation_fault(esr) && (regs->pstate & PSR_PAN_BIT); return false; } static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { unsigned long flags; u64 par, dfsc; if (!is_el1_data_abort(esr) || !esr_fsc_is_translation_fault(esr)) return false; local_irq_save(flags); asm volatile("at s1e1r, %0" :: "r" (addr)); isb(); par = read_sysreg_par(); local_irq_restore(flags); /* * If we now have a valid translation, treat the translation fault as * spurious. */ if (!(par & SYS_PAR_EL1_F)) return true; /* * If we got a different type of fault from the AT instruction, * treat the translation fault as spurious. */ dfsc = FIELD_GET(SYS_PAR_EL1_FST, par); return !esr_fsc_is_translation_fault(dfsc); } static void die_kernel_fault(const char *msg, unsigned long addr, unsigned long esr, struct pt_regs *regs) { bust_spinlocks(1); pr_alert("Unable to handle kernel %s at virtual address %016lx\n", msg, addr); kasan_non_canonical_hook(addr); mem_abort_decode(esr); show_pte(addr); die("Oops", regs, esr); bust_spinlocks(0); make_task_dead(SIGKILL); } #ifdef CONFIG_KASAN_HW_TAGS static void report_tag_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { /* * SAS bits aren't set for all faults reported in EL1, so we can't * find out access size. */ bool is_write = !!(esr & ESR_ELx_WNR); kasan_report((void *)addr, 0, is_write, regs->pc); } #else /* Tag faults aren't enabled without CONFIG_KASAN_HW_TAGS. */ static inline void report_tag_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { } #endif static void do_tag_recovery(unsigned long addr, unsigned long esr, struct pt_regs *regs) { report_tag_fault(addr, esr, regs); /* * Disable MTE Tag Checking on the local CPU for the current EL. * It will be done lazily on the other CPUs when they will hit a * tag fault. */ sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF_MASK, SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF, NONE)); isb(); } static bool is_el1_mte_sync_tag_check_fault(unsigned long esr) { unsigned long fsc = esr & ESR_ELx_FSC; if (!is_el1_data_abort(esr)) return false; if (fsc == ESR_ELx_FSC_MTE) return true; return false; } static void __do_kernel_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { const char *msg; /* * Are we prepared to handle this kernel fault? * We are almost certainly not prepared to handle instruction faults. */ if (!is_el1_instruction_abort(esr) && fixup_exception(regs, esr)) return; if (WARN_RATELIMIT(is_spurious_el1_translation_fault(addr, esr, regs), "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr)) return; if (is_el1_mte_sync_tag_check_fault(esr)) { do_tag_recovery(addr, esr, regs); return; } if (is_el1_permission_fault(addr, esr, regs)) { if (esr & ESR_ELx_WNR) msg = "write to read-only memory"; else if (is_el1_instruction_abort(esr)) msg = "execute from non-executable memory"; else msg = "read from unreadable memory"; } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { if (esr_fsc_is_translation_fault(esr) && kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) return; msg = "paging request"; } if (efi_runtime_fixup_exception(regs, msg)) return; die_kernel_fault(msg, addr, esr, regs); } static void set_thread_esr(unsigned long address, unsigned long esr) { current->thread.fault_address = address; /* * If the faulting address is in the kernel, we must sanitize the ESR. * From userspace's point of view, kernel-only mappings don't exist * at all, so we report them as level 0 translation faults. * (This is not quite the way that "no mapping there at all" behaves: * an alignment fault not caused by the memory type would take * precedence over translation fault for a real access to empty * space. Unfortunately we can't easily distinguish "alignment fault * not caused by memory type" from "alignment fault caused by memory * type", so we ignore this wrinkle and just return the translation * fault.) */ if (!is_ttbr0_addr(current->thread.fault_address)) { switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_DABT_LOW: /* * These bits provide only information about the * faulting instruction, which userspace knows already. * We explicitly clear bits which are architecturally * RES0 in case they are given meanings in future. * We always report the ESR as if the fault was taken * to EL1 and so ISV and the bits in ISS[23:14] are * clear. (In fact it always will be a fault to EL1.) */ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL | ESR_ELx_CM | ESR_ELx_WNR; esr |= ESR_ELx_FSC_FAULT; break; case ESR_ELx_EC_IABT_LOW: /* * Claim a level 0 translation fault. * All other bits are architecturally RES0 for faults * reported with that DFSC value, so we clear them. */ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL; esr |= ESR_ELx_FSC_FAULT; break; default: /* * This should never happen (entry.S only brings us * into this code for insn and data aborts from a lower * exception level). Fail safe by not providing an ESR * context record at all. */ WARN(1, "ESR 0x%lx is not DABT or IABT from EL0\n", esr); esr = 0; break; } } current->thread.fault_code = esr; } static void do_bad_area(unsigned long far, unsigned long esr, struct pt_regs *regs) { unsigned long addr = untagged_addr(far); /* * If we are in kernel mode at this point, we have no context to * handle this fault with. */ if (user_mode(regs)) { const struct fault_info *inf = esr_to_fault_info(esr); set_thread_esr(addr, esr); arm64_force_sig_fault(inf->sig, inf->code, far, inf->name); } else { __do_kernel_fault(addr, esr, regs); } } static bool fault_from_pkey(struct vm_area_struct *vma, unsigned int mm_flags) { if (!system_supports_poe()) return false; /* * We do not check whether an Overlay fault has occurred because we * cannot make a decision based solely on its value: * * - If Overlay is set, a fault did occur due to POE, but it may be * spurious in those cases where we update POR_EL0 without ISB (e.g. * on context-switch). We would then need to manually check POR_EL0 * against vma_pkey(vma), which is exactly what * arch_vma_access_permitted() does. * * - If Overlay is not set, we may still need to report a pkey fault. * This is the case if an access was made within a mapping but with no * page mapped, and POR_EL0 forbids the access (according to * vma_pkey()). Such access will result in a SIGSEGV regardless * because core code checks arch_vma_access_permitted(), but in order * to report the correct error code - SEGV_PKUERR - we must handle * that case here. */ return !arch_vma_access_permitted(vma, mm_flags & FAULT_FLAG_WRITE, mm_flags & FAULT_FLAG_INSTRUCTION, false); } static bool is_gcs_fault(unsigned long esr) { if (!esr_is_data_abort(esr)) return false; return ESR_ELx_ISS2(esr) & ESR_ELx_GCS; } static bool is_el0_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; } /* * Note: not valid for EL1 DC IVAC, but we never use that such that it * should fault. EL0 cannot issue DC IVAC (undef). */ static bool is_write_abort(unsigned long esr) { return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); } static bool is_invalid_gcs_access(struct vm_area_struct *vma, u64 esr) { if (!system_supports_gcs()) return false; if (unlikely(is_gcs_fault(esr))) { /* GCS accesses must be performed on a GCS page */ if (!(vma->vm_flags & VM_SHADOW_STACK)) return true; } else if (unlikely(vma->vm_flags & VM_SHADOW_STACK)) { /* Only GCS operations can write to a GCS page */ return esr_is_data_abort(esr) && is_write_abort(esr); } return false; } static int __kprobes do_page_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf; struct mm_struct *mm = current->mm; vm_fault_t fault; vm_flags_t vm_flags; unsigned int mm_flags = FAULT_FLAG_DEFAULT; unsigned long addr = untagged_addr(far); struct vm_area_struct *vma; int si_code; int pkey = -1; if (kprobe_page_fault(regs, esr)) return 0; /* * If we're in an interrupt or have no user context, we must not take * the fault. */ if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) mm_flags |= FAULT_FLAG_USER; /* * vm_flags tells us what bits we must have in vma->vm_flags * for the fault to be benign, __do_page_fault() would check * vma->vm_flags & vm_flags and returns an error if the * intersection is empty */ if (is_el0_instruction_abort(esr)) { /* It was exec fault */ vm_flags = VM_EXEC; mm_flags |= FAULT_FLAG_INSTRUCTION; } else if (is_gcs_fault(esr)) { /* * The GCS permission on a page implies both read and * write so always handle any GCS fault as a write fault, * we need to trigger CoW even for GCS reads. */ vm_flags = VM_WRITE; mm_flags |= FAULT_FLAG_WRITE; } else if (is_write_abort(esr)) { /* It was write fault */ vm_flags = VM_WRITE; mm_flags |= FAULT_FLAG_WRITE; } else { /* It was read fault */ vm_flags = VM_READ; /* Write implies read */ vm_flags |= VM_WRITE; /* If EPAN is absent then exec implies read */ if (!alternative_has_cap_unlikely(ARM64_HAS_EPAN)) vm_flags |= VM_EXEC; } if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) { if (is_el1_instruction_abort(esr)) die_kernel_fault("execution of user memory", addr, esr, regs); if (!insn_may_access_user(regs->pc, esr)) die_kernel_fault("access to user memory outside uaccess routines", addr, esr, regs); } perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); if (!(mm_flags & FAULT_FLAG_USER)) goto lock_mmap; vma = lock_vma_under_rcu(mm, addr); if (!vma) goto lock_mmap; if (is_invalid_gcs_access(vma, esr)) { vma_end_read(vma); fault = 0; si_code = SEGV_ACCERR; goto bad_area; } if (!(vma->vm_flags & vm_flags)) { vma_end_read(vma); fault = 0; si_code = SEGV_ACCERR; count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto bad_area; } if (fault_from_pkey(vma, mm_flags)) { pkey = vma_pkey(vma); vma_end_read(vma); fault = 0; si_code = SEGV_PKUERR; count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); if (fault & VM_FAULT_MAJOR) mm_flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return 0; } lock_mmap: retry: vma = lock_mm_and_find_vma(mm, addr, regs); if (unlikely(!vma)) { fault = 0; si_code = SEGV_MAPERR; goto bad_area; } if (!(vma->vm_flags & vm_flags)) { mmap_read_unlock(mm); fault = 0; si_code = SEGV_ACCERR; goto bad_area; } if (fault_from_pkey(vma, mm_flags)) { pkey = vma_pkey(vma); mmap_read_unlock(mm); fault = 0; si_code = SEGV_PKUERR; goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return 0; } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) return 0; if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; } mmap_read_unlock(mm); done: /* Handle the "normal" (no error) case first. */ if (likely(!(fault & VM_FAULT_ERROR))) return 0; si_code = SEGV_MAPERR; bad_area: /* * If we are in kernel mode at this point, we have no context to * handle this fault with. */ if (!user_mode(regs)) goto no_context; if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return to * userspace (which will retry the fault, or kill us if we got * oom-killed). */ pagefault_out_of_memory(); return 0; } inf = esr_to_fault_info(esr); set_thread_esr(addr, esr); if (fault & VM_FAULT_SIGBUS) { /* * We had some memory, but were unable to successfully fix up * this page fault. */ arm64_force_sig_fault(SIGBUS, BUS_ADRERR, far, inf->name); } else if (fault & (VM_FAULT_HWPOISON_LARGE | VM_FAULT_HWPOISON)) { unsigned int lsb; lsb = PAGE_SHIFT; if (fault & VM_FAULT_HWPOISON_LARGE) lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); arm64_force_sig_mceerr(BUS_MCEERR_AR, far, lsb, inf->name); } else { /* * The pkey value that we return to userspace can be different * from the pkey that caused the fault. * * 1. T1 : mprotect_key(foo, PAGE_SIZE, pkey=4); * 2. T1 : set POR_EL0 to deny access to pkey=4, touches, page * 3. T1 : faults... * 4. T2: mprotect_key(foo, PAGE_SIZE, pkey=5); * 5. T1 : enters fault handler, takes mmap_lock, etc... * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ /* Something tried to access memory that out of memory map */ if (si_code == SEGV_PKUERR) arm64_force_sig_fault_pkey(far, inf->name, pkey); else arm64_force_sig_fault(SIGSEGV, si_code, far, inf->name); } return 0; no_context: __do_kernel_fault(addr, esr, regs); return 0; } static int __kprobes do_translation_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { unsigned long addr = untagged_addr(far); if (is_ttbr0_addr(addr)) return do_page_fault(far, esr, regs); do_bad_area(far, esr, regs); return 0; } static int do_alignment_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { if (IS_ENABLED(CONFIG_COMPAT_ALIGNMENT_FIXUPS) && compat_user_mode(regs)) return do_compat_alignment_fixup(far, regs); do_bad_area(far, esr, regs); return 0; } static int do_bad(unsigned long far, unsigned long esr, struct pt_regs *regs) { return 1; /* "fault" */ } static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf; unsigned long siaddr; inf = esr_to_fault_info(esr); if (user_mode(regs) && apei_claim_sea(regs) == 0) { /* * APEI claimed this as a firmware-first notification. * Some processing deferred to task_work before ret_to_user(). */ return 0; } if (esr & ESR_ELx_FnV) { siaddr = 0; } else { /* * The architecture specifies that the tag bits of FAR_EL1 are * UNKNOWN for synchronous external aborts. Mask them out now * so that userspace doesn't see them. */ siaddr = untagged_addr(far); } add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK); arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr); return 0; } static int do_tag_check_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { /* * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN * for tag check faults. Set them to corresponding bits in the untagged * address if ARM64_MTE_FAR isn't supported. * Otherwise, bits 63:60 of FAR_EL1 are not UNKNOWN. */ if (!cpus_have_cap(ARM64_MTE_FAR)) far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK); do_bad_area(far, esr, regs); return 0; } static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "ttbr address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 1 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 2 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 3 address size fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" }, { do_sea, SIGBUS, BUS_OBJERR, "synchronous external abort" }, { do_tag_check_fault, SIGSEGV, SEGV_MTESERR, "synchronous tag check fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 18" }, { do_sea, SIGKILL, SI_KERNEL, "level -1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 0 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 2 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 3 (translation table walk)" }, { do_sea, SIGBUS, BUS_OBJERR, "synchronous parity or ECC error" }, // Reserved when RAS is implemented { do_bad, SIGKILL, SI_KERNEL, "unknown 25" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 26" }, { do_sea, SIGKILL, SI_KERNEL, "level -1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 0 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 2 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 3 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_bad, SIGKILL, SI_KERNEL, "unknown 32" }, { do_alignment_fault, SIGBUS, BUS_ADRALN, "alignment fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 34" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 35" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 36" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 37" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 38" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 39" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 40" }, { do_bad, SIGKILL, SI_KERNEL, "level -1 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 42" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level -1 translation fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 44" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 45" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 46" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 47" }, { do_bad, SIGKILL, SI_KERNEL, "TLB conflict abort" }, { do_bad, SIGKILL, SI_KERNEL, "Unsupported atomic hardware update fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 50" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 51" }, { do_bad, SIGKILL, SI_KERNEL, "implementation fault (lockdown abort)" }, { do_bad, SIGBUS, BUS_OBJERR, "implementation fault (unsupported exclusive)" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 54" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 55" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 56" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 57" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 58" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 59" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 60" }, { do_bad, SIGKILL, SI_KERNEL, "section domain fault" }, { do_bad, SIGKILL, SI_KERNEL, "page domain fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 63" }, }; void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_fault_info(esr); unsigned long addr = untagged_addr(far); if (!inf->fn(far, esr, regs)) return; if (!user_mode(regs)) die_kernel_fault(inf->name, addr, esr, regs); /* * At this point we have an unrecognized fault type whose tag bits may * have been defined as UNKNOWN. Therefore we only expose the untagged * address to the signal handler. */ arm64_notify_die(inf->name, regs, inf->sig, inf->code, addr, esr); } NOKPROBE_SYMBOL(do_mem_abort); void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs) { arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN, addr, esr); } NOKPROBE_SYMBOL(do_sp_pc_abort); /* * Used during anonymous page fault handling. */ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { gfp_t flags = GFP_HIGHUSER_MOVABLE | __GFP_ZERO; /* * If the page is mapped with PROT_MTE, initialise the tags at the * point of allocation and page zeroing as this is usually faster than * separate DC ZVA and STGM. */ if (vma->vm_flags & VM_MTE) flags |= __GFP_ZEROTAGS; return vma_alloc_folio(flags, 0, vma, vaddr); } void tag_clear_highpage(struct page *page) { /* Newly allocated page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(page)); mte_zero_clear_page_tags(page_address(page)); set_page_mte_tagged(page); } |
| 100 136 156 24 54 3 3 30 7 12 21 183 9 51 5 5 51 5 5 29 1 11 1 11 149 62 92 47 59 149 61 62 92 172 45 45 46 1 93 45 9 44 4 26 6 4 8 196 306 68 100 20 17 17 7 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 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_H #define _LINUX_FS_H #include <linux/vfsdebug.h> #include <linux/linkage.h> #include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> #include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/pid.h> #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fcntl.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> #include <linux/shrinker.h> #include <linux/migrate_mode.h> #include <linux/uidgid.h> #include <linux/lockdep.h> #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/delayed_call.h> #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> #include <linux/fs_types.h> #include <linux/build_bug.h> #include <linux/stddef.h> #include <linux/mount.h> #include <linux/cred.h> #include <linux/mnt_idmapping.h> #include <linux/slab.h> #include <linux/maple_tree.h> #include <linux/rw_hint.h> #include <linux/file_ref.h> #include <linux/unicode.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> struct backing_dev_info; struct bdi_writeback; struct bio; struct io_comp_batch; struct export_operations; struct fiemap_extent_info; struct hd_geometry; struct iovec; struct kiocb; struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; struct vm_area_struct; struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; struct fscrypt_operations; struct fsverity_operations; struct fsnotify_mark_connector; struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; struct file_kattr; struct iomap_ops; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; typedef __kernel_rwf_t rwf_t; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 #define MAY_READ 0x00000004 #define MAY_APPEND 0x00000008 #define MAY_ACCESS 0x00000010 #define MAY_OPEN 0x00000020 #define MAY_CHDIR 0x00000040 /* called from RCU mode, don't block */ #define MAY_NOT_BLOCK 0x00000080 /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open() */ /* file is open for reading */ #define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ #define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ #define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ #define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ #define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ #define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) /* File supports atomic writes */ #define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7)) /* FMODE_* bit 8 */ /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ #define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. * * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ #define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) /* Supports IOCB_HAS_METADATA */ #define FMODE_HAS_METADATA ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) /* File needs atomic accesses to f_pos */ #define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ #define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) #define FMODE_OPENED ((__force fmode_t)(1 << 19)) #define FMODE_CREATED ((__force fmode_t)(1 << 20)) /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ #define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) #define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) /* File is embedded in backing_file object */ #define FMODE_BACKING ((__force fmode_t)(1 << 24)) /* * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be * generated (see below) */ #define FMODE_NONOTIFY ((__force fmode_t)(1 << 25)) /* * Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be * generated (see below) */ #define FMODE_NONOTIFY_PERM ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ #define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ #define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* * The two FMODE_NONOTIFY* define which fsnotify events should not be generated * for an open file. These are the possible values of * (f->f_mode & FMODE_FSNOTIFY_MASK) and their meaning: * * FMODE_NONOTIFY - suppress all (incl. non-permission) events. * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events. * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only FAN_ACCESS_PERM. */ #define FMODE_FSNOTIFY_MASK \ (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM) #define FMODE_FSNOTIFY_NONE(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS #define FMODE_FSNOTIFY_HSM(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == 0 || \ (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)) #define FMODE_FSNOTIFY_ACCESS_PERM(mode) \ ((mode & FMODE_FSNOTIFY_MASK) == 0) #else #define FMODE_FSNOTIFY_ACCESS_PERM(mode) 0 #define FMODE_FSNOTIFY_HSM(mode) 0 #endif /* * Attribute flags. These should be or-ed together to figure out what * has been changed! */ #define ATTR_MODE (1 << 0) #define ATTR_UID (1 << 1) #define ATTR_GID (1 << 2) #define ATTR_SIZE (1 << 3) #define ATTR_ATIME (1 << 4) #define ATTR_MTIME (1 << 5) #define ATTR_CTIME (1 << 6) #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ #define ATTR_CTIME_SET (1 << 10) #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) #define ATTR_KILL_PRIV (1 << 14) #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) #define ATTR_DELEG (1 << 18) /* Delegated attrs. Don't break write delegations */ /* * Whiteout is represented by a char device. The following constants define the * mode and device number to use. */ #define WHITEOUT_MODE 0 #define WHITEOUT_DEV 0 /* * This is the Inode Attributes structure, used for notify_change(). It * uses the above definitions as flags, to know which values have changed. * Also, in this manner, a Filesystem can look at only the values it cares * about. Basically, these are the attributes that the VFS layer can * request to change from the FS layer. * * Derek Atkins <warlord@MIT.EDU> 94-10-20 */ struct iattr { unsigned int ia_valid; umode_t ia_mode; /* * The two anonymous unions wrap structures with the same member. * * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which * are a dedicated type requiring the filesystem to use the dedicated * helpers. Other filesystem can continue to use ia_{g,u}id until they * have been ported. * * They always contain the same value. In other words FS_ALLOW_IDMAP * pass down the same value on idmapped mounts as they would on regular * mounts. */ union { kuid_t ia_uid; vfsuid_t ia_vfsuid; }; union { kgid_t ia_gid; vfsgid_t ia_vfsgid; }; loff_t ia_size; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to * implement an ftruncate() like method. NOTE: filesystem should * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL). */ struct file *ia_file; }; /* * Includes for diskquotas. */ #include <linux/quota.h> /* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ #define FILESYSTEM_MAX_STACK_DEPTH 2 /** * enum positive_aop_returns - aop return codes with specific semantics * * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has * completed, that the page is still locked, and * should be considered active. The VM uses this hint * to return the page to the active list -- it won't * be a candidate for writeback again in the near * future. Other callers must be careful to unlock * the page if they get this return. Returned by * writepage(); * * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has * unlocked it and the page might have been truncated. * The caller should back up to acquiring a new page and * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned * by read_folio(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a * page to allow for functions that return the number of bytes operated on in a * given page. */ enum positive_aop_returns { AOP_WRITEPAGE_ACTIVATE = 0x80000, AOP_TRUNCATED_PAGE = 0x80001, }; /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; struct readahead_control; /* Match RWF_* bits to IOCB bits */ #define IOCB_HIPRI (__force int) RWF_HIPRI #define IOCB_DSYNC (__force int) RWF_DSYNC #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND #define IOCB_ATOMIC (__force int) RWF_ATOMIC #define IOCB_DONTCACHE (__force int) RWF_DONTCACHE #define IOCB_NOSIGNAL (__force int) RWF_NOSIGNAL /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) #define IOCB_DIRECT (1 << 17) #define IOCB_WRITE (1 << 18) /* iocb->ki_waitq is valid */ #define IOCB_WAITQ (1 << 19) #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) /* * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the * iocb completion can be passed back to the owner for execution from a safe * context rather than needing to be punted through a workqueue. If this * flag is set, the bio completion handling may set iocb->dio_complete to a * handler function and iocb->private to context information for that handler. * The issuer should call the handler with that context information from task * context to complete the processing of the iocb. Note that while this * provides a task context for the dio_complete() callback, it should only be * used on the completion side for non-IO generating completions. It's fine to * call blocking functions from this callback, but they should not wait for * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) /* kiocb is a read or write operation submitted by fs/aio.c. */ #define IOCB_AIO_RW (1 << 23) #define IOCB_HAS_METADATA (1 << 24) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ { IOCB_HIPRI, "HIPRI" }, \ { IOCB_DSYNC, "DSYNC" }, \ { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ { IOCB_ATOMIC, "ATOMIC" }, \ { IOCB_DONTCACHE, "DONTCACHE" }, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ { IOCB_WAITQ, "WAITQ" }, \ { IOCB_NOIO, "NOIO" }, \ { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ { IOCB_DIO_CALLER_COMP, "CALLER_COMP" }, \ { IOCB_AIO_RW, "AIO_RW" }, \ { IOCB_HAS_METADATA, "AIO_HAS_METADATA" } struct kiocb { struct file *ki_filp; loff_t ki_pos; void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ u8 ki_write_stream; union { /* * Only used for async buffered reads, where it denotes the * page waitqueue associated with completing the read. Valid * IFF IOCB_WAITQ is set. */ struct wait_page_queue *ki_waitq; /* * Can be used for O_DIRECT IO, where the completion handling * is punted back to the issuer of the IO. May only be set * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer * must then check for presence of this handler when ki_complete * is invoked. The data passed in to this handler must be * assigned to ->private when dio_complete is assigned. */ ssize_t (*dio_complete)(void *data); }; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } struct address_space_operations { int (*read_folio)(struct file *, struct folio *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); /* Mark a folio dirty. Return true if this dirtied it */ bool (*dirty_folio)(struct address_space *, struct folio *); void (*readahead)(struct readahead_control *); int (*write_begin)(const struct kiocb *, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); int (*write_end)(const struct kiocb *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidate_folio) (struct folio *, size_t offset, size_t len); bool (*release_folio)(struct folio *, gfp_t); void (*free_folio)(struct folio *folio); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a folio to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ int (*migrate_folio)(struct address_space *, struct folio *dst, struct folio *src, enum migrate_mode); int (*launder_folio)(struct folio *); bool (*is_partially_uptodate) (struct folio *, size_t from, size_t count); void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb); int (*error_remove_folio)(struct address_space *, struct folio *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter); }; extern const struct address_space_operations empty_aops; /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. * @invalidate_lock: Guards coherency between page cache contents and * file offset->disk block mappings in the filesystem during invalidates. * It is also used to block modification of page cache contents through * memory mappings. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings. * @nr_thps: Number of THPs in the pagecache (non-shmem only). * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. * @i_private_lock: For use by the owner of the address_space. * @i_private_list: For use by the owner of the address_space. * @i_private_data: For use by the owner of the address_space. */ struct address_space { struct inode *host; struct xarray i_pages; struct rw_semaphore invalidate_lock; gfp_t gfp_mask; atomic_t i_mmap_writable; #ifdef CONFIG_READ_ONLY_THP_FOR_FS /* number of thp, only for non-shmem files */ atomic_t nr_thps; #endif struct rb_root_cached i_mmap; unsigned long nrpages; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; errseq_t wb_err; spinlock_t i_private_lock; struct list_head i_private_list; struct rw_semaphore i_mmap_rwsem; void * i_private_data; } __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit * of struct folio's "mapping" pointer be used for FOLIO_MAPPING_ANON. */ /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 #define PAGECACHE_TAG_WRITEBACK XA_MARK_1 #define PAGECACHE_TAG_TOWRITE XA_MARK_2 /* * Returns true if any of the pages in the mapping are marked with the tag. */ static inline bool mapping_tagged(const struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } static inline void i_mmap_lock_write(struct address_space *mapping) { down_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_write(struct address_space *mapping) { return down_write_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_write(struct address_space *mapping) { up_write(&mapping->i_mmap_rwsem); } static inline int i_mmap_trylock_read(struct address_space *mapping) { return down_read_trylock(&mapping->i_mmap_rwsem); } static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_read(struct address_space *mapping) { up_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_locked(struct address_space *mapping) { lockdep_assert_held(&mapping->i_mmap_rwsem); } static inline void i_mmap_assert_write_locked(struct address_space *mapping) { lockdep_assert_held_write(&mapping->i_mmap_rwsem); } /* * Might pages of this file be mapped into userspace? */ static inline int mapping_mapped(const struct address_space *mapping) { return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* * Might pages of this file have been modified in userspace? * Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * * If i_mmap_writable is negative, no new writable mappings are allowed. You * can only deny writable mappings, if none exists right now. */ static inline int mapping_writably_mapped(const struct address_space *mapping) { return atomic_read(&mapping->i_mmap_writable) > 0; } static inline int mapping_map_writable(struct address_space *mapping) { return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? 0 : -EPERM; } static inline void mapping_unmap_writable(struct address_space *mapping) { atomic_dec(&mapping->i_mmap_writable); } static inline int mapping_deny_writable(struct address_space *mapping) { return atomic_dec_unless_positive(&mapping->i_mmap_writable) ? 0 : -EBUSY; } static inline void mapping_allow_writable(struct address_space *mapping) { atomic_inc(&mapping->i_mmap_writable); } /* * Use sequence counter to get consistent i_size on 32-bit processors. */ #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include <linux/seqlock.h> #define __NEED_I_SIZE_ORDERED #define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount) #else #define i_size_ordered_init(inode) do { } while (0) #endif struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) /* * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to * cache the ACL. This also means that ->get_inode_acl() can be called in RCU * mode with the LOOKUP_RCU flag. */ #define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) { return (void *)task + 1; } static inline bool is_uncached_acl(struct posix_acl *acl) { return (long)acl & 1; } #define IOP_FASTPERM 0x0001 #define IOP_LOOKUP 0x0002 #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 #define IOP_MGTIME 0x0020 #define IOP_CACHED_LINK 0x0040 /* * Inode state bits. Protected by inode->i_lock * * Four bits determine the dirty state of the inode: I_DIRTY_SYNC, * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME. * * Four bits define the lifetime of an inode. Initially, inodes are I_NEW, * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at * various stages of removing an inode. * * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on * fdatasync() (unless I_DIRTY_DATASYNC is also set). * Timestamp updates are the usual cause. * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of * these changes separately from I_DIRTY_SYNC so that we * don't have to write inode on fdatasync() when only * e.g. the timestamps have changed. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. * I_DIRTY_TIME The inode itself has dirty timestamps, and the * lazytime mount option is enabled. We keep track of this * separately from I_DIRTY_SYNC in order to implement * lazytime. This gets cleared if I_DIRTY_INODE * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already * in place because writeback might already be in progress * and we don't want to lose the time update * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and * wait for I_NEW to be released before returning. * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can * also cause waiting on I_NEW, without I_NEW actually * being set. find_inode() uses this to prevent returning * nearly-dead inodes. * I_WILL_FREE Must be set when calling write_inode_now() if i_count * is zero. I_FREEING must be set when I_WILL_FREE is * cleared. * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. * I_CLEAR Added by clear_inode(). In this state the inode is * clean and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are * prohibited for many purposes. iget() must wait for * the inode to be completely released, then create it * anew. Other functions will just ignore such inodes, * if appropriate. I_NEW is used for waiting. * * I_SYNC Writeback of inode is running. The bit is set during * data writeback, and cleared with a wakeup on the bit * address once it is done. The bit is also used to pin * the inode in memory for flusher thread. * * I_REFERENCED Marks the inode as recently references on the LRU list. * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See * inode_switch_wbs_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper * and work dirs among overlayfs mounts. * * I_CREATING New object's inode in the middle of setting up. * * I_DONTCACHE Evict inode as soon as it is not used anymore. * * I_SYNC_QUEUED Inode is queued in b_io or b_more_io writeback lists. * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding * i_count. * * Q: What is the difference between I_WILL_FREE and I_FREEING? * * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait * upon. There's one free address left. */ enum inode_state_bits { __I_NEW = 0U, __I_SYNC = 1U, __I_LRU_ISOLATING = 2U /* reserved wait address bit 3 */ }; enum inode_state_flags_t { I_NEW = (1U << __I_NEW), I_SYNC = (1U << __I_SYNC), I_LRU_ISOLATING = (1U << __I_LRU_ISOLATING), /* reserved flag bit 3 */ I_DIRTY_SYNC = (1U << 4), I_DIRTY_DATASYNC = (1U << 5), I_DIRTY_PAGES = (1U << 6), I_WILL_FREE = (1U << 7), I_FREEING = (1U << 8), I_CLEAR = (1U << 9), I_REFERENCED = (1U << 10), I_LINKABLE = (1U << 11), I_DIRTY_TIME = (1U << 12), I_WB_SWITCH = (1U << 13), I_OVL_INUSE = (1U << 14), I_CREATING = (1U << 15), I_DONTCACHE = (1U << 16), I_SYNC_QUEUED = (1U << 17), I_PINNING_NETFS_WB = (1U << 18) }; #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' */ struct inode { umode_t i_mode; unsigned short i_opflags; kuid_t i_uid; kgid_t i_gid; unsigned int i_flags; #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif const struct inode_operations *i_op; struct super_block *i_sb; struct address_space *i_mapping; #ifdef CONFIG_SECURITY void *i_security; #endif /* Stat data, not accessed from path walking */ unsigned long i_ino; /* * Filesystems may only read i_nlink directly. They shall use the * following functions for modification: * * (set|clear|inc|drop)_nlink * inode_(inc|dec)_link_count */ union { const unsigned int i_nlink; unsigned int __i_nlink; }; dev_t i_rdev; loff_t i_size; time64_t i_atime_sec; time64_t i_mtime_sec; time64_t i_ctime_sec; u32 i_atime_nsec; u32 i_mtime_nsec; u32 i_ctime_nsec; u32 i_generation; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif /* Misc */ enum inode_state_flags_t i_state; /* 32-bit hole */ struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_io_list; /* backing dev IO list */ #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *i_wb; /* the associated cgroup wb */ /* foreign inode detection, see wbc_detach_inode() */ int i_wb_frn_winner; u16 i_wb_frn_avg_time; u16 i_wb_frn_history; #endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; struct list_head i_wb_list; /* backing dev writeback list */ union { struct hlist_head i_dentry; struct rcu_head i_rcu; }; atomic64_t i_version; atomic64_t i_sequence; /* see futex */ atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) atomic_t i_readcount; /* struct files open RO */ #endif union { const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ void (*free_inode)(struct inode *); }; struct file_lock_context *i_flctx; struct address_space i_data; union { struct list_head i_devices; int i_linklen; }; union { struct pipe_inode_info *i_pipe; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; }; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ /* 32-bit hole reserved for expanding i_fsnotify_mask */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif void *i_private; /* fs or device private pointer */ } __randomize_layout; static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) { VFS_WARN_ON_INODE(strlen(link) != linklen, inode); VFS_WARN_ON_INODE(inode->i_opflags & IOP_CACHED_LINK, inode); inode->i_link = link; inode->i_linklen = linklen; inode->i_opflags |= IOP_CACHED_LINK; } /* * Get bit address from inode->i_state to use with wait_var_event() * infrastructre. */ #define inode_state_wait_address(inode, bit) ((char *)&(inode)->i_state + (bit)) struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, struct inode *inode, u32 bit); static inline void inode_wake_up_bit(struct inode *inode, u32 bit) { /* Caller is responsible for correct memory barriers. */ wake_up_var(inode_state_wait_address(inode, bit)); } struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); static inline unsigned int i_blocksize(const struct inode *node) { return (1 << node->i_blkbits); } static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); } /* * __mark_inode_dirty expects inodes to be hashed. Since we don't * want special inodes in the fileset inode space, we make them * appear hashed, but do not put on any lists. hlist_del() * will work fine and require no locking. */ static inline void inode_fake_hash(struct inode *inode) { hlist_add_fake(&inode->i_hash); } /* * inode->i_rwsem nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent * 2: child/target * 3: xattr * 4: second non-directory * 5: second parent (when locking independent directories in rename) * * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two * non-directories at once. * * The locking order between these classes is * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { I_MUTEX_NORMAL, I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, I_MUTEX_NONDIR2, I_MUTEX_PARENT2, }; static inline void inode_lock(struct inode *inode) { down_write(&inode->i_rwsem); } static inline __must_check int inode_lock_killable(struct inode *inode) { return down_write_killable(&inode->i_rwsem); } static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); } static inline void inode_lock_shared(struct inode *inode) { down_read(&inode->i_rwsem); } static inline __must_check int inode_lock_shared_killable(struct inode *inode) { return down_read_killable(&inode->i_rwsem); } static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); } static inline int inode_trylock(struct inode *inode) { return down_write_trylock(&inode->i_rwsem); } static inline int inode_trylock_shared(struct inode *inode) { return down_read_trylock(&inode->i_rwsem); } static inline int inode_is_locked(struct inode *inode) { return rwsem_is_locked(&inode->i_rwsem); } static inline void inode_lock_nested(struct inode *inode, unsigned subclass) { down_write_nested(&inode->i_rwsem, subclass); } static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass) { down_read_nested(&inode->i_rwsem, subclass); } static inline void filemap_invalidate_lock(struct address_space *mapping) { down_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock(struct address_space *mapping) { up_write(&mapping->invalidate_lock); } static inline void filemap_invalidate_lock_shared(struct address_space *mapping) { down_read(&mapping->invalidate_lock); } static inline int filemap_invalidate_trylock_shared( struct address_space *mapping) { return down_read_trylock(&mapping->invalidate_lock); } static inline void filemap_invalidate_unlock_shared( struct address_space *mapping) { up_read(&mapping->invalidate_lock); } void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2); void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2); /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic * with respect to the local cpu (unlike with preempt disabled), * but they don't need to be atomic with respect to other cpus like in * true SMP (so they need either to either locally disable irq around * the read or for example on x86 they can be still implemented as a * cmpxchg8b without the need of the lock prefix). For SMP compiles * and 64bit archs it makes no difference if preempt is enabled or not. */ static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; unsigned int seq; do { seq = read_seqcount_begin(&inode->i_size_seqcount); i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) loff_t i_size; preempt_disable(); i_size = inode->i_size; preempt_enable(); return i_size; #else /* Pairs with smp_store_release() in i_size_write() */ return smp_load_acquire(&inode->i_size); #endif } /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it * (normally i_rwsem), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) preempt_disable(); inode->i_size = i_size; preempt_enable(); #else /* * Pairs with smp_load_acquire() in i_size_read() to ensure * changes related to inode size (such as page contents) are * visible before we see the changed inode size. */ smp_store_release(&inode->i_size, i_size); #endif } static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } static inline unsigned imajor(const struct inode *inode) { return MAJOR(inode->i_rdev); } struct fown_struct { struct file *file; /* backpointer for security modules */ rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ kuid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; /** * struct file_ra_state - Track a file's readahead state. * @start: Where the most recent readahead started. * @size: Number of pages read in the most recent readahead. * @async_size: Numer of pages that were/are not needed immediately * and so were/are genuinely "ahead". Start next readahead when * the first of these pages is accessed. * @ra_pages: Maximum size of a readahead request, copied from the bdi. * @order: Preferred folio order used for most recent readahead. * @mmap_miss: How many mmap accesses missed in the page cache. * @prev_pos: The last byte in the most recent read request. * * When this structure is passed to ->readahead(), the "most recent" * readahead means the current readahead. */ struct file_ra_state { pgoff_t start; unsigned int size; unsigned int async_size; unsigned int ra_pages; unsigned short order; unsigned short mmap_miss; loff_t prev_pos; }; /* * Check if @index falls in the readahead windows. */ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) { return (index >= ra->start && index < ra->start + ra->size); } /** * struct file - Represents a file * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. * @f_mode: FMODE_* flags often used in hotpaths * @f_op: file operations * @f_mapping: Contents of a cacheable, mappable object. * @private_data: filesystem or driver specific data * @f_inode: cached inode * @f_flags: file flags * @f_iocb_flags: iocb flags * @f_cred: stashed credentials of creator/opener * @f_owner: file owner * @f_path: path of the file * @__f_path: writable alias for @f_path; *ONLY* for core VFS and only before * the file gets open * @f_pos_lock: lock protecting file position * @f_pipe: specific to pipes * @f_pos: file position * @f_security: LSM security context of this file * @f_wb_err: writeback error * @f_sb_err: per sb writeback errors * @f_ep: link of all epoll hooks for this file * @f_task_work: task work entry point * @f_llist: work queue entrypoint * @f_ra: file's readahead state * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) * @f_ref: reference count */ struct file { spinlock_t f_lock; fmode_t f_mode; const struct file_operations *f_op; struct address_space *f_mapping; void *private_data; struct inode *f_inode; unsigned int f_flags; unsigned int f_iocb_flags; const struct cred *f_cred; struct fown_struct *f_owner; /* --- cacheline 1 boundary (64 bytes) --- */ union { const struct path f_path; struct path __f_path; }; union { /* regular files (with FMODE_ATOMIC_POS) and directories */ struct mutex f_pos_lock; /* pipes */ u64 f_pipe; }; loff_t f_pos; #ifdef CONFIG_SECURITY void *f_security; #endif /* --- cacheline 2 boundary (128 bytes) --- */ errseq_t f_wb_err; errseq_t f_sb_err; #ifdef CONFIG_EPOLL struct hlist_head *f_ep; #endif union { struct callback_head f_task_work; struct llist_node f_llist; struct file_ra_state f_ra; freeptr_t f_freeptr; }; file_ref_t f_ref; /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { file_ref_inc(&f->f_ref); return f; } struct file *get_file_rcu(struct file __rcu **f); struct file *get_file_active(struct file **f); #define file_count(f) file_ref_read(&(f)->f_ref) #define MAX_NON_LFS ((1UL<<31) - 1) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 #define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; struct file_lease; /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define OFFSET_MAX type_max(loff_t) #define OFFT_OFFSET_MAX type_max(off_t) #endif int file_f_owner_allocate(struct file *file); static inline struct fown_struct *file_f_owner(const struct file *file) { return READ_ONCE(file->f_owner); } extern void send_sigio(struct fown_struct *fown, int fd, int band); static inline struct inode *file_inode(const struct file *f) { return f->f_inode; } /* * file_dentry() is a relic from the days that overlayfs was using files with a * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs. * In those days, file_dentry() was needed to get the underlying fs dentry that * matches f_inode. * Files with "fake" path should not exist nowadays, so use an assertion to make * sure that file_dentry() was not papering over filesystem bugs. */ static inline struct dentry *file_dentry(const struct file *file) { struct dentry *dentry = file->f_path.dentry; WARN_ON_ONCE(d_inode(dentry) != file_inode(file)); return dentry; } struct fasync_struct { rwlock_t fa_lock; int magic; int fa_fd; struct fasync_struct *fa_next; /* singly linked list */ struct file *fa_file; struct rcu_head fa_rcu; }; #define FASYNC_MAGIC 0x4601 /* SMP safe fasync helpers: */ extern int fasync_helper(int, struct file *, int, struct fasync_struct **); extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); extern int fasync_remove_entry(struct file *, struct fasync_struct **); extern struct fasync_struct *fasync_alloc(void); extern void fasync_free(struct fasync_struct *); /* can be called from interrupts */ extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); extern int f_setown(struct file *filp, int who, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct file *file); /* * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ #define SB_RDONLY BIT(0) /* Mount read-only */ #define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ #define SB_NODEV BIT(2) /* Disallow access to device special files */ #define SB_NOEXEC BIT(3) /* Disallow program execution */ #define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ #define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ #define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ #define SB_NOATIME BIT(10) /* Do not update access times. */ #define SB_NODIRATIME BIT(11) /* Do not update directory access times */ #define SB_SILENT BIT(15) #define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ #define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ #define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ #define SB_I_VERSION BIT(23) /* Update inode I_version field */ #define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ #define SB_DEAD BIT(21) #define SB_DYING BIT(24) #define SB_FORCE BIT(27) #define SB_NOSEC BIT(28) #define SB_BORN BIT(29) #define SB_ACTIVE BIT(30) #define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) #define SB_ENC_NO_COMPAT_FALLBACK_FL (1 << 1) #define sb_has_strict_encoding(sb) \ (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) #if IS_ENABLED(CONFIG_UNICODE) #define sb_no_casefold_compat_fallback(sb) \ (sb->s_encoding_flags & SB_ENC_NO_COMPAT_FALLBACK_FL) #else #define sb_no_casefold_compat_fallback(sb) (1) #endif /* * Umount options */ #define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ #define MNT_DETACH 0x00000002 /* Just detach from the tree */ #define MNT_EXPIRE 0x00000004 /* Mark for expiry */ #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ /* sb->s_iflags */ #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ #define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 #define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ #define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ #define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ #define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ #define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ #define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop * internal threads if needed) */ SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ }; #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) struct sb_writers { unsigned short frozen; /* Is sb frozen? */ int freeze_kcount; /* How many kernel freeze requests? */ int freeze_ucount; /* How many userspace freeze requests? */ const void *freeze_owner; /* Owner of the freeze */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; struct mount; struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ unsigned char s_blocksize_bits; unsigned long s_blocksize; loff_t s_maxbytes; /* Max file size */ struct file_system_type *s_type; const struct super_operations *s_op; const struct dquot_operations *dq_op; const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; unsigned long s_iflags; /* internal SB_I_* flags */ unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; int s_count; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; #endif const struct xattr_handler * const *s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif #if IS_ENABLED(CONFIG_UNICODE) struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct mount *s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */ struct file *s_bdev_file; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; unsigned int s_quota_types; /* Bitmask of supported quota types */ struct quota_info s_dquot; /* Diskquota specific options */ struct sb_writers s_writers; /* * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and * s_fsnotify_info together for cache efficiency. They are frequently * accessed and rarely modified. */ void *s_fs_info; /* Filesystem private info */ /* Granularity of c/m/atime in ns (cannot be worse than a second) */ u32 s_time_gran; /* Time limits for c/m/atime in seconds */ time64_t s_time_min; time64_t s_time_max; #ifdef CONFIG_FSNOTIFY u32 s_fsnotify_mask; struct fsnotify_sb_info *s_fsnotify_info; #endif /* * q: why are s_id and s_sysfs_name not the same? both are human * readable strings that identify the filesystem * a: s_id is allowed to change at runtime; it's used in log messages, * and we want to when a device starts out as single device (s_id is dev * name) but then a device is hot added and we have to switch to * identifying it by UUID * but s_sysfs_name is a handle for programmatic access, and can't * change at runtime */ char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ char s_sysfs_name[UUID_STRING_LEN + 1]; unsigned int s_max_links; unsigned int s_d_flags; /* default d_flags for dentries */ /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ struct mutex s_vfs_rename_mutex; /* Kludge */ /* * Filesystem subtype. If non-empty the filesystem type field * in /proc/mounts will be "type.subtype" */ const char *s_subtype; const struct dentry_operations *__s_d_op; /* default d_op for dentries */ struct shrinker *s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; /* Read-only state of the superblock is being changed */ int s_readonly_remount; /* per-sb errseq_t for reporting writeback errors via syncfs */ errseq_t s_wb_err; /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; /* * Owning user namespace and default context in which to * interpret filesystem uids, gids, quotas, device nodes, * xattrs and security labels. */ struct user_namespace *s_user_ns; /* * The list_lru structure is essentially just a pointer to a table * of per-node lru lists, each of which has its own spinlock. * There is no need to put them into separate cachelines. */ struct list_lru s_dentry_lru; struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; struct mutex s_sync_lock; /* sync serialisation lock */ /* * Indicates how deep in a filesystem stack this SB is */ int s_stack_depth; /* s_inode_list_lock protects s_inodes */ spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; struct list_head s_inodes; /* all inodes */ spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ } __randomize_layout; static inline struct user_namespace *i_user_ns(const struct inode *inode) { return inode->i_sb->s_user_ns; } /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can * instead deal with the raw numeric values that are stored * in the filesystem. */ static inline uid_t i_uid_read(const struct inode *inode) { return from_kuid(i_user_ns(inode), inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { return from_kgid(i_user_ns(inode), inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { inode->i_uid = make_kuid(i_user_ns(inode), uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { inode->i_gid = make_kgid(i_user_ns(inode), gid); } /** * i_uid_into_vfsuid - map an inode's i_uid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: whe inode's i_uid mapped down according to @idmap. * If the inode's i_uid has no mapping INVALID_VFSUID is returned. */ static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid); } /** * i_uid_needs_update - check whether inode's i_uid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_uid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_uid field needs to be updated, false if not. */ static inline bool i_uid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_UID) && !vfsuid_eq(attr->ia_vfsuid, i_uid_into_vfsuid(idmap, inode))); } /** * i_uid_update - update @inode's i_uid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_uid field translating the vfsuid of any idmapped * mount into the filesystem kuid. */ static inline void i_uid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_UID) inode->i_uid = from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid); } /** * i_gid_into_vfsgid - map an inode's i_gid down according to an idmapping * @idmap: idmap of the mount the inode was found from * @inode: inode to map * * Return: the inode's i_gid mapped down according to @idmap. * If the inode's i_gid has no mapping INVALID_VFSGID is returned. */ static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap, const struct inode *inode) { return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid); } /** * i_gid_needs_update - check whether inode's i_gid needs to be updated * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Check whether the $inode's i_gid field needs to be updated taking idmapped * mounts into account if the filesystem supports it. * * Return: true if @inode's i_gid field needs to be updated, false if not. */ static inline bool i_gid_needs_update(struct mnt_idmap *idmap, const struct iattr *attr, const struct inode *inode) { return ((attr->ia_valid & ATTR_GID) && !vfsgid_eq(attr->ia_vfsgid, i_gid_into_vfsgid(idmap, inode))); } /** * i_gid_update - update @inode's i_gid field * @idmap: idmap of the mount the inode was found from * @attr: the new attributes of @inode * @inode: the inode to update * * Safely update @inode's i_gid field translating the vfsgid of any idmapped * mount into the filesystem kgid. */ static inline void i_gid_update(struct mnt_idmap *idmap, const struct iattr *attr, struct inode *inode) { if (attr->ia_valid & ATTR_GID) inode->i_gid = from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid); } /** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_uid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsuid according to @idmap. */ static inline void inode_fsuid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode)); } /** * inode_fsgid_set - initialize inode's i_gid field with callers fsgid * @inode: inode to initialize * @idmap: idmap of the mount the inode was found from * * Initialize the i_gid field of @inode. If the inode was found/created via * an idmapped mount map the caller's fsgid according to @idmap. */ static inline void inode_fsgid_set(struct inode *inode, struct mnt_idmap *idmap) { inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode)); } /** * fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped * @sb: the superblock we want a mapping in * @idmap: idmap of the relevant mount * * Check whether the caller's fsuid and fsgid have a valid mapping in the * s_user_ns of the superblock @sb. If the caller is on an idmapped mount map * the caller's fsuid and fsgid according to the @idmap first. * * Return: true if fsuid and fsgid is mapped, false if not. */ static inline bool fsuidgid_has_mapping(struct super_block *sb, struct mnt_idmap *idmap) { struct user_namespace *fs_userns = sb->s_user_ns; kuid_t kuid; kgid_t kgid; kuid = mapped_fsuid(idmap, fs_userns); if (!uid_valid(kuid)) return false; kgid = mapped_fsgid(idmap, fs_userns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && kgid_has_mapping(fs_userns, kgid); } struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); struct timespec64 inode_set_ctime_deleg(struct inode *inode, struct timespec64 update); static inline time64_t inode_get_atime_sec(const struct inode *inode) { return inode->i_atime_sec; } static inline long inode_get_atime_nsec(const struct inode *inode) { return inode->i_atime_nsec; } static inline struct timespec64 inode_get_atime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_atime_sec(inode), .tv_nsec = inode_get_atime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_atime_sec = ts.tv_sec; inode->i_atime_nsec = ts.tv_nsec; return ts; } static inline struct timespec64 inode_set_atime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_atime_to_ts(inode, ts); } static inline time64_t inode_get_mtime_sec(const struct inode *inode) { return inode->i_mtime_sec; } static inline long inode_get_mtime_nsec(const struct inode *inode) { return inode->i_mtime_nsec; } static inline struct timespec64 inode_get_mtime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_mtime_sec(inode), .tv_nsec = inode_get_mtime_nsec(inode) }; return ts; } static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, struct timespec64 ts) { inode->i_mtime_sec = ts.tv_sec; inode->i_mtime_nsec = ts.tv_nsec; return ts; } static inline struct timespec64 inode_set_mtime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_mtime_to_ts(inode, ts); } /* * Multigrain timestamps * * Conditionally use fine-grained ctime and mtime timestamps when there * are users actively observing them via getattr. The primary use-case * for this is NFS clients that use the ctime to distinguish between * different states of the file, and that are often fooled by multiple * operations that occur in the same coarse-grained timer tick. */ #define I_CTIME_QUERIED ((u32)BIT(31)) static inline time64_t inode_get_ctime_sec(const struct inode *inode) { return inode->i_ctime_sec; } static inline long inode_get_ctime_nsec(const struct inode *inode) { return inode->i_ctime_nsec & ~I_CTIME_QUERIED; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) { struct timespec64 ts = { .tv_sec = inode_get_ctime_sec(inode), .tv_nsec = inode_get_ctime_nsec(inode) }; return ts; } struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts); /** * inode_set_ctime - set the ctime in the inode * @inode: inode in which to set the ctime * @sec: tv_sec value to set * @nsec: tv_nsec value to set * * Set the ctime in @inode to { @sec, @nsec } */ static inline struct timespec64 inode_set_ctime(struct inode *inode, time64_t sec, long nsec) { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; return inode_set_ctime_to_ts(inode, ts); } struct timespec64 simple_inode_init_ts(struct inode *inode); /* * Snapshotting support. */ /* * These are internal functions, please use sb_start_{write,pagefault,intwrite} * instead. */ static inline void __sb_end_write(struct super_block *sb, int level) { percpu_up_read(sb->s_writers.rw_sem + level-1); } static inline void __sb_start_write(struct super_block *sb, int level) { percpu_down_read_freezable(sb->s_writers.rw_sem + level - 1, true); } static inline bool __sb_start_write_trylock(struct super_block *sb, int level) { return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); } #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) #define __sb_writers_release(sb, lev) \ percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], _THIS_IP_) /** * __sb_write_started - check if sb freeze level is held * @sb: the super we write to * @level: the freeze level * * * > 0 - sb freeze level is held * * 0 - sb freeze level is not held * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN */ static inline int __sb_write_started(const struct super_block *sb, int level) { return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); } /** * sb_write_started - check if SB_FREEZE_WRITE is held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE); } /** * sb_write_not_started - check if SB_FREEZE_WRITE is not held * @sb: the super we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. */ static inline bool sb_write_not_started(const struct super_block *sb) { return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; } /** * file_write_started - check if SB_FREEZE_WRITE is held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_started(file_inode(file)->i_sb); } /** * file_write_not_started - check if SB_FREEZE_WRITE is not held * @file: the file we write to * * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. * May be false positive with !S_ISREG, because file_start_write() has * no effect on !S_ISREG. */ static inline bool file_write_not_started(const struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_write_not_started(file_inode(file)->i_sb); } /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to * * Decrement number of writers to the filesystem. Wake up possible waiters * wanting to freeze the filesystem. */ static inline void sb_end_write(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_WRITE); } /** * sb_end_pagefault - drop write access to a superblock from a page fault * @sb: the super we wrote to * * Decrement number of processes handling write page fault to the filesystem. * Wake up possible waiters wanting to freeze the filesystem. */ static inline void sb_end_pagefault(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_end_intwrite - drop write access to a superblock for internal fs purposes * @sb: the super we wrote to * * Decrement fs-internal number of writers to the filesystem. Wake up possible * waiters wanting to freeze the filesystem. */ static inline void sb_end_intwrite(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_FS); } /** * sb_start_write - get write access to a superblock * @sb: the super we write to * * When a process wants to write data or metadata to a file system (i.e. dirty * a page or an inode), it should embed the operation in a sb_start_write() - * sb_end_write() pair to get exclusion against file system freezing. This * function increments number of writers preventing freezing. If the file * system is already frozen, the function waits until the file system is * thawed. * * Since freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. Generally, * freeze protection should be the outermost lock. In particular, we have: * * sb_start_write * -> i_rwsem (write path, truncate, directory ops, ...) * -> s_umount (freeze_super, thaw_super) */ static inline void sb_start_write(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_WRITE); } static inline bool sb_start_write_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** * sb_start_pagefault - get write access to a superblock from a page fault * @sb: the super we write to * * When a process starts handling write page fault, it should embed the * operation into sb_start_pagefault() - sb_end_pagefault() pair to get * exclusion against file system freezing. This is needed since the page fault * is going to dirty a page. This function increments number of running page * faults preventing freezing. If the file system is already frozen, the * function waits until the file system is thawed. * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault * handling code implies lock dependency: * * mmap_lock * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_start_intwrite - get write access to a superblock for internal fs purposes * @sb: the super we write to * * This is the third level of protection against filesystem freezing. It is * free for use by a filesystem. The only requirement is that it must rank * below sb_start_pagefault. * * For example filesystem can call sb_start_intwrite() when starting a * transaction which somewhat eases handling of freezing for internal sources * of filesystem changes (internal fs threads, discarding preallocation on file * close, etc.). */ static inline void sb_start_intwrite(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_FS); } static inline bool sb_start_intwrite_trylock(struct super_block *sb) { return __sb_start_write_trylock(sb, SB_FREEZE_FS); } bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ int vfs_create(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, bool); struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, umode_t, dev_t); int vfs_symlink(struct mnt_idmap *, struct inode *, struct dentry *, const char *); int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *); int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, struct inode **); /** * struct renamedata - contains all information required for renaming * @mnt_idmap: idmap of the mount in which the rename is happening. * @old_parent: parent of source * @old_dentry: source * @new_parent: parent of destination * @new_dentry: destination * @delegated_inode: returns an inode needing a delegation break * @flags: rename flags */ struct renamedata { struct mnt_idmap *mnt_idmap; struct dentry *old_parent; struct dentry *old_dentry; struct dentry *new_parent; struct dentry *new_dentry; struct inode **delegated_inode; unsigned int flags; } __randomize_layout; int vfs_rename(struct renamedata *); static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV); } struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred); struct file *kernel_file_open(const struct path *path, int flags, const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); int vfs_fchown(struct file *file, uid_t user, gid_t group); int vfs_fchmod(struct file *file, umode_t mode); int vfs_utimes(const struct path *path, struct timespec64 *times); #ifdef CONFIG_COMPAT extern long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #else #define compat_ptr_ioctl NULL #endif /* * VFS file helper functions. */ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode); bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. * Return 'true' to keep going and 'false' if there are no more entries. */ struct dir_context; typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { filldir_t actor; loff_t pos; /* * Filesystems MUST NOT MODIFY count, but may use as a hint: * 0 unknown * > 0 space in buffer (assume at least one entry) * INT_MAX unlimited */ int count; }; /* If OR-ed with d_type, pending signals are not checked */ #define FILLDIR_FLAG_NOINTR 0x1000 /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. * * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) * NOMMU_MAP_READ: Can be mapped for reading * NOMMU_MAP_WRITE: Can be mapped for writing * NOMMU_MAP_EXEC: Can be mapped for execution */ #define NOMMU_MAP_COPY 0x00000001 #define NOMMU_MAP_DIRECT 0x00000008 #define NOMMU_MAP_READ VM_MAYREAD #define NOMMU_MAP_WRITE VM_MAYWRITE #define NOMMU_MAP_EXEC VM_MAYEXEC #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) /* * These flags control the behavior of the remap_file_range function pointer. * If it is called with len == 0 that means "remap to end of source file". * See Documentation/filesystems/vfs.rst for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) #define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of * the behavior of the remap operation. The changes must be made by the * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) /* * These flags control the behavior of vfs_copy_file_range(). * They are not available to the user via syscall. * * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops */ #define COPY_FILE_SPLICE (1 << 0) struct iov_iter; struct io_uring_cmd; struct offset_ctx; typedef unsigned int __bitwise fop_flags_t; struct file_operations { struct module *owner; fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *, unsigned int flags); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); void (*splice_eof)(struct file *file); int (*setlease)(struct file *, int, struct file_lease **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *, unsigned int poll_flags); int (*mmap_prepare)(struct vm_area_desc *); } __randomize_layout; /* Supports async buffered reads */ #define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) /* Supports async buffered writes */ #define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) /* Supports synchronous page faults for mappings */ #define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) /* Supports non-exclusive O_DIRECT writes from multiple threads */ #define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) /* Contains huge pages */ #define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) /* Treat loff_t as unsigned (e.g., /dev/mem) */ #define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) /* Supports asynchronous lock callbacks */ #define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) /* File system supports uncached read/write buffered IO */ #define FOP_DONTCACHE ((__force fop_flags_t)(1 << 7)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); #define WRAP_DIR_ITER(x) \ static int shared_##x(struct file *file , struct dir_context *ctx) \ { return wrap_directory_iterator(file, ctx, x); } struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct mnt_idmap *, struct inode *, int); struct posix_acl * (*get_inode_acl)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); int (*create) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *, const char *); struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *, struct dentry *, umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *, umode_t,dev_t); int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *); int (*getattr) (struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct mnt_idmap *, struct inode *, struct file *, umode_t); struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *, int); int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int); int (*fileattr_set)(struct mnt_idmap *idmap, struct dentry *dentry, struct file_kattr *fa); int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa); struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; /* Did the driver provide valid mmap hook configuration? */ static inline bool can_mmap_file(struct file *file) { bool has_mmap = file->f_op->mmap; bool has_mmap_prepare = file->f_op->mmap_prepare; /* Hooks are mutually exclusive. */ if (WARN_ON_ONCE(has_mmap && has_mmap_prepare)) return false; if (!has_mmap && !has_mmap_prepare) return false; return true; } int __compat_vma_mmap_prepare(const struct file_operations *f_op, struct file *file, struct vm_area_struct *vma); int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma); static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma) { if (file->f_op->mmap_prepare) return compat_vma_mmap_prepare(file, vma); return file->f_op->mmap(file, vma); } static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc) { return file->f_op->mmap_prepare(desc); } extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write); int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, const struct iomap_ops *dax_read_ops); int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); /** * enum freeze_holder - holder of the freeze * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed * @FREEZE_EXCL: a freeze that can only be undone by the owner * * Indicate who the owner of the freeze or thaw request is and whether * the freeze needs to be exclusive or can nest. * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the * same holder aren't allowed. It is however allowed to hold a single * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at * the same time. This is relied upon by some filesystems during online * repair or similar. */ enum freeze_holder { FREEZE_HOLDER_KERNEL = (1U << 0), FREEZE_HOLDER_USERSPACE = (1U << 1), FREEZE_MAY_NEST = (1U << 2), FREEZE_EXCL = (1U << 3), }; struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); void (*free_inode)(struct inode *); void (*dirty_inode) (struct inode *, int flags); int (*write_inode) (struct inode *, struct writeback_control *wbc); int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); int (*freeze_super) (struct super_block *, enum freeze_holder who, const void *owner); int (*freeze_fs) (struct super_block *); int (*thaw_super) (struct super_block *, enum freeze_holder who, const void *owner); int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); int (*show_devname)(struct seq_file *, struct dentry *); int (*show_path)(struct seq_file *, struct dentry *); int (*show_stats)(struct seq_file *, struct dentry *); #ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot __rcu **(*get_dquots)(struct inode *); #endif long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); /* * If a filesystem can support graceful removal of a device and * continue read-write operations, implement this callback. * * Return 0 if the filesystem can continue read-write. * Non-zero return value or no such callback means the fs will be shutdown * as usual. */ int (*remove_bdev)(struct super_block *sb, struct block_device *bdev); void (*shutdown)(struct super_block *sb); }; /* * Inode flags - they have no relation to superblock flags now */ #define S_SYNC (1 << 0) /* Writes are synced at once */ #define S_NOATIME (1 << 1) /* Do not update access times */ #define S_APPEND (1 << 2) /* Append-only file */ #define S_IMMUTABLE (1 << 3) /* Immutable file */ #define S_DEAD (1 << 4) /* removed, but still open directory */ #define S_NOQUOTA (1 << 5) /* Inode is not counted to quota */ #define S_DIRSYNC (1 << 6) /* Directory modifications are synchronous */ #define S_NOCMTIME (1 << 7) /* Do not update file c/mtime */ #define S_SWAPFILE (1 << 8) /* Do not truncate: swapon got its bmaps */ #define S_PRIVATE (1 << 9) /* Inode is fs-internal */ #define S_IMA (1 << 10) /* Inode has an associated IMA struct */ #define S_AUTOMOUNT (1 << 11) /* Automount/referral quasi-directory */ #define S_NOSEC (1 << 12) /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX #define S_DAX (1 << 13) /* Direct Access, avoiding the page cache */ #else #define S_DAX 0 /* Make all the DAX code disappear */ #endif #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ #define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ #define S_ANON_INODE (1 << 19) /* Inode is an anonymous inode */ /* * Note that nosuid etc flags are inode-specific: setting some file-system * flags just means all the inodes inherit those flags by default. It might be * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their * i_flags updated. Hence, i_flags no longer inherit the superblock mount * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) #define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) #define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) #ifdef CONFIG_FS_POSIX_ACL #define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) #else #define IS_POSIXACL(inode) 0 #endif #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) #ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #else #define IS_SWAPFILE(inode) ((void)(inode), 0U) #endif #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) #define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) #define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) #define IS_VERITY(inode) ((inode)->i_flags & S_VERITY) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) #define IS_ANON_FILE(inode) ((inode)->i_flags & S_ANON_INODE) static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap, struct inode *inode) { return !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) || !vfsgid_valid(i_gid_into_vfsgid(idmap, inode)); } static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = filp->f_iocb_flags, .ki_ioprio = get_current_ioprio(), }; } static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, struct file *filp) { *kiocb = (struct kiocb) { .ki_filp = filp, .ki_flags = kiocb_src->ki_flags, .ki_ioprio = kiocb_src->ki_ioprio, .ki_pos = kiocb_src->ki_pos, }; } extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY); } static inline void mark_inode_dirty_sync(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY_SYNC); } static inline int icount_read(const struct inode *inode) { return atomic_read(&inode->i_count); } /* * Returns true if the given inode itself only has dirty timestamps (its pages * may still be dirty) and isn't currently being allocated or freed. * Filesystems should call this if when writing an inode when lazytime is * enabled, they want to opportunistically write the timestamps of other inodes * located very nearby on-disk, e.g. in the same inode block. This returns true * if the given inode is in need of such an opportunistic update. Requires * i_lock, or at least later re-checking under i_lock. */ static inline bool inode_is_dirtytime_only(struct inode *inode) { return (inode->i_state & (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; } extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(struct inode *inode); extern void set_nlink(struct inode *inode, unsigned int nlink); static inline void inode_inc_link_count(struct inode *inode) { inc_nlink(inode); mark_inode_dirty(inode); } static inline void inode_dec_link_count(struct inode *inode) { drop_nlink(inode); mark_inode_dirty(inode); } enum file_time_flags { S_ATIME = 1, S_MTIME = 2, S_CTIME = 4, S_VERSION = 8, }; extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); int inode_update_time(struct inode *inode, int flags); static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) touch_atime(&file->f_path); } extern int file_modified(struct file *file); int kiocb_modified(struct kiocb *iocb); int sync_inode_metadata(struct inode *inode, int wait); struct file_system_type { const char *name; int fs_flags; #define FS_REQUIRES_DEV 1 #define FS_BINARY_MOUNTDATA 2 #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_MGTIME 64 /* FS uses multigrain timestamps */ #define FS_LBS 128 /* FS supports LBS */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); void (*kill_sb) (struct super_block *); struct module *owner; struct file_system_type * next; struct hlist_head fs_supers; struct lock_class_key s_lock_key; struct lock_class_key s_umount_key; struct lock_class_key s_vfs_rename_key; struct lock_class_key s_writers_key[SB_FREEZE_LEVELS]; struct lock_class_key i_lock_key; struct lock_class_key i_mutex_key; struct lock_class_key invalidate_lock_key; struct lock_class_key i_mutex_dir_key; }; #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) /** * is_mgtime: is this inode using multigrain timestamps * @inode: inode to test for multigrain timestamps * * Return true if the inode uses multigrain timestamps, false otherwise. */ static inline bool is_mgtime(const struct inode *inode) { return inode->i_opflags & IOP_MGTIME; } extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void retire_super(struct super_block *sb); void generic_shutdown_super(struct super_block *sb); void kill_block_super(struct super_block *sb); void kill_anon_super(struct super_block *sb); void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); void deactivate_locked_super(struct super_block *sb); int set_anon_super(struct super_block *s, void *data); int set_anon_super_fc(struct super_block *s, struct fs_context *fc); int get_anon_bdev(dev_t *); void free_anon_bdev(dev_t); struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*set)(struct super_block *, struct fs_context *)); struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data); struct super_block *sget_dev(struct fs_context *fc, dev_t dev); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ #define fops_get(fops) ({ \ const struct file_operations *_fops = (fops); \ (((_fops) && try_module_get((_fops)->owner) ? (_fops) : NULL)); \ }) #define fops_put(fops) ({ \ const struct file_operations *_fops = (fops); \ if (_fops) \ module_put((_fops)->owner); \ }) /* * This one is to be used *ONLY* from ->open() instances. * fops must be non-NULL, pinned down *and* module dependencies * should be sufficient to pin the caller down as well. */ #define replace_fops(f, fops) \ do { \ struct file *__file = (f); \ fops_put(__file->f_op); \ BUG_ON(!(__file->f_op = (fops))); \ } while(0) extern int register_filesystem(struct file_system_type *); extern int unregister_filesystem(struct file_system_type *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); int freeze_super(struct super_block *super, enum freeze_holder who, const void *freeze_owner); int thaw_super(struct super_block *super, enum freeze_holder who, const void *freeze_owner); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len) { if (WARN_ON(len > sizeof(sb->s_uuid))) len = sizeof(sb->s_uuid); sb->s_uuid_len = len; memcpy(&sb->s_uuid, uuid, len); } /* set sb sysfs name based on sb->s_bdev */ static inline void super_set_sysfs_name_bdev(struct super_block *sb) { snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev); } /* set sb sysfs name based on sb->s_uuid */ static inline void super_set_sysfs_name_uuid(struct super_block *sb) { WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid)); snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b); } /* set sb sysfs name based on sb->s_id */ static inline void super_set_sysfs_name_id(struct super_block *sb) { strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name)); } /* try to use something standard before you use this */ __printf(2, 3) static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...) { va_list args; va_start(args, fmt); vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args); va_end(args); } extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); int inode_update_timestamps(struct inode *inode, int flags); int generic_update_time(struct inode *, int); /* /sys/fs */ extern struct kobject *fs_kobj; #define MAX_RW_COUNT (INT_MAX & PAGE_MASK) /* fs/open.c */ struct audit_names; struct filename { const char *name; /* pointer to actual string */ const __user char *uptr; /* original userland pointer */ atomic_t refcnt; struct audit_names *aname; const char iname[]; }; static_assert(offsetof(struct filename, iname) % sizeof(long) == 0); static inline struct mnt_idmap *file_mnt_idmap(const struct file *file) { return mnt_idmap(file->f_path.mnt); } /** * is_idmapped_mnt - check whether a mount is mapped * @mnt: the mount to check * * If @mnt has an non @nop_mnt_idmap attached to it then @mnt is mapped. * * Return: true if mount is mapped, false if not. */ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) { return mnt_idmap(mnt) != &nop_mnt_idmap; } int vfs_truncate(const struct path *, loff_t); int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); extern int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len); int do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode); extern struct file *file_open_name(struct filename *, int, umode_t); extern struct file *filp_open(const char *, int, umode_t); extern struct file *file_open_root(const struct path *, const char *, int, umode_t); static inline struct file *file_open_root_mnt(struct vfsmount *mnt, const char *name, int flags, umode_t mode) { return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, name, flags, mode); } struct file *dentry_open(const struct path *path, int flags, const struct cred *creds); struct file *dentry_open_nonotify(const struct path *path, int flags, const struct cred *cred); struct file *dentry_create(const struct path *path, int flags, umode_t mode, const struct cred *cred); const struct path *backing_file_user_path(const struct file *f); /* * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file * stored in ->vm_file is a backing file whose f_inode is on the underlying * filesystem. When the mapped file path and inode number are displayed to * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the * path and inode number to display to the user, which is the path of the fd * that user has requested to map and the inode number that would be returned * by fstat() on that same fd. */ /* Get the path to display in /proc/<pid>/maps */ static inline const struct path *file_user_path(const struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return backing_file_user_path(f); return &f->f_path; } /* Get the inode whose inode number to display in /proc/<pid>/maps */ static inline const struct inode *file_user_inode(const struct file *f) { if (unlikely(f->f_mode & FMODE_BACKING)) return d_inode(backing_file_user_path(f)->dentry); return file_inode(f); } static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); } extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); static inline struct filename *getname(const char __user *name) { return getname_flags(name, 0); } extern struct filename *getname_kernel(const char *); extern struct filename *__getname_maybe_null(const char __user *); static inline struct filename *getname_maybe_null(const char __user *name, int flags) { if (!(flags & AT_EMPTY_PATH)) return getname(name); if (!name) return NULL; return __getname_maybe_null(name); } extern void putname(struct filename *name); DEFINE_FREE(putname, struct filename *, if (!IS_ERR_OR_NULL(_T)) putname(_T)) static inline struct filename *refname(struct filename *name) { atomic_inc(&name->refcnt); return name; } extern int finish_open(struct file *file, struct dentry *dentry, int (*open)(struct inode *, struct file *)); extern int finish_no_open(struct file *file, struct dentry *dentry); /* Helper for the simple case when original dentry is used */ static inline int finish_open_simple(struct file *file, int error) { if (error) return error; return finish_open(file, file->f_path.dentry, NULL); } /* fs/dcache.c */ extern void __init vfs_caches_init_early(void); extern void __init vfs_caches_init(void); extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) extern struct super_block *blockdev_superblock; static inline bool sb_is_blkdev_sb(struct super_block *sb) { return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 /* Marks the top and bottom of the second segment of free char majors */ #define CHRDEV_MAJOR_DYN_EXT_START 511 #define CHRDEV_MAJOR_DYN_EXT_END 384 extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name, const struct file_operations *fops); extern void __unregister_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name); extern void unregister_chrdev_region(dev_t, unsigned); extern void chrdev_show(struct seq_file *,off_t); static inline int register_chrdev(unsigned int major, const char *name, const struct file_operations *fops) { return __register_chrdev(major, 0, 256, name, fops); } static inline void unregister_chrdev(unsigned int major, const char *name) { __unregister_chrdev(major, 0, 256, name); } extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, loff_t end); static inline int file_write_and_wait(struct file *file) { return file_write_and_wait_range(file, 0, LLONG_MAX); } extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes, unsigned int flags); static inline bool iocb_is_dsync(const struct kiocb *iocb) { return (iocb->ki_flags & IOCB_DSYNC) || IS_SYNC(iocb->ki_filp->f_mapping->host); } /* * Sync the bytes written if this was a synchronous write. Expect ki_pos * to already be updated for the write, and will return either the amount * of bytes passed in, or an error if syncing the file failed. */ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) { if (iocb_is_dsync(iocb)) { int ret = vfs_fsync_range(iocb->ki_filp, iocb->ki_pos - count, iocb->ki_pos - 1, (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; } else if (iocb->ki_flags & IOCB_DONTCACHE) { struct address_space *mapping = iocb->ki_filp->f_mapping; filemap_fdatawrite_range_kick(mapping, iocb->ki_pos - count, iocb->ki_pos - 1); } return count; } extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK extern int bmap(struct inode *inode, sector_t *block); #else static inline int bmap(struct inode *inode, sector_t *block) { return -EINVAL; } #endif int notify_change(struct mnt_idmap *, struct dentry *, struct iattr *, struct inode **); int inode_permission(struct mnt_idmap *, struct inode *, int); int generic_permission(struct mnt_idmap *, struct inode *, int); static inline int file_permission(struct file *file, int mask) { return inode_permission(file_mnt_idmap(file), file_inode(file), mask); } static inline int path_permission(const struct path *path, int mask) { return inode_permission(mnt_idmap(path->mnt), d_inode(path->dentry), mask); } int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode); static inline bool execute_ok(struct inode *inode) { return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) { return (inode->i_mode ^ mode) & S_IFMT; } /** * file_start_write - get write access to a superblock for regular file io * @file: the file we want to write to * * This is a variant of sb_start_write() which is a noop on non-regualr file. * Should be matched with a call to file_end_write(). */ static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; return sb_start_write_trylock(file_inode(file)->i_sb); } /** * file_end_write - drop write access to a superblock of a regular file * @file: the file we wrote to * * Should be matched with a call to file_start_write(). */ static inline void file_end_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; sb_end_write(file_inode(file)->i_sb); } /** * kiocb_start_write - get write access to a superblock for async file io * @iocb: the io context we want to submit the write with * * This is a variant of sb_start_write() for async io submission. * Should be matched with a call to kiocb_end_write(). */ static inline void kiocb_start_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); sb_start_write(inode->i_sb); /* * Fool lockdep by telling it the lock got released so that it * doesn't complain about the held lock when we return to userspace. */ __sb_writers_release(inode->i_sb, SB_FREEZE_WRITE); } /** * kiocb_end_write - drop write access to a superblock after async file io * @iocb: the io context we sumbitted the write with * * Should be matched with a call to kiocb_start_write(). */ static inline void kiocb_end_write(struct kiocb *iocb) { struct inode *inode = file_inode(iocb->ki_filp); /* * Tell lockdep we inherited freeze protection from submission thread. */ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); sb_end_write(inode->i_sb); } /* * This is used for regular files where some users -- especially the * currently executed binary in a process, previously handled via * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap * read-write shared) accesses. * * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. * deny_write_access() denies write access to a file. * allow_write_access() re-enables write access to a file. * * The i_writecount field of an inode can have the following values: * 0: no write access, no denied write access * < 0: (-i_writecount) users that denied write access to the file. * > 0: (i_writecount) users that have write access to the file. * * Normally we operate on that counter with atomic_{inc,dec} and it's safe * except for the cases where we don't hold i_writecount yet. Then we need to * use {get,deny}_write_access() - these functions check the sign and refuse * to do the change if sign is wrong. */ static inline int get_write_access(struct inode *inode) { return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline int deny_write_access(struct file *file) { struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); } static inline void allow_write_access(struct file *file) { if (file) atomic_inc(&file_inode(file)->i_writecount); } /* * Do not prevent write to executable file when watched by pre-content events. * * Note that FMODE_FSNOTIFY_HSM mode is set depending on pre-content watches at * the time of file open and remains constant for entire lifetime of the file, * so if pre-content watches are added post execution or removed before the end * of the execution, it will not cause i_writecount reference leak. */ static inline int exe_file_deny_write_access(struct file *exe_file) { if (unlikely(FMODE_FSNOTIFY_HSM(exe_file->f_mode))) return 0; return deny_write_access(exe_file); } static inline void exe_file_allow_write_access(struct file *exe_file) { if (unlikely(!exe_file || FMODE_FSNOTIFY_HSM(exe_file->f_mode))) return; allow_write_access(exe_file); } static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode) { file->f_mode &= ~FMODE_FSNOTIFY_MASK; file->f_mode |= mode; } static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; } #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) static inline void i_readcount_dec(struct inode *inode) { BUG_ON(atomic_dec_return(&inode->i_readcount) < 0); } static inline void i_readcount_inc(struct inode *inode) { atomic_inc(&inode->i_readcount); } #else static inline void i_readcount_dec(struct inode *inode) { return; } static inline void i_readcount_inc(struct inode *inode) { return; } #endif extern int do_pipe_flags(int *, int); extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos); extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(const struct path *, const struct path *); extern char *file_path(struct file *, char *, int); /** * is_dot_dotdot - returns true only if @name is "." or ".." * @name: file name to check * @len: length of file name, in bytes */ static inline bool is_dot_dotdot(const char *name, size_t len) { return len && unlikely(name[0] == '.') && (len == 1 || (len == 2 && name[1] == '.')); } /** * name_contains_dotdot - check if a file name contains ".." path components * @name: File path string to check * Search for ".." surrounded by either '/' or start/end of string. */ static inline bool name_contains_dotdot(const char *name) { size_t name_len; name_len = strlen(name); return strcmp(name, "..") == 0 || strncmp(name, "../", 3) == 0 || strstr(name, "/../") != NULL || (name_len >= 3 && strcmp(name + name_len - 3, "/..") == 0); } #include <linux/err.h> /* needed for stackable file system support */ extern loff_t default_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence); extern int inode_init_always_gfp(struct super_block *, struct inode *, gfp_t); static inline int inode_init_always(struct super_block *sb, struct inode *inode) { return inode_init_always_gfp(sb, inode, GFP_NOFS); } extern void inode_init_once(struct inode *); extern void address_space_init_once(struct address_space *mapping); extern struct inode * igrab(struct inode *); extern ino_t iunique(struct super_block *, ino_t); extern int inode_needs_sync(struct inode *inode); extern int inode_just_drop(struct inode *inode); static inline int inode_generic_drop(struct inode *inode) { return !inode->i_nlink || inode_unhashed(inode); } extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); struct inode *iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); struct inode *iget5_locked_rcu(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); extern struct inode *find_inode_nowait(struct super_block *, unsigned long, int (*match)(struct inode *, unsigned long, void *), void *data); extern struct inode *find_inode_rcu(struct super_block *, unsigned long, int (*)(struct inode *, void *), void *); extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long); extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *); extern int insert_inode_locked(struct inode *); #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void lockdep_annotate_inode_mutex_key(struct inode *inode); #else static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); void dump_mapping(const struct address_space *); /* * Userspace may rely on the inode number being non-zero. For example, glibc * simply ignores files with zero i_ino in unlink() and other places. * * As an additional complication, if userspace was compiled with * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the * lower 32 bits, so we need to check that those aren't zero explicitly. With * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but * better safe than sorry. */ static inline bool is_zero_ino(ino_t ino) { return (u32)ino == 0; } /* * inode->i_lock must be held */ static inline void __iget(struct inode *inode) { atomic_inc(&inode->i_count); } extern void iget_failed(struct inode *); extern void clear_inode(struct inode *); extern void __destroy_inode(struct inode *); struct inode *alloc_inode(struct super_block *sb); static inline struct inode *new_inode_pseudo(struct super_block *sb) { return alloc_inode(sb); } extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); extern int file_remove_privs(struct file *); int setattr_should_drop_sgid(struct mnt_idmap *idmap, const struct inode *inode); /* * This must be used for allocating filesystems specific inodes to set * up the inode reclaim context correctly. */ #define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp) extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) { __insert_inode_hash(inode, inode->i_ino); } extern void __remove_inode_hash(struct inode *); static inline void remove_inode_hash(struct inode *inode) { if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash)) __remove_inode_hash(inode); } extern void inode_sb_list_add(struct inode *inode); extern void inode_add_lru(struct inode *inode); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); int generic_file_mmap(struct file *, struct vm_area_struct *); int generic_file_mmap_prepare(struct vm_area_desc *desc); int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); int generic_write_checks_count(struct kiocb *iocb, loff_t *count); extern int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count); extern int generic_file_rw_checks(struct file *file_in, struct file *file_out); ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to, ssize_t already_read); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); ssize_t generic_perform_write(struct kiocb *, struct iov_iter *); ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, ssize_t direct_written, ssize_t buffered_written); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags); ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter); ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter); /* fs/splice.c */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); ssize_t copy_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping); extern loff_t noop_llseek(struct file *file, loff_t offset, int whence); extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, u64 *cookie); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); int rw_verify_area(int, struct file *, const loff_t *, size_t); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, loff_t file_offset); enum { /* need locking between buffered and direct access */ DIO_LOCKING = 0x01, /* filesystem does not support filling holes */ DIO_SKIP_HOLES = 0x02, }; ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct iov_iter *iter, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif bool inode_dio_finished(const struct inode *inode); void inode_dio_wait(struct inode *inode); void inode_dio_wait_interruptible(struct inode *inode); /** * inode_dio_begin - signal start of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_begin(struct inode *inode) { atomic_inc(&inode->i_dio_count); } /** * inode_dio_end - signal finish of a direct I/O requests * @inode: inode the direct I/O happens on * * This is called once we've finished processing a direct I/O request, * and is used to wake up callers waiting for direct I/O to be quiesced. */ static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) wake_up_var(&inode->i_dio_count); } extern void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask); extern const struct file_operations generic_ro_fops; #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m)) extern int readlink_copy(char __user *, int, const char *, int); extern int page_readlink(struct dentry *, char __user *, int); extern const char *page_get_link_raw(struct dentry *, struct inode *, struct delayed_call *); extern const char *page_get_link(struct dentry *, struct inode *, struct delayed_call *); extern void page_put_link(void *); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); void generic_fill_statx_atomic_writes(struct kstat *stat, unsigned int unit_min, unsigned int unit_max, unsigned int unit_max_opt); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); static inline loff_t __inode_get_bytes(struct inode *inode) { return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; } loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); const char *simple_get_link(struct dentry *, struct inode *, struct delayed_call *); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags); int vfs_fstat(int fd, struct kstat *stat); static inline int vfs_stat(const char __user *filename, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, filename, stat, 0); } static inline int vfs_lstat(const char __user *name, struct kstat *stat) { return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW); } extern const char *vfs_get_link(struct dentry *, struct delayed_call *); extern int vfs_readlink(struct dentry *, char __user *, int); extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern void drop_super(struct super_block *sb); extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*f)(struct super_block *, void *), void *arg); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); void filesystems_freeze(void); void filesystems_thaw(void); extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, struct dir_context *); extern int simple_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); extern int simple_getattr(struct mnt_idmap *, const struct path *, struct kstat *, u32, unsigned int); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename(struct mnt_idmap *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern void simple_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern void locked_recursive_removal(struct dentry *, void (*callback)(struct dentry *)); extern int noop_fsync(struct file *, loff_t, loff_t, int); extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name, const struct inode *context_inode); extern int simple_nosetlease(struct file *, int, struct file_lease **, void **); extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags); extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *); extern const struct file_operations simple_dir_operations; extern const struct inode_operations simple_dir_inode_operations; extern void make_empty_dir_inode(struct inode *inode); extern bool is_empty_dir_inode(struct inode *inode); struct tree_descr { const char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, unsigned long, const struct tree_descr *); extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); struct dentry *simple_start_creating(struct dentry *, const char *); extern ssize_t simple_read_from_buffer(void __user *to, size_t count, loff_t *ppos, const void *from, size_t available); extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); struct offset_ctx { struct maple_tree mt; unsigned long next_offset; }; void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry); void simple_offset_destroy(struct offset_ctx *octx); extern const struct file_operations simple_offset_dir_operations; extern int __generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); extern void generic_set_sb_d_ops(struct super_block *sb); extern int generic_ci_match(const struct inode *parent, const struct qstr *name, const struct qstr *folded_name, const u8 *de_name, u32 de_name_len); #if IS_ENABLED(CONFIG_UNICODE) int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str); int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name); /** * generic_ci_validate_strict_name - Check if a given name is suitable * for a directory * * This functions checks if the proposed filename is valid for the * parent directory. That means that only valid UTF-8 filenames will be * accepted for casefold directories from filesystems created with the * strict encoding flag. That also means that any name will be * accepted for directories that doesn't have casefold enabled, or * aren't being strict with the encoding. * * @dir: inode of the directory where the new file will be created * @name: name of the new file * * Return: * * True: if the filename is suitable for this directory. It can be * true if a given name is not suitable for a strict encoding * directory, but the directory being used isn't strict * * False if the filename isn't suitable for this directory. This only * happens when a directory is casefolded and the filesystem is strict * about its encoding. */ static inline bool generic_ci_validate_strict_name(struct inode *dir, const struct qstr *name) { if (!IS_CASEFOLDED(dir) || !sb_has_strict_encoding(dir->i_sb)) return true; /* * A casefold dir must have a encoding set, unless the filesystem * is corrupted */ if (WARN_ON_ONCE(!dir->i_sb->s_encoding)) return true; return !utf8_validate(dir->i_sb->s_encoding, name); } #else static inline bool generic_ci_validate_strict_name(struct inode *dir, const struct qstr *name) { return true; } #endif static inline struct unicode_map *sb_encoding(const struct super_block *sb) { #if IS_ENABLED(CONFIG_UNICODE) return sb->s_encoding; #else return NULL; #endif } static inline bool sb_has_encoding(const struct super_block *sb) { return !!sb_encoding(sb); } /* * Compare if two super blocks have the same encoding and flags */ static inline bool sb_same_encoding(const struct super_block *sb1, const struct super_block *sb2) { #if IS_ENABLED(CONFIG_UNICODE) if (sb1->s_encoding == sb2->s_encoding) return true; return (sb1->s_encoding && sb2->s_encoding && (sb1->s_encoding->version == sb2->s_encoding->version) && (sb1->s_encoding_flags == sb2->s_encoding_flags)); #else return true; #endif } int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); void setattr_copy(struct mnt_idmap *, struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); static inline bool file_is_dax(const struct file *file) { return file && IS_DAX(file->f_mapping->host); } static inline bool vma_is_dax(const struct vm_area_struct *vma) { return file_is_dax(vma->vm_file); } static inline bool vma_is_fsdax(struct vm_area_struct *vma) { struct inode *inode; if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file) return false; if (!vma_is_dax(vma)) return false; inode = file_inode(vma->vm_file); if (S_ISCHR(inode->i_mode)) return false; /* device-dax */ return true; } static inline int iocb_flags(struct file *file) { int res = 0; if (file->f_flags & O_APPEND) res |= IOCB_APPEND; if (file->f_flags & O_DIRECT) res |= IOCB_DIRECT; if (file->f_flags & O_DSYNC) res |= IOCB_DSYNC; if (file->f_flags & __O_SYNC) res |= IOCB_SYNC; return res; } static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, int rw_type) { int kiocb_flags = 0; /* make sure there's no overlap between RWF and private IOCB flags */ BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD); if (!flags) return 0; if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND))) return -EINVAL; if (flags & RWF_NOWAIT) { if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) return -EOPNOTSUPP; } if (flags & RWF_ATOMIC) { if (rw_type != WRITE) return -EOPNOTSUPP; if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) return -EOPNOTSUPP; } if (flags & RWF_DONTCACHE) { /* file system must support it */ if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE)) return -EOPNOTSUPP; /* DAX mappings not supported */ if (IS_DAX(ki->ki_filp->f_mapping->host)) return -EOPNOTSUPP; } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) { if (IS_APPEND(file_inode(ki->ki_filp))) return -EPERM; ki->ki_flags &= ~IOCB_APPEND; } ki->ki_flags |= kiocb_flags; return 0; } /* Transaction based IO helpers */ /* * An argresp is stored in an allocated page and holds the * size of the argument or response, along with its content */ struct simple_transaction_argresp { ssize_t size; char data[]; }; #define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp)) char *simple_transaction_get(struct file *file, const char __user *buf, size_t size); ssize_t simple_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos); int simple_transaction_release(struct inode *inode, struct file *file); void simple_transaction_set(struct file *file, size_t n); /* * simple attribute files * * These attributes behave similar to those in sysfs: * * Writing to an attribute immediately sets a value, an open file can be * written to multiple times. * * Reading from an attribute creates a buffer from the value that might get * read with multiple read calls. When the attribute has been read * completely, no further read calls are possible until the file is opened * again. * * All attributes contain a text representation of a numeric value * that are accessed with the get() and set() functions. */ #define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed) \ static int __fops ## _open(struct inode *inode, struct file *file) \ { \ __simple_attr_check_format(__fmt, 0ull); \ return simple_attr_open(inode, file, __get, __set, __fmt); \ } \ static const struct file_operations __fops = { \ .owner = THIS_MODULE, \ .open = __fops ## _open, \ .release = simple_attr_release, \ .read = simple_attr_read, \ .write = (__is_signed) ? simple_attr_write_signed : simple_attr_write, \ .llseek = generic_file_llseek, \ } #define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false) #define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt) \ DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true) static inline __printf(1, 2) void __simple_attr_check_format(const char *fmt, ...) { /* don't do anything, just let the compiler check the arguments; */ } int simple_attr_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt); int simple_attr_release(struct inode *inode, struct file *file); ssize_t simple_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); ssize_t simple_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE]) #define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE)) static inline bool is_sxid(umode_t mode) { return mode & (S_ISUID | S_ISGID); } static inline int check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { if (!(dir->i_mode & S_ISVTX)) return 0; return __check_sticky(idmap, dir, inode); } static inline void inode_has_no_xattr(struct inode *inode) { if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } static inline bool is_root_inode(struct inode *inode) { return inode == inode->i_sb->s_root->d_inode; } static inline bool dir_emit(struct dir_context *ctx, const char *name, int namelen, u64 ino, unsigned type) { return ctx->actor(ctx, name, namelen, ctx->pos, ino, type); } static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, ".", 1, ctx->pos, file->f_path.dentry->d_inode->i_ino, DT_DIR); } static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, d_parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) return false; ctx->pos = 1; } if (ctx->pos == 1) { if (!dir_emit_dotdot(file, ctx)) return false; ctx->pos = 2; } return true; } static inline bool dir_relax(struct inode *inode) { inode_unlock(inode); inode_lock(inode); return !IS_DEADDIR(inode); } static inline bool dir_relax_shared(struct inode *inode) { inode_unlock_shared(inode); inode_lock_shared(inode); return !IS_DEADDIR(inode); } extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); /* mm/fadvise.c */ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice); extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); static inline bool vfs_empty_path(int dfd, const char __user *path) { char c; if (dfd < 0) return false; /* We now allow NULL to be used for empty path. */ if (!path) return true; if (unlikely(get_user(c, path))) return false; return !c; } int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter); static inline bool extensible_ioctl_valid(unsigned int cmd_a, unsigned int cmd_b, size_t min_size) { if (_IOC_DIR(cmd_a) != _IOC_DIR(cmd_b)) return false; if (_IOC_TYPE(cmd_a) != _IOC_TYPE(cmd_b)) return false; if (_IOC_NR(cmd_a) != _IOC_NR(cmd_b)) return false; if (_IOC_SIZE(cmd_a) < min_size) return false; return true; } #endif /* _LINUX_FS_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 | /* SPDX-License-Identifier: GPL-1.0+ */ /* * Bond several ethernet interfaces into a Cisco, running 'Etherchannel'. * * Portions are (c) Copyright 1995 Simon "Guru Aleph-Null" Janes * NCM: Network and Communications Management, Inc. * * BUT, I'm the one who modified it for ethernet, so: * (c) Copyright 1999, Thomas Davis, tadavis@lbl.gov * */ #ifndef _NET_BONDING_H #define _NET_BONDING_H #include <linux/timer.h> #include <linux/proc_fs.h> #include <linux/if_bonding.h> #include <linux/cpumask.h> #include <linux/in6.h> #include <linux/netpoll.h> #include <linux/inetdevice.h> #include <linux/etherdevice.h> #include <linux/reciprocal_div.h> #include <linux/if_link.h> #include <net/bond_3ad.h> #include <net/bond_alb.h> #include <net/bond_options.h> #include <net/ipv6.h> #include <net/addrconf.h> #define BOND_MAX_ARP_TARGETS 16 #define BOND_MAX_NS_TARGETS BOND_MAX_ARP_TARGETS #define BOND_DEFAULT_MIIMON 100 #ifndef __long_aligned #define __long_aligned __attribute__((aligned((sizeof(long))))) #endif #define slave_info(bond_dev, slave_dev, fmt, ...) \ netdev_info(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_warn(bond_dev, slave_dev, fmt, ...) \ netdev_warn(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_dbg(bond_dev, slave_dev, fmt, ...) \ netdev_dbg(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define slave_err(bond_dev, slave_dev, fmt, ...) \ netdev_err(bond_dev, "(slave %s): " fmt, (slave_dev)->name, ##__VA_ARGS__) #define BOND_MODE(bond) ((bond)->params.mode) /* slave list primitives */ #define bond_slave_list(bond) (&(bond)->dev->adj_list.lower) #define bond_has_slaves(bond) !list_empty(bond_slave_list(bond)) /* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */ #define bond_first_slave(bond) \ (bond_has_slaves(bond) ? \ netdev_adjacent_get_private(bond_slave_list(bond)->next) : \ NULL) #define bond_last_slave(bond) \ (bond_has_slaves(bond) ? \ netdev_adjacent_get_private(bond_slave_list(bond)->prev) : \ NULL) /* Caller must have rcu_read_lock */ #define bond_first_slave_rcu(bond) \ netdev_lower_get_first_private_rcu(bond->dev) #define bond_is_first_slave(bond, pos) (pos == bond_first_slave(bond)) #define bond_is_last_slave(bond, pos) (pos == bond_last_slave(bond)) /** * bond_for_each_slave - iterate over all slaves * @bond: the bond holding this list * @pos: current slave * @iter: list_head * iterator * * Caller must hold RTNL */ #define bond_for_each_slave(bond, pos, iter) \ netdev_for_each_lower_private((bond)->dev, pos, iter) /* Caller must have rcu_read_lock */ #define bond_for_each_slave_rcu(bond, pos, iter) \ netdev_for_each_lower_private_rcu((bond)->dev, pos, iter) #define BOND_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; static inline void block_netpoll_tx(void) { atomic_inc(&netpoll_block_tx); } static inline void unblock_netpoll_tx(void) { atomic_dec(&netpoll_block_tx); } static inline int is_netpoll_tx_blocked(struct net_device *dev) { if (unlikely(netpoll_tx_running(dev))) return atomic_read(&netpoll_block_tx); return 0; } #else #define block_netpoll_tx() #define unblock_netpoll_tx() #define is_netpoll_tx_blocked(dev) (0) #endif DECLARE_STATIC_KEY_FALSE(bond_bcast_neigh_enabled); struct bond_params { int mode; int xmit_policy; int miimon; u8 num_peer_notif; u8 missed_max; int arp_interval; int arp_validate; int arp_all_targets; int fail_over_mac; int updelay; int downdelay; int peer_notif_delay; int lacp_active; int lacp_fast; unsigned int min_links; int ad_select; char primary[IFNAMSIZ]; int primary_reselect; __be32 arp_targets[BOND_MAX_ARP_TARGETS]; int tx_queues; int all_slaves_active; int resend_igmp; int lp_interval; int packets_per_slave; int tlb_dynamic_lb; struct reciprocal_value reciprocal_packets_per_slave; u16 ad_actor_sys_prio; u16 ad_user_port_key; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr ns_targets[BOND_MAX_NS_TARGETS]; #endif int coupled_control; int broadcast_neighbor; /* 2 bytes of padding : see ether_addr_equal_64bits() */ u8 ad_actor_system[ETH_ALEN + 2]; }; struct slave { struct net_device *dev; /* first - useful for panic debug */ struct bonding *bond; /* our master */ int delay; /* all 4 in jiffies */ unsigned long last_link_up; unsigned long last_tx; unsigned long last_rx; unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS]; s8 link; /* one of BOND_LINK_XXXX */ s8 link_new_state; /* one of BOND_LINK_XXXX */ u8 backup:1, /* indicates backup slave. Value corresponds with BOND_STATE_ACTIVE and BOND_STATE_BACKUP */ inactive:1, /* indicates inactive slave */ rx_disabled:1, /* indicates whether slave's Rx is disabled */ should_notify:1, /* indicates whether the state changed */ should_notify_link:1; /* indicates whether the link changed */ u8 duplex; u32 original_mtu; u32 link_failure_count; u32 speed; u16 queue_id; u8 perm_hwaddr[MAX_ADDR_LEN]; int prio; struct ad_slave_info *ad_info; struct tlb_slave_info tlb_info; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *np; #endif struct delayed_work notify_work; struct kobject kobj; struct rtnl_link_stats64 slave_stats; }; static inline struct slave *to_slave(struct kobject *kobj) { return container_of(kobj, struct slave, kobj); } struct bond_up_slave { unsigned int count; struct rcu_head rcu; struct slave *arr[]; }; /* * Link pseudo-state only used internally by monitors */ #define BOND_LINK_NOCHANGE -1 struct bond_ipsec { struct list_head list; struct xfrm_state *xs; }; /* * Here are the locking policies for the two bonding locks: * Get rcu_read_lock when reading or RTNL when writing slave list. */ struct bonding { struct net_device *dev; /* first - useful for panic debug */ struct slave __rcu *curr_active_slave; struct slave __rcu *current_arp_slave; struct slave __rcu *primary_slave; struct bond_up_slave __rcu *usable_slaves; struct bond_up_slave __rcu *all_slaves; bool force_primary; bool notifier_ctx; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); /* mode_lock is used for mode-specific locking needs, currently used by: * 3ad mode (4) - protect against running bond_3ad_unbind_slave() and * bond_3ad_state_machine_handler() concurrently and also * the access to the state machine shared variables. * TLB mode (5) - to sync the use and modifications of its hash table * ALB mode (6) - to sync the use and modifications of its hash table */ spinlock_t mode_lock; spinlock_t stats_lock; u32 send_peer_notif; u8 igmp_retrans; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_entry; char proc_file_name[IFNAMSIZ]; #endif /* CONFIG_PROC_FS */ struct list_head bond_list; u32 __percpu *rr_tx_counter; struct ad_bond_info ad_info; struct alb_bond_info alb_info; struct bond_params params; struct workqueue_struct *wq; struct delayed_work mii_work; struct delayed_work arp_work; struct delayed_work alb_work; struct delayed_work ad_work; struct delayed_work mcast_work; struct delayed_work slave_arr_work; #ifdef CONFIG_DEBUG_FS /* debugging support via debugfs */ struct dentry *debug_dir; #endif /* CONFIG_DEBUG_FS */ struct rtnl_link_stats64 bond_stats; #ifdef CONFIG_XFRM_OFFLOAD struct list_head ipsec_list; /* protecting ipsec_list */ struct mutex ipsec_lock; #endif /* CONFIG_XFRM_OFFLOAD */ struct bpf_prog *xdp_prog; }; #define bond_slave_get_rcu(dev) \ ((struct slave *) rcu_dereference(dev->rx_handler_data)) #define bond_slave_get_rtnl(dev) \ ((struct slave *) rtnl_dereference(dev->rx_handler_data)) void bond_queue_slave_event(struct slave *slave); void bond_lower_state_changed(struct slave *slave); struct bond_vlan_tag { __be16 vlan_proto; unsigned short vlan_id; }; /* * Returns NULL if the net_device does not belong to any of the bond's slaves * * Caller must hold bond lock for read */ static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, struct net_device *slave_dev) { return netdev_lower_dev_get_private(bond->dev, slave_dev); } static inline struct bonding *bond_get_bond_by_slave(struct slave *slave) { return slave->bond; } static inline bool bond_should_override_tx_queue(struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP || BOND_MODE(bond) == BOND_MODE_ROUNDROBIN; } static inline bool bond_is_lb(const struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_TLB || BOND_MODE(bond) == BOND_MODE_ALB; } static inline bool bond_needs_speed_duplex(const struct bonding *bond) { return BOND_MODE(bond) == BOND_MODE_8023AD || bond_is_lb(bond); } static inline bool bond_is_nondyn_tlb(const struct bonding *bond) { return (bond_is_lb(bond) && bond->params.tlb_dynamic_lb == 0); } static inline bool bond_mode_can_use_xmit_hash(const struct bonding *bond) { return (BOND_MODE(bond) == BOND_MODE_8023AD || BOND_MODE(bond) == BOND_MODE_XOR || BOND_MODE(bond) == BOND_MODE_TLB || BOND_MODE(bond) == BOND_MODE_ALB); } static inline bool bond_mode_uses_xmit_hash(const struct bonding *bond) { return (BOND_MODE(bond) == BOND_MODE_8023AD || BOND_MODE(bond) == BOND_MODE_XOR || bond_is_nondyn_tlb(bond)); } static inline bool bond_mode_uses_arp(int mode) { return mode != BOND_MODE_8023AD && mode != BOND_MODE_TLB && mode != BOND_MODE_ALB; } static inline bool bond_mode_uses_primary(int mode) { return mode == BOND_MODE_ACTIVEBACKUP || mode == BOND_MODE_TLB || mode == BOND_MODE_ALB; } static inline bool bond_uses_primary(struct bonding *bond) { return bond_mode_uses_primary(BOND_MODE(bond)); } static inline struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond) { struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); return bond_uses_primary(bond) && slave ? slave->dev : NULL; } static inline bool bond_slave_is_up(struct slave *slave) { return netif_running(slave->dev) && netif_carrier_ok(slave->dev); } static inline void bond_set_active_slave(struct slave *slave) { if (slave->backup) { slave->backup = 0; bond_queue_slave_event(slave); bond_lower_state_changed(slave); } } static inline void bond_set_backup_slave(struct slave *slave) { if (!slave->backup) { slave->backup = 1; bond_queue_slave_event(slave); bond_lower_state_changed(slave); } } static inline void bond_set_slave_state(struct slave *slave, int slave_state, bool notify) { if (slave->backup == slave_state) return; slave->backup = slave_state; if (notify) { bond_lower_state_changed(slave); bond_queue_slave_event(slave); slave->should_notify = 0; } else { if (slave->should_notify) slave->should_notify = 0; else slave->should_notify = 1; } } static inline void bond_slave_state_change(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->link == BOND_LINK_UP) bond_set_active_slave(tmp); else if (tmp->link == BOND_LINK_DOWN) bond_set_backup_slave(tmp); } } static inline void bond_slave_state_notify(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->should_notify) { bond_lower_state_changed(tmp); tmp->should_notify = 0; } } } static inline int bond_slave_state(struct slave *slave) { return slave->backup; } static inline bool bond_is_active_slave(struct slave *slave) { return !bond_slave_state(slave); } static inline bool bond_slave_can_tx(struct slave *slave) { return bond_slave_is_up(slave) && slave->link == BOND_LINK_UP && bond_is_active_slave(slave); } static inline bool bond_is_active_slave_dev(const struct net_device *slave_dev) { struct slave *slave; bool active; rcu_read_lock(); slave = bond_slave_get_rcu(slave_dev); active = bond_is_active_slave(slave); rcu_read_unlock(); return active; } static inline void bond_hw_addr_copy(u8 *dst, const u8 *src, unsigned int len) { if (len == ETH_ALEN) { ether_addr_copy(dst, src); return; } memcpy(dst, src, len); } #define BOND_PRI_RESELECT_ALWAYS 0 #define BOND_PRI_RESELECT_BETTER 1 #define BOND_PRI_RESELECT_FAILURE 2 #define BOND_FOM_NONE 0 #define BOND_FOM_ACTIVE 1 #define BOND_FOM_FOLLOW 2 #define BOND_ARP_TARGETS_ANY 0 #define BOND_ARP_TARGETS_ALL 1 #define BOND_ARP_VALIDATE_NONE 0 #define BOND_ARP_VALIDATE_ACTIVE (1 << BOND_STATE_ACTIVE) #define BOND_ARP_VALIDATE_BACKUP (1 << BOND_STATE_BACKUP) #define BOND_ARP_VALIDATE_ALL (BOND_ARP_VALIDATE_ACTIVE | \ BOND_ARP_VALIDATE_BACKUP) #define BOND_ARP_FILTER (BOND_ARP_VALIDATE_ALL + 1) #define BOND_ARP_FILTER_ACTIVE (BOND_ARP_VALIDATE_ACTIVE | \ BOND_ARP_FILTER) #define BOND_ARP_FILTER_BACKUP (BOND_ARP_VALIDATE_BACKUP | \ BOND_ARP_FILTER) #define BOND_SLAVE_NOTIFY_NOW true #define BOND_SLAVE_NOTIFY_LATER false static inline int slave_do_arp_validate(struct bonding *bond, struct slave *slave) { return bond->params.arp_validate & (1 << bond_slave_state(slave)); } static inline int slave_do_arp_validate_only(struct bonding *bond) { return bond->params.arp_validate & BOND_ARP_FILTER; } static inline int bond_is_ip_target_ok(__be32 addr) { return !ipv4_is_lbcast(addr) && !ipv4_is_zeronet(addr); } #if IS_ENABLED(CONFIG_IPV6) static inline int bond_is_ip6_target_ok(struct in6_addr *addr) { return !ipv6_addr_any(addr) && !ipv6_addr_loopback(addr) && !ipv6_addr_is_multicast(addr); } #endif /* Get the oldest arp which we've received on this slave for bond's * arp_targets. */ static inline unsigned long slave_oldest_target_arp_rx(struct bonding *bond, struct slave *slave) { int i = 1; unsigned long ret = slave->target_last_arp_rx[0]; for (; (i < BOND_MAX_ARP_TARGETS) && bond->params.arp_targets[i]; i++) if (time_before(slave->target_last_arp_rx[i], ret)) ret = slave->target_last_arp_rx[i]; return ret; } static inline unsigned long slave_last_rx(struct bonding *bond, struct slave *slave) { if (bond->params.arp_all_targets == BOND_ARP_TARGETS_ALL) return slave_oldest_target_arp_rx(bond, slave); return slave->last_rx; } static inline void slave_update_last_tx(struct slave *slave) { WRITE_ONCE(slave->last_tx, jiffies); } static inline unsigned long slave_last_tx(struct slave *slave) { return READ_ONCE(slave->last_tx); } #ifdef CONFIG_NET_POLL_CONTROLLER static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb) { return netpoll_send_skb(slave->np, skb); } #else static inline netdev_tx_t bond_netpoll_send_skb(const struct slave *slave, struct sk_buff *skb) { BUG(); return NETDEV_TX_OK; } #endif static inline void bond_set_slave_inactive_flags(struct slave *slave, bool notify) { if (!bond_is_lb(slave->bond)) bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); if (!slave->bond->params.all_slaves_active) slave->inactive = 1; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) slave->rx_disabled = 1; } static inline void bond_set_slave_tx_disabled_flags(struct slave *slave, bool notify) { bond_set_slave_state(slave, BOND_STATE_BACKUP, notify); } static inline void bond_set_slave_active_flags(struct slave *slave, bool notify) { bond_set_slave_state(slave, BOND_STATE_ACTIVE, notify); slave->inactive = 0; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) slave->rx_disabled = 0; } static inline void bond_set_slave_rx_enabled_flags(struct slave *slave, bool notify) { slave->rx_disabled = 0; } static inline bool bond_is_slave_inactive(struct slave *slave) { return slave->inactive; } static inline bool bond_is_slave_rx_disabled(struct slave *slave) { return slave->rx_disabled; } static inline void bond_propose_link_state(struct slave *slave, int state) { slave->link_new_state = state; } static inline void bond_commit_link_state(struct slave *slave, bool notify) { if (slave->link_new_state == BOND_LINK_NOCHANGE) return; slave->link = slave->link_new_state; if (notify) { bond_queue_slave_event(slave); bond_lower_state_changed(slave); slave->should_notify_link = 0; } else { if (slave->should_notify_link) slave->should_notify_link = 0; else slave->should_notify_link = 1; } } static inline void bond_set_slave_link_state(struct slave *slave, int state, bool notify) { bond_propose_link_state(slave, state); bond_commit_link_state(slave, notify); } static inline void bond_slave_link_notify(struct bonding *bond) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) { if (tmp->should_notify_link) { bond_queue_slave_event(tmp); bond_lower_state_changed(tmp); tmp->should_notify_link = 0; } } } static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local) { struct in_device *in_dev; __be32 addr = 0; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) addr = inet_confirm_addr(dev_net(dev), in_dev, dst, local, RT_SCOPE_HOST); rcu_read_unlock(); return addr; } struct bond_net { struct net *net; /* Associated network namespace */ struct list_head dev_list; #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_dir; #endif struct class_attribute class_attr_bonding_masters; }; int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); int bond_create(struct net *net, const char *name); int bond_create_sysfs(struct bond_net *net); void bond_destroy_sysfs(struct bond_net *net); void bond_prepare_sysfs_group(struct bonding *bond); int bond_sysfs_slave_add(struct slave *slave); void bond_sysfs_slave_del(struct slave *slave); void bond_xdp_set_features(struct net_device *bond_dev); int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, struct netlink_ext_ack *extack); int bond_release(struct net_device *bond_dev, struct net_device *slave_dev); u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb); int bond_set_carrier(struct bonding *bond); void bond_select_active_slave(struct bonding *bond); void bond_change_active_slave(struct bonding *bond, struct slave *new_active); void bond_create_debugfs(void); void bond_destroy_debugfs(void); void bond_debug_register(struct bonding *bond); void bond_debug_unregister(struct bonding *bond); void bond_debug_reregister(struct bonding *bond); const char *bond_mode_name(int mode); bool bond_xdp_check(struct bonding *bond, int mode); void bond_setup(struct net_device *bond_dev); unsigned int bond_get_num_tx_queues(void); int bond_netlink_init(void); void bond_netlink_fini(void); struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond); const char *bond_slave_link_status(s8 link); struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, struct net_device *end_dev, int level); int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave); void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay); void bond_work_init_all(struct bonding *bond); void bond_work_cancel_all(struct bonding *bond); #ifdef CONFIG_PROC_FS void bond_create_proc_entry(struct bonding *bond); void bond_remove_proc_entry(struct bonding *bond); void bond_create_proc_dir(struct bond_net *bn); void bond_destroy_proc_dir(struct bond_net *bn); #else static inline void bond_create_proc_entry(struct bonding *bond) { } static inline void bond_remove_proc_entry(struct bonding *bond) { } static inline void bond_create_proc_dir(struct bond_net *bn) { } static inline void bond_destroy_proc_dir(struct bond_net *bn) { } #endif static inline struct slave *bond_slave_has_mac(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; bond_for_each_slave(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return tmp; return NULL; } /* Caller must hold rcu_read_lock() for read */ static inline bool bond_slave_has_mac_rcu(struct bonding *bond, const u8 *mac) { struct list_head *iter; struct slave *tmp; bond_for_each_slave_rcu(bond, tmp, iter) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return true; return false; } /* Check if the ip is present in arp ip list, or first free slot if ip == 0 * Returns -1 if not found, index if found */ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) { int i; for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) if (targets[i] == ip) return i; else if (targets[i] == 0) break; return -1; } #if IS_ENABLED(CONFIG_IPV6) static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr *ip) { struct in6_addr mcaddr; int i; for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { addrconf_addr_solict_mult(&targets[i], &mcaddr); if ((ipv6_addr_equal(&targets[i], ip)) || (ipv6_addr_equal(&mcaddr, ip))) return i; else if (ipv6_addr_any(&targets[i])) break; } return -1; } #endif /* exported from bond_main.c */ extern unsigned int bond_net_id; /* exported from bond_netlink.c */ extern struct rtnl_link_ops bond_link_ops; /* exported from bond_sysfs_slave.c */ extern const struct sysfs_ops slave_sysfs_ops; /* exported from bond_3ad.c */ extern const u8 lacpdu_mcast_addr[]; static inline netdev_tx_t bond_tx_drop(struct net_device *dev, struct sk_buff *skb) { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); return NET_XMIT_DROP; } #endif /* _NET_BONDING_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/init.h> #include <linux/module.h> #include <linux/netfilter.h> #include <net/flow_offload.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_offload.h> #include <net/pkt_cls.h> static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) { struct nft_flow_rule *flow; flow = kzalloc(sizeof(struct nft_flow_rule), GFP_KERNEL); if (!flow) return NULL; flow->rule = flow_rule_alloc(num_actions); if (!flow->rule) { kfree(flow); return NULL; } flow->rule->match.dissector = &flow->match.dissector; flow->rule->match.mask = &flow->match.mask; flow->rule->match.key = &flow->match.key; return flow; } void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, enum flow_dissector_key_id addr_type) { struct nft_flow_match *match = &flow->match; struct nft_flow_key *mask = &match->mask; struct nft_flow_key *key = &match->key; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL)) return; key->control.addr_type = addr_type; mask->control.addr_type = 0xffff; match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL); match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] = offsetof(struct nft_flow_key, control); } struct nft_offload_ethertype { __be16 value; __be16 mask; }; static void nft_flow_rule_transfer_vlan(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow) { struct nft_flow_match *match = &flow->match; struct nft_offload_ethertype ethertype = { .value = match->key.basic.n_proto, .mask = match->mask.basic.n_proto, }; if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) && (match->key.vlan.vlan_tpid == htons(ETH_P_8021Q) || match->key.vlan.vlan_tpid == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.cvlan.vlan_tpid; match->mask.basic.n_proto = match->mask.cvlan.vlan_tpid; match->key.cvlan.vlan_tpid = match->key.vlan.vlan_tpid; match->mask.cvlan.vlan_tpid = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_CVLAN] = offsetof(struct nft_flow_key, cvlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_CVLAN); } else if (match->dissector.used_keys & BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) && (match->key.basic.n_proto == htons(ETH_P_8021Q) || match->key.basic.n_proto == htons(ETH_P_8021AD))) { match->key.basic.n_proto = match->key.vlan.vlan_tpid; match->mask.basic.n_proto = match->mask.vlan.vlan_tpid; match->key.vlan.vlan_tpid = ethertype.value; match->mask.vlan.vlan_tpid = ethertype.mask; match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = offsetof(struct nft_flow_key, vlan); match->dissector.used_keys |= BIT_ULL(FLOW_DISSECTOR_KEY_VLAN); } } struct nft_flow_rule *nft_flow_rule_create(struct net *net, const struct nft_rule *rule) { struct nft_offload_ctx *ctx; struct nft_flow_rule *flow; int num_actions = 0, err; struct nft_expr *expr; expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { if (expr->ops->offload_action && expr->ops->offload_action(expr)) num_actions++; expr = nft_expr_next(expr); } if (num_actions == 0) return ERR_PTR(-EOPNOTSUPP); flow = nft_flow_rule_alloc(num_actions); if (!flow) return ERR_PTR(-ENOMEM); expr = nft_expr_first(rule); ctx = kzalloc(sizeof(struct nft_offload_ctx), GFP_KERNEL); if (!ctx) { err = -ENOMEM; goto err_out; } ctx->net = net; ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; while (nft_expr_more(rule, expr)) { if (!expr->ops->offload) { err = -EOPNOTSUPP; goto err_out; } err = expr->ops->offload(ctx, flow, expr); if (err < 0) goto err_out; expr = nft_expr_next(expr); } nft_flow_rule_transfer_vlan(ctx, flow); flow->proto = ctx->dep.l3num; kfree(ctx); return flow; err_out: kfree(ctx); nft_flow_rule_destroy(flow); return ERR_PTR(err); } void nft_flow_rule_destroy(struct nft_flow_rule *flow) { struct flow_action_entry *entry; int i; flow_action_for_each(i, entry, &flow->rule->action) { switch (entry->id) { case FLOW_ACTION_REDIRECT: case FLOW_ACTION_MIRRED: dev_put(entry->dev); break; default: break; } } kfree(flow->rule); kfree(flow); } void nft_offload_set_dependency(struct nft_offload_ctx *ctx, enum nft_offload_dep_type type) { ctx->dep.type = type; } void nft_offload_update_dependency(struct nft_offload_ctx *ctx, const void *data, u32 len) { switch (ctx->dep.type) { case NFT_OFFLOAD_DEP_NETWORK: WARN_ON(len != sizeof(__u16)); memcpy(&ctx->dep.l3num, data, sizeof(__u16)); break; case NFT_OFFLOAD_DEP_TRANSPORT: WARN_ON(len != sizeof(__u8)); memcpy(&ctx->dep.protonum, data, sizeof(__u8)); break; default: break; } ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC; } static void nft_flow_offload_common_init(struct flow_cls_common_offload *common, __be16 proto, int priority, struct netlink_ext_ack *extack) { common->protocol = proto; common->prio = priority; common->extack = extack; } static int nft_setup_cb_call(enum tc_setup_type type, void *type_data, struct list_head *cb_list) { struct flow_block_cb *block_cb; int err; list_for_each_entry(block_cb, cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err < 0) return err; } return 0; } static int nft_chain_offload_priority(const struct nft_base_chain *basechain) { if (basechain->ops.priority <= 0 || basechain->ops.priority > USHRT_MAX) return -1; return 0; } bool nft_chain_offload_support(const struct nft_base_chain *basechain) { struct nf_hook_ops *ops; struct net_device *dev; struct nft_hook *hook; if (nft_chain_offload_priority(basechain) < 0) return false; list_for_each_entry(hook, &basechain->hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) { if (ops->pf != NFPROTO_NETDEV || ops->hooknum != NF_NETDEV_INGRESS) return false; dev = ops->dev; if (!dev->netdev_ops->ndo_setup_tc && !flow_indr_dev_exists()) return false; } } return true; } static void nft_flow_cls_offload_setup(struct flow_cls_offload *cls_flow, const struct nft_base_chain *basechain, const struct nft_rule *rule, const struct nft_flow_rule *flow, struct netlink_ext_ack *extack, enum flow_cls_command command) { __be16 proto = ETH_P_ALL; memset(cls_flow, 0, sizeof(*cls_flow)); if (flow) proto = flow->proto; nft_flow_offload_common_init(&cls_flow->common, proto, basechain->ops.priority, extack); cls_flow->command = command; cls_flow->cookie = (unsigned long) rule; if (flow) cls_flow->rule = flow->rule; } static int nft_flow_offload_cmd(const struct nft_chain *chain, const struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command, struct flow_cls_offload *cls_flow) { struct netlink_ext_ack extack = {}; struct nft_base_chain *basechain; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); nft_flow_cls_offload_setup(cls_flow, basechain, rule, flow, &extack, command); return nft_setup_cb_call(TC_SETUP_CLSFLOWER, cls_flow, &basechain->flow_block.cb_list); } static int nft_flow_offload_rule(const struct nft_chain *chain, struct nft_rule *rule, struct nft_flow_rule *flow, enum flow_cls_command command) { struct flow_cls_offload cls_flow; return nft_flow_offload_cmd(chain, rule, flow, command, &cls_flow); } int nft_flow_rule_stats(const struct nft_chain *chain, const struct nft_rule *rule) { struct flow_cls_offload cls_flow = {}; struct nft_expr *expr, *next; int err; err = nft_flow_offload_cmd(chain, rule, NULL, FLOW_CLS_STATS, &cls_flow); if (err < 0) return err; nft_rule_for_each_expr(expr, next, rule) { if (expr->ops->offload_stats) expr->ops->offload_stats(expr, &cls_flow.stats); } return 0; } static int nft_flow_offload_bind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { list_splice(&bo->cb_list, &basechain->flow_block.cb_list); return 0; } static int nft_flow_offload_unbind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { struct flow_block_cb *block_cb, *next; struct flow_cls_offload cls_flow; struct netlink_ext_ack extack; struct nft_chain *chain; struct nft_rule *rule; chain = &basechain->chain; list_for_each_entry(rule, &chain->rules, list) { memset(&extack, 0, sizeof(extack)); nft_flow_cls_offload_setup(&cls_flow, basechain, rule, NULL, &extack, FLOW_CLS_DESTROY); nft_setup_cb_call(TC_SETUP_CLSFLOWER, &cls_flow, &bo->cb_list); } list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) { list_del(&block_cb->list); flow_block_cb_free(block_cb); } return 0; } static int nft_block_setup(struct nft_base_chain *basechain, struct flow_block_offload *bo, enum flow_block_command cmd) { int err; switch (cmd) { case FLOW_BLOCK_BIND: err = nft_flow_offload_bind(bo, basechain); break; case FLOW_BLOCK_UNBIND: err = nft_flow_offload_unbind(bo, basechain); break; default: WARN_ON_ONCE(1); err = -EOPNOTSUPP; } return err; } static void nft_flow_block_offload_init(struct flow_block_offload *bo, struct net *net, enum flow_block_command cmd, struct nft_base_chain *basechain, struct netlink_ext_ack *extack) { memset(bo, 0, sizeof(*bo)); bo->net = net; bo->block = &basechain->flow_block; bo->command = cmd; bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; bo->extack = extack; bo->cb_list_head = &basechain->flow_block.cb_list; INIT_LIST_HEAD(&bo->cb_list); } static int nft_block_offload_cmd(struct nft_base_chain *chain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, chain, &extack); err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo); if (err < 0) return err; return nft_block_setup(chain, &bo, cmd); } static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) { struct nft_base_chain *basechain = block_cb->indr.data; struct net_device *dev = block_cb->indr.dev; struct netlink_ext_ack extack = {}; struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct flow_block_offload bo; nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, basechain, &extack); nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); nft_flow_offload_unbind(&bo, basechain); mutex_unlock(&nft_net->commit_mutex); } static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { struct netlink_ext_ack extack = {}; struct flow_block_offload bo; int err; nft_flow_block_offload_init(&bo, dev_net(dev), cmd, basechain, &extack); err = flow_indr_dev_setup_offload(dev, NULL, TC_SETUP_BLOCK, basechain, &bo, nft_indr_block_cleanup); if (err < 0) return err; if (list_empty(&bo.cb_list)) return -EOPNOTSUPP; return nft_block_setup(basechain, &bo, cmd); } static int nft_chain_offload_cmd(struct nft_base_chain *basechain, struct net_device *dev, enum flow_block_command cmd) { int err; if (dev->netdev_ops->ndo_setup_tc) err = nft_block_offload_cmd(basechain, dev, cmd); else err = nft_indr_block_offload_cmd(basechain, dev, cmd); return err; } static int nft_flow_block_chain(struct nft_base_chain *basechain, const struct net_device *this_dev, enum flow_block_command cmd) { struct nf_hook_ops *ops; struct nft_hook *hook; int err, i = 0; list_for_each_entry(hook, &basechain->hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) { if (this_dev && this_dev != ops->dev) continue; err = nft_chain_offload_cmd(basechain, ops->dev, cmd); if (err < 0 && cmd == FLOW_BLOCK_BIND) { if (!this_dev) goto err_flow_block; return err; } i++; } } return 0; err_flow_block: list_for_each_entry(hook, &basechain->hook_list, list) { list_for_each_entry(ops, &hook->ops_list, list) { if (i-- <= 0) break; nft_chain_offload_cmd(basechain, ops->dev, FLOW_BLOCK_UNBIND); } } return err; } static int nft_flow_offload_chain(struct nft_chain *chain, u8 *ppolicy, enum flow_block_command cmd) { struct nft_base_chain *basechain; u8 policy; if (!nft_is_base_chain(chain)) return -EOPNOTSUPP; basechain = nft_base_chain(chain); policy = ppolicy ? *ppolicy : basechain->policy; /* Only default policy to accept is supported for now. */ if (cmd == FLOW_BLOCK_BIND && policy == NF_DROP) return -EOPNOTSUPP; return nft_flow_block_chain(basechain, NULL, cmd); } static void nft_flow_rule_offload_abort(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); int err = 0; list_for_each_entry_continue_reverse(trans, &nft_net->commit_list, list) { if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_UNBIND); break; case NFT_MSG_DELCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_BIND); break; case NFT_MSG_NEWRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; case NFT_MSG_DELRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; } if (WARN_ON_ONCE(err)) break; } } int nft_flow_rule_offload_commit(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans; int err = 0; u8 policy; list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_BIND); break; case NFT_MSG_DELCHAIN: if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_UNBIND); break; case NFT_MSG_NEWRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; if (trans->flags & NLM_F_REPLACE || !(trans->flags & NLM_F_APPEND)) { err = -EOPNOTSUPP; break; } err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; case NFT_MSG_DELRULE: if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; } if (err) { nft_flow_rule_offload_abort(net, trans); break; } } return err; } static struct nft_chain *__nft_offload_get_chain(const struct nftables_pernet *nft_net, struct net_device *dev) { struct nft_base_chain *basechain; struct nft_hook *hook, *found; const struct nft_table *table; struct nft_chain *chain; list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; list_for_each_entry(chain, &table->chains, list) { if (!nft_is_base_chain(chain) || !(chain->flags & NFT_CHAIN_HW_OFFLOAD)) continue; found = NULL; basechain = nft_base_chain(chain); list_for_each_entry(hook, &basechain->hook_list, list) { if (!nft_hook_find_ops(hook, dev)) continue; found = hook; break; } if (!found) continue; return chain; } } return NULL; } static int nft_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct nft_chain *chain; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); chain = __nft_offload_get_chain(nft_net, dev); if (chain) nft_flow_block_chain(nft_base_chain(chain), dev, FLOW_BLOCK_UNBIND); mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } static struct notifier_block nft_offload_netdev_notifier = { .notifier_call = nft_offload_netdev_event, }; int nft_offload_init(void) { return register_netdevice_notifier(&nft_offload_netdev_notifier); } void nft_offload_exit(void) { unregister_netdevice_notifier(&nft_offload_netdev_notifier); } |
| 1563 1562 4 1556 32 1555 1563 53 564 12 60 61 60 62 61 61 1559 614 1276 606 8 608 567 53 1558 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/realpath.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/magic.h> #include <linux/proc_fs.h> /** * tomoyo_encode2 - Encode binary string to ascii string. * * @str: String in binary format. * @str_len: Size of @str in byte. * * Returns pointer to @str in ascii format on success, NULL otherwise. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ char *tomoyo_encode2(const char *str, int str_len) { int i; int len = 0; const char *p = str; char *cp; char *cp0; if (!p) return NULL; for (i = 0; i < str_len; i++) { const unsigned char c = p[i]; if (c == '\\') len += 2; else if (c > ' ' && c < 127) len++; else len += 4; } len++; /* Reserve space for appending "/". */ cp = kzalloc(len + 10, GFP_NOFS); if (!cp) return NULL; cp0 = cp; p = str; for (i = 0; i < str_len; i++) { const unsigned char c = p[i]; if (c == '\\') { *cp++ = '\\'; *cp++ = '\\'; } else if (c > ' ' && c < 127) { *cp++ = c; } else { *cp++ = '\\'; *cp++ = (c >> 6) + '0'; *cp++ = ((c >> 3) & 7) + '0'; *cp++ = (c & 7) + '0'; } } return cp0; } /** * tomoyo_encode - Encode binary string to ascii string. * * @str: String in binary format. * * Returns pointer to @str in ascii format on success, NULL otherwise. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ char *tomoyo_encode(const char *str) { return str ? tomoyo_encode2(str, strlen(str)) : NULL; } /** * tomoyo_get_absolute_path - Get the path of a dentry but ignores chroot'ed root. * * @path: Pointer to "struct path". * @buffer: Pointer to buffer to return value in. * @buflen: Sizeof @buffer. * * Returns the buffer on success, an error code otherwise. * * If dentry is a directory, trailing '/' is appended. */ static char *tomoyo_get_absolute_path(const struct path *path, char * const buffer, const int buflen) { char *pos = ERR_PTR(-ENOMEM); if (buflen >= 256) { /* go to whatever namespace root we are under */ pos = d_absolute_path(path, buffer, buflen - 1); if (!IS_ERR(pos) && *pos == '/' && pos[1]) { struct inode *inode = d_backing_inode(path->dentry); if (inode && S_ISDIR(inode->i_mode)) { buffer[buflen - 2] = '/'; buffer[buflen - 1] = '\0'; } } } return pos; } /** * tomoyo_get_dentry_path - Get the path of a dentry. * * @dentry: Pointer to "struct dentry". * @buffer: Pointer to buffer to return value in. * @buflen: Sizeof @buffer. * * Returns the buffer on success, an error code otherwise. * * If dentry is a directory, trailing '/' is appended. */ static char *tomoyo_get_dentry_path(struct dentry *dentry, char * const buffer, const int buflen) { char *pos = ERR_PTR(-ENOMEM); if (buflen >= 256) { pos = dentry_path_raw(dentry, buffer, buflen - 1); if (!IS_ERR(pos) && *pos == '/' && pos[1]) { struct inode *inode = d_backing_inode(dentry); if (inode && S_ISDIR(inode->i_mode)) { buffer[buflen - 2] = '/'; buffer[buflen - 1] = '\0'; } } } return pos; } /** * tomoyo_get_local_path - Get the path of a dentry. * * @dentry: Pointer to "struct dentry". * @buffer: Pointer to buffer to return value in. * @buflen: Sizeof @buffer. * * Returns the buffer on success, an error code otherwise. */ static char *tomoyo_get_local_path(struct dentry *dentry, char * const buffer, const int buflen) { struct super_block *sb = dentry->d_sb; char *pos = tomoyo_get_dentry_path(dentry, buffer, buflen); if (IS_ERR(pos)) return pos; /* Convert from $PID to self if $PID is current thread. */ if (sb->s_magic == PROC_SUPER_MAGIC && *pos == '/') { char *ep; const pid_t pid = (pid_t) simple_strtoul(pos + 1, &ep, 10); struct pid_namespace *proc_pidns = proc_pid_ns(sb); if (*ep == '/' && pid && pid == task_tgid_nr_ns(current, proc_pidns)) { pos = ep - 5; if (pos < buffer) goto out; memmove(pos, "/self", 5); } goto prepend_filesystem_name; } /* Use filesystem name for unnamed devices. */ if (!MAJOR(sb->s_dev)) goto prepend_filesystem_name; { struct inode *inode = d_backing_inode(sb->s_root); /* * Use filesystem name if filesystem does not support rename() * operation. */ if (!inode->i_op->rename) goto prepend_filesystem_name; } /* Prepend device name. */ { char name[64]; int name_len; const dev_t dev = sb->s_dev; name[sizeof(name) - 1] = '\0'; snprintf(name, sizeof(name) - 1, "dev(%u,%u):", MAJOR(dev), MINOR(dev)); name_len = strlen(name); pos -= name_len; if (pos < buffer) goto out; memmove(pos, name, name_len); return pos; } /* Prepend filesystem name. */ prepend_filesystem_name: { const char *name = sb->s_type->name; const int name_len = strlen(name); pos -= name_len + 1; if (pos < buffer) goto out; memmove(pos, name, name_len); pos[name_len] = ':'; } return pos; out: return ERR_PTR(-ENOMEM); } /** * tomoyo_realpath_from_path - Returns realpath(3) of the given pathname but ignores chroot'ed root. * * @path: Pointer to "struct path". * * Returns the realpath of the given @path on success, NULL otherwise. * * If dentry is a directory, trailing '/' is appended. * Characters out of 0x20 < c < 0x7F range are converted to * \ooo style octal string. * Character \ is converted to \\ string. * * These functions use kzalloc(), so the caller must call kfree() * if these functions didn't return NULL. */ char *tomoyo_realpath_from_path(const struct path *path) { char *buf = NULL; char *name = NULL; unsigned int buf_len = PAGE_SIZE / 2; struct dentry *dentry = path->dentry; struct super_block *sb = dentry->d_sb; while (1) { char *pos; struct inode *inode; buf_len <<= 1; kfree(buf); buf = kmalloc(buf_len, GFP_NOFS); if (!buf) break; /* To make sure that pos is '\0' terminated. */ buf[buf_len - 1] = '\0'; /* For "pipe:[\$]" and "socket:[\$]". */ if (dentry->d_op && dentry->d_op->d_dname) { pos = dentry->d_op->d_dname(dentry, buf, buf_len - 1); goto encode; } inode = d_backing_inode(sb->s_root); /* * Get local name for filesystems without rename() operation */ if ((!inode->i_op->rename && !(sb->s_type->fs_flags & FS_REQUIRES_DEV))) pos = tomoyo_get_local_path(path->dentry, buf, buf_len - 1); /* Get absolute name for the rest. */ else { pos = tomoyo_get_absolute_path(path, buf, buf_len - 1); /* * Fall back to local name if absolute name is not * available. */ if (pos == ERR_PTR(-EINVAL)) pos = tomoyo_get_local_path(path->dentry, buf, buf_len - 1); } encode: if (IS_ERR(pos)) continue; name = tomoyo_encode(pos); break; } kfree(buf); if (!name) tomoyo_warn_oom(__func__); return name; } /** * tomoyo_realpath_nofollow - Get realpath of a pathname. * * @pathname: The pathname to solve. * * Returns the realpath of @pathname on success, NULL otherwise. */ char *tomoyo_realpath_nofollow(const char *pathname) { struct path path; if (pathname && kern_path(pathname, 0, &path) == 0) { char *buf = tomoyo_realpath_from_path(&path); path_put(&path); return buf; } return 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2023 Arm Ltd. */ #ifndef _ASM_ARM64_POR_H #define _ASM_ARM64_POR_H #include <asm/sysreg.h> #define POR_EL0_INIT POR_ELx_PERM_PREP(0, POE_RWX) static inline bool por_elx_allows_read(u64 por, u8 pkey) { u8 perm = POR_ELx_PERM_GET(pkey, por); return perm & POE_R; } static inline bool por_elx_allows_write(u64 por, u8 pkey) { u8 perm = POR_ELx_PERM_GET(pkey, por); return perm & POE_W; } static inline bool por_elx_allows_exec(u64 por, u8 pkey) { u8 perm = POR_ELx_PERM_GET(pkey, por); return perm & POE_X; } #endif /* _ASM_ARM64_POR_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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This is a module which is used for queueing packets and communicating with * userspace via nfnetlink. * * (C) 2005 by Harald Welte <laforge@netfilter.org> * (C) 2007 by Patrick McHardy <kaber@trash.net> * * Based on the old ipv4-only ip_queue.c: * (C) 2000-2002 James Morris <jmorris@intercode.com.au> * (C) 2003-2005 Netfilter Core Team <coreteam@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/proc_fs.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_queue.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/list.h> #include <linux/cgroup-defs.h> #include <net/gso.h> #include <net/sock.h> #include <net/tcp_states.h> #include <net/netfilter/nf_queue.h> #include <net/netns/generic.h> #include <linux/atomic.h> #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) #include "../bridge/br_private.h" #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #endif #define NFQNL_QMAX_DEFAULT 1024 /* We're using struct nlattr which has 16bit nla_len. Note that nla_len * includes the header length. Thus, the maximum packet length that we * support is 65531 bytes. We send truncated packets if the specified length * is larger than that. Userspace can check for presence of NFQA_CAP_LEN * attribute to detect truncation. */ #define NFQNL_MAX_COPY_RANGE (0xffff - NLA_HDRLEN) struct nfqnl_instance { struct hlist_node hlist; /* global list of queues */ struct rcu_head rcu; u32 peer_portid; unsigned int queue_maxlen; unsigned int copy_range; unsigned int queue_dropped; unsigned int queue_user_dropped; u_int16_t queue_num; /* number of this queue */ u_int8_t copy_mode; u_int32_t flags; /* Set using NFQA_CFG_FLAGS */ /* * Following fields are dirtied for each queued packet, * keep them in same cache line if possible. */ spinlock_t lock ____cacheline_aligned_in_smp; unsigned int queue_total; unsigned int id_sequence; /* 'sequence' of pkt ids */ struct list_head queue_list; /* packets in queue */ }; typedef int (*nfqnl_cmpfn)(struct nf_queue_entry *, unsigned long); static unsigned int nfnl_queue_net_id __read_mostly; #define INSTANCE_BUCKETS 16 struct nfnl_queue_net { spinlock_t instances_lock; struct hlist_head instance_table[INSTANCE_BUCKETS]; }; static struct nfnl_queue_net *nfnl_queue_pernet(struct net *net) { return net_generic(net, nfnl_queue_net_id); } static inline u_int8_t instance_hashfn(u_int16_t queue_num) { return ((queue_num >> 8) ^ queue_num) % INSTANCE_BUCKETS; } static struct nfqnl_instance * instance_lookup(struct nfnl_queue_net *q, u_int16_t queue_num) { struct hlist_head *head; struct nfqnl_instance *inst; head = &q->instance_table[instance_hashfn(queue_num)]; hlist_for_each_entry_rcu(inst, head, hlist) { if (inst->queue_num == queue_num) return inst; } return NULL; } static struct nfqnl_instance * instance_create(struct nfnl_queue_net *q, u_int16_t queue_num, u32 portid) { struct nfqnl_instance *inst; unsigned int h; int err; spin_lock(&q->instances_lock); if (instance_lookup(q, queue_num)) { err = -EEXIST; goto out_unlock; } inst = kzalloc(sizeof(*inst), GFP_ATOMIC); if (!inst) { err = -ENOMEM; goto out_unlock; } inst->queue_num = queue_num; inst->peer_portid = portid; inst->queue_maxlen = NFQNL_QMAX_DEFAULT; inst->copy_range = NFQNL_MAX_COPY_RANGE; inst->copy_mode = NFQNL_COPY_NONE; spin_lock_init(&inst->lock); INIT_LIST_HEAD(&inst->queue_list); if (!try_module_get(THIS_MODULE)) { err = -EAGAIN; goto out_free; } h = instance_hashfn(queue_num); hlist_add_head_rcu(&inst->hlist, &q->instance_table[h]); spin_unlock(&q->instances_lock); return inst; out_free: kfree(inst); out_unlock: spin_unlock(&q->instances_lock); return ERR_PTR(err); } static void nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data); static void instance_destroy_rcu(struct rcu_head *head) { struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance, rcu); rcu_read_lock(); nfqnl_flush(inst, NULL, 0); rcu_read_unlock(); kfree(inst); module_put(THIS_MODULE); } static void __instance_destroy(struct nfqnl_instance *inst) { hlist_del_rcu(&inst->hlist); call_rcu(&inst->rcu, instance_destroy_rcu); } static void instance_destroy(struct nfnl_queue_net *q, struct nfqnl_instance *inst) { spin_lock(&q->instances_lock); __instance_destroy(inst); spin_unlock(&q->instances_lock); } static inline void __enqueue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry) { list_add_tail(&entry->list, &queue->queue_list); queue->queue_total++; } static void __dequeue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry) { list_del(&entry->list); queue->queue_total--; } static struct nf_queue_entry * find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) { struct nf_queue_entry *entry = NULL, *i; spin_lock_bh(&queue->lock); list_for_each_entry(i, &queue->queue_list, list) { if (i->id == id) { entry = i; break; } } if (entry) __dequeue_entry(queue, entry); spin_unlock_bh(&queue->lock); return entry; } static unsigned int nf_iterate(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *hooks, unsigned int *index) { const struct nf_hook_entry *hook; unsigned int verdict, i = *index; while (i < hooks->num_hook_entries) { hook = &hooks->hooks[i]; repeat: verdict = nf_hook_entry_hookfn(hook, skb, state); if (verdict != NF_ACCEPT) { *index = i; if (verdict != NF_REPEAT) return verdict; goto repeat; } i++; } *index = i; return NF_ACCEPT; } static struct nf_hook_entries *nf_hook_entries_head(const struct net *net, u8 pf, u8 hooknum) { switch (pf) { #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE case NFPROTO_BRIDGE: return rcu_dereference(net->nf.hooks_bridge[hooknum]); #endif case NFPROTO_IPV4: return rcu_dereference(net->nf.hooks_ipv4[hooknum]); case NFPROTO_IPV6: return rcu_dereference(net->nf.hooks_ipv6[hooknum]); default: WARN_ON_ONCE(1); return NULL; } return NULL; } static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) { #ifdef CONFIG_INET const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); if (entry->state.hook == NF_INET_LOCAL_OUT) { const struct iphdr *iph = ip_hdr(skb); if (!(iph->tos == rt_info->tos && skb->mark == rt_info->mark && iph->daddr == rt_info->daddr && iph->saddr == rt_info->saddr)) return ip_route_me_harder(entry->state.net, entry->state.sk, skb, RTN_UNSPEC); } #endif return 0; } static int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry) { const struct nf_ipv6_ops *v6ops; int ret = 0; switch (entry->state.pf) { case AF_INET: ret = nf_ip_reroute(skb, entry); break; case AF_INET6: v6ops = rcu_dereference(nf_ipv6_ops); if (v6ops) ret = v6ops->reroute(skb, entry); break; } return ret; } /* caller must hold rcu read-side lock */ static void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_hook_entry *hook_entry; const struct nf_hook_entries *hooks; struct sk_buff *skb = entry->skb; const struct net *net; unsigned int i; int err; u8 pf; net = entry->state.net; pf = entry->state.pf; hooks = nf_hook_entries_head(net, pf, entry->state.hook); i = entry->hook_index; if (!hooks || i >= hooks->num_hook_entries) { kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP); nf_queue_entry_free(entry); return; } hook_entry = &hooks->hooks[i]; /* Continue traversal iff userspace said ok... */ if (verdict == NF_REPEAT) verdict = nf_hook_entry_hookfn(hook_entry, skb, &entry->state); if (verdict == NF_ACCEPT) { if (nf_reroute(skb, entry) < 0) verdict = NF_DROP; } if (verdict == NF_ACCEPT) { next_hook: ++i; verdict = nf_iterate(skb, &entry->state, hooks, &i); } switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: case NF_STOP: local_bh_disable(); entry->state.okfn(entry->state.net, entry->state.sk, skb); local_bh_enable(); break; case NF_QUEUE: err = nf_queue(skb, &entry->state, i, verdict); if (err == 1) goto next_hook; break; case NF_STOLEN: break; default: kfree_skb(skb); } nf_queue_entry_free(entry); } static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_ct_hook *ct_hook; if (verdict == NF_ACCEPT || verdict == NF_REPEAT || verdict == NF_STOP) { unsigned int ct_verdict = verdict; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ct_verdict = ct_hook->update(entry->state.net, entry->skb); rcu_read_unlock(); switch (ct_verdict & NF_VERDICT_MASK) { case NF_ACCEPT: /* follow userspace verdict, could be REPEAT */ break; case NF_STOLEN: nf_queue_entry_free(entry); return; default: verdict = ct_verdict & NF_VERDICT_MASK; break; } } nf_reinject(entry, verdict); } static void nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data) { struct nf_queue_entry *entry, *next; spin_lock_bh(&queue->lock); list_for_each_entry_safe(entry, next, &queue->queue_list, list) { if (!cmpfn || cmpfn(entry, data)) { list_del(&entry->list); queue->queue_total--; nfqnl_reinject(entry, NF_DROP); } } spin_unlock_bh(&queue->lock); } static int nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet, bool csum_verify) { __u32 flags = 0; if (packet->ip_summed == CHECKSUM_PARTIAL) flags = NFQA_SKB_CSUMNOTREADY; else if (csum_verify) flags = NFQA_SKB_CSUM_NOTVERIFIED; if (skb_is_gso(packet)) flags |= NFQA_SKB_GSO; return flags ? nla_put_be32(nlskb, NFQA_SKB_INFO, htonl(flags)) : 0; } static int nfqnl_put_sk_uidgid(struct sk_buff *skb, struct sock *sk) { const struct cred *cred; if (!sk_fullsock(sk)) return 0; read_lock_bh(&sk->sk_callback_lock); if (sk->sk_socket && sk->sk_socket->file) { cred = sk->sk_socket->file->f_cred; if (nla_put_be32(skb, NFQA_UID, htonl(from_kuid_munged(&init_user_ns, cred->fsuid)))) goto nla_put_failure; if (nla_put_be32(skb, NFQA_GID, htonl(from_kgid_munged(&init_user_ns, cred->fsgid)))) goto nla_put_failure; } read_unlock_bh(&sk->sk_callback_lock); return 0; nla_put_failure: read_unlock_bh(&sk->sk_callback_lock); return -1; } static int nfqnl_put_sk_classid(struct sk_buff *skb, struct sock *sk) { #if IS_ENABLED(CONFIG_CGROUP_NET_CLASSID) if (sk && sk_fullsock(sk)) { u32 classid = sock_cgroup_classid(&sk->sk_cgrp_data); if (classid && nla_put_be32(skb, NFQA_CGROUP_CLASSID, htonl(classid))) return -1; } #endif return 0; } static int nfqnl_get_sk_secctx(struct sk_buff *skb, struct lsm_context *ctx) { int seclen = 0; #if IS_ENABLED(CONFIG_NETWORK_SECMARK) if (!skb || !sk_fullsock(skb->sk)) return 0; read_lock_bh(&skb->sk->sk_callback_lock); if (skb->secmark) seclen = security_secid_to_secctx(skb->secmark, ctx); read_unlock_bh(&skb->sk->sk_callback_lock); #endif return seclen; } static u32 nfqnl_get_bridge_size(struct nf_queue_entry *entry) { struct sk_buff *entskb = entry->skb; u32 nlalen = 0; if (entry->state.pf != PF_BRIDGE || !skb_mac_header_was_set(entskb)) return 0; if (skb_vlan_tag_present(entskb)) nlalen += nla_total_size(nla_total_size(sizeof(__be16)) + nla_total_size(sizeof(__be16))); if (entskb->network_header > entskb->mac_header) nlalen += nla_total_size((entskb->network_header - entskb->mac_header)); return nlalen; } static int nfqnl_put_bridge(struct nf_queue_entry *entry, struct sk_buff *skb) { struct sk_buff *entskb = entry->skb; if (entry->state.pf != PF_BRIDGE || !skb_mac_header_was_set(entskb)) return 0; if (skb_vlan_tag_present(entskb)) { struct nlattr *nest; nest = nla_nest_start(skb, NFQA_VLAN); if (!nest) goto nla_put_failure; if (nla_put_be16(skb, NFQA_VLAN_TCI, htons(entskb->vlan_tci)) || nla_put_be16(skb, NFQA_VLAN_PROTO, entskb->vlan_proto)) goto nla_put_failure; nla_nest_end(skb, nest); } if (entskb->mac_header < entskb->network_header) { int len = (int)(entskb->network_header - entskb->mac_header); if (nla_put(skb, NFQA_L2HDR, len, skb_mac_header(entskb))) goto nla_put_failure; } return 0; nla_put_failure: return -1; } static int nf_queue_checksum_help(struct sk_buff *entskb) { if (skb_csum_is_sctp(entskb)) return skb_crc32c_csum_help(entskb); return skb_checksum_help(entskb); } static struct sk_buff * nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry, __be32 **packet_id_ptr) { size_t size; size_t data_len = 0, cap_len = 0; unsigned int hlen = 0; struct sk_buff *skb; struct nlattr *nla; struct nfqnl_msg_packet_hdr *pmsg; struct nlmsghdr *nlh; struct sk_buff *entskb = entry->skb; struct net_device *indev; struct net_device *outdev; struct nf_conn *ct = NULL; enum ip_conntrack_info ctinfo = 0; const struct nfnl_ct_hook *nfnl_ct; bool csum_verify; struct lsm_context ctx = { NULL, 0, 0 }; int seclen = 0; ktime_t tstamp; size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfqnl_msg_packet_hdr)) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #endif + nla_total_size(sizeof(u_int32_t)) /* mark */ + nla_total_size(sizeof(u_int32_t)) /* priority */ + nla_total_size(sizeof(struct nfqnl_msg_packet_hw)) + nla_total_size(sizeof(u_int32_t)) /* skbinfo */ #if IS_ENABLED(CONFIG_CGROUP_NET_CLASSID) + nla_total_size(sizeof(u_int32_t)) /* classid */ #endif + nla_total_size(sizeof(u_int32_t)); /* cap_len */ tstamp = skb_tstamp_cond(entskb, false); if (tstamp) size += nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp)); size += nfqnl_get_bridge_size(entry); if (entry->state.hook <= NF_INET_FORWARD || (entry->state.hook == NF_INET_POST_ROUTING && entskb->sk == NULL)) csum_verify = !skb_csum_unnecessary(entskb); else csum_verify = false; outdev = entry->state.out; switch ((enum nfqnl_config_mode)READ_ONCE(queue->copy_mode)) { case NFQNL_COPY_META: case NFQNL_COPY_NONE: break; case NFQNL_COPY_PACKET: if (!(queue->flags & NFQA_CFG_F_GSO) && entskb->ip_summed == CHECKSUM_PARTIAL && nf_queue_checksum_help(entskb)) return NULL; data_len = READ_ONCE(queue->copy_range); if (data_len > entskb->len) data_len = entskb->len; hlen = skb_zerocopy_headlen(entskb); hlen = min_t(unsigned int, hlen, data_len); size += sizeof(struct nlattr) + hlen; cap_len = entskb->len; break; } nfnl_ct = rcu_dereference(nfnl_ct_hook); #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (queue->flags & NFQA_CFG_F_CONNTRACK) { if (nfnl_ct != NULL) { ct = nf_ct_get(entskb, &ctinfo); if (ct != NULL) size += nfnl_ct->build_size(ct); } } #endif if (queue->flags & NFQA_CFG_F_UID_GID) { size += (nla_total_size(sizeof(u_int32_t)) /* uid */ + nla_total_size(sizeof(u_int32_t))); /* gid */ } if ((queue->flags & NFQA_CFG_F_SECCTX) && entskb->sk) { seclen = nfqnl_get_sk_secctx(entskb, &ctx); if (seclen < 0) return NULL; if (seclen) size += nla_total_size(seclen); } skb = alloc_skb(size, GFP_ATOMIC); if (!skb) { skb_tx_error(entskb); goto nlmsg_failure; } nlh = nfnl_msg_put(skb, 0, 0, nfnl_msg_type(NFNL_SUBSYS_QUEUE, NFQNL_MSG_PACKET), 0, entry->state.pf, NFNETLINK_V0, htons(queue->queue_num)); if (!nlh) { skb_tx_error(entskb); kfree_skb(skb); goto nlmsg_failure; } nla = __nla_reserve(skb, NFQA_PACKET_HDR, sizeof(*pmsg)); pmsg = nla_data(nla); pmsg->hw_protocol = entskb->protocol; pmsg->hook = entry->state.hook; *packet_id_ptr = &pmsg->packet_id; indev = entry->state.in; if (indev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; #else if (entry->state.pf == PF_BRIDGE) { /* Case 1: indev is physical input device, we need to * look for bridge group (when called from * netfilter_bridge) */ if (nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV, htonl(indev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by __nf_queue */ nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(br_port_get_rcu(indev)->br->dev->ifindex))) goto nla_put_failure; } else { int physinif; /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; physinif = nf_bridge_get_physinif(entskb); if (physinif && nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV, htonl(physinif))) goto nla_put_failure; } #endif } if (outdev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; #else if (entry->state.pf == PF_BRIDGE) { /* Case 1: outdev is physical output device, we need to * look for bridge group (when called from * netfilter_bridge) */ if (nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV, htonl(outdev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by __nf_queue */ nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) goto nla_put_failure; } else { int physoutif; /* Case 2: outdev is bridge group, we need to look for * physical output device (when called from ipv4) */ if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; physoutif = nf_bridge_get_physoutif(entskb); if (physoutif && nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV, htonl(physoutif))) goto nla_put_failure; } #endif } if (entskb->mark && nla_put_be32(skb, NFQA_MARK, htonl(entskb->mark))) goto nla_put_failure; if (entskb->priority && nla_put_be32(skb, NFQA_PRIORITY, htonl(entskb->priority))) goto nla_put_failure; if (indev && entskb->dev && skb_mac_header_was_set(entskb) && skb_mac_header_len(entskb) != 0) { struct nfqnl_msg_packet_hw phw; int len; memset(&phw, 0, sizeof(phw)); len = dev_parse_header(entskb, phw.hw_addr); if (len) { phw.hw_addrlen = htons(len); if (nla_put(skb, NFQA_HWADDR, sizeof(phw), &phw)) goto nla_put_failure; } } if (nfqnl_put_bridge(entry, skb) < 0) goto nla_put_failure; if (entry->state.hook <= NF_INET_FORWARD && tstamp) { struct nfqnl_msg_packet_timestamp ts; struct timespec64 kts = ktime_to_timespec64(tstamp); ts.sec = cpu_to_be64(kts.tv_sec); ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC); if (nla_put(skb, NFQA_TIMESTAMP, sizeof(ts), &ts)) goto nla_put_failure; } if ((queue->flags & NFQA_CFG_F_UID_GID) && entskb->sk && nfqnl_put_sk_uidgid(skb, entskb->sk) < 0) goto nla_put_failure; if (nfqnl_put_sk_classid(skb, entskb->sk) < 0) goto nla_put_failure; if (seclen > 0 && nla_put(skb, NFQA_SECCTX, ctx.len, ctx.context)) goto nla_put_failure; if (ct && nfnl_ct->build(skb, ct, ctinfo, NFQA_CT, NFQA_CT_INFO) < 0) goto nla_put_failure; if (cap_len > data_len && nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len))) goto nla_put_failure; if (nfqnl_put_packet_info(skb, entskb, csum_verify)) goto nla_put_failure; if (data_len) { struct nlattr *nla; if (skb_tailroom(skb) < sizeof(*nla) + hlen) goto nla_put_failure; nla = skb_put(skb, sizeof(*nla)); nla->nla_type = NFQA_PAYLOAD; nla->nla_len = nla_attr_size(data_len); if (skb_zerocopy(skb, entskb, data_len, hlen)) goto nla_put_failure; } nlh->nlmsg_len = skb->len; if (seclen >= 0) security_release_secctx(&ctx); return skb; nla_put_failure: skb_tx_error(entskb); kfree_skb(skb); net_err_ratelimited("nf_queue: error creating packet message\n"); nlmsg_failure: if (seclen >= 0) security_release_secctx(&ctx); return NULL; } static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) static const unsigned long flags = IPS_CONFIRMED | IPS_DYING; struct nf_conn *ct = (void *)skb_nfct(entry->skb); unsigned long status; unsigned int use; if (!ct) return false; status = READ_ONCE(ct->status); if ((status & flags) == IPS_DYING) return true; if (status & IPS_CONFIRMED) return false; /* in some cases skb_clone() can occur after initial conntrack * pickup, but conntrack assumes exclusive skb->_nfct ownership for * unconfirmed entries. * * This happens for br_netfilter and with ip multicast routing. * We can't be solved with serialization here because one clone could * have been queued for local delivery. */ use = refcount_read(&ct->ct_general.use); if (likely(use == 1)) return false; /* Can't decrement further? Exclusive ownership. */ if (!refcount_dec_not_one(&ct->ct_general.use)) return false; skb_set_nfct(entry->skb, 0); /* No nf_ct_put(): we already decremented .use and it cannot * drop down to 0. */ return true; #endif return false; } static int __nfqnl_enqueue_packet(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry) { struct sk_buff *nskb; int err = -ENOBUFS; __be32 *packet_id_ptr; int failopen = 0; nskb = nfqnl_build_packet_message(net, queue, entry, &packet_id_ptr); if (nskb == NULL) { err = -ENOMEM; goto err_out; } spin_lock_bh(&queue->lock); if (nf_ct_drop_unconfirmed(entry)) goto err_out_free_nskb; if (queue->queue_total >= queue->queue_maxlen) { if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { failopen = 1; err = 0; } else { queue->queue_dropped++; net_warn_ratelimited("nf_queue: full at %d entries, dropping packets(s)\n", queue->queue_total); } goto err_out_free_nskb; } entry->id = ++queue->id_sequence; *packet_id_ptr = htonl(entry->id); /* nfnetlink_unicast will either free the nskb or add it to a socket */ err = nfnetlink_unicast(nskb, net, queue->peer_portid); if (err < 0) { if (queue->flags & NFQA_CFG_F_FAIL_OPEN) { failopen = 1; err = 0; } else { queue->queue_user_dropped++; } goto err_out_unlock; } __enqueue_entry(queue, entry); spin_unlock_bh(&queue->lock); return 0; err_out_free_nskb: kfree_skb(nskb); err_out_unlock: spin_unlock_bh(&queue->lock); if (failopen) nfqnl_reinject(entry, NF_ACCEPT); err_out: return err; } static struct nf_queue_entry * nf_queue_entry_dup(struct nf_queue_entry *e) { struct nf_queue_entry *entry = kmemdup(e, e->size, GFP_ATOMIC); if (!entry) return NULL; if (nf_queue_entry_get_refs(entry)) return entry; kfree(entry); return NULL; } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) /* When called from bridge netfilter, skb->data must point to MAC header * before calling skb_gso_segment(). Else, original MAC header is lost * and segmented skbs will be sent to wrong destination. */ static void nf_bridge_adjust_skb_data(struct sk_buff *skb) { if (nf_bridge_info_get(skb)) __skb_push(skb, skb->network_header - skb->mac_header); } static void nf_bridge_adjust_segmented_data(struct sk_buff *skb) { if (nf_bridge_info_get(skb)) __skb_pull(skb, skb->network_header - skb->mac_header); } #else #define nf_bridge_adjust_skb_data(s) do {} while (0) #define nf_bridge_adjust_segmented_data(s) do {} while (0) #endif static int __nfqnl_enqueue_packet_gso(struct net *net, struct nfqnl_instance *queue, struct sk_buff *skb, struct nf_queue_entry *entry) { int ret = -ENOMEM; struct nf_queue_entry *entry_seg; nf_bridge_adjust_segmented_data(skb); if (skb->next == NULL) { /* last packet, no need to copy entry */ struct sk_buff *gso_skb = entry->skb; entry->skb = skb; ret = __nfqnl_enqueue_packet(net, queue, entry); if (ret) entry->skb = gso_skb; return ret; } skb_mark_not_on_list(skb); entry_seg = nf_queue_entry_dup(entry); if (entry_seg) { entry_seg->skb = skb; ret = __nfqnl_enqueue_packet(net, queue, entry_seg); if (ret) nf_queue_entry_free(entry_seg); } return ret; } static int nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) { unsigned int queued; struct nfqnl_instance *queue; struct sk_buff *skb, *segs, *nskb; int err = -ENOBUFS; struct net *net = entry->state.net; struct nfnl_queue_net *q = nfnl_queue_pernet(net); /* rcu_read_lock()ed by nf_hook_thresh */ queue = instance_lookup(q, queuenum); if (!queue) return -ESRCH; if (queue->copy_mode == NFQNL_COPY_NONE) return -EINVAL; skb = entry->skb; switch (entry->state.pf) { case NFPROTO_IPV4: skb->protocol = htons(ETH_P_IP); break; case NFPROTO_IPV6: skb->protocol = htons(ETH_P_IPV6); break; } if (!skb_is_gso(skb) || ((queue->flags & NFQA_CFG_F_GSO) && !skb_is_gso_sctp(skb))) return __nfqnl_enqueue_packet(net, queue, entry); nf_bridge_adjust_skb_data(skb); segs = skb_gso_segment(skb, 0); /* Does not use PTR_ERR to limit the number of error codes that can be * returned by nf_queue. For instance, callers rely on -ESRCH to * mean 'ignore this hook'. */ if (IS_ERR_OR_NULL(segs)) goto out_err; queued = 0; err = 0; skb_list_walk_safe(segs, segs, nskb) { if (err == 0) err = __nfqnl_enqueue_packet_gso(net, queue, segs, entry); if (err == 0) queued++; else kfree_skb(segs); } if (queued) { if (err) /* some segments are already queued */ nf_queue_entry_free(entry); kfree_skb(skb); return 0; } out_err: nf_bridge_adjust_segmented_data(skb); return err; } static int nfqnl_mangle(void *data, unsigned int data_len, struct nf_queue_entry *e, int diff) { struct sk_buff *nskb; if (diff < 0) { unsigned int min_len = skb_transport_offset(e->skb); if (data_len < min_len) return -EINVAL; if (pskb_trim(e->skb, data_len)) return -ENOMEM; } else if (diff > 0) { if (data_len > 0xFFFF) return -EINVAL; if (diff > skb_tailroom(e->skb)) { nskb = skb_copy_expand(e->skb, skb_headroom(e->skb), diff, GFP_ATOMIC); if (!nskb) return -ENOMEM; kfree_skb(e->skb); e->skb = nskb; } skb_put(e->skb, diff); } if (skb_ensure_writable(e->skb, data_len)) return -ENOMEM; skb_copy_to_linear_data(e->skb, data, data_len); e->skb->ip_summed = CHECKSUM_NONE; return 0; } static int nfqnl_set_mode(struct nfqnl_instance *queue, unsigned char mode, unsigned int range) { int status = 0; spin_lock_bh(&queue->lock); switch (mode) { case NFQNL_COPY_NONE: case NFQNL_COPY_META: queue->copy_mode = mode; queue->copy_range = 0; break; case NFQNL_COPY_PACKET: queue->copy_mode = mode; if (range == 0 || range > NFQNL_MAX_COPY_RANGE) queue->copy_range = NFQNL_MAX_COPY_RANGE; else queue->copy_range = range; break; default: status = -EINVAL; } spin_unlock_bh(&queue->lock); return status; } static int dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) int physinif, physoutif; physinif = nf_bridge_get_physinif(entry->skb); physoutif = nf_bridge_get_physoutif(entry->skb); if (physinif == ifindex || physoutif == ifindex) return 1; #endif if (entry->state.in) if (entry->state.in->ifindex == ifindex) return 1; if (entry->state.out) if (entry->state.out->ifindex == ifindex) return 1; return 0; } /* drop all packets with either indev or outdev == ifindex from all queue * instances */ static void nfqnl_dev_drop(struct net *net, int ifindex) { int i; struct nfnl_queue_net *q = nfnl_queue_pernet(net); rcu_read_lock(); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct nfqnl_instance *inst; struct hlist_head *head = &q->instance_table[i]; hlist_for_each_entry_rcu(inst, head, hlist) nfqnl_flush(inst, dev_cmp, ifindex); } rcu_read_unlock(); } static int nfqnl_rcv_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); /* Drop any packets associated with the downed device */ if (event == NETDEV_DOWN) nfqnl_dev_drop(dev_net(dev), dev->ifindex); return NOTIFY_DONE; } static struct notifier_block nfqnl_dev_notifier = { .notifier_call = nfqnl_rcv_dev_event, }; static void nfqnl_nf_hook_drop(struct net *net) { struct nfnl_queue_net *q = nfnl_queue_pernet(net); int i; /* This function is also called on net namespace error unwind, * when pernet_ops->init() failed and ->exit() functions of the * previous pernet_ops gets called. * * This may result in a call to nfqnl_nf_hook_drop() before * struct nfnl_queue_net was allocated. */ if (!q) return; for (i = 0; i < INSTANCE_BUCKETS; i++) { struct nfqnl_instance *inst; struct hlist_head *head = &q->instance_table[i]; hlist_for_each_entry_rcu(inst, head, hlist) nfqnl_flush(inst, NULL, 0); } } static int nfqnl_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netlink_notify *n = ptr; struct nfnl_queue_net *q = nfnl_queue_pernet(n->net); if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) { int i; /* destroy all instances for this portid */ spin_lock(&q->instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct hlist_node *t2; struct nfqnl_instance *inst; struct hlist_head *head = &q->instance_table[i]; hlist_for_each_entry_safe(inst, t2, head, hlist) { if (n->portid == inst->peer_portid) __instance_destroy(inst); } } spin_unlock(&q->instances_lock); } return NOTIFY_DONE; } static struct notifier_block nfqnl_rtnl_notifier = { .notifier_call = nfqnl_rcv_nl_event, }; static const struct nla_policy nfqa_vlan_policy[NFQA_VLAN_MAX + 1] = { [NFQA_VLAN_TCI] = { .type = NLA_U16}, [NFQA_VLAN_PROTO] = { .type = NLA_U16}, }; static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = { [NFQA_VERDICT_HDR] = { .len = sizeof(struct nfqnl_msg_verdict_hdr) }, [NFQA_MARK] = { .type = NLA_U32 }, [NFQA_PAYLOAD] = { .type = NLA_UNSPEC }, [NFQA_CT] = { .type = NLA_UNSPEC }, [NFQA_EXP] = { .type = NLA_UNSPEC }, [NFQA_VLAN] = { .type = NLA_NESTED }, [NFQA_PRIORITY] = { .type = NLA_U32 }, }; static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { [NFQA_VERDICT_HDR] = { .len = sizeof(struct nfqnl_msg_verdict_hdr) }, [NFQA_MARK] = { .type = NLA_U32 }, [NFQA_PRIORITY] = { .type = NLA_U32 }, }; static struct nfqnl_instance * verdict_instance_lookup(struct nfnl_queue_net *q, u16 queue_num, u32 nlportid) { struct nfqnl_instance *queue; queue = instance_lookup(q, queue_num); if (!queue) return ERR_PTR(-ENODEV); if (queue->peer_portid != nlportid) return ERR_PTR(-EPERM); return queue; } static struct nfqnl_msg_verdict_hdr* verdicthdr_get(const struct nlattr * const nfqa[]) { struct nfqnl_msg_verdict_hdr *vhdr; unsigned int verdict; if (!nfqa[NFQA_VERDICT_HDR]) return NULL; vhdr = nla_data(nfqa[NFQA_VERDICT_HDR]); verdict = ntohl(vhdr->verdict) & NF_VERDICT_MASK; if (verdict > NF_MAX_VERDICT || verdict == NF_STOLEN) return NULL; return vhdr; } static int nfq_id_after(unsigned int id, unsigned int max) { return (int)(id - max) > 0; } static int nfqnl_recv_verdict_batch(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); u16 queue_num = ntohs(info->nfmsg->res_id); struct nf_queue_entry *entry, *tmp; struct nfqnl_msg_verdict_hdr *vhdr; struct nfqnl_instance *queue; unsigned int verdict, maxid; LIST_HEAD(batch_list); queue = verdict_instance_lookup(q, queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); vhdr = verdicthdr_get(nfqa); if (!vhdr) return -EINVAL; verdict = ntohl(vhdr->verdict); maxid = ntohl(vhdr->id); spin_lock_bh(&queue->lock); list_for_each_entry_safe(entry, tmp, &queue->queue_list, list) { if (nfq_id_after(entry->id, maxid)) break; __dequeue_entry(queue, entry); list_add_tail(&entry->list, &batch_list); } spin_unlock_bh(&queue->lock); if (list_empty(&batch_list)) return -ENOENT; list_for_each_entry_safe(entry, tmp, &batch_list, list) { if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); if (nfqa[NFQA_PRIORITY]) entry->skb->priority = ntohl(nla_get_be32(nfqa[NFQA_PRIORITY])); nfqnl_reinject(entry, verdict); } return 0; } static struct nf_conn *nfqnl_ct_parse(const struct nfnl_ct_hook *nfnl_ct, const struct nlmsghdr *nlh, const struct nlattr * const nfqa[], struct nf_queue_entry *entry, enum ip_conntrack_info *ctinfo) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct nf_conn *ct; ct = nf_ct_get(entry->skb, ctinfo); if (ct == NULL) return NULL; if (nfnl_ct->parse(nfqa[NFQA_CT], ct) < 0) return NULL; if (nfqa[NFQA_EXP]) nfnl_ct->attach_expect(nfqa[NFQA_EXP], ct, NETLINK_CB(entry->skb).portid, nlmsg_report(nlh)); return ct; #else return NULL; #endif } static int nfqa_parse_bridge(struct nf_queue_entry *entry, const struct nlattr * const nfqa[]) { if (nfqa[NFQA_VLAN]) { struct nlattr *tb[NFQA_VLAN_MAX + 1]; int err; err = nla_parse_nested_deprecated(tb, NFQA_VLAN_MAX, nfqa[NFQA_VLAN], nfqa_vlan_policy, NULL); if (err < 0) return err; if (!tb[NFQA_VLAN_TCI] || !tb[NFQA_VLAN_PROTO]) return -EINVAL; __vlan_hwaccel_put_tag(entry->skb, nla_get_be16(tb[NFQA_VLAN_PROTO]), ntohs(nla_get_be16(tb[NFQA_VLAN_TCI]))); } if (nfqa[NFQA_L2HDR]) { int mac_header_len = entry->skb->network_header - entry->skb->mac_header; if (mac_header_len != nla_len(nfqa[NFQA_L2HDR])) return -EINVAL; else if (mac_header_len > 0) memcpy(skb_mac_header(entry->skb), nla_data(nfqa[NFQA_L2HDR]), mac_header_len); } return 0; } static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); u_int16_t queue_num = ntohs(info->nfmsg->res_id); const struct nfnl_ct_hook *nfnl_ct; struct nfqnl_msg_verdict_hdr *vhdr; enum ip_conntrack_info ctinfo; struct nfqnl_instance *queue; struct nf_queue_entry *entry; struct nf_conn *ct = NULL; unsigned int verdict; int err; queue = verdict_instance_lookup(q, queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); vhdr = verdicthdr_get(nfqa); if (!vhdr) return -EINVAL; verdict = ntohl(vhdr->verdict); entry = find_dequeue_entry(queue, ntohl(vhdr->id)); if (entry == NULL) return -ENOENT; /* rcu lock already held from nfnl->call_rcu. */ nfnl_ct = rcu_dereference(nfnl_ct_hook); if (nfqa[NFQA_CT]) { if (nfnl_ct != NULL) ct = nfqnl_ct_parse(nfnl_ct, info->nlh, nfqa, entry, &ctinfo); } if (entry->state.pf == PF_BRIDGE) { err = nfqa_parse_bridge(entry, nfqa); if (err < 0) return err; } if (nfqa[NFQA_PAYLOAD]) { u16 payload_len = nla_len(nfqa[NFQA_PAYLOAD]); int diff = payload_len - entry->skb->len; if (nfqnl_mangle(nla_data(nfqa[NFQA_PAYLOAD]), payload_len, entry, diff) < 0) verdict = NF_DROP; if (ct && diff) nfnl_ct->seq_adjust(entry->skb, ct, ctinfo, diff); } if (nfqa[NFQA_MARK]) entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); if (nfqa[NFQA_PRIORITY]) entry->skb->priority = ntohl(nla_get_be32(nfqa[NFQA_PRIORITY])); nfqnl_reinject(entry, verdict); return 0; } static int nfqnl_recv_unsupp(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const cda[]) { return -ENOTSUPP; } static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = { [NFQA_CFG_CMD] = { .len = sizeof(struct nfqnl_msg_config_cmd) }, [NFQA_CFG_PARAMS] = { .len = sizeof(struct nfqnl_msg_config_params) }, [NFQA_CFG_QUEUE_MAXLEN] = { .type = NLA_U32 }, [NFQA_CFG_MASK] = { .type = NLA_U32 }, [NFQA_CFG_FLAGS] = { .type = NLA_U32 }, }; static const struct nf_queue_handler nfqh = { .outfn = nfqnl_enqueue_packet, .nf_hook_drop = nfqnl_nf_hook_drop, }; static int nfqnl_recv_config(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const nfqa[]) { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); u_int16_t queue_num = ntohs(info->nfmsg->res_id); struct nfqnl_msg_config_cmd *cmd = NULL; struct nfqnl_instance *queue; __u32 flags = 0, mask = 0; int ret = 0; if (nfqa[NFQA_CFG_CMD]) { cmd = nla_data(nfqa[NFQA_CFG_CMD]); /* Obsolete commands without queue context */ switch (cmd->command) { case NFQNL_CFG_CMD_PF_BIND: return 0; case NFQNL_CFG_CMD_PF_UNBIND: return 0; } } /* Check if we support these flags in first place, dependencies should * be there too not to break atomicity. */ if (nfqa[NFQA_CFG_FLAGS]) { if (!nfqa[NFQA_CFG_MASK]) { /* A mask is needed to specify which flags are being * changed. */ return -EINVAL; } flags = ntohl(nla_get_be32(nfqa[NFQA_CFG_FLAGS])); mask = ntohl(nla_get_be32(nfqa[NFQA_CFG_MASK])); if (flags >= NFQA_CFG_F_MAX) return -EOPNOTSUPP; #if !IS_ENABLED(CONFIG_NETWORK_SECMARK) if (flags & mask & NFQA_CFG_F_SECCTX) return -EOPNOTSUPP; #endif if ((flags & mask & NFQA_CFG_F_CONNTRACK) && !rcu_access_pointer(nfnl_ct_hook)) { #ifdef CONFIG_MODULES nfnl_unlock(NFNL_SUBSYS_QUEUE); request_module("ip_conntrack_netlink"); nfnl_lock(NFNL_SUBSYS_QUEUE); if (rcu_access_pointer(nfnl_ct_hook)) return -EAGAIN; #endif return -EOPNOTSUPP; } } rcu_read_lock(); queue = instance_lookup(q, queue_num); if (queue && queue->peer_portid != NETLINK_CB(skb).portid) { ret = -EPERM; goto err_out_unlock; } if (cmd != NULL) { switch (cmd->command) { case NFQNL_CFG_CMD_BIND: if (queue) { ret = -EBUSY; goto err_out_unlock; } queue = instance_create(q, queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) { ret = PTR_ERR(queue); goto err_out_unlock; } break; case NFQNL_CFG_CMD_UNBIND: if (!queue) { ret = -ENODEV; goto err_out_unlock; } instance_destroy(q, queue); goto err_out_unlock; case NFQNL_CFG_CMD_PF_BIND: case NFQNL_CFG_CMD_PF_UNBIND: break; default: ret = -ENOTSUPP; goto err_out_unlock; } } if (!queue) { ret = -ENODEV; goto err_out_unlock; } if (nfqa[NFQA_CFG_PARAMS]) { struct nfqnl_msg_config_params *params = nla_data(nfqa[NFQA_CFG_PARAMS]); nfqnl_set_mode(queue, params->copy_mode, ntohl(params->copy_range)); } if (nfqa[NFQA_CFG_QUEUE_MAXLEN]) { __be32 *queue_maxlen = nla_data(nfqa[NFQA_CFG_QUEUE_MAXLEN]); spin_lock_bh(&queue->lock); queue->queue_maxlen = ntohl(*queue_maxlen); spin_unlock_bh(&queue->lock); } if (nfqa[NFQA_CFG_FLAGS]) { spin_lock_bh(&queue->lock); queue->flags &= ~mask; queue->flags |= flags & mask; spin_unlock_bh(&queue->lock); } err_out_unlock: rcu_read_unlock(); return ret; } static const struct nfnl_callback nfqnl_cb[NFQNL_MSG_MAX] = { [NFQNL_MSG_PACKET] = { .call = nfqnl_recv_unsupp, .type = NFNL_CB_RCU, .attr_count = NFQA_MAX, }, [NFQNL_MSG_VERDICT] = { .call = nfqnl_recv_verdict, .type = NFNL_CB_RCU, .attr_count = NFQA_MAX, .policy = nfqa_verdict_policy }, [NFQNL_MSG_CONFIG] = { .call = nfqnl_recv_config, .type = NFNL_CB_MUTEX, .attr_count = NFQA_CFG_MAX, .policy = nfqa_cfg_policy }, [NFQNL_MSG_VERDICT_BATCH] = { .call = nfqnl_recv_verdict_batch, .type = NFNL_CB_RCU, .attr_count = NFQA_MAX, .policy = nfqa_verdict_batch_policy }, }; static const struct nfnetlink_subsystem nfqnl_subsys = { .name = "nf_queue", .subsys_id = NFNL_SUBSYS_QUEUE, .cb_count = NFQNL_MSG_MAX, .cb = nfqnl_cb, }; #ifdef CONFIG_PROC_FS struct iter_state { struct seq_net_private p; unsigned int bucket; }; static struct hlist_node *get_first(struct seq_file *seq) { struct iter_state *st = seq->private; struct net *net; struct nfnl_queue_net *q; if (!st) return NULL; net = seq_file_net(seq); q = nfnl_queue_pernet(net); for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) { if (!hlist_empty(&q->instance_table[st->bucket])) return q->instance_table[st->bucket].first; } return NULL; } static struct hlist_node *get_next(struct seq_file *seq, struct hlist_node *h) { struct iter_state *st = seq->private; struct net *net = seq_file_net(seq); h = h->next; while (!h) { struct nfnl_queue_net *q; if (++st->bucket >= INSTANCE_BUCKETS) return NULL; q = nfnl_queue_pernet(net); h = q->instance_table[st->bucket].first; } return h; } static struct hlist_node *get_idx(struct seq_file *seq, loff_t pos) { struct hlist_node *head; head = get_first(seq); if (head) while (pos && (head = get_next(seq, head))) pos--; return pos ? NULL : head; } static void *seq_start(struct seq_file *s, loff_t *pos) __acquires(nfnl_queue_pernet(seq_file_net(s))->instances_lock) { spin_lock(&nfnl_queue_pernet(seq_file_net(s))->instances_lock); return get_idx(s, *pos); } static void *seq_next(struct seq_file *s, void *v, loff_t *pos) { (*pos)++; return get_next(s, v); } static void seq_stop(struct seq_file *s, void *v) __releases(nfnl_queue_pernet(seq_file_net(s))->instances_lock) { spin_unlock(&nfnl_queue_pernet(seq_file_net(s))->instances_lock); } static int seq_show(struct seq_file *s, void *v) { const struct nfqnl_instance *inst = v; seq_printf(s, "%5u %6u %5u %1u %5u %5u %5u %8u %2d\n", inst->queue_num, inst->peer_portid, inst->queue_total, inst->copy_mode, inst->copy_range, inst->queue_dropped, inst->queue_user_dropped, inst->id_sequence, 1); return 0; } static const struct seq_operations nfqnl_seq_ops = { .start = seq_start, .next = seq_next, .stop = seq_stop, .show = seq_show, }; #endif /* PROC_FS */ static int __net_init nfnl_queue_net_init(struct net *net) { unsigned int i; struct nfnl_queue_net *q = nfnl_queue_pernet(net); for (i = 0; i < INSTANCE_BUCKETS; i++) INIT_HLIST_HEAD(&q->instance_table[i]); spin_lock_init(&q->instances_lock); #ifdef CONFIG_PROC_FS if (!proc_create_net("nfnetlink_queue", 0440, net->nf.proc_netfilter, &nfqnl_seq_ops, sizeof(struct iter_state))) return -ENOMEM; #endif return 0; } static void __net_exit nfnl_queue_net_exit(struct net *net) { struct nfnl_queue_net *q = nfnl_queue_pernet(net); unsigned int i; #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_queue", net->nf.proc_netfilter); #endif for (i = 0; i < INSTANCE_BUCKETS; i++) WARN_ON_ONCE(!hlist_empty(&q->instance_table[i])); } static struct pernet_operations nfnl_queue_net_ops = { .init = nfnl_queue_net_init, .exit = nfnl_queue_net_exit, .id = &nfnl_queue_net_id, .size = sizeof(struct nfnl_queue_net), }; static int __init nfnetlink_queue_init(void) { int status; status = register_pernet_subsys(&nfnl_queue_net_ops); if (status < 0) { pr_err("failed to register pernet ops\n"); goto out; } netlink_register_notifier(&nfqnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfqnl_subsys); if (status < 0) { pr_err("failed to create netlink socket\n"); goto cleanup_netlink_notifier; } status = register_netdevice_notifier(&nfqnl_dev_notifier); if (status < 0) { pr_err("failed to register netdevice notifier\n"); goto cleanup_netlink_subsys; } nf_register_queue_handler(&nfqh); return status; cleanup_netlink_subsys: nfnetlink_subsys_unregister(&nfqnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfqnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_queue_net_ops); out: return status; } static void __exit nfnetlink_queue_fini(void) { nf_unregister_queue_handler(); unregister_netdevice_notifier(&nfqnl_dev_notifier); nfnetlink_subsys_unregister(&nfqnl_subsys); netlink_unregister_notifier(&nfqnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_queue_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ } MODULE_DESCRIPTION("netfilter packet queue handler"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_QUEUE); module_init(nfnetlink_queue_init); module_exit(nfnetlink_queue_fini); |
| 3 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NS_COMMON_H #define _LINUX_NS_COMMON_H #include <linux/refcount.h> #include <linux/rbtree.h> #include <uapi/linux/sched.h> struct proc_ns_operations; struct cgroup_namespace; struct ipc_namespace; struct mnt_namespace; struct net; struct pid_namespace; struct time_namespace; struct user_namespace; struct uts_namespace; extern struct cgroup_namespace init_cgroup_ns; extern struct ipc_namespace init_ipc_ns; extern struct mnt_namespace init_mnt_ns; extern struct net init_net; extern struct pid_namespace init_pid_ns; extern struct time_namespace init_time_ns; extern struct user_namespace init_user_ns; extern struct uts_namespace init_uts_ns; extern const struct proc_ns_operations netns_operations; extern const struct proc_ns_operations utsns_operations; extern const struct proc_ns_operations ipcns_operations; extern const struct proc_ns_operations pidns_operations; extern const struct proc_ns_operations pidns_for_children_operations; extern const struct proc_ns_operations userns_operations; extern const struct proc_ns_operations mntns_operations; extern const struct proc_ns_operations cgroupns_operations; extern const struct proc_ns_operations timens_operations; extern const struct proc_ns_operations timens_for_children_operations; struct ns_common { u32 ns_type; struct dentry *stashed; const struct proc_ns_operations *ops; unsigned int inum; refcount_t __ns_ref; /* do not use directly */ union { struct { u64 ns_id; struct rb_node ns_tree_node; struct list_head ns_list_node; }; struct rcu_head ns_rcu; }; }; int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_operations *ops, int inum); void __ns_common_free(struct ns_common *ns); #define to_ns_common(__ns) \ _Generic((__ns), \ struct cgroup_namespace *: &(__ns)->ns, \ const struct cgroup_namespace *: &(__ns)->ns, \ struct ipc_namespace *: &(__ns)->ns, \ const struct ipc_namespace *: &(__ns)->ns, \ struct mnt_namespace *: &(__ns)->ns, \ const struct mnt_namespace *: &(__ns)->ns, \ struct net *: &(__ns)->ns, \ const struct net *: &(__ns)->ns, \ struct pid_namespace *: &(__ns)->ns, \ const struct pid_namespace *: &(__ns)->ns, \ struct time_namespace *: &(__ns)->ns, \ const struct time_namespace *: &(__ns)->ns, \ struct user_namespace *: &(__ns)->ns, \ const struct user_namespace *: &(__ns)->ns, \ struct uts_namespace *: &(__ns)->ns, \ const struct uts_namespace *: &(__ns)->ns) #define ns_init_inum(__ns) \ _Generic((__ns), \ struct cgroup_namespace *: CGROUP_NS_INIT_INO, \ struct ipc_namespace *: IPC_NS_INIT_INO, \ struct mnt_namespace *: MNT_NS_INIT_INO, \ struct net *: NET_NS_INIT_INO, \ struct pid_namespace *: PID_NS_INIT_INO, \ struct time_namespace *: TIME_NS_INIT_INO, \ struct user_namespace *: USER_NS_INIT_INO, \ struct uts_namespace *: UTS_NS_INIT_INO) #define ns_init_ns(__ns) \ _Generic((__ns), \ struct cgroup_namespace *: &init_cgroup_ns, \ struct ipc_namespace *: &init_ipc_ns, \ struct mnt_namespace *: &init_mnt_ns, \ struct net *: &init_net, \ struct pid_namespace *: &init_pid_ns, \ struct time_namespace *: &init_time_ns, \ struct user_namespace *: &init_user_ns, \ struct uts_namespace *: &init_uts_ns) #define to_ns_operations(__ns) \ _Generic((__ns), \ struct cgroup_namespace *: (IS_ENABLED(CONFIG_CGROUPS) ? &cgroupns_operations : NULL), \ struct ipc_namespace *: (IS_ENABLED(CONFIG_IPC_NS) ? &ipcns_operations : NULL), \ struct mnt_namespace *: &mntns_operations, \ struct net *: (IS_ENABLED(CONFIG_NET_NS) ? &netns_operations : NULL), \ struct pid_namespace *: (IS_ENABLED(CONFIG_PID_NS) ? &pidns_operations : NULL), \ struct time_namespace *: (IS_ENABLED(CONFIG_TIME_NS) ? &timens_operations : NULL), \ struct user_namespace *: (IS_ENABLED(CONFIG_USER_NS) ? &userns_operations : NULL), \ struct uts_namespace *: (IS_ENABLED(CONFIG_UTS_NS) ? &utsns_operations : NULL)) #define ns_common_type(__ns) \ _Generic((__ns), \ struct cgroup_namespace *: CLONE_NEWCGROUP, \ struct ipc_namespace *: CLONE_NEWIPC, \ struct mnt_namespace *: CLONE_NEWNS, \ struct net *: CLONE_NEWNET, \ struct pid_namespace *: CLONE_NEWPID, \ struct time_namespace *: CLONE_NEWTIME, \ struct user_namespace *: CLONE_NEWUSER, \ struct uts_namespace *: CLONE_NEWUTS) #define ns_common_init(__ns) \ __ns_common_init(to_ns_common(__ns), \ ns_common_type(__ns), \ to_ns_operations(__ns), \ (((__ns) == ns_init_ns(__ns)) ? ns_init_inum(__ns) : 0)) #define ns_common_init_inum(__ns, __inum) \ __ns_common_init(to_ns_common(__ns), \ ns_common_type(__ns), \ to_ns_operations(__ns), \ __inum) #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns))) static __always_inline __must_check bool __ns_ref_put(struct ns_common *ns) { return refcount_dec_and_test(&ns->__ns_ref); } static __always_inline __must_check bool __ns_ref_get(struct ns_common *ns) { return refcount_inc_not_zero(&ns->__ns_ref); } #define ns_ref_read(__ns) refcount_read(&to_ns_common((__ns))->__ns_ref) #define ns_ref_inc(__ns) refcount_inc(&to_ns_common((__ns))->__ns_ref) #define ns_ref_get(__ns) __ns_ref_get(to_ns_common((__ns))) #define ns_ref_put(__ns) __ns_ref_put(to_ns_common((__ns))) #define ns_ref_put_and_lock(__ns, __lock) \ refcount_dec_and_lock(&to_ns_common((__ns))->__ns_ref, (__lock)) #endif |
| 2 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * workqueue.h --- work queue handling for Linux. */ #ifndef _LINUX_WORKQUEUE_H #define _LINUX_WORKQUEUE_H #include <linux/alloc_tag.h> #include <linux/timer.h> #include <linux/linkage.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/threads.h> #include <linux/atomic.h> #include <linux/cpumask_types.h> #include <linux/rcupdate.h> #include <linux/workqueue_types.h> /* * The first word is the work queue pointer and the flags rolled into * one */ #define work_data_bits(work) ((unsigned long *)(&(work)->data)) enum work_bits { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ WORK_STRUCT_INACTIVE_BIT, /* work item is inactive */ WORK_STRUCT_PWQ_BIT, /* data points to pwq */ WORK_STRUCT_LINKED_BIT, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT, /* static initializer (debugobjects) */ #endif WORK_STRUCT_FLAG_BITS, /* color for workqueue flushing */ WORK_STRUCT_COLOR_SHIFT = WORK_STRUCT_FLAG_BITS, WORK_STRUCT_COLOR_BITS = 4, /* * When WORK_STRUCT_PWQ is set, reserve 8 bits off of pwq pointer w/ * debugobjects turned off. This makes pwqs aligned to 256 bytes (512 * bytes w/ DEBUG_OBJECTS_WORK) and allows 16 workqueue flush colors. * * MSB * [ pwq pointer ] [ flush color ] [ STRUCT flags ] * 4 bits 4 or 5 bits */ WORK_STRUCT_PWQ_SHIFT = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, /* * data contains off-queue information when !WORK_STRUCT_PWQ. * * MSB * [ pool ID ] [ disable depth ] [ OFFQ flags ] [ STRUCT flags ] * 16 bits 1 bit 4 or 5 bits */ WORK_OFFQ_FLAG_SHIFT = WORK_STRUCT_FLAG_BITS, WORK_OFFQ_BH_BIT = WORK_OFFQ_FLAG_SHIFT, WORK_OFFQ_FLAG_END, WORK_OFFQ_FLAG_BITS = WORK_OFFQ_FLAG_END - WORK_OFFQ_FLAG_SHIFT, WORK_OFFQ_DISABLE_SHIFT = WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_DISABLE_BITS = 16, /* * When a work item is off queue, the high bits encode off-queue flags * and the last pool it was on. Cap pool ID to 31 bits and use the * highest number to indicate that no pool is associated. */ WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_DISABLE_SHIFT + WORK_OFFQ_DISABLE_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, }; enum work_flags { WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT, WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, #else WORK_STRUCT_STATIC = 0, #endif }; enum wq_misc_consts { WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS), /* not bound to any CPU, prefer the local CPU */ WORK_CPU_UNBOUND = NR_CPUS, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, WORK_BUSY_RUNNING = 1 << 1, /* maximum string length for set_worker_desc() */ WORKER_DESC_LEN = 32, }; /* Convenience constants - of type 'unsigned long', not 'enum'! */ #define WORK_OFFQ_BH (1ul << WORK_OFFQ_BH_BIT) #define WORK_OFFQ_FLAG_MASK (((1ul << WORK_OFFQ_FLAG_BITS) - 1) << WORK_OFFQ_FLAG_SHIFT) #define WORK_OFFQ_DISABLE_MASK (((1ul << WORK_OFFQ_DISABLE_BITS) - 1) << WORK_OFFQ_DISABLE_SHIFT) #define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) #define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) #define WORK_STRUCT_PWQ_MASK (~((1ul << WORK_STRUCT_PWQ_SHIFT) - 1)) #define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)) struct delayed_work { struct work_struct work; struct timer_list timer; /* target workqueue and CPU ->timer uses to queue ->work */ struct workqueue_struct *wq; int cpu; }; struct rcu_work { struct work_struct work; struct rcu_head rcu; /* target workqueue ->rcu uses to queue ->work */ struct workqueue_struct *wq; }; enum wq_affn_scope { WQ_AFFN_DFL, /* use system default */ WQ_AFFN_CPU, /* one pod per CPU */ WQ_AFFN_SMT, /* one pod poer SMT */ WQ_AFFN_CACHE, /* one pod per LLC */ WQ_AFFN_NUMA, /* one pod per NUMA node */ WQ_AFFN_SYSTEM, /* one pod across the whole system */ WQ_AFFN_NR_TYPES, }; /** * struct workqueue_attrs - A struct for workqueue attributes. * * This can be used to change attributes of an unbound workqueue. */ struct workqueue_attrs { /** * @nice: nice level */ int nice; /** * @cpumask: allowed CPUs * * Work items in this workqueue are affine to these CPUs and not allowed * to execute on other CPUs. A pool serving a workqueue must have the * same @cpumask. */ cpumask_var_t cpumask; /** * @__pod_cpumask: internal attribute used to create per-pod pools * * Internal use only. * * Per-pod unbound worker pools are used to improve locality. Always a * subset of ->cpumask. A workqueue can be associated with multiple * worker pools with disjoint @__pod_cpumask's. Whether the enforcement * of a pool's @__pod_cpumask is strict depends on @affn_strict. */ cpumask_var_t __pod_cpumask; /** * @affn_strict: affinity scope is strict * * If clear, workqueue will make a best-effort attempt at starting the * worker inside @__pod_cpumask but the scheduler is free to migrate it * outside. * * If set, workers are only allowed to run inside @__pod_cpumask. */ bool affn_strict; /* * Below fields aren't properties of a worker_pool. They only modify how * :c:func:`apply_workqueue_attrs` select pools and thus don't * participate in pool hash calculations or equality comparisons. * * If @affn_strict is set, @cpumask isn't a property of a worker_pool * either. */ /** * @affn_scope: unbound CPU affinity scope * * CPU pods are used to improve execution locality of unbound work * items. There are multiple pod types, one for each wq_affn_scope, and * every CPU in the system belongs to one pod in every pod type. CPUs * that belong to the same pod share the worker pool. For example, * selecting %WQ_AFFN_NUMA makes the workqueue use a separate worker * pool for each NUMA node. */ enum wq_affn_scope affn_scope; /** * @ordered: work items must be executed one by one in queueing order */ bool ordered; }; static inline struct delayed_work *to_delayed_work(struct work_struct *work) { return container_of(work, struct delayed_work, work); } static inline struct rcu_work *to_rcu_work(struct work_struct *work) { return container_of(work, struct rcu_work, work); } struct execute_work { struct work_struct work; }; #ifdef CONFIG_LOCKDEP /* * NB: because we have to copy the lockdep_map, setting _key * here is required, otherwise it could get initialised to the * copy of the lockdep_map! */ #define __WORK_INIT_LOCKDEP_MAP(n, k) \ .lockdep_map = STATIC_LOCKDEP_MAP_INIT(n, k), #else #define __WORK_INIT_LOCKDEP_MAP(n, k) #endif #define __WORK_INITIALIZER(n, f) { \ .data = WORK_DATA_STATIC_INIT(), \ .entry = { &(n).entry, &(n).entry }, \ .func = (f), \ __WORK_INIT_LOCKDEP_MAP(#n, &(n)) \ } #define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ .work = __WORK_INITIALIZER((n).work, (f)), \ .timer = __TIMER_INITIALIZER(delayed_work_timer_fn,\ (tflags) | TIMER_IRQSAFE), \ } #define DECLARE_WORK(n, f) \ struct work_struct n = __WORK_INITIALIZER(n, f) #define DECLARE_DELAYED_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0) #define DECLARE_DEFERRABLE_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, TIMER_DEFERRABLE) #ifdef CONFIG_DEBUG_OBJECTS_WORK extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); extern void destroy_delayed_work_on_stack(struct delayed_work *work); static inline unsigned int work_static(struct work_struct *work) { return *work_data_bits(work) & WORK_STRUCT_STATIC; } #else static inline void __init_work(struct work_struct *work, int onstack) { } static inline void destroy_work_on_stack(struct work_struct *work) { } static inline void destroy_delayed_work_on_stack(struct delayed_work *work) { } static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif /* * initialize all of a work item in one go * * NOTE! No point in using "atomic_long_set()": using a direct * assignment of the work data initializer allows the compiler * to generate better code. */ #ifdef CONFIG_LOCKDEP #define __INIT_WORK_KEY(_work, _func, _onstack, _key) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, (_key), 0); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #else #define __INIT_WORK_KEY(_work, _func, _onstack, _key) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #endif #define __INIT_WORK(_work, _func, _onstack) \ do { \ static __maybe_unused struct lock_class_key __key; \ \ __INIT_WORK_KEY(_work, _func, _onstack, &__key); \ } while (0) #define INIT_WORK(_work, _func) \ __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ __INIT_WORK((_work), (_func), 1) #define INIT_WORK_ONSTACK_KEY(_work, _func, _key) \ __INIT_WORK_KEY((_work), (_func), 1, _key) #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ INIT_WORK(&(_work)->work, (_func)); \ __timer_init(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define __INIT_DELAYED_WORK_ONSTACK(_work, _func, _tflags) \ do { \ INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ __timer_init_on_stack(&(_work)->timer, \ delayed_work_timer_fn, \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define INIT_DELAYED_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, 0) #define INIT_DELAYED_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, 0) #define INIT_DEFERRABLE_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, TIMER_DEFERRABLE) #define INIT_DEFERRABLE_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, TIMER_DEFERRABLE) #define INIT_RCU_WORK(_work, _func) \ INIT_WORK(&(_work)->work, (_func)) #define INIT_RCU_WORK_ONSTACK(_work, _func) \ INIT_WORK_ONSTACK(&(_work)->work, (_func)) /** * work_pending - Find out whether a work item is currently pending * @work: The work item in question */ #define work_pending(work) \ test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) /** * delayed_work_pending - Find out whether a delayable work item is currently * pending * @w: The work item in question */ #define delayed_work_pending(w) \ work_pending(&(w)->work) /* * Workqueue flags and constants. For details, please refer to * Documentation/core-api/workqueue.rst. */ enum wq_flags { WQ_BH = 1 << 0, /* execute in bottom half (softirq) context */ WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu intensive workqueue */ WQ_SYSFS = 1 << 6, /* visible in sysfs, see workqueue_sysfs_register() */ /* * Per-cpu workqueues are generally preferred because they tend to * show better performance thanks to cache locality. Per-cpu * workqueues exclude the scheduler from choosing the CPU to * execute the worker threads, which has an unfortunate side effect * of increasing power consumption. * * The scheduler considers a CPU idle if it doesn't have any task * to execute and tries to keep idle cores idle to conserve power; * however, for example, a per-cpu work item scheduled from an * interrupt handler on an idle CPU will force the scheduler to * execute the work item on that CPU breaking the idleness, which in * turn may lead to more scheduling choices which are sub-optimal * in terms of power consumption. * * Workqueues marked with WQ_POWER_EFFICIENT are per-cpu by default * but become unbound if workqueue.power_efficient kernel param is * specified. Per-cpu workqueues which are identified to * contribute significantly to power-consumption are identified and * marked with this flag and enabling the power_efficient mode * leads to noticeable power saving at the cost of small * performance disadvantage. * * http://thread.gmane.org/gmane.linux.kernel/1480396 */ WQ_POWER_EFFICIENT = 1 << 7, WQ_PERCPU = 1 << 8, /* bound to a specific cpu */ __WQ_DESTROYING = 1 << 15, /* internal: workqueue is destroying */ __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ /* BH wq only allows the following flags */ __WQ_BH_ALLOWS = WQ_BH | WQ_HIGHPRI | WQ_PERCPU, }; enum wq_consts { WQ_MAX_ACTIVE = 2048, /* I like 2048, better ideas? */ WQ_UNBOUND_MAX_ACTIVE = WQ_MAX_ACTIVE, WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, /* * Per-node default cap on min_active. Unless explicitly set, min_active * is set to min(max_active, WQ_DFL_MIN_ACTIVE). For more details, see * workqueue_struct->min_active definition. */ WQ_DFL_MIN_ACTIVE = 8, }; /* * System-wide workqueues which are always present. * * system_percpu_wq is the one used by schedule[_delayed]_work[_on](). * Multi-CPU multi-threaded. There are users which expect relatively * short queue flush time. Don't queue works which can run for too * long. * * system_highpri_wq is similar to system_percpu_wq but for work items which * require WQ_HIGHPRI. * * system_long_wq is similar to system_percpu_wq but may host long running * works. Queue flushing might take relatively long. * * system_dfl_wq is unbound workqueue. Workers are not bound to * any specific CPU, not concurrency managed, and all queued works are * executed immediately as long as max_active limit is not reached and * resources are available. * * system_freezable_wq is equivalent to system_percpu_wq except that it's * freezable. * * *_power_efficient_wq are inclined towards saving power and converted * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise, * they are same as their non-power-efficient counterparts - e.g. * system_power_efficient_wq is identical to system_percpu_wq if * 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info. * * system_bh[_highpri]_wq are convenience interface to softirq. BH work items * are executed in the queueing CPU's BH context in the queueing order. */ extern struct workqueue_struct *system_wq; /* use system_percpu_wq, this will be removed */ extern struct workqueue_struct *system_percpu_wq; extern struct workqueue_struct *system_highpri_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct *system_dfl_wq; extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; extern struct workqueue_struct *system_bh_wq; extern struct workqueue_struct *system_bh_highpri_wq; void workqueue_softirq_action(bool highpri); void workqueue_softirq_dead(unsigned int cpu); /** * alloc_workqueue - allocate a workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default * @...: args for @fmt * * For a per-cpu workqueue, @max_active limits the number of in-flight work * items for each CPU. e.g. @max_active of 1 indicates that each CPU can be * executing at most one work item for the workqueue. * * For unbound workqueues, @max_active limits the number of in-flight work items * for the whole system. e.g. @max_active of 16 indicates that there can be * at most 16 work items executing for the workqueue in the whole system. * * As sharing the same active counter for an unbound workqueue across multiple * NUMA nodes can be expensive, @max_active is distributed to each NUMA node * according to the proportion of the number of online CPUs and enforced * independently. * * Depending on online CPU distribution, a node may end up with per-node * max_active which is significantly lower than @max_active, which can lead to * deadlocks if the per-node concurrency limit is lower than the maximum number * of interdependent work items for the workqueue. * * To guarantee forward progress regardless of online CPU distribution, the * concurrency limit on every node is guaranteed to be equal to or greater than * min_active which is set to min(@max_active, %WQ_DFL_MIN_ACTIVE). This means * that the sum of per-node max_active's may be larger than @max_active. * * For detailed information on %WQ_\* flags, please refer to * Documentation/core-api/workqueue.rst. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ __printf(1, 4) struct workqueue_struct * alloc_workqueue_noprof(const char *fmt, unsigned int flags, int max_active, ...); #define alloc_workqueue(...) alloc_hooks(alloc_workqueue_noprof(__VA_ARGS__)) #ifdef CONFIG_LOCKDEP /** * alloc_workqueue_lockdep_map - allocate a workqueue with user-defined lockdep_map * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default * @lockdep_map: user-defined lockdep_map * @...: args for @fmt * * Same as alloc_workqueue but with the a user-define lockdep_map. Useful for * workqueues created with the same purpose and to avoid leaking a lockdep_map * on each workqueue creation. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ __printf(1, 5) struct workqueue_struct * alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, struct lockdep_map *lockdep_map, ...); /** * alloc_ordered_workqueue_lockdep_map - allocate an ordered workqueue with * user-defined lockdep_map * * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @lockdep_map: user-defined lockdep_map * @args: args for @fmt * * Same as alloc_ordered_workqueue but with the a user-define lockdep_map. * Useful for workqueues created with the same purpose and to avoid leaking a * lockdep_map on each workqueue creation. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue_lockdep_map(fmt, flags, lockdep_map, args...) \ alloc_hooks(alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags),\ 1, lockdep_map, ##args)) #endif /** * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @args: args for @fmt * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are * implemented as unbound workqueues with @max_active of one. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_PERCPU, 1, (name)) #define create_freezable_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \ WQ_MEM_RECLAIM, 1, (name)) #define create_singlethread_workqueue(name) \ alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name) #define from_work(var, callback_work, work_fieldname) \ container_of(callback_work, typeof(*var), work_fieldname) extern void destroy_workqueue(struct workqueue_struct *wq); struct workqueue_attrs *alloc_workqueue_attrs_noprof(void); #define alloc_workqueue_attrs(...) alloc_hooks(alloc_workqueue_attrs_noprof(__VA_ARGS__)) void free_workqueue_attrs(struct workqueue_attrs *attrs); int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs); extern int workqueue_unbound_exclude_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); extern bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork); extern void __flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern bool disable_work(struct work_struct *work); extern bool disable_work_sync(struct work_struct *work); extern bool enable_work(struct work_struct *work); extern bool disable_delayed_work(struct delayed_work *dwork); extern bool disable_delayed_work_sync(struct delayed_work *dwork); extern bool enable_delayed_work(struct delayed_work *dwork); extern bool flush_rcu_work(struct rcu_work *rwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); extern void workqueue_set_min_active(struct workqueue_struct *wq, int min_active); extern struct work_struct *current_work(void); extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_all_workqueues(void); extern void show_freezable_workqueues(void); extern void show_one_workqueue(struct workqueue_struct *wq); extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); /** * queue_work - queue work on a workqueue * @wq: workqueue to use * @work: work to queue * * Returns %false if @work was already on a queue, %true otherwise. * * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. * * Memory-ordering properties: If it returns %true, guarantees that all stores * preceding the call to queue_work() in the program order will be visible from * the CPU which will execute @work by the time such work executes, e.g., * * { x is initially 0 } * * CPU0 CPU1 * * WRITE_ONCE(x, 1); [ @work is being executed ] * r0 = queue_work(wq, work); r1 = READ_ONCE(x); * * Forbids: r0 == true && r1 == 0 */ static inline bool queue_work(struct workqueue_struct *wq, struct work_struct *work) { return queue_work_on(WORK_CPU_UNBOUND, wq, work); } /** * queue_delayed_work - queue work on a workqueue after delay * @wq: workqueue to use * @dwork: delayable work to queue * @delay: number of jiffies to wait before queueing * * Equivalent to queue_delayed_work_on() but tries to use the local CPU. */ static inline bool queue_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * mod_delayed_work - modify delay of or queue a delayed work * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * mod_delayed_work_on() on local CPU. */ static inline bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * schedule_work_on - put work task on a specific cpu * @cpu: cpu to put the work task on * @work: job to be done * * This puts a job on a specific cpu */ static inline bool schedule_work_on(int cpu, struct work_struct *work) { return queue_work_on(cpu, system_percpu_wq, work); } /** * schedule_work - put work task in global workqueue * @work: job to be done * * Returns %false if @work was already on the kernel-global workqueue and * %true otherwise. * * This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. * * Shares the same memory-ordering properties of queue_work(), cf. the * DocBook header of queue_work(). */ static inline bool schedule_work(struct work_struct *work) { return queue_work(system_percpu_wq, work); } /** * enable_and_queue_work - Enable and queue a work item on a specific workqueue * @wq: The target workqueue * @work: The work item to be enabled and queued * * This function combines the operations of enable_work() and queue_work(), * providing a convenient way to enable and queue a work item in a single call. * It invokes enable_work() on @work and then queues it if the disable depth * reached 0. Returns %true if the disable depth reached 0 and @work is queued, * and %false otherwise. * * Note that @work is always queued when disable depth reaches zero. If the * desired behavior is queueing only if certain events took place while @work is * disabled, the user should implement the necessary state tracking and perform * explicit conditional queueing after enable_work(). */ static inline bool enable_and_queue_work(struct workqueue_struct *wq, struct work_struct *work) { if (enable_work(work)) { queue_work(wq, work); return true; } return false; } /* * Detect attempt to flush system-wide workqueues at compile time when possible. * Warn attempt to flush system-wide workqueues at runtime. * * See https://lkml.kernel.org/r/49925af7-78a8-a3dd-bce6-cfc02e1a9236@I-love.SAKURA.ne.jp * for reasons and steps for converting system-wide workqueues into local workqueues. */ extern void __warn_flushing_systemwide_wq(void) __compiletime_warning("Please avoid flushing system-wide workqueues."); /* Please stop using this function, for this function will be removed in near future. */ #define flush_scheduled_work() \ ({ \ __warn_flushing_systemwide_wq(); \ __flush_workqueue(system_percpu_wq); \ }) #define flush_workqueue(wq) \ ({ \ struct workqueue_struct *_wq = (wq); \ \ if ((__builtin_constant_p(_wq == system_percpu_wq) && \ _wq == system_percpu_wq) || \ (__builtin_constant_p(_wq == system_highpri_wq) && \ _wq == system_highpri_wq) || \ (__builtin_constant_p(_wq == system_long_wq) && \ _wq == system_long_wq) || \ (__builtin_constant_p(_wq == system_dfl_wq) && \ _wq == system_dfl_wq) || \ (__builtin_constant_p(_wq == system_freezable_wq) && \ _wq == system_freezable_wq) || \ (__builtin_constant_p(_wq == system_power_efficient_wq) && \ _wq == system_power_efficient_wq) || \ (__builtin_constant_p(_wq == system_freezable_power_efficient_wq) && \ _wq == system_freezable_power_efficient_wq)) \ __warn_flushing_systemwide_wq(); \ __flush_workqueue(_wq); \ }) /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use * @dwork: job to be done * @delay: number of jiffies to wait * * After waiting for a given time this puts a job in the kernel-global * workqueue on the specified CPU. */ static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(cpu, system_percpu_wq, dwork, delay); } /** * schedule_delayed_work - put work task in global workqueue after delay * @dwork: job to be done * @delay: number of jiffies to wait or 0 for immediate execution * * After waiting for a given time this puts a job in the kernel-global * workqueue. */ static inline bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work(system_percpu_wq, dwork, delay); } #ifndef CONFIG_SMP static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } #else long work_on_cpu_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key); /* * A new key is defined for each caller to make sure the work * associated with the function doesn't share its locking class. */ #define work_on_cpu(_cpu, _fn, _arg) \ ({ \ static struct lock_class_key __key; \ \ work_on_cpu_key(_cpu, _fn, _arg, &__key); \ }) #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER extern void freeze_workqueues_begin(void); extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ #ifdef CONFIG_SYSFS int workqueue_sysfs_register(struct workqueue_struct *wq); #else /* CONFIG_SYSFS */ static inline int workqueue_sysfs_register(struct workqueue_struct *wq) { return 0; } #endif /* CONFIG_SYSFS */ #ifdef CONFIG_WQ_WATCHDOG void wq_watchdog_touch(int cpu); #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_touch(int cpu) { } #endif /* CONFIG_WQ_WATCHDOG */ #ifdef CONFIG_SMP int workqueue_prepare_cpu(unsigned int cpu); int workqueue_online_cpu(unsigned int cpu); int workqueue_offline_cpu(unsigned int cpu); #endif void __init workqueue_init_early(void); void __init workqueue_init(void); void __init workqueue_init_topology(void); #endif |
| 46 46 46 46 46 46 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef _LINUX_RCUREF_H #define _LINUX_RCUREF_H #include <linux/atomic.h> #include <linux/bug.h> #include <linux/limits.h> #include <linux/lockdep.h> #include <linux/preempt.h> #include <linux/rcupdate.h> #define RCUREF_ONEREF 0x00000000U #define RCUREF_MAXREF 0x7FFFFFFFU #define RCUREF_SATURATED 0xA0000000U #define RCUREF_RELEASED 0xC0000000U #define RCUREF_DEAD 0xE0000000U #define RCUREF_NOREF 0xFFFFFFFFU /** * rcuref_init - Initialize a rcuref reference count with the given reference count * @ref: Pointer to the reference count * @cnt: The initial reference count typically '1' */ static inline void rcuref_init(rcuref_t *ref, unsigned int cnt) { atomic_set(&ref->refcnt, cnt - 1); } /** * rcuref_read - Read the number of held reference counts of a rcuref * @ref: Pointer to the reference count * * Return: The number of held references (0 ... N). The value 0 does not * indicate that it is safe to schedule the object, protected by this reference * counter, for deconstruction. * If you want to know if the reference counter has been marked DEAD (as * signaled by rcuref_put()) please use rcuread_is_dead(). */ static inline unsigned int rcuref_read(rcuref_t *ref) { unsigned int c = atomic_read(&ref->refcnt); /* Return 0 if within the DEAD zone. */ return c >= RCUREF_RELEASED ? 0 : c + 1; } /** * rcuref_is_dead - Check if the rcuref has been already marked dead * @ref: Pointer to the reference count * * Return: True if the object has been marked DEAD. This signals that a previous * invocation of rcuref_put() returned true on this reference counter meaning * the protected object can safely be scheduled for deconstruction. * Otherwise, returns false. */ static inline bool rcuref_is_dead(rcuref_t *ref) { unsigned int c = atomic_read(&ref->refcnt); return (c >= RCUREF_RELEASED) && (c < RCUREF_NOREF); } extern __must_check bool rcuref_get_slowpath(rcuref_t *ref); /** * rcuref_get - Acquire one reference on a rcuref reference count * @ref: Pointer to the reference count * * Similar to atomic_inc_not_zero() but saturates at RCUREF_MAXREF. * * Provides no memory ordering, it is assumed the caller has guaranteed the * object memory to be stable (RCU, etc.). It does provide a control dependency * and thereby orders future stores. See documentation in lib/rcuref.c * * Return: * False if the attempt to acquire a reference failed. This happens * when the last reference has been put already * * True if a reference was successfully acquired */ static inline __must_check bool rcuref_get(rcuref_t *ref) { /* * Unconditionally increase the reference count. The saturation and * dead zones provide enough tolerance for this. */ if (likely(!atomic_add_negative_relaxed(1, &ref->refcnt))) return true; /* Handle the cases inside the saturation and dead zones */ return rcuref_get_slowpath(ref); } extern __must_check bool rcuref_put_slowpath(rcuref_t *ref, unsigned int cnt); /* * Internal helper. Do not invoke directly. */ static __always_inline __must_check bool __rcuref_put(rcuref_t *ref) { int cnt; RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(), "suspicious rcuref_put_rcusafe() usage"); /* * Unconditionally decrease the reference count. The saturation and * dead zones provide enough tolerance for this. */ cnt = atomic_sub_return_release(1, &ref->refcnt); if (likely(cnt >= 0)) return false; /* * Handle the last reference drop and cases inside the saturation * and dead zones. */ return rcuref_put_slowpath(ref, cnt); } /** * rcuref_put_rcusafe -- Release one reference for a rcuref reference count RCU safe * @ref: Pointer to the reference count * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Can be invoked from contexts, which guarantee that no grace period can * happen which would free the object concurrently if the decrement drops * the last reference and the slowpath races against a concurrent get() and * put() pair. rcu_read_lock()'ed and atomic contexts qualify. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely release the * object which is protected by the reference counter. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * release the protected object. */ static inline __must_check bool rcuref_put_rcusafe(rcuref_t *ref) { return __rcuref_put(ref); } /** * rcuref_put -- Release one reference for a rcuref reference count * @ref: Pointer to the reference count * * Can be invoked from any context. * * Provides release memory ordering, such that prior loads and stores are done * before, and provides an acquire ordering on success such that free() * must come after. * * Return: * * True if this was the last reference with no future references * possible. This signals the caller that it can safely schedule the * object, which is protected by the reference counter, for * deconstruction. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * deconstruct the protected object. */ static inline __must_check bool rcuref_put(rcuref_t *ref) { bool released; preempt_disable(); released = __rcuref_put(ref); preempt_enable(); return released; } #endif |
| 5 5 5 5 5 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/copypage.c * * Copyright (C) 2002 Deep Blue Solutions Ltd, All Rights Reserved. * Copyright (C) 2012 ARM Ltd. */ #include <linux/bitops.h> #include <linux/mm.h> #include <asm/page.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/mte.h> void copy_highpage(struct page *to, struct page *from) { void *kto = page_address(to); void *kfrom = page_address(from); struct folio *src = page_folio(from); struct folio *dst = page_folio(to); unsigned int i, nr_pages; copy_page(kto, kfrom); if (kasan_hw_tags_enabled()) page_kasan_tag_reset(to); if (!system_supports_mte()) return; if (folio_test_hugetlb(src)) { if (!folio_test_hugetlb_mte_tagged(src) || from != folio_page(src, 0)) return; folio_try_hugetlb_mte_tagging(dst); /* * Populate tags for all subpages. * * Don't assume the first page is head page since * huge page copy may start from any subpage. */ nr_pages = folio_nr_pages(src); for (i = 0; i < nr_pages; i++) { kfrom = page_address(folio_page(src, i)); kto = page_address(folio_page(dst, i)); mte_copy_page_tags(kto, kfrom); } folio_set_hugetlb_mte_tagged(dst); } else if (page_mte_tagged(from)) { /* * Most of the time it's a new page that shouldn't have been * tagged yet. However, folio migration can end up reusing the * same page without untagging it. Ignore the warning if the * page is already tagged. */ try_page_mte_tagging(to); mte_copy_page_tags(kto, kfrom); set_page_mte_tagged(to); } } EXPORT_SYMBOL(copy_highpage); void copy_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { copy_highpage(to, from); flush_dcache_page(to); } EXPORT_SYMBOL_GPL(copy_user_highpage); |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/traps.h * * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_TRAP_H #define __ASM_TRAP_H #include <linux/list.h> #include <asm/esr.h> #include <asm/ptrace.h> #include <asm/sections.h> #ifdef CONFIG_ARMV8_DEPRECATED bool try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn); #else static inline bool try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn) { return false; } #endif /* CONFIG_ARMV8_DEPRECATED */ void force_signal_inject(int signal, int code, unsigned long address, unsigned long err); void arm64_notify_segfault(unsigned long addr); void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str); void arm64_force_sig_fault_pkey(unsigned long far, const char *str, int pkey); void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str); void arm64_force_sig_ptrace_errno_trap(int errno, unsigned long far, const char *str); int bug_brk_handler(struct pt_regs *regs, unsigned long esr); int cfi_brk_handler(struct pt_regs *regs, unsigned long esr); int reserved_fault_brk_handler(struct pt_regs *regs, unsigned long esr); int kasan_brk_handler(struct pt_regs *regs, unsigned long esr); int ubsan_brk_handler(struct pt_regs *regs, unsigned long esr); int early_brk64(unsigned long addr, unsigned long esr, struct pt_regs *regs); void dump_kernel_instr(unsigned long kaddr); /* * Move regs->pc to next instruction and do necessary setup before it * is executed. */ void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size); static inline int __in_irqentry_text(unsigned long ptr) { return ptr >= (unsigned long)&__irqentry_text_start && ptr < (unsigned long)&__irqentry_text_end; } static inline int in_entry_text(unsigned long ptr) { return ptr >= (unsigned long)&__entry_text_start && ptr < (unsigned long)&__entry_text_end; } /* * CPUs with the RAS extensions have an Implementation-Defined-Syndrome bit * to indicate whether this ESR has a RAS encoding. CPUs without this feature * have a ISS-Valid bit in the same position. * If this bit is set, we know its not a RAS SError. * If its clear, we need to know if the CPU supports RAS. Uncategorized RAS * errors share the same encoding as an all-zeros encoding from a CPU that * doesn't support RAS. */ static inline bool arm64_is_ras_serror(unsigned long esr) { WARN_ON(preemptible()); if (esr & ESR_ELx_IDS) return false; if (this_cpu_has_cap(ARM64_HAS_RAS_EXTN)) return true; else return false; } /* * Return the AET bits from a RAS SError's ESR. * * It is implementation defined whether Uncategorized errors are containable. * We treat them as Uncontainable. * Non-RAS SError's are reported as Uncontained/Uncategorized. */ static inline unsigned long arm64_ras_serror_get_severity(unsigned long esr) { unsigned long aet = esr & ESR_ELx_AET; if (!arm64_is_ras_serror(esr)) { /* Not a RAS error, we can't interpret the ESR. */ return ESR_ELx_AET_UC; } /* * AET is RES0 if 'the value returned in the DFSC field is not * [ESR_ELx_FSC_SERROR]' */ if ((esr & ESR_ELx_FSC) != ESR_ELx_FSC_SERROR) { /* No severity information : Uncategorized */ return ESR_ELx_AET_UC; } return aet; } bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr); void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr); static inline void arm64_mops_reset_regs(struct user_pt_regs *regs, unsigned long esr) { bool wrong_option = esr & ESR_ELx_MOPS_ISS_WRONG_OPTION; bool option_a = esr & ESR_ELx_MOPS_ISS_OPTION_A; int dstreg = ESR_ELx_MOPS_ISS_DESTREG(esr); int srcreg = ESR_ELx_MOPS_ISS_SRCREG(esr); int sizereg = ESR_ELx_MOPS_ISS_SIZEREG(esr); unsigned long dst, size; dst = regs->regs[dstreg]; size = regs->regs[sizereg]; /* * Put the registers back in the original format suitable for a * prologue instruction, using the generic return routine from the * Arm ARM (DDI 0487I.a) rules CNTMJ and MWFQH. */ if (esr & ESR_ELx_MOPS_ISS_MEM_INST) { /* SET* instruction */ if (option_a ^ wrong_option) { /* Format is from Option A; forward set */ regs->regs[dstreg] = dst + size; regs->regs[sizereg] = -size; } } else { /* CPY* instruction */ unsigned long src = regs->regs[srcreg]; if (!(option_a ^ wrong_option)) { /* Format is from Option B */ if (regs->pstate & PSR_N_BIT) { /* Backward copy */ regs->regs[dstreg] = dst - size; regs->regs[srcreg] = src - size; } } else { /* Format is from Option A */ if (size & BIT(63)) { /* Forward copy */ regs->regs[dstreg] = dst + size; regs->regs[srcreg] = src + size; regs->regs[sizereg] = -size; } } } if (esr & ESR_ELx_MOPS_ISS_FROM_EPILOGUE) regs->pc -= 8; else regs->pc -= 4; } #endif |
| 557 555 526 524 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Kernel thread helper functions. * Copyright (C) 2004 IBM Corporation, Rusty Russell. * Copyright (C) 2009 Red Hat, Inc. * * Creation is done via kthreadd, so that we get a clean environment * even if we're invoked from userspace (think modprobe, hotplug cpu, * etc.). */ #include <uapi/linux/sched/types.h> #include <linux/mm.h> #include <linux/mmu_context.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/kthread.h> #include <linux/completion.h> #include <linux/err.h> #include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/unistd.h> #include <linux/file.h> #include <linux/export.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/freezer.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/numa.h> #include <linux/sched/isolation.h> #include <trace/events/sched.h> static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; static LIST_HEAD(kthreads_hotplug); static DEFINE_MUTEX(kthreads_hotplug_lock); struct kthread_create_info { /* Information passed to kthread() from kthreadd. */ char *full_name; int (*threadfn)(void *data); void *data; int node; /* Result passed back to kthread_create() from kthreadd. */ struct task_struct *result; struct completion *done; struct list_head list; }; struct kthread { unsigned long flags; unsigned int cpu; unsigned int node; int started; int result; int (*threadfn)(void *); void *data; struct completion parked; struct completion exited; #ifdef CONFIG_BLK_CGROUP struct cgroup_subsys_state *blkcg_css; #endif /* To store the full name if task comm is truncated. */ char *full_name; struct task_struct *task; struct list_head hotplug_node; struct cpumask *preferred_affinity; }; enum KTHREAD_BITS { KTHREAD_IS_PER_CPU = 0, KTHREAD_SHOULD_STOP, KTHREAD_SHOULD_PARK, }; static inline struct kthread *to_kthread(struct task_struct *k) { WARN_ON(!(k->flags & PF_KTHREAD)); return k->worker_private; } /* * Variant of to_kthread() that doesn't assume @p is a kthread. * * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will * always remain a kthread. For kthreads p->worker_private always * points to a struct kthread. For tasks that are not kthreads * p->worker_private is used to point to other things. * * Return NULL for any task that is not a kthread. */ static inline struct kthread *__to_kthread(struct task_struct *p) { void *kthread = p->worker_private; if (kthread && !(p->flags & PF_KTHREAD)) kthread = NULL; return kthread; } void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk) { struct kthread *kthread = to_kthread(tsk); if (!kthread || !kthread->full_name) { strscpy(buf, tsk->comm, buf_size); return; } strscpy_pad(buf, kthread->full_name, buf_size); } bool set_kthread_struct(struct task_struct *p) { struct kthread *kthread; if (WARN_ON_ONCE(to_kthread(p))) return false; kthread = kzalloc(sizeof(*kthread), GFP_KERNEL); if (!kthread) return false; init_completion(&kthread->exited); init_completion(&kthread->parked); INIT_LIST_HEAD(&kthread->hotplug_node); p->vfork_done = &kthread->exited; kthread->task = p; kthread->node = tsk_fork_get_node(current); p->worker_private = kthread; return true; } void free_kthread_struct(struct task_struct *k) { struct kthread *kthread; /* * Can be NULL if kmalloc() in set_kthread_struct() failed. */ kthread = to_kthread(k); if (!kthread) return; #ifdef CONFIG_BLK_CGROUP WARN_ON_ONCE(kthread->blkcg_css); #endif k->worker_private = NULL; kfree(kthread->full_name); kfree(kthread); } /** * kthread_should_stop - should this kthread return now? * * When someone calls kthread_stop() on your kthread, it will be woken * and this will return true. You should then return, and your return * value will be passed through to kthread_stop(). */ bool kthread_should_stop(void) { return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags); } EXPORT_SYMBOL(kthread_should_stop); static bool __kthread_should_park(struct task_struct *k) { return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(k)->flags); } /** * kthread_should_park - should this kthread park now? * * When someone calls kthread_park() on your kthread, it will be woken * and this will return true. You should then do the necessary * cleanup and call kthread_parkme() * * Similar to kthread_should_stop(), but this keeps the thread alive * and in a park position. kthread_unpark() "restarts" the thread and * calls the thread function again. */ bool kthread_should_park(void) { return __kthread_should_park(current); } EXPORT_SYMBOL_GPL(kthread_should_park); bool kthread_should_stop_or_park(void) { struct kthread *kthread = __to_kthread(current); if (!kthread) return false; return kthread->flags & (BIT(KTHREAD_SHOULD_STOP) | BIT(KTHREAD_SHOULD_PARK)); } /** * kthread_freezable_should_stop - should this freezable kthread return now? * @was_frozen: optional out parameter, indicates whether %current was frozen * * kthread_should_stop() for freezable kthreads, which will enter * refrigerator if necessary. This function is safe from kthread_stop() / * freezer deadlock and freezable kthreads should use this function instead * of calling try_to_freeze() directly. */ bool kthread_freezable_should_stop(bool *was_frozen) { bool frozen = false; might_sleep(); if (unlikely(freezing(current))) frozen = __refrigerator(true); if (was_frozen) *was_frozen = frozen; return kthread_should_stop(); } EXPORT_SYMBOL_GPL(kthread_freezable_should_stop); /** * kthread_func - return the function specified on kthread creation * @task: kthread task in question * * Returns NULL if the task is not a kthread. */ void *kthread_func(struct task_struct *task) { struct kthread *kthread = __to_kthread(task); if (kthread) return kthread->threadfn; return NULL; } EXPORT_SYMBOL_GPL(kthread_func); /** * kthread_data - return data value specified on kthread creation * @task: kthread task in question * * Return the data value specified when kthread @task was created. * The caller is responsible for ensuring the validity of @task when * calling this function. */ void *kthread_data(struct task_struct *task) { return to_kthread(task)->data; } EXPORT_SYMBOL_GPL(kthread_data); /** * kthread_probe_data - speculative version of kthread_data() * @task: possible kthread task in question * * @task could be a kthread task. Return the data value specified when it * was created if accessible. If @task isn't a kthread task or its data is * inaccessible for any reason, %NULL is returned. This function requires * that @task itself is safe to dereference. */ void *kthread_probe_data(struct task_struct *task) { struct kthread *kthread = __to_kthread(task); void *data = NULL; if (kthread) copy_from_kernel_nofault(&data, &kthread->data, sizeof(data)); return data; } static void __kthread_parkme(struct kthread *self) { for (;;) { /* * TASK_PARKED is a special state; we must serialize against * possible pending wakeups to avoid store-store collisions on * task->state. * * Such a collision might possibly result in the task state * changin from TASK_PARKED and us failing the * wait_task_inactive() in kthread_park(). */ set_special_state(TASK_PARKED); if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags)) break; /* * Thread is going to call schedule(), do not preempt it, * or the caller of kthread_park() may spend more time in * wait_task_inactive(). */ preempt_disable(); complete(&self->parked); schedule_preempt_disabled(); preempt_enable(); } __set_current_state(TASK_RUNNING); } void kthread_parkme(void) { __kthread_parkme(to_kthread(current)); } EXPORT_SYMBOL_GPL(kthread_parkme); /** * kthread_exit - Cause the current kthread return @result to kthread_stop(). * @result: The integer value to return to kthread_stop(). * * While kthread_exit can be called directly, it exists so that * functions which do some additional work in non-modular code such as * module_put_and_kthread_exit can be implemented. * * Does not return. */ void __noreturn kthread_exit(long result) { struct kthread *kthread = to_kthread(current); kthread->result = result; if (!list_empty(&kthread->hotplug_node)) { mutex_lock(&kthreads_hotplug_lock); list_del(&kthread->hotplug_node); mutex_unlock(&kthreads_hotplug_lock); if (kthread->preferred_affinity) { kfree(kthread->preferred_affinity); kthread->preferred_affinity = NULL; } } do_exit(0); } EXPORT_SYMBOL(kthread_exit); /** * kthread_complete_and_exit - Exit the current kthread. * @comp: Completion to complete * @code: The integer value to return to kthread_stop(). * * If present, complete @comp and then return code to kthread_stop(). * * A kernel thread whose module may be removed after the completion of * @comp can use this function to exit safely. * * Does not return. */ void __noreturn kthread_complete_and_exit(struct completion *comp, long code) { if (comp) complete(comp); kthread_exit(code); } EXPORT_SYMBOL(kthread_complete_and_exit); static void kthread_fetch_affinity(struct kthread *kthread, struct cpumask *cpumask) { const struct cpumask *pref; if (kthread->preferred_affinity) { pref = kthread->preferred_affinity; } else { if (WARN_ON_ONCE(kthread->node == NUMA_NO_NODE)) return; pref = cpumask_of_node(kthread->node); } cpumask_and(cpumask, pref, housekeeping_cpumask(HK_TYPE_KTHREAD)); if (cpumask_empty(cpumask)) cpumask_copy(cpumask, housekeeping_cpumask(HK_TYPE_KTHREAD)); } static void kthread_affine_node(void) { struct kthread *kthread = to_kthread(current); cpumask_var_t affinity; WARN_ON_ONCE(kthread_is_per_cpu(current)); if (kthread->node == NUMA_NO_NODE) { housekeeping_affine(current, HK_TYPE_KTHREAD); } else { if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) { WARN_ON_ONCE(1); return; } mutex_lock(&kthreads_hotplug_lock); WARN_ON_ONCE(!list_empty(&kthread->hotplug_node)); list_add_tail(&kthread->hotplug_node, &kthreads_hotplug); /* * The node cpumask is racy when read from kthread() but: * - a racing CPU going down will either fail on the subsequent * call to set_cpus_allowed_ptr() or be migrated to housekeepers * afterwards by the scheduler. * - a racing CPU going up will be handled by kthreads_online_cpu() */ kthread_fetch_affinity(kthread, affinity); set_cpus_allowed_ptr(current, affinity); mutex_unlock(&kthreads_hotplug_lock); free_cpumask_var(affinity); } } static int kthread(void *_create) { static const struct sched_param param = { .sched_priority = 0 }; /* Copy data: it's on kthread's stack */ struct kthread_create_info *create = _create; int (*threadfn)(void *data) = create->threadfn; void *data = create->data; struct completion *done; struct kthread *self; int ret; self = to_kthread(current); /* Release the structure when caller killed by a fatal signal. */ done = xchg(&create->done, NULL); if (!done) { kfree(create->full_name); kfree(create); kthread_exit(-EINTR); } self->full_name = create->full_name; self->threadfn = threadfn; self->data = data; /* * The new thread inherited kthreadd's priority and CPU mask. Reset * back to default in case they have been changed. */ sched_setscheduler_nocheck(current, SCHED_NORMAL, ¶m); /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); create->result = current; /* * Thread is going to call schedule(), do not preempt it, * or the creator may spend more time in wait_task_inactive(). */ preempt_disable(); complete(done); schedule_preempt_disabled(); preempt_enable(); self->started = 1; if (!(current->flags & PF_NO_SETAFFINITY) && !self->preferred_affinity) kthread_affine_node(); ret = -EINTR; if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) { cgroup_kthread_ready(); __kthread_parkme(self); ret = threadfn(data); } kthread_exit(ret); } /* called from kernel_clone() to get node information for about to be created task */ int tsk_fork_get_node(struct task_struct *tsk) { #ifdef CONFIG_NUMA if (tsk == kthreadd_task) return tsk->pref_node_fork; #endif return NUMA_NO_NODE; } static void create_kthread(struct kthread_create_info *create) { int pid; #ifdef CONFIG_NUMA current->pref_node_fork = create->node; #endif /* We want our own signal handler (we take no signals by default). */ pid = kernel_thread(kthread, create, create->full_name, CLONE_FS | CLONE_FILES | SIGCHLD); if (pid < 0) { /* Release the structure when caller killed by a fatal signal. */ struct completion *done = xchg(&create->done, NULL); kfree(create->full_name); if (!done) { kfree(create); return; } create->result = ERR_PTR(pid); complete(done); } } static __printf(4, 0) struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), void *data, int node, const char namefmt[], va_list args) { DECLARE_COMPLETION_ONSTACK(done); struct task_struct *task; struct kthread_create_info *create = kmalloc(sizeof(*create), GFP_KERNEL); if (!create) return ERR_PTR(-ENOMEM); create->threadfn = threadfn; create->data = data; create->node = node; create->done = &done; create->full_name = kvasprintf(GFP_KERNEL, namefmt, args); if (!create->full_name) { task = ERR_PTR(-ENOMEM); goto free_create; } spin_lock(&kthread_create_lock); list_add_tail(&create->list, &kthread_create_list); spin_unlock(&kthread_create_lock); wake_up_process(kthreadd_task); /* * Wait for completion in killable state, for I might be chosen by * the OOM killer while kthreadd is trying to allocate memory for * new kernel thread. */ if (unlikely(wait_for_completion_killable(&done))) { /* * If I was killed by a fatal signal before kthreadd (or new * kernel thread) calls complete(), leave the cleanup of this * structure to that thread. */ if (xchg(&create->done, NULL)) return ERR_PTR(-EINTR); /* * kthreadd (or new kernel thread) will call complete() * shortly. */ wait_for_completion(&done); } task = create->result; free_create: kfree(create); return task; } /** * kthread_create_on_node - create a kthread. * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @node: task and thread structures for the thread are allocated on this node * @namefmt: printf-style name for the thread. * * Description: This helper function creates and names a kernel * thread. The thread will be stopped: use wake_up_process() to start * it. See also kthread_run(). The new thread has SCHED_NORMAL policy and * is affine to all CPUs. * * If thread is going to be bound on a particular cpu, give its node * in @node, to get NUMA affinity for kthread stack, or else give NUMA_NO_NODE. * When woken, the thread will run @threadfn() with @data as its * argument. @threadfn() can either return directly if it is a * standalone thread for which no one will call kthread_stop(), or * return when 'kthread_should_stop()' is true (which means * kthread_stop() has been called). The return value should be zero * or a negative error number; it will be passed to kthread_stop(). * * Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR). */ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, int node, const char namefmt[], ...) { struct task_struct *task; va_list args; va_start(args, namefmt); task = __kthread_create_on_node(threadfn, data, node, namefmt, args); va_end(args); return task; } EXPORT_SYMBOL(kthread_create_on_node); static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, unsigned int state) { unsigned long flags; if (!wait_task_inactive(p, state)) { WARN_ON(1); return; } /* It's safe because the task is inactive. */ raw_spin_lock_irqsave(&p->pi_lock, flags); do_set_cpus_allowed(p, mask); p->flags |= PF_NO_SETAFFINITY; raw_spin_unlock_irqrestore(&p->pi_lock, flags); } static void __kthread_bind(struct task_struct *p, unsigned int cpu, unsigned int state) { __kthread_bind_mask(p, cpumask_of(cpu), state); } void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask) { struct kthread *kthread = to_kthread(p); __kthread_bind_mask(p, mask, TASK_UNINTERRUPTIBLE); WARN_ON_ONCE(kthread->started); } /** * kthread_bind - bind a just-created kthread to a cpu. * @p: thread created by kthread_create(). * @cpu: cpu (might not be online, must be possible) for @k to run on. * * Description: This function is equivalent to set_cpus_allowed(), * except that @cpu doesn't need to be online, and the thread must be * stopped (i.e., just returned from kthread_create()). */ void kthread_bind(struct task_struct *p, unsigned int cpu) { struct kthread *kthread = to_kthread(p); __kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE); WARN_ON_ONCE(kthread->started); } EXPORT_SYMBOL(kthread_bind); /** * kthread_create_on_cpu - Create a cpu bound kthread * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @cpu: The cpu on which the thread should be bound, * @namefmt: printf-style name for the thread. Format is restricted * to "name.*%u". Code fills in cpu number. * * Description: This helper function creates and names a kernel thread */ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), void *data, unsigned int cpu, const char *namefmt) { struct task_struct *p; p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt, cpu); if (IS_ERR(p)) return p; kthread_bind(p, cpu); /* CPU hotplug need to bind once again when unparking the thread. */ to_kthread(p)->cpu = cpu; return p; } EXPORT_SYMBOL(kthread_create_on_cpu); void kthread_set_per_cpu(struct task_struct *k, int cpu) { struct kthread *kthread = to_kthread(k); if (!kthread) return; WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY)); if (cpu < 0) { clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags); return; } kthread->cpu = cpu; set_bit(KTHREAD_IS_PER_CPU, &kthread->flags); } bool kthread_is_per_cpu(struct task_struct *p) { struct kthread *kthread = __to_kthread(p); if (!kthread) return false; return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags); } /** * kthread_unpark - unpark a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_park() for @k to return false, wakes it, and * waits for it to return. If the thread is marked percpu then its * bound to the cpu again. */ void kthread_unpark(struct task_struct *k) { struct kthread *kthread = to_kthread(k); if (!test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)) return; /* * Newly created kthread was parked when the CPU was offline. * The binding was lost and we need to set it again. */ if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) __kthread_bind(k, kthread->cpu, TASK_PARKED); clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); /* * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup. */ wake_up_state(k, TASK_PARKED); } EXPORT_SYMBOL_GPL(kthread_unpark); /** * kthread_park - park a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_park() for @k to return true, wakes it, and * waits for it to return. This can also be called after kthread_create() * instead of calling wake_up_process(): the thread will park without * calling threadfn(). * * Returns 0 if the thread is parked, -ENOSYS if the thread exited. * If called by the kthread itself just the park bit is set. */ int kthread_park(struct task_struct *k) { struct kthread *kthread = to_kthread(k); if (WARN_ON(k->flags & PF_EXITING)) return -ENOSYS; if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags))) return -EBUSY; set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); if (k != current) { wake_up_process(k); /* * Wait for __kthread_parkme() to complete(), this means we * _will_ have TASK_PARKED and are about to call schedule(). */ wait_for_completion(&kthread->parked); /* * Now wait for that schedule() to complete and the task to * get scheduled out. */ WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED)); } return 0; } EXPORT_SYMBOL_GPL(kthread_park); /** * kthread_stop - stop a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_stop() for @k to return true, wakes it, and * waits for it to exit. This can also be called after kthread_create() * instead of calling wake_up_process(): the thread will exit without * calling threadfn(). * * If threadfn() may call kthread_exit() itself, the caller must ensure * task_struct can't go away. * * Returns the result of threadfn(), or %-EINTR if wake_up_process() * was never called. */ int kthread_stop(struct task_struct *k) { struct kthread *kthread; int ret; trace_sched_kthread_stop(k); get_task_struct(k); kthread = to_kthread(k); set_bit(KTHREAD_SHOULD_STOP, &kthread->flags); kthread_unpark(k); set_tsk_thread_flag(k, TIF_NOTIFY_SIGNAL); wake_up_process(k); wait_for_completion(&kthread->exited); ret = kthread->result; put_task_struct(k); trace_sched_kthread_stop_ret(ret); return ret; } EXPORT_SYMBOL(kthread_stop); /** * kthread_stop_put - stop a thread and put its task struct * @k: thread created by kthread_create(). * * Stops a thread created by kthread_create() and put its task_struct. * Only use when holding an extra task struct reference obtained by * calling get_task_struct(). */ int kthread_stop_put(struct task_struct *k) { int ret; ret = kthread_stop(k); put_task_struct(k); return ret; } EXPORT_SYMBOL(kthread_stop_put); int kthreadd(void *unused) { static const char comm[TASK_COMM_LEN] = "kthreadd"; struct task_struct *tsk = current; /* Setup a clean context for our children to inherit. */ set_task_comm(tsk, comm); ignore_signals(tsk); set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_TYPE_KTHREAD)); set_mems_allowed(node_states[N_MEMORY]); current->flags |= PF_NOFREEZE; cgroup_init_kthreadd(); for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (list_empty(&kthread_create_list)) schedule(); __set_current_state(TASK_RUNNING); spin_lock(&kthread_create_lock); while (!list_empty(&kthread_create_list)) { struct kthread_create_info *create; create = list_entry(kthread_create_list.next, struct kthread_create_info, list); list_del_init(&create->list); spin_unlock(&kthread_create_lock); create_kthread(create); spin_lock(&kthread_create_lock); } spin_unlock(&kthread_create_lock); } return 0; } int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask) { struct kthread *kthread = to_kthread(p); cpumask_var_t affinity; unsigned long flags; int ret = 0; if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE) || kthread->started) { WARN_ON(1); return -EINVAL; } WARN_ON_ONCE(kthread->preferred_affinity); if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) return -ENOMEM; kthread->preferred_affinity = kzalloc(sizeof(struct cpumask), GFP_KERNEL); if (!kthread->preferred_affinity) { ret = -ENOMEM; goto out; } mutex_lock(&kthreads_hotplug_lock); cpumask_copy(kthread->preferred_affinity, mask); WARN_ON_ONCE(!list_empty(&kthread->hotplug_node)); list_add_tail(&kthread->hotplug_node, &kthreads_hotplug); kthread_fetch_affinity(kthread, affinity); /* It's safe because the task is inactive. */ raw_spin_lock_irqsave(&p->pi_lock, flags); do_set_cpus_allowed(p, affinity); raw_spin_unlock_irqrestore(&p->pi_lock, flags); mutex_unlock(&kthreads_hotplug_lock); out: free_cpumask_var(affinity); return ret; } EXPORT_SYMBOL_GPL(kthread_affine_preferred); /* * Re-affine kthreads according to their preferences * and the newly online CPU. The CPU down part is handled * by select_fallback_rq() which default re-affines to * housekeepers from other nodes in case the preferred * affinity doesn't apply anymore. */ static int kthreads_online_cpu(unsigned int cpu) { cpumask_var_t affinity; struct kthread *k; int ret; guard(mutex)(&kthreads_hotplug_lock); if (list_empty(&kthreads_hotplug)) return 0; if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) return -ENOMEM; ret = 0; list_for_each_entry(k, &kthreads_hotplug, hotplug_node) { if (WARN_ON_ONCE((k->task->flags & PF_NO_SETAFFINITY) || kthread_is_per_cpu(k->task))) { ret = -EINVAL; continue; } kthread_fetch_affinity(k, affinity); set_cpus_allowed_ptr(k->task, affinity); } free_cpumask_var(affinity); return ret; } static int kthreads_init(void) { return cpuhp_setup_state(CPUHP_AP_KTHREADS_ONLINE, "kthreads:online", kthreads_online_cpu, NULL); } early_initcall(kthreads_init); void __kthread_init_worker(struct kthread_worker *worker, const char *name, struct lock_class_key *key) { memset(worker, 0, sizeof(struct kthread_worker)); raw_spin_lock_init(&worker->lock); lockdep_set_class_and_name(&worker->lock, key, name); INIT_LIST_HEAD(&worker->work_list); INIT_LIST_HEAD(&worker->delayed_work_list); } EXPORT_SYMBOL_GPL(__kthread_init_worker); /** * kthread_worker_fn - kthread function to process kthread_worker * @worker_ptr: pointer to initialized kthread_worker * * This function implements the main cycle of kthread worker. It processes * work_list until it is stopped with kthread_stop(). It sleeps when the queue * is empty. * * The works are not allowed to keep any locks, disable preemption or interrupts * when they finish. There is defined a safe point for freezing when one work * finishes and before a new one is started. * * Also the works must not be handled by more than one worker at the same time, * see also kthread_queue_work(). */ int kthread_worker_fn(void *worker_ptr) { struct kthread_worker *worker = worker_ptr; struct kthread_work *work; /* * FIXME: Update the check and remove the assignment when all kthread * worker users are created using kthread_create_worker*() functions. */ WARN_ON(worker->task && worker->task != current); worker->task = current; if (worker->flags & KTW_FREEZABLE) set_freezable(); repeat: set_current_state(TASK_INTERRUPTIBLE); /* mb paired w/ kthread_stop */ if (kthread_should_stop()) { __set_current_state(TASK_RUNNING); raw_spin_lock_irq(&worker->lock); worker->task = NULL; raw_spin_unlock_irq(&worker->lock); return 0; } work = NULL; raw_spin_lock_irq(&worker->lock); if (!list_empty(&worker->work_list)) { work = list_first_entry(&worker->work_list, struct kthread_work, node); list_del_init(&work->node); } worker->current_work = work; raw_spin_unlock_irq(&worker->lock); if (work) { kthread_work_func_t func = work->func; __set_current_state(TASK_RUNNING); trace_sched_kthread_work_execute_start(work); work->func(work); /* * Avoid dereferencing work after this point. The trace * event only cares about the address. */ trace_sched_kthread_work_execute_end(work, func); } else if (!freezing(current)) { schedule(); } else { /* * Handle the case where the current remains * TASK_INTERRUPTIBLE. try_to_freeze() expects * the current to be TASK_RUNNING. */ __set_current_state(TASK_RUNNING); } try_to_freeze(); cond_resched(); goto repeat; } EXPORT_SYMBOL_GPL(kthread_worker_fn); static __printf(3, 0) struct kthread_worker * __kthread_create_worker_on_node(unsigned int flags, int node, const char namefmt[], va_list args) { struct kthread_worker *worker; struct task_struct *task; worker = kzalloc(sizeof(*worker), GFP_KERNEL); if (!worker) return ERR_PTR(-ENOMEM); kthread_init_worker(worker); task = __kthread_create_on_node(kthread_worker_fn, worker, node, namefmt, args); if (IS_ERR(task)) goto fail_task; worker->flags = flags; worker->task = task; return worker; fail_task: kfree(worker); return ERR_CAST(task); } /** * kthread_create_worker_on_node - create a kthread worker * @flags: flags modifying the default behavior of the worker * @node: task structure for the thread is allocated on this node * @namefmt: printf-style name for the kthread worker (task). * * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM) * when the needed structures could not get allocated, and ERR_PTR(-EINTR) * when the caller was killed by a fatal signal. */ struct kthread_worker * kthread_create_worker_on_node(unsigned int flags, int node, const char namefmt[], ...) { struct kthread_worker *worker; va_list args; va_start(args, namefmt); worker = __kthread_create_worker_on_node(flags, node, namefmt, args); va_end(args); return worker; } EXPORT_SYMBOL(kthread_create_worker_on_node); /** * kthread_create_worker_on_cpu - create a kthread worker and bind it * to a given CPU and the associated NUMA node. * @cpu: CPU number * @flags: flags modifying the default behavior of the worker * @namefmt: printf-style name for the thread. Format is restricted * to "name.*%u". Code fills in cpu number. * * Use a valid CPU number if you want to bind the kthread worker * to the given CPU and the associated NUMA node. * * A good practice is to add the cpu number also into the worker name. * For example, use kthread_create_worker_on_cpu(cpu, "helper/%d", cpu). * * CPU hotplug: * The kthread worker API is simple and generic. It just provides a way * to create, use, and destroy workers. * * It is up to the API user how to handle CPU hotplug. They have to decide * how to handle pending work items, prevent queuing new ones, and * restore the functionality when the CPU goes off and on. There are a * few catches: * * - CPU affinity gets lost when it is scheduled on an offline CPU. * * - The worker might not exist when the CPU was off when the user * created the workers. * * Good practice is to implement two CPU hotplug callbacks and to * destroy/create the worker when the CPU goes down/up. * * Return: * The pointer to the allocated worker on success, ERR_PTR(-ENOMEM) * when the needed structures could not get allocated, and ERR_PTR(-EINTR) * when the caller was killed by a fatal signal. */ struct kthread_worker * kthread_create_worker_on_cpu(int cpu, unsigned int flags, const char namefmt[]) { struct kthread_worker *worker; worker = kthread_create_worker_on_node(flags, cpu_to_node(cpu), namefmt, cpu); if (!IS_ERR(worker)) kthread_bind(worker->task, cpu); return worker; } EXPORT_SYMBOL(kthread_create_worker_on_cpu); /* * Returns true when the work could not be queued at the moment. * It happens when it is already pending in a worker list * or when it is being cancelled. */ static inline bool queuing_blocked(struct kthread_worker *worker, struct kthread_work *work) { lockdep_assert_held(&worker->lock); return !list_empty(&work->node) || work->canceling; } static void kthread_insert_work_sanity_check(struct kthread_worker *worker, struct kthread_work *work) { lockdep_assert_held(&worker->lock); WARN_ON_ONCE(!list_empty(&work->node)); /* Do not use a work with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker && work->worker != worker); } /* insert @work before @pos in @worker */ static void kthread_insert_work(struct kthread_worker *worker, struct kthread_work *work, struct list_head *pos) { kthread_insert_work_sanity_check(worker, work); trace_sched_kthread_work_queue_work(worker, work); list_add_tail(&work->node, pos); work->worker = worker; if (!worker->current_work && likely(worker->task)) wake_up_process(worker->task); } /** * kthread_queue_work - queue a kthread_work * @worker: target kthread_worker * @work: kthread_work to queue * * Queue @work to work processor @task for async execution. @task * must have been created with kthread_create_worker(). Returns %true * if @work was successfully queued, %false if it was already pending. * * Reinitialize the work if it needs to be used by another worker. * For example, when the worker was stopped and started again. */ bool kthread_queue_work(struct kthread_worker *worker, struct kthread_work *work) { bool ret = false; unsigned long flags; raw_spin_lock_irqsave(&worker->lock, flags); if (!queuing_blocked(worker, work)) { kthread_insert_work(worker, work, &worker->work_list); ret = true; } raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_queue_work); /** * kthread_delayed_work_timer_fn - callback that queues the associated kthread * delayed work when the timer expires. * @t: pointer to the expired timer * * The format of the function is defined by struct timer_list. * It should have been called from irqsafe timer with irq already off. */ void kthread_delayed_work_timer_fn(struct timer_list *t) { struct kthread_delayed_work *dwork = timer_container_of(dwork, t, timer); struct kthread_work *work = &dwork->work; struct kthread_worker *worker = work->worker; unsigned long flags; /* * This might happen when a pending work is reinitialized. * It means that it is used a wrong way. */ if (WARN_ON_ONCE(!worker)) return; raw_spin_lock_irqsave(&worker->lock, flags); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); /* Move the work from worker->delayed_work_list. */ WARN_ON_ONCE(list_empty(&work->node)); list_del_init(&work->node); if (!work->canceling) kthread_insert_work(worker, work, &worker->work_list); raw_spin_unlock_irqrestore(&worker->lock, flags); } EXPORT_SYMBOL(kthread_delayed_work_timer_fn); static void __kthread_queue_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct kthread_work *work = &dwork->work; WARN_ON_ONCE(timer->function != kthread_delayed_work_timer_fn); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { kthread_insert_work(worker, work, &worker->work_list); return; } /* Be paranoid and try to detect possible races already now. */ kthread_insert_work_sanity_check(worker, work); list_add(&work->node, &worker->delayed_work_list); work->worker = worker; timer->expires = jiffies + delay; add_timer(timer); } /** * kthread_queue_delayed_work - queue the associated kthread work * after a delay. * @worker: target kthread_worker * @dwork: kthread_delayed_work to queue * @delay: number of jiffies to wait before queuing * * If the work has not been pending it starts a timer that will queue * the work after the given @delay. If @delay is zero, it queues the * work immediately. * * Return: %false if the @work has already been pending. It means that * either the timer was running or the work was queued. It returns %true * otherwise. */ bool kthread_queue_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay) { struct kthread_work *work = &dwork->work; unsigned long flags; bool ret = false; raw_spin_lock_irqsave(&worker->lock, flags); if (!queuing_blocked(worker, work)) { __kthread_queue_delayed_work(worker, dwork, delay); ret = true; } raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_queue_delayed_work); struct kthread_flush_work { struct kthread_work work; struct completion done; }; static void kthread_flush_work_fn(struct kthread_work *work) { struct kthread_flush_work *fwork = container_of(work, struct kthread_flush_work, work); complete(&fwork->done); } /** * kthread_flush_work - flush a kthread_work * @work: work to flush * * If @work is queued or executing, wait for it to finish execution. */ void kthread_flush_work(struct kthread_work *work) { struct kthread_flush_work fwork = { KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), COMPLETION_INITIALIZER_ONSTACK(fwork.done), }; struct kthread_worker *worker; bool noop = false; worker = work->worker; if (!worker) return; raw_spin_lock_irq(&worker->lock); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); if (!list_empty(&work->node)) kthread_insert_work(worker, &fwork.work, work->node.next); else if (worker->current_work == work) kthread_insert_work(worker, &fwork.work, worker->work_list.next); else noop = true; raw_spin_unlock_irq(&worker->lock); if (!noop) wait_for_completion(&fwork.done); } EXPORT_SYMBOL_GPL(kthread_flush_work); /* * Make sure that the timer is neither set nor running and could * not manipulate the work list_head any longer. * * The function is called under worker->lock. The lock is temporary * released but the timer can't be set again in the meantime. */ static void kthread_cancel_delayed_work_timer(struct kthread_work *work, unsigned long *flags) { struct kthread_delayed_work *dwork = container_of(work, struct kthread_delayed_work, work); struct kthread_worker *worker = work->worker; /* * timer_delete_sync() must be called to make sure that the timer * callback is not running. The lock must be temporary released * to avoid a deadlock with the callback. In the meantime, * any queuing is blocked by setting the canceling counter. */ work->canceling++; raw_spin_unlock_irqrestore(&worker->lock, *flags); timer_delete_sync(&dwork->timer); raw_spin_lock_irqsave(&worker->lock, *flags); work->canceling--; } /* * This function removes the work from the worker queue. * * It is called under worker->lock. The caller must make sure that * the timer used by delayed work is not running, e.g. by calling * kthread_cancel_delayed_work_timer(). * * The work might still be in use when this function finishes. See the * current_work proceed by the worker. * * Return: %true if @work was pending and successfully canceled, * %false if @work was not pending */ static bool __kthread_cancel_work(struct kthread_work *work) { /* * Try to remove the work from a worker list. It might either * be from worker->work_list or from worker->delayed_work_list. */ if (!list_empty(&work->node)) { list_del_init(&work->node); return true; } return false; } /** * kthread_mod_delayed_work - modify delay of or queue a kthread delayed work * @worker: kthread worker to use * @dwork: kthread delayed work to queue * @delay: number of jiffies to wait before queuing * * If @dwork is idle, equivalent to kthread_queue_delayed_work(). Otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is zero, * @work is guaranteed to be queued immediately. * * Return: %false if @dwork was idle and queued, %true otherwise. * * A special case is when the work is being canceled in parallel. * It might be caused either by the real kthread_cancel_delayed_work_sync() * or yet another kthread_mod_delayed_work() call. We let the other command * win and return %true here. The return value can be used for reference * counting and the number of queued works stays the same. Anyway, the caller * is supposed to synchronize these operations a reasonable way. * * This function is safe to call from any context including IRQ handler. * See __kthread_cancel_work() and kthread_delayed_work_timer_fn() * for details. */ bool kthread_mod_delayed_work(struct kthread_worker *worker, struct kthread_delayed_work *dwork, unsigned long delay) { struct kthread_work *work = &dwork->work; unsigned long flags; int ret; raw_spin_lock_irqsave(&worker->lock, flags); /* Do not bother with canceling when never queued. */ if (!work->worker) { ret = false; goto fast_queue; } /* Work must not be used with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker != worker); /* * Temporary cancel the work but do not fight with another command * that is canceling the work as well. * * It is a bit tricky because of possible races with another * mod_delayed_work() and cancel_delayed_work() callers. * * The timer must be canceled first because worker->lock is released * when doing so. But the work can be removed from the queue (list) * only when it can be queued again so that the return value can * be used for reference counting. */ kthread_cancel_delayed_work_timer(work, &flags); if (work->canceling) { /* The number of works in the queue does not change. */ ret = true; goto out; } ret = __kthread_cancel_work(work); fast_queue: __kthread_queue_delayed_work(worker, dwork, delay); out: raw_spin_unlock_irqrestore(&worker->lock, flags); return ret; } EXPORT_SYMBOL_GPL(kthread_mod_delayed_work); static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) { struct kthread_worker *worker = work->worker; unsigned long flags; int ret = false; if (!worker) goto out; raw_spin_lock_irqsave(&worker->lock, flags); /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); if (is_dwork) kthread_cancel_delayed_work_timer(work, &flags); ret = __kthread_cancel_work(work); if (worker->current_work != work) goto out_fast; /* * The work is in progress and we need to wait with the lock released. * In the meantime, block any queuing by setting the canceling counter. */ work->canceling++; raw_spin_unlock_irqrestore(&worker->lock, flags); kthread_flush_work(work); raw_spin_lock_irqsave(&worker->lock, flags); work->canceling--; out_fast: raw_spin_unlock_irqrestore(&worker->lock, flags); out: return ret; } /** * kthread_cancel_work_sync - cancel a kthread work and wait for it to finish * @work: the kthread work to cancel * * Cancel @work and wait for its execution to finish. This function * can be used even if the work re-queues itself. On return from this * function, @work is guaranteed to be not pending or executing on any CPU. * * kthread_cancel_work_sync(&delayed_work->work) must not be used for * delayed_work's. Use kthread_cancel_delayed_work_sync() instead. * * The caller must ensure that the worker on which @work was last * queued can't be destroyed before this function returns. * * Return: %true if @work was pending, %false otherwise. */ bool kthread_cancel_work_sync(struct kthread_work *work) { return __kthread_cancel_work_sync(work, false); } EXPORT_SYMBOL_GPL(kthread_cancel_work_sync); /** * kthread_cancel_delayed_work_sync - cancel a kthread delayed work and * wait for it to finish. * @dwork: the kthread delayed work to cancel * * This is kthread_cancel_work_sync() for delayed works. * * Return: %true if @dwork was pending, %false otherwise. */ bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *dwork) { return __kthread_cancel_work_sync(&dwork->work, true); } EXPORT_SYMBOL_GPL(kthread_cancel_delayed_work_sync); /** * kthread_flush_worker - flush all current works on a kthread_worker * @worker: worker to flush * * Wait until all currently executing or pending works on @worker are * finished. */ void kthread_flush_worker(struct kthread_worker *worker) { struct kthread_flush_work fwork = { KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), COMPLETION_INITIALIZER_ONSTACK(fwork.done), }; kthread_queue_work(worker, &fwork.work); wait_for_completion(&fwork.done); } EXPORT_SYMBOL_GPL(kthread_flush_worker); /** * kthread_destroy_worker - destroy a kthread worker * @worker: worker to be destroyed * * Flush and destroy @worker. The simple flush is enough because the kthread * worker API is used only in trivial scenarios. There are no multi-step state * machines needed. * * Note that this function is not responsible for handling delayed work, so * caller should be responsible for queuing or canceling all delayed work items * before invoke this function. */ void kthread_destroy_worker(struct kthread_worker *worker) { struct task_struct *task; task = worker->task; if (WARN_ON(!task)) return; kthread_flush_worker(worker); kthread_stop(task); WARN_ON(!list_empty(&worker->delayed_work_list)); WARN_ON(!list_empty(&worker->work_list)); kfree(worker); } EXPORT_SYMBOL(kthread_destroy_worker); /** * kthread_use_mm - make the calling kthread operate on an address space * @mm: address space to operate on */ void kthread_use_mm(struct mm_struct *mm) { struct mm_struct *active_mm; struct task_struct *tsk = current; WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(tsk->mm); /* * It is possible for mm to be the same as tsk->active_mm, but * we must still mmgrab(mm) and mmdrop_lazy_tlb(active_mm), * because these references are not equivalent. */ mmgrab(mm); task_lock(tsk); /* Hold off tlb flush IPIs while switching mm's */ local_irq_disable(); active_mm = tsk->active_mm; tsk->active_mm = mm; tsk->mm = mm; membarrier_update_current_mm(mm); switch_mm_irqs_off(active_mm, mm, tsk); local_irq_enable(); task_unlock(tsk); #ifdef finish_arch_post_lock_switch finish_arch_post_lock_switch(); #endif /* * When a kthread starts operating on an address space, the loop * in membarrier_{private,global}_expedited() may not observe * that tsk->mm, and not issue an IPI. Membarrier requires a * memory barrier after storing to tsk->mm, before accessing * user-space memory. A full memory barrier for membarrier * {PRIVATE,GLOBAL}_EXPEDITED is implicitly provided by * mmdrop_lazy_tlb(). */ mmdrop_lazy_tlb(active_mm); } EXPORT_SYMBOL_GPL(kthread_use_mm); /** * kthread_unuse_mm - reverse the effect of kthread_use_mm() * @mm: address space to operate on */ void kthread_unuse_mm(struct mm_struct *mm) { struct task_struct *tsk = current; WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(!tsk->mm); task_lock(tsk); /* * When a kthread stops operating on an address space, the loop * in membarrier_{private,global}_expedited() may not observe * that tsk->mm, and not issue an IPI. Membarrier requires a * memory barrier after accessing user-space memory, before * clearing tsk->mm. */ smp_mb__after_spinlock(); local_irq_disable(); tsk->mm = NULL; membarrier_update_current_mm(NULL); mmgrab_lazy_tlb(mm); /* active_mm is still 'mm' */ enter_lazy_tlb(mm, tsk); local_irq_enable(); task_unlock(tsk); mmdrop(mm); } EXPORT_SYMBOL_GPL(kthread_unuse_mm); #ifdef CONFIG_BLK_CGROUP /** * kthread_associate_blkcg - associate blkcg to current kthread * @css: the cgroup info * * Current thread must be a kthread. The thread is running jobs on behalf of * other threads. In some cases, we expect the jobs attach cgroup info of * original threads instead of that of current thread. This function stores * original thread's cgroup info in current kthread context for later * retrieval. */ void kthread_associate_blkcg(struct cgroup_subsys_state *css) { struct kthread *kthread; if (!(current->flags & PF_KTHREAD)) return; kthread = to_kthread(current); if (!kthread) return; if (kthread->blkcg_css) { css_put(kthread->blkcg_css); kthread->blkcg_css = NULL; } if (css) { css_get(css); kthread->blkcg_css = css; } } EXPORT_SYMBOL(kthread_associate_blkcg); /** * kthread_blkcg - get associated blkcg css of current kthread * * Current thread must be a kthread. */ struct cgroup_subsys_state *kthread_blkcg(void) { struct kthread *kthread; if (current->flags & PF_KTHREAD) { kthread = to_kthread(current); if (kthread) return kthread->blkcg_css; } return NULL; } #endif |
| 284 178 3 109 270 270 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timer #if !defined(_TRACE_TIMER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMER_H #include <linux/tracepoint.h> #include <linux/hrtimer.h> #include <linux/timer.h> DECLARE_EVENT_CLASS(timer_class, TP_PROTO(struct timer_list *timer), TP_ARGS(timer), TP_STRUCT__entry( __field( void *, timer ) ), TP_fast_assign( __entry->timer = timer; ), TP_printk("timer=%p", __entry->timer) ); /** * timer_init - called when the timer is initialized * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_init, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_timer_flags(flags) \ __print_flags(flags, "|", \ { TIMER_MIGRATING, "M" }, \ { TIMER_DEFERRABLE, "D" }, \ { TIMER_PINNED, "P" }, \ { TIMER_IRQSAFE, "I" }) /** * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @bucket_expiry: the bucket expiry time */ TRACE_EVENT(timer_start, TP_PROTO(struct timer_list *timer, unsigned long bucket_expiry), TP_ARGS(timer, bucket_expiry), TP_STRUCT__entry( __field( void *, timer ) __field( void *, function ) __field( unsigned long, expires ) __field( unsigned long, bucket_expiry ) __field( unsigned long, now ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->timer = timer; __entry->function = timer->function; __entry->expires = timer->expires; __entry->bucket_expiry = bucket_expiry; __entry->now = jiffies; __entry->flags = timer->flags; ), TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] bucket_expiry=%lu cpu=%u idx=%u flags=%s", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now, __entry->bucket_expiry, __entry->flags & TIMER_CPUMASK, __entry->flags >> TIMER_ARRAYSHIFT, decode_timer_flags(__entry->flags & TIMER_TRACE_FLAGMASK)) ); /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list * @baseclk: value of timer_base::clk when timer expires * * Allows to determine the timer latency. */ TRACE_EVENT(timer_expire_entry, TP_PROTO(struct timer_list *timer, unsigned long baseclk), TP_ARGS(timer, baseclk), TP_STRUCT__entry( __field( void *, timer ) __field( unsigned long, now ) __field( void *, function) __field( unsigned long, baseclk ) ), TP_fast_assign( __entry->timer = timer; __entry->now = jiffies; __entry->function = timer->function; __entry->baseclk = baseclk; ), TP_printk("timer=%p function=%ps now=%lu baseclk=%lu", __entry->timer, __entry->function, __entry->now, __entry->baseclk) ); /** * timer_expire_exit - called immediately after the timer callback returns * @timer: pointer to struct timer_list * * When used in combination with the timer_expire_entry tracepoint we can * determine the runtime of the timer callback function. * * NOTE: Do NOT dereference timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ DEFINE_EVENT(timer_class, timer_expire_exit, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); /** * timer_cancel - called when the timer is canceled * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_cancel, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); TRACE_EVENT(timer_base_idle, TP_PROTO(bool is_idle, unsigned int cpu), TP_ARGS(is_idle, cpu), TP_STRUCT__entry( __field( bool, is_idle ) __field( unsigned int, cpu ) ), TP_fast_assign( __entry->is_idle = is_idle; __entry->cpu = cpu; ), TP_printk("is_idle=%d cpu=%d", __entry->is_idle, __entry->cpu) ); #define decode_clockid(type) \ __print_symbolic(type, \ { CLOCK_REALTIME, "CLOCK_REALTIME" }, \ { CLOCK_MONOTONIC, "CLOCK_MONOTONIC" }, \ { CLOCK_BOOTTIME, "CLOCK_BOOTTIME" }, \ { CLOCK_TAI, "CLOCK_TAI" }) #define decode_hrtimer_mode(mode) \ __print_symbolic(mode, \ { HRTIMER_MODE_ABS, "ABS" }, \ { HRTIMER_MODE_REL, "REL" }, \ { HRTIMER_MODE_ABS_PINNED, "ABS|PINNED" }, \ { HRTIMER_MODE_REL_PINNED, "REL|PINNED" }, \ { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }, \ { HRTIMER_MODE_ABS_HARD, "ABS|HARD" }, \ { HRTIMER_MODE_REL_HARD, "REL|HARD" }, \ { HRTIMER_MODE_ABS_PINNED_HARD, "ABS|PINNED|HARD" }, \ { HRTIMER_MODE_REL_PINNED_HARD, "REL|PINNED|HARD" }) /** * hrtimer_setup - called when the hrtimer is initialized * @hrtimer: pointer to struct hrtimer * @clockid: the hrtimers clock * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_setup, TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid, enum hrtimer_mode mode), TP_ARGS(hrtimer, clockid, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( clockid_t, clockid ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->clockid = clockid; __entry->mode = mode; ), TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer, decode_clockid(__entry->clockid), decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_start - called when the hrtimer is started * @hrtimer: pointer to struct hrtimer * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_start, TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode), TP_ARGS(hrtimer, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( void *, function ) __field( s64, expires ) __field( s64, softexpires ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->function = ACCESS_PRIVATE(hrtimer, function); __entry->expires = hrtimer_get_expires(hrtimer); __entry->softexpires = hrtimer_get_softexpires(hrtimer); __entry->mode = mode; ), TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu " "mode=%s", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires, decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_expire_entry - called immediately before the hrtimer callback * @hrtimer: pointer to struct hrtimer * @now: pointer to variable which contains current time of the * timers base. * * Allows to determine the timer latency. */ TRACE_EVENT(hrtimer_expire_entry, TP_PROTO(struct hrtimer *hrtimer, ktime_t *now), TP_ARGS(hrtimer, now), TP_STRUCT__entry( __field( void *, hrtimer ) __field( s64, now ) __field( void *, function) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->now = *now; __entry->function = ACCESS_PRIVATE(hrtimer, function); ), TP_printk("hrtimer=%p function=%ps now=%llu", __entry->hrtimer, __entry->function, (unsigned long long) __entry->now) ); DECLARE_EVENT_CLASS(hrtimer_class, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer), TP_STRUCT__entry( __field( void *, hrtimer ) ), TP_fast_assign( __entry->hrtimer = hrtimer; ), TP_printk("hrtimer=%p", __entry->hrtimer) ); /** * hrtimer_expire_exit - called immediately after the hrtimer callback returns * @hrtimer: pointer to struct hrtimer * * When used in combination with the hrtimer_expire_entry tracepoint we can * determine the runtime of the callback function. */ DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * hrtimer_cancel - called when the hrtimer is canceled * @hrtimer: pointer to struct hrtimer */ DEFINE_EVENT(hrtimer_class, hrtimer_cancel, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * itimer_state - called when itimer is started or canceled * @which: name of the interval timer * @value: the itimers value, itimer is canceled if value->it_value is * zero, otherwise it is started * @expires: the itimers expiry time */ TRACE_EVENT(itimer_state, TP_PROTO(int which, const struct itimerspec64 *const value, unsigned long long expires), TP_ARGS(which, value, expires), TP_STRUCT__entry( __field( int, which ) __field( unsigned long long, expires ) __field( long, value_sec ) __field( long, value_nsec ) __field( long, interval_sec ) __field( long, interval_nsec ) ), TP_fast_assign( __entry->which = which; __entry->expires = expires; __entry->value_sec = value->it_value.tv_sec; __entry->value_nsec = value->it_value.tv_nsec; __entry->interval_sec = value->it_interval.tv_sec; __entry->interval_nsec = value->it_interval.tv_nsec; ), TP_printk("which=%d expires=%llu it_value=%ld.%06ld it_interval=%ld.%06ld", __entry->which, __entry->expires, __entry->value_sec, __entry->value_nsec / NSEC_PER_USEC, __entry->interval_sec, __entry->interval_nsec / NSEC_PER_USEC) ); /** * itimer_expire - called when itimer expires * @which: type of the interval timer * @pid: pid of the process which owns the timer * @now: current time, used to calculate the latency of itimer */ TRACE_EVENT(itimer_expire, TP_PROTO(int which, struct pid *pid, unsigned long long now), TP_ARGS(which, pid, now), TP_STRUCT__entry( __field( int , which ) __field( pid_t, pid ) __field( unsigned long long, now ) ), TP_fast_assign( __entry->which = which; __entry->now = now; __entry->pid = pid_nr(pid); ), TP_printk("which=%d pid=%d now=%llu", __entry->which, (int) __entry->pid, __entry->now) ); #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name(CLOCK_UNSTABLE) \ tick_dep_name(RCU) \ tick_dep_name_end(RCU_EXP) #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end /* The MASK will convert to their bits and they need to be processed too */ #define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); #define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); /* NONE only has a mask defined for it */ #define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ __print_symbolic(val, TICK_DEP_NAMES) TRACE_EVENT(tick_stop, TP_PROTO(int success, int dependency), TP_ARGS(success, dependency), TP_STRUCT__entry( __field( int , success ) __field( int , dependency ) ), TP_fast_assign( __entry->success = success; __entry->dependency = dependency; ), TP_printk("success=%d dependency=%s", __entry->success, \ show_tick_dep_name(__entry->dependency)) ); #endif #endif /* _TRACE_TIMER_H */ /* 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 | /* 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_ */ |
| 302 302 302 302 302 302 302 2 1 1 1 2 2 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 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 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 12302 12303 12304 12305 12306 12307 12308 12309 12310 12311 12312 12313 12314 12315 12316 12317 12318 12319 12320 12321 12322 12323 12324 12325 12326 12327 12328 12329 12330 12331 12332 12333 12334 12335 12336 12337 12338 12339 12340 12341 12342 12343 12344 12345 12346 12347 12348 12349 12350 12351 12352 12353 12354 12355 12356 12357 12358 12359 12360 12361 12362 12363 12364 12365 12366 12367 12368 12369 12370 12371 12372 12373 12374 12375 12376 12377 12378 12379 12380 12381 12382 12383 12384 12385 12386 12387 12388 12389 12390 12391 12392 12393 12394 12395 12396 12397 12398 12399 12400 12401 12402 12403 12404 12405 12406 12407 12408 12409 12410 12411 12412 12413 12414 12415 12416 12417 12418 12419 12420 12421 12422 12423 12424 12425 12426 12427 12428 12429 12430 12431 12432 12433 12434 12435 12436 12437 12438 12439 12440 12441 12442 12443 12444 12445 12446 12447 12448 12449 12450 12451 12452 12453 12454 12455 12456 12457 12458 12459 12460 12461 12462 12463 12464 12465 12466 12467 12468 12469 12470 12471 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux Socket Filter - Kernel level socket filtering * * Based on the design of the Berkeley Packet Filter. The new * internal format has been designed by PLUMgrid: * * Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com * * Authors: * * Jay Schulist <jschlst@samba.org> * Alexei Starovoitov <ast@plumgrid.com> * Daniel Borkmann <dborkman@redhat.com> * * Andi Kleen - Fix a few bad bugs and races. * Kris Katterjohn - Added many additional checks in bpf_check_classic() */ #include <linux/atomic.h> #include <linux/bpf_verifier.h> #include <linux/module.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/sock_diag.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> #include <linux/if_arp.h> #include <linux/gfp.h> #include <net/inet_common.h> #include <net/ip.h> #include <net/protocol.h> #include <net/netlink.h> #include <linux/skbuff.h> #include <linux/skmsg.h> #include <net/sock.h> #include <net/flow_dissector.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <linux/unaligned.h> #include <linux/filter.h> #include <linux/ratelimit.h> #include <linux/seccomp.h> #include <linux/if_vlan.h> #include <linux/bpf.h> #include <linux/btf.h> #include <net/sch_generic.h> #include <net/cls_cgroup.h> #include <net/dst_metadata.h> #include <net/dst.h> #include <net/sock_reuseport.h> #include <net/busy_poll.h> #include <net/tcp.h> #include <net/xfrm.h> #include <net/udp.h> #include <linux/bpf_trace.h> #include <net/xdp_sock.h> #include <linux/inetdevice.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/flow.h> #include <net/arp.h> #include <net/ipv6.h> #include <net/net_namespace.h> #include <linux/seg6_local.h> #include <net/seg6.h> #include <net/seg6_local.h> #include <net/lwtunnel.h> #include <net/ipv6_stubs.h> #include <net/bpf_sk_storage.h> #include <net/transp_v6.h> #include <linux/btf_ids.h> #include <net/tls.h> #include <net/xdp.h> #include <net/mptcp.h> #include <net/netfilter/nf_conntrack_bpf.h> #include <net/netkit.h> #include <linux/un.h> #include <net/xdp_sock_drv.h> #include <net/inet_dscp.h> #include "dev.h" /* Keep the struct bpf_fib_lookup small so that it fits into a cacheline */ static_assert(sizeof(struct bpf_fib_lookup) == 64, "struct bpf_fib_lookup size check"); static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { if (in_compat_syscall()) { struct compat_sock_fprog f32; if (len != sizeof(f32)) return -EINVAL; if (copy_from_sockptr(&f32, src, sizeof(f32))) return -EFAULT; memset(dst, 0, sizeof(*dst)); dst->len = f32.len; dst->filter = compat_ptr(f32.filter); } else { if (len != sizeof(*dst)) return -EINVAL; if (copy_from_sockptr(dst, src, sizeof(*dst))) return -EFAULT; } return 0; } EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user); /** * sk_filter_trim_cap - run a packet through a socket filter * @sk: sock associated with &sk_buff * @skb: buffer to filter * @cap: limit on how short the eBPF program may trim the packet * @reason: record drop reason on errors (negative return value) * * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller * than pkt_len we keep whole skb->data. This is the socket level * wrapper to bpf_prog_run. It returns 0 if the packet should * be accepted or -EPERM if the packet should be tossed. * */ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap, enum skb_drop_reason *reason) { int err; struct sk_filter *filter; /* * If the skb was allocated from pfmemalloc reserves, only * allow SOCK_MEMALLOC sockets to use it as this socket is * helping free memory */ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP); *reason = SKB_DROP_REASON_PFMEMALLOC; return -ENOMEM; } err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb); if (err) { *reason = SKB_DROP_REASON_SOCKET_FILTER; return err; } err = security_sock_rcv_skb(sk, skb); if (err) { *reason = SKB_DROP_REASON_SECURITY_HOOK; return err; } rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter) { struct sock *save_sk = skb->sk; unsigned int pkt_len; skb->sk = sk; pkt_len = bpf_prog_run_save_cb(filter->prog, skb); skb->sk = save_sk; err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM; if (err) *reason = SKB_DROP_REASON_SOCKET_FILTER; } rcu_read_unlock(); return err; } EXPORT_SYMBOL(sk_filter_trim_cap); BPF_CALL_1(bpf_skb_get_pay_offset, struct sk_buff *, skb) { return skb_get_poff(skb); } BPF_CALL_3(bpf_skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; if (skb_is_nonlinear(skb)) return 0; if (skb->len < sizeof(struct nlattr)) return 0; if (a > skb->len - sizeof(struct nlattr)) return 0; nla = nla_find((struct nlattr *) &skb->data[a], skb->len - a, x); if (nla) return (void *) nla - (void *) skb->data; return 0; } BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; if (skb_is_nonlinear(skb)) return 0; if (skb->len < sizeof(struct nlattr)) return 0; if (a > skb->len - sizeof(struct nlattr)) return 0; nla = (struct nlattr *) &skb->data[a]; if (!nla_ok(nla, skb->len - a)) return 0; nla = nla_find_nested(nla, x); if (nla) return (void *) nla - (void *) skb->data; return 0; } static int bpf_skb_load_helper_convert_offset(const struct sk_buff *skb, int offset) { if (likely(offset >= 0)) return offset; if (offset >= SKF_NET_OFF) return offset - SKF_NET_OFF + skb_network_offset(skb); if (offset >= SKF_LL_OFF && skb_mac_header_was_set(skb)) return offset - SKF_LL_OFF + skb_mac_offset(skb); return INT_MIN; } BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { u8 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return *(u8 *)(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return tmp; else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_8(skb, skb->data, skb->len - skb->data_len, offset); } BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { __be16 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return get_unaligned_be16(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return be16_to_cpu(tmp); else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_16(skb, skb->data, skb->len - skb->data_len, offset); } BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *, data, int, headlen, int, offset) { __be32 tmp; const int len = sizeof(tmp); offset = bpf_skb_load_helper_convert_offset(skb, offset); if (offset == INT_MIN) return -EFAULT; if (headlen - offset >= len) return get_unaligned_be32(data + offset); if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) return be32_to_cpu(tmp); else return -EFAULT; } BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb, int, offset) { return ____bpf_skb_load_helper_32(skb, skb->data, skb->len - skb->data_len, offset); } static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; switch (skb_field) { case SKF_AD_MARK: BUILD_BUG_ON(sizeof_field(struct sk_buff, mark) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, mark)); break; case SKF_AD_PKTTYPE: *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, PKT_TYPE_MAX); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 5); #endif break; case SKF_AD_QUEUE: BUILD_BUG_ON(sizeof_field(struct sk_buff, queue_mapping) != 2); *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, queue_mapping)); break; case SKF_AD_VLAN_TAG: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_tci) != 2); /* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, vlan_tci)); break; case SKF_AD_VLAN_TAG_PRESENT: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_all) != 4); *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, vlan_all)); *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); *insn++ = BPF_ALU32_IMM(BPF_MOV, dst_reg, 1); break; } return insn - insn_buf; } static bool convert_bpf_extensions(struct sock_filter *fp, struct bpf_insn **insnp) { struct bpf_insn *insn = *insnp; u32 cnt; switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: BUILD_BUG_ON(sizeof_field(struct sk_buff, protocol) != 2); /* A = *(u16 *) (CTX + offsetof(protocol)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, protocol)); /* A = ntohs(A) [emitting a nop or swap16] */ *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PKTTYPE: cnt = convert_skb_access(SKF_AD_PKTTYPE, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: BUILD_BUG_ON(sizeof_field(struct net_device, ifindex) != 4); BUILD_BUG_ON(sizeof_field(struct net_device, type) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), BPF_REG_TMP, BPF_REG_CTX, offsetof(struct sk_buff, dev)); /* if (tmp != 0) goto pc + 1 */ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1); *insn++ = BPF_EXIT_INSN(); if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_TMP, offsetof(struct net_device, ifindex)); else *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_TMP, offsetof(struct net_device, type)); break; case SKF_AD_OFF + SKF_AD_MARK: cnt = convert_skb_access(SKF_AD_MARK, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_RXHASH: BUILD_BUG_ON(sizeof_field(struct sk_buff, hash) != 4); *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, hash)); break; case SKF_AD_OFF + SKF_AD_QUEUE: cnt = convert_skb_access(SKF_AD_QUEUE, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TAG: cnt = convert_skb_access(SKF_AD_VLAN_TAG, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: cnt = convert_skb_access(SKF_AD_VLAN_TAG_PRESENT, BPF_REG_A, BPF_REG_CTX, insn); insn += cnt - 1; break; case SKF_AD_OFF + SKF_AD_VLAN_TPID: BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_proto) != 2); /* A = *(u16 *) (CTX + offsetof(vlan_proto)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, vlan_proto)); /* A = ntohs(A) [emitting a nop or swap16] */ *insn = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, 16); break; case SKF_AD_OFF + SKF_AD_PAY_OFFSET: case SKF_AD_OFF + SKF_AD_NLATTR: case SKF_AD_OFF + SKF_AD_NLATTR_NEST: case SKF_AD_OFF + SKF_AD_CPU: case SKF_AD_OFF + SKF_AD_RANDOM: /* arg1 = CTX */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); /* arg2 = A */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_A); /* arg3 = X */ *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_X); /* Emit call(arg1=CTX, arg2=A, arg3=X) */ switch (fp->k) { case SKF_AD_OFF + SKF_AD_PAY_OFFSET: *insn = BPF_EMIT_CALL(bpf_skb_get_pay_offset); break; case SKF_AD_OFF + SKF_AD_NLATTR: *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr); break; case SKF_AD_OFF + SKF_AD_NLATTR_NEST: *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr_nest); break; case SKF_AD_OFF + SKF_AD_CPU: *insn = BPF_EMIT_CALL(bpf_get_raw_cpu_id); break; case SKF_AD_OFF + SKF_AD_RANDOM: *insn = BPF_EMIT_CALL(bpf_user_rnd_u32); bpf_user_rnd_init_once(); break; } break; case SKF_AD_OFF + SKF_AD_ALU_XOR_X: /* A ^= X */ *insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X); break; default: /* This is just a dummy call to avoid letting the compiler * evict __bpf_call_base() as an optimization. Placed here * where no-one bothers. */ BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0); return false; } *insnp = insn; return true; } static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp) { const bool unaligned_ok = IS_BUILTIN(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS); int size = bpf_size_to_bytes(BPF_SIZE(fp->code)); bool endian = BPF_SIZE(fp->code) == BPF_H || BPF_SIZE(fp->code) == BPF_W; bool indirect = BPF_MODE(fp->code) == BPF_IND; const int ip_align = NET_IP_ALIGN; struct bpf_insn *insn = *insnp; int offset = fp->k; if (!indirect && ((unaligned_ok && offset >= 0) || (!unaligned_ok && offset >= 0 && offset + ip_align >= 0 && offset + ip_align % size == 0))) { bool ldx_off_ok = offset <= S16_MAX; *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H); if (offset) *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset); *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian + (!ldx_off_ok * 2)); if (ldx_off_ok) { *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D, offset); } else { *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D); *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset); *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_TMP, 0); } if (endian) *insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8); *insn++ = BPF_JMP_A(8); } *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_D); *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_H); if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_ARG4, offset); } else { *insn++ = BPF_MOV64_REG(BPF_REG_ARG4, BPF_REG_X); if (fp->k) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG4, offset); } switch (BPF_SIZE(fp->code)) { case BPF_B: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8); break; case BPF_H: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16); break; case BPF_W: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32); break; default: return false; } *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_A, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *insn = BPF_EXIT_INSN(); *insnp = insn; return true; } /** * bpf_convert_filter - convert filter program * @prog: the user passed filter program * @len: the length of the user passed filter program * @new_prog: allocated 'struct bpf_prog' or NULL * @new_len: pointer to store length of converted program * @seen_ld_abs: bool whether we've seen ld_abs/ind * * Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn' * style extended BPF (eBPF). * Conversion workflow: * * 1) First pass for calculating the new program length: * bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs) * * 2) 2nd pass to remap in two passes: 1st pass finds new * jump offsets, 2nd pass remapping: * bpf_convert_filter(old_prog, old_len, new_prog, &new_len, &seen_ld_abs) */ static int bpf_convert_filter(struct sock_filter *prog, int len, struct bpf_prog *new_prog, int *new_len, bool *seen_ld_abs) { int new_flen = 0, pass = 0, target, i, stack_off; struct bpf_insn *new_insn, *first_insn = NULL; struct sock_filter *fp; int *addrs = NULL; u8 bpf_src; BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK); BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); if (len <= 0 || len > BPF_MAXINSNS) return -EINVAL; if (new_prog) { first_insn = new_prog->insnsi; addrs = kcalloc(len, sizeof(*addrs), GFP_KERNEL | __GFP_NOWARN); if (!addrs) return -ENOMEM; } do_pass: new_insn = first_insn; fp = prog; /* Classic BPF related prologue emission. */ if (new_prog) { /* Classic BPF expects A and X to be reset first. These need * to be guaranteed to be the first two instructions. */ *new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *new_insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_X, BPF_REG_X); /* All programs must keep CTX in callee saved BPF_REG_CTX. * In eBPF case it's done by the compiler, here we need to * do this ourself. Initial CTX is present in BPF_REG_ARG1. */ *new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); if (*seen_ld_abs) { /* For packet access in classic BPF, cache skb->data * in callee-saved BPF R8 and skb->len - skb->data_len * (headlen) in BPF R9. Since classic BPF is read-only * on CTX, we only need to cache it once. */ *new_insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), BPF_REG_D, BPF_REG_CTX, offsetof(struct sk_buff, data)); *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_H, BPF_REG_CTX, offsetof(struct sk_buff, len)); *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_TMP, BPF_REG_CTX, offsetof(struct sk_buff, data_len)); *new_insn++ = BPF_ALU32_REG(BPF_SUB, BPF_REG_H, BPF_REG_TMP); } } else { new_insn += 3; } for (i = 0; i < len; fp++, i++) { struct bpf_insn tmp_insns[32] = { }; struct bpf_insn *insn = tmp_insns; if (addrs) addrs[i] = new_insn - first_insn; switch (fp->code) { /* All arithmetic insns and skb loads map as-is. */ case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU | BPF_MOD | BPF_K: case BPF_ALU | BPF_NEG: case BPF_LD | BPF_ABS | BPF_W: case BPF_LD | BPF_ABS | BPF_H: case BPF_LD | BPF_ABS | BPF_B: case BPF_LD | BPF_IND | BPF_W: case BPF_LD | BPF_IND | BPF_H: case BPF_LD | BPF_IND | BPF_B: /* Check for overloaded BPF extension and * directly convert it if found, otherwise * just move on with mapping. */ if (BPF_CLASS(fp->code) == BPF_LD && BPF_MODE(fp->code) == BPF_ABS && convert_bpf_extensions(fp, &insn)) break; if (BPF_CLASS(fp->code) == BPF_LD && convert_bpf_ld_abs(fp, &insn)) { *seen_ld_abs = true; break; } if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) || fp->code == (BPF_ALU | BPF_MOD | BPF_X)) { *insn++ = BPF_MOV32_REG(BPF_REG_X, BPF_REG_X); /* Error with exception code on div/mod by 0. * For cBPF programs, this was always return 0. */ *insn++ = BPF_JMP_IMM(BPF_JNE, BPF_REG_X, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); *insn++ = BPF_EXIT_INSN(); } *insn = BPF_RAW_INSN(fp->code, BPF_REG_A, BPF_REG_X, 0, fp->k); break; /* Jump transformation cannot use BPF block macros * everywhere as offset calculation and target updates * require a bit more work than the rest, i.e. jump * opcodes map as-is, but offsets need adjustment. */ #define BPF_EMIT_JMP \ do { \ const s32 off_min = S16_MIN, off_max = S16_MAX; \ s32 off; \ \ if (target >= len || target < 0) \ goto err; \ off = addrs ? addrs[target] - addrs[i] - 1 : 0; \ /* Adjust pc relative offset for 2nd or 3rd insn. */ \ off -= insn - tmp_insns; \ /* Reject anything not fitting into insn->off. */ \ if (off < off_min || off > off_max) \ goto err; \ insn->off = off; \ } while (0) case BPF_JMP | BPF_JA: target = i + fp->k + 1; insn->code = fp->code; BPF_EMIT_JMP; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) { /* BPF immediates are signed, zero extend * immediate into tmp register and use it * in compare insn. */ *insn++ = BPF_MOV32_IMM(BPF_REG_TMP, fp->k); insn->dst_reg = BPF_REG_A; insn->src_reg = BPF_REG_TMP; bpf_src = BPF_X; } else { insn->dst_reg = BPF_REG_A; insn->imm = fp->k; bpf_src = BPF_SRC(fp->code); insn->src_reg = bpf_src == BPF_X ? BPF_REG_X : 0; } /* Common case where 'jump_false' is next insn. */ if (fp->jf == 0) { insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; target = i + fp->jt + 1; BPF_EMIT_JMP; break; } /* Convert some jumps when 'jump_true' is next insn. */ if (fp->jt == 0) { switch (BPF_OP(fp->code)) { case BPF_JEQ: insn->code = BPF_JMP | BPF_JNE | bpf_src; break; case BPF_JGT: insn->code = BPF_JMP | BPF_JLE | bpf_src; break; case BPF_JGE: insn->code = BPF_JMP | BPF_JLT | bpf_src; break; default: goto jmp_rest; } target = i + fp->jf + 1; BPF_EMIT_JMP; break; } jmp_rest: /* Other jumps are mapped into two insns: Jxx and JA. */ target = i + fp->jt + 1; insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src; BPF_EMIT_JMP; insn++; insn->code = BPF_JMP | BPF_JA; target = i + fp->jf + 1; BPF_EMIT_JMP; break; /* ldxb 4 * ([14] & 0xf) is remapped into 6 insns. */ case BPF_LDX | BPF_MSH | BPF_B: { struct sock_filter tmp = { .code = BPF_LD | BPF_ABS | BPF_B, .k = fp->k, }; *seen_ld_abs = true; /* X = A */ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = BPF_R0 = *(u8 *) (skb->data + K) */ convert_bpf_ld_abs(&tmp, &insn); insn++; /* A &= 0xf */ *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); /* A <<= 2 */ *insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); /* tmp = X */ *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_X); /* X = A */ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = tmp */ *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); break; } /* RET_K is remapped into 2 insns. RET_A case doesn't need an * extra mov as BPF_REG_0 is already mapped into BPF_REG_A. */ case BPF_RET | BPF_A: case BPF_RET | BPF_K: if (BPF_RVAL(fp->code) == BPF_K) *insn++ = BPF_MOV32_RAW(BPF_K, BPF_REG_0, 0, fp->k); *insn = BPF_EXIT_INSN(); break; /* Store to stack. */ case BPF_ST: case BPF_STX: stack_off = fp->k * 4 + 4; *insn = BPF_STX_MEM(BPF_W, BPF_REG_FP, BPF_CLASS(fp->code) == BPF_ST ? BPF_REG_A : BPF_REG_X, -stack_off); /* check_load_and_stores() verifies that classic BPF can * load from stack only after write, so tracking * stack_depth for ST|STX insns is enough */ if (new_prog && new_prog->aux->stack_depth < stack_off) new_prog->aux->stack_depth = stack_off; break; /* Load from stack. */ case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: stack_off = fp->k * 4 + 4; *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, BPF_REG_FP, -stack_off); break; /* A = K or X = K */ case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: *insn = BPF_MOV32_IMM(BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, fp->k); break; /* X = A */ case BPF_MISC | BPF_TAX: *insn = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); break; /* A = X */ case BPF_MISC | BPF_TXA: *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_X); break; /* A = skb->len or X = skb->len */ case BPF_LD | BPF_W | BPF_LEN: case BPF_LDX | BPF_W | BPF_LEN: *insn = BPF_LDX_MEM(BPF_W, BPF_CLASS(fp->code) == BPF_LD ? BPF_REG_A : BPF_REG_X, BPF_REG_CTX, offsetof(struct sk_buff, len)); break; /* Access seccomp_data fields. */ case BPF_LDX | BPF_ABS | BPF_W: /* A = *(u32 *) (ctx + K) */ *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k); break; /* Unknown instruction. */ default: goto err; } insn++; if (new_prog) memcpy(new_insn, tmp_insns, sizeof(*insn) * (insn - tmp_insns)); new_insn += insn - tmp_insns; } if (!new_prog) { /* Only calculating new length. */ *new_len = new_insn - first_insn; if (*seen_ld_abs) *new_len += 4; /* Prologue bits. */ return 0; } pass++; if (new_flen != new_insn - first_insn) { new_flen = new_insn - first_insn; if (pass > 2) goto err; goto do_pass; } kfree(addrs); BUG_ON(*new_len != new_flen); return 0; err: kfree(addrs); return -EINVAL; } /* Security: * * As we dont want to clear mem[] array for each packet going through * __bpf_prog_run(), we check that filter loaded by user never try to read * a cell if not previously written, and we check all branches to be sure * a malicious user doesn't try to abuse us. */ static int check_load_and_stores(const struct sock_filter *filter, int flen) { u16 *masks, memvalid = 0; /* One bit per cell, 16 cells */ int pc, ret = 0; BUILD_BUG_ON(BPF_MEMWORDS > 16); masks = kmalloc_array(flen, sizeof(*masks), GFP_KERNEL); if (!masks) return -ENOMEM; memset(masks, 0xff, flen * sizeof(*masks)); for (pc = 0; pc < flen; pc++) { memvalid &= masks[pc]; switch (filter[pc].code) { case BPF_ST: case BPF_STX: memvalid |= (1 << filter[pc].k); break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: if (!(memvalid & (1 << filter[pc].k))) { ret = -EINVAL; goto error; } break; case BPF_JMP | BPF_JA: /* A jump must set masks on target */ masks[pc + 1 + filter[pc].k] &= memvalid; memvalid = ~0; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: /* A jump must set masks on targets */ masks[pc + 1 + filter[pc].jt] &= memvalid; masks[pc + 1 + filter[pc].jf] &= memvalid; memvalid = ~0; break; } } error: kfree(masks); return ret; } static bool chk_code_allowed(u16 code_to_probe) { static const bool codes[] = { /* 32 bit ALU operations */ [BPF_ALU | BPF_ADD | BPF_K] = true, [BPF_ALU | BPF_ADD | BPF_X] = true, [BPF_ALU | BPF_SUB | BPF_K] = true, [BPF_ALU | BPF_SUB | BPF_X] = true, [BPF_ALU | BPF_MUL | BPF_K] = true, [BPF_ALU | BPF_MUL | BPF_X] = true, [BPF_ALU | BPF_DIV | BPF_K] = true, [BPF_ALU | BPF_DIV | BPF_X] = true, [BPF_ALU | BPF_MOD | BPF_K] = true, [BPF_ALU | BPF_MOD | BPF_X] = true, [BPF_ALU | BPF_AND | BPF_K] = true, [BPF_ALU | BPF_AND | BPF_X] = true, [BPF_ALU | BPF_OR | BPF_K] = true, [BPF_ALU | BPF_OR | BPF_X] = true, [BPF_ALU | BPF_XOR | BPF_K] = true, [BPF_ALU | BPF_XOR | BPF_X] = true, [BPF_ALU | BPF_LSH | BPF_K] = true, [BPF_ALU | BPF_LSH | BPF_X] = true, [BPF_ALU | BPF_RSH | BPF_K] = true, [BPF_ALU | BPF_RSH | BPF_X] = true, [BPF_ALU | BPF_NEG] = true, /* Load instructions */ [BPF_LD | BPF_W | BPF_ABS] = true, [BPF_LD | BPF_H | BPF_ABS] = true, [BPF_LD | BPF_B | BPF_ABS] = true, [BPF_LD | BPF_W | BPF_LEN] = true, [BPF_LD | BPF_W | BPF_IND] = true, [BPF_LD | BPF_H | BPF_IND] = true, [BPF_LD | BPF_B | BPF_IND] = true, [BPF_LD | BPF_IMM] = true, [BPF_LD | BPF_MEM] = true, [BPF_LDX | BPF_W | BPF_LEN] = true, [BPF_LDX | BPF_B | BPF_MSH] = true, [BPF_LDX | BPF_IMM] = true, [BPF_LDX | BPF_MEM] = true, /* Store instructions */ [BPF_ST] = true, [BPF_STX] = true, /* Misc instructions */ [BPF_MISC | BPF_TAX] = true, [BPF_MISC | BPF_TXA] = true, /* Return instructions */ [BPF_RET | BPF_K] = true, [BPF_RET | BPF_A] = true, /* Jump instructions */ [BPF_JMP | BPF_JA] = true, [BPF_JMP | BPF_JEQ | BPF_K] = true, [BPF_JMP | BPF_JEQ | BPF_X] = true, [BPF_JMP | BPF_JGE | BPF_K] = true, [BPF_JMP | BPF_JGE | BPF_X] = true, [BPF_JMP | BPF_JGT | BPF_K] = true, [BPF_JMP | BPF_JGT | BPF_X] = true, [BPF_JMP | BPF_JSET | BPF_K] = true, [BPF_JMP | BPF_JSET | BPF_X] = true, }; if (code_to_probe >= ARRAY_SIZE(codes)) return false; return codes[code_to_probe]; } static bool bpf_check_basics_ok(const struct sock_filter *filter, unsigned int flen) { if (filter == NULL) return false; if (flen == 0 || flen > BPF_MAXINSNS) return false; return true; } /** * bpf_check_classic - verify socket filter code * @filter: filter to verify * @flen: length of filter * * Check the user's filter code. If we let some ugly * filter code slip through kaboom! The filter must contain * no references or jumps that are out of range, no illegal * instructions, and must end with a RET instruction. * * All jumps are forward as they are not signed. * * Returns 0 if the rule set is legal or -EINVAL if not. */ static int bpf_check_classic(const struct sock_filter *filter, unsigned int flen) { bool anc_found; int pc; /* Check the filter code now */ for (pc = 0; pc < flen; pc++) { const struct sock_filter *ftest = &filter[pc]; /* May we actually operate on this code? */ if (!chk_code_allowed(ftest->code)) return -EINVAL; /* Some instructions need special checks */ switch (ftest->code) { case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_MOD | BPF_K: /* Check for division by zero */ if (ftest->k == 0) return -EINVAL; break; case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_K: if (ftest->k >= 32) return -EINVAL; break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: case BPF_STX: /* Check for invalid memory addresses */ if (ftest->k >= BPF_MEMWORDS) return -EINVAL; break; case BPF_JMP | BPF_JA: /* Note, the large ftest->k might cause loops. * Compare this with conditional jumps below, * where offsets are limited. --ANK (981016) */ if (ftest->k >= (unsigned int)(flen - pc - 1)) return -EINVAL; break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: /* Both conditionals must be safe */ if (pc + ftest->jt + 1 >= flen || pc + ftest->jf + 1 >= flen) return -EINVAL; break; case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: anc_found = false; if (bpf_anc_helper(ftest) & BPF_ANC) anc_found = true; /* Ancillary operation unknown or unsupported */ if (anc_found == false && ftest->k >= SKF_AD_OFF) return -EINVAL; } } /* Last instruction must be a RET code */ switch (filter[flen - 1].code) { case BPF_RET | BPF_K: case BPF_RET | BPF_A: return check_load_and_stores(filter, flen); } return -EINVAL; } static int bpf_prog_store_orig_filter(struct bpf_prog *fp, const struct sock_fprog *fprog) { unsigned int fsize = bpf_classic_proglen(fprog); struct sock_fprog_kern *fkprog; fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL); if (!fp->orig_prog) return -ENOMEM; fkprog = fp->orig_prog; fkprog->len = fprog->len; fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL | __GFP_NOWARN); if (!fkprog->filter) { kfree(fp->orig_prog); return -ENOMEM; } return 0; } static void bpf_release_orig_filter(struct bpf_prog *fp) { struct sock_fprog_kern *fprog = fp->orig_prog; if (fprog) { kfree(fprog->filter); kfree(fprog); } } static void __bpf_prog_release(struct bpf_prog *prog) { if (prog->type == BPF_PROG_TYPE_SOCKET_FILTER) { bpf_prog_put(prog); } else { bpf_release_orig_filter(prog); bpf_prog_free(prog); } } static void __sk_filter_release(struct sk_filter *fp) { __bpf_prog_release(fp->prog); kfree(fp); } /** * sk_filter_release_rcu - Release a socket filter by rcu_head * @rcu: rcu_head that contains the sk_filter to free */ static void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); __sk_filter_release(fp); } /** * sk_filter_release - release a socket filter * @fp: filter to remove * * Remove a filter from a socket and release its resources. */ static void sk_filter_release(struct sk_filter *fp) { if (refcount_dec_and_test(&fp->refcnt)) call_rcu(&fp->rcu, sk_filter_release_rcu); } void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) { u32 filter_size = bpf_prog_size(fp->prog->len); atomic_sub(filter_size, &sk->sk_omem_alloc); sk_filter_release(fp); } /* try to charge the socket memory if there is space available * return true on success */ static bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp) { int optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); u32 filter_size = bpf_prog_size(fp->prog->len); /* same check as in sock_kmalloc() */ if (filter_size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + filter_size < optmem_max) { atomic_add(filter_size, &sk->sk_omem_alloc); return true; } return false; } bool sk_filter_charge(struct sock *sk, struct sk_filter *fp) { if (!refcount_inc_not_zero(&fp->refcnt)) return false; if (!__sk_filter_charge(sk, fp)) { sk_filter_release(fp); return false; } return true; } static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) { struct sock_filter *old_prog; struct bpf_prog *old_fp; int err, new_len, old_len = fp->len; bool seen_ld_abs = false; /* We are free to overwrite insns et al right here as it won't be used at * this point in time anymore internally after the migration to the eBPF * instruction representation. */ BUILD_BUG_ON(sizeof(struct sock_filter) != sizeof(struct bpf_insn)); /* Conversion cannot happen on overlapping memory areas, * so we need to keep the user BPF around until the 2nd * pass. At this time, the user BPF is stored in fp->insns. */ old_prog = kmemdup_array(fp->insns, old_len, sizeof(struct sock_filter), GFP_KERNEL | __GFP_NOWARN); if (!old_prog) { err = -ENOMEM; goto out_err; } /* 1st pass: calculate the new program length. */ err = bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs); if (err) goto out_err_free; /* Expand fp for appending the new filter representation. */ old_fp = fp; fp = bpf_prog_realloc(old_fp, bpf_prog_size(new_len), 0); if (!fp) { /* The old_fp is still around in case we couldn't * allocate new memory, so uncharge on that one. */ fp = old_fp; err = -ENOMEM; goto out_err_free; } fp->len = new_len; /* 2nd pass: remap sock_filter insns into bpf_insn insns. */ err = bpf_convert_filter(old_prog, old_len, fp, &new_len, &seen_ld_abs); if (err) /* 2nd bpf_convert_filter() can fail only if it fails * to allocate memory, remapping must succeed. Note, * that at this time old_fp has already been released * by krealloc(). */ goto out_err_free; fp = bpf_prog_select_runtime(fp, &err); if (err) goto out_err_free; kfree(old_prog); return fp; out_err_free: kfree(old_prog); out_err: __bpf_prog_release(fp); return ERR_PTR(err); } static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp, bpf_aux_classic_check_t trans) { int err; fp->bpf_func = NULL; fp->jited = 0; err = bpf_check_classic(fp->insns, fp->len); if (err) { __bpf_prog_release(fp); return ERR_PTR(err); } /* There might be additional checks and transformations * needed on classic filters, f.e. in case of seccomp. */ if (trans) { err = trans(fp->insns, fp->len); if (err) { __bpf_prog_release(fp); return ERR_PTR(err); } } /* Probe if we can JIT compile the filter and if so, do * the compilation of the filter. */ bpf_jit_compile(fp); /* JIT compiler couldn't process this filter, so do the eBPF translation * for the optimized interpreter. */ if (!fp->jited) fp = bpf_migrate_filter(fp); return fp; } /** * bpf_prog_create - create an unattached filter * @pfp: the unattached filter that is created * @fprog: the filter program * * Create a filter independent of any socket. We first run some * sanity checks on it to make sure it does not explode on us later. * If an error occurs or there is insufficient memory for the filter * a negative errno code is returned. On success the return is zero. */ int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return -EINVAL; fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!fp) return -ENOMEM; memcpy(fp->insns, fprog->filter, fsize); fp->len = fprog->len; /* Since unattached filters are not copied back to user * space through sk_get_filter(), we do not need to hold * a copy here, and can spare us the work. */ fp->orig_prog = NULL; /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ fp = bpf_prepare_filter(fp, NULL); if (IS_ERR(fp)) return PTR_ERR(fp); *pfp = fp; return 0; } EXPORT_SYMBOL_GPL(bpf_prog_create); /** * bpf_prog_create_from_user - create an unattached filter from user buffer * @pfp: the unattached filter that is created * @fprog: the filter program * @trans: post-classic verifier transformation handler * @save_orig: save classic BPF program * * This function effectively does the same as bpf_prog_create(), only * that it builds up its insns buffer from user space provided buffer. * It also allows for passing a bpf_aux_classic_check_t handler. */ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *fp; int err; /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return -EINVAL; fp = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!fp) return -ENOMEM; if (copy_from_user(fp->insns, fprog->filter, fsize)) { __bpf_prog_free(fp); return -EFAULT; } fp->len = fprog->len; fp->orig_prog = NULL; if (save_orig) { err = bpf_prog_store_orig_filter(fp, fprog); if (err) { __bpf_prog_free(fp); return -ENOMEM; } } /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ fp = bpf_prepare_filter(fp, trans); if (IS_ERR(fp)) return PTR_ERR(fp); *pfp = fp; return 0; } EXPORT_SYMBOL_GPL(bpf_prog_create_from_user); void bpf_prog_destroy(struct bpf_prog *fp) { __bpf_prog_release(fp); } EXPORT_SYMBOL_GPL(bpf_prog_destroy); static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk) { struct sk_filter *fp, *old_fp; fp = kmalloc(sizeof(*fp), GFP_KERNEL); if (!fp) return -ENOMEM; fp->prog = prog; if (!__sk_filter_charge(sk, fp)) { kfree(fp); return -ENOMEM; } refcount_set(&fp->refcnt, 1); old_fp = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_filter, fp); if (old_fp) sk_filter_uncharge(sk, old_fp); return 0; } static struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk) { unsigned int fsize = bpf_classic_proglen(fprog); struct bpf_prog *prog; int err; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return ERR_PTR(-EPERM); /* Make sure new filter is there and in the right amounts. */ if (!bpf_check_basics_ok(fprog->filter, fprog->len)) return ERR_PTR(-EINVAL); prog = bpf_prog_alloc(bpf_prog_size(fprog->len), 0); if (!prog) return ERR_PTR(-ENOMEM); if (copy_from_user(prog->insns, fprog->filter, fsize)) { __bpf_prog_free(prog); return ERR_PTR(-EFAULT); } prog->len = fprog->len; err = bpf_prog_store_orig_filter(prog, fprog); if (err) { __bpf_prog_free(prog); return ERR_PTR(-ENOMEM); } /* bpf_prepare_filter() already takes care of freeing * memory in case something goes wrong. */ return bpf_prepare_filter(prog, NULL); } /** * sk_attach_filter - attach a socket filter * @fprog: the filter program * @sk: the socket to use * * Attach the user's filter code. We first run some sanity checks on * it to make sure it does not explode on us later. If an error * occurs or there is insufficient memory for the filter a negative * errno code is returned. On success the return is zero. */ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct bpf_prog *prog = __get_filter(fprog, sk); int err; if (IS_ERR(prog)) return PTR_ERR(prog); err = __sk_attach_prog(prog, sk); if (err < 0) { __bpf_prog_release(prog); return err; } return 0; } EXPORT_SYMBOL_GPL(sk_attach_filter); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk) { struct bpf_prog *prog = __get_filter(fprog, sk); int err, optmem_max; if (IS_ERR(prog)) return PTR_ERR(prog); optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); if (bpf_prog_size(prog->len) > optmem_max) err = -ENOMEM; else err = reuseport_attach_prog(sk, prog); if (err) __bpf_prog_release(prog); return err; } static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk) { if (sock_flag(sk, SOCK_FILTER_LOCKED)) return ERR_PTR(-EPERM); return bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); } int sk_attach_bpf(u32 ufd, struct sock *sk) { struct bpf_prog *prog = __get_bpf(ufd, sk); int err; if (IS_ERR(prog)) return PTR_ERR(prog); err = __sk_attach_prog(prog, sk); if (err < 0) { bpf_prog_put(prog); return err; } return 0; } int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk) { struct bpf_prog *prog; int err, optmem_max; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER); if (PTR_ERR(prog) == -EINVAL) prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SK_REUSEPORT); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) { /* Like other non BPF_PROG_TYPE_SOCKET_FILTER * bpf prog (e.g. sockmap). It depends on the * limitation imposed by bpf_prog_load(). * Hence, sysctl_optmem_max is not checked. */ if ((sk->sk_type != SOCK_STREAM && sk->sk_type != SOCK_DGRAM) || (sk->sk_protocol != IPPROTO_UDP && sk->sk_protocol != IPPROTO_TCP) || (sk->sk_family != AF_INET && sk->sk_family != AF_INET6)) { err = -ENOTSUPP; goto err_prog_put; } } else { /* BPF_PROG_TYPE_SOCKET_FILTER */ optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); if (bpf_prog_size(prog->len) > optmem_max) { err = -ENOMEM; goto err_prog_put; } } err = reuseport_attach_prog(sk, prog); err_prog_put: if (err) bpf_prog_put(prog); return err; } void sk_reuseport_prog_free(struct bpf_prog *prog) { if (!prog) return; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) bpf_prog_put(prog); else bpf_prog_destroy(prog); } static inline int __bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { #ifdef CONFIG_DEBUG_NET /* Avoid a splat in pskb_may_pull_reason() */ if (write_len > INT_MAX) return -EINVAL; #endif return skb_ensure_writable(skb, write_len); } static inline int bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { int err = __bpf_try_make_writable(skb, write_len); bpf_compute_data_pointers(skb); return err; } static int bpf_try_make_head_writable(struct sk_buff *skb) { return bpf_try_make_writable(skb, skb_headlen(skb)); } static inline void bpf_push_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len); } static inline void bpf_pull_mac_rcsum(struct sk_buff *skb) { if (skb_at_tc_ingress(skb)) skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len); } BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len, u64, flags) { void *ptr; if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; if (unlikely(offset > INT_MAX)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; ptr = skb->data + offset; if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpull_rcsum(skb, ptr, len, offset); memcpy(ptr, from, len); if (flags & BPF_F_RECOMPUTE_CSUM) __skb_postpush_rcsum(skb, ptr, len, offset); if (flags & BPF_F_INVALIDATE_HASH) skb_clear_hash(skb); return 0; } static const struct bpf_func_proto bpf_skb_store_bytes_proto = { .func = bpf_skb_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) { return ____bpf_skb_store_bytes(skb, offset, from, len, flags); } BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset, void *, to, u32, len) { void *ptr; if (unlikely(offset > INT_MAX)) goto err_clear; ptr = skb_header_pointer(skb, offset, len, to); if (unlikely(!ptr)) goto err_clear; if (ptr != to) memcpy(to, ptr, len); return 0; err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .func = bpf_skb_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) { return ____bpf_skb_load_bytes(skb, offset, to, len); } BPF_CALL_4(bpf_flow_dissector_load_bytes, const struct bpf_flow_dissector *, ctx, u32, offset, void *, to, u32, len) { void *ptr; if (unlikely(offset > 0xffff)) goto err_clear; if (unlikely(!ctx->skb)) goto err_clear; ptr = skb_header_pointer(ctx->skb, offset, len, to); if (unlikely(!ptr)) goto err_clear; if (ptr != to) memcpy(to, ptr, len); return 0; err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_flow_dissector_load_bytes_proto = { .func = bpf_flow_dissector_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { u8 *end = skb_tail_pointer(skb); u8 *start, *ptr; if (unlikely(offset > 0xffff)) goto err_clear; switch (start_header) { case BPF_HDR_START_MAC: if (unlikely(!skb_mac_header_was_set(skb))) goto err_clear; start = skb_mac_header(skb); break; case BPF_HDR_START_NET: start = skb_network_header(skb); break; default: goto err_clear; } ptr = start + offset; if (likely(ptr + len <= end)) { memcpy(to, ptr, len); return 0; } err_clear: memset(to, 0, len); return -EFAULT; } static const struct bpf_func_proto bpf_skb_load_bytes_relative_proto = { .func = bpf_skb_load_bytes_relative, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len) { /* Idea is the following: should the needed direct read/write * test fail during runtime, we can pull in more data and redo * again, since implicitly, we invalidate previous checks here. * * Or, since we know how much we need to make read/writeable, * this can be done once at the program beginning for direct * access case. By this we overcome limitations of only current * headroom being accessible. */ return bpf_try_make_writable(skb, len ? : skb_headlen(skb)); } static const struct bpf_func_proto bpf_skb_pull_data_proto = { .func = bpf_skb_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_fullsock, struct sock *, sk) { return sk_fullsock(sk) ? (unsigned long)sk : (unsigned long)NULL; } static const struct bpf_func_proto bpf_sk_fullsock_proto = { .func = bpf_sk_fullsock, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; static inline int sk_skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return __bpf_try_make_writable(skb, write_len); } BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) { /* Idea is the following: should the needed direct read/write * test fail during runtime, we can pull in more data and redo * again, since implicitly, we invalidate previous checks here. * * Or, since we know how much we need to make read/writeable, * this can be done once at the program beginning for direct * access case. By this we overcome limitations of only current * headroom being accessible. */ return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb)); } static const struct bpf_func_proto sk_skb_pull_data_proto = { .func = sk_skb_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { __sum16 *ptr; if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; ptr = (__sum16 *)(skb->data + offset); switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) return -EINVAL; csum_replace_by_diff(ptr, to); break; case 2: csum_replace2(ptr, from, to); break; case 4: csum_replace4(ptr, from, to); break; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_l3_csum_replace_proto = { .func = bpf_l3_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_l4_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; bool do_mforce = flags & BPF_F_MARK_ENFORCE; bool is_ipv6 = flags & BPF_F_IPV6; __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_MARK_ENFORCE | BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK | BPF_F_IPV6))) return -EINVAL; if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; ptr = (__sum16 *)(skb->data + offset); if (is_mmzero && !do_mforce && !*ptr) return 0; switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) return -EINVAL; inet_proto_csum_replace_by_diff(ptr, skb, to, is_pseudo, is_ipv6); break; case 2: inet_proto_csum_replace2(ptr, skb, from, to, is_pseudo); break; case 4: inet_proto_csum_replace4(ptr, skb, from, to, is_pseudo); break; default: return -EINVAL; } if (is_mmzero && !*ptr) *ptr = CSUM_MANGLED_0; return 0; } static const struct bpf_func_proto bpf_l4_csum_replace_proto = { .func = bpf_l4_csum_replace, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, __be32 *, to, u32, to_size, __wsum, seed) { /* This is quite flexible, some examples: * * from_size == 0, to_size > 0, seed := csum --> pushing data * from_size > 0, to_size == 0, seed := csum --> pulling data * from_size > 0, to_size > 0, seed := 0 --> diffing data * * Even for diffing, from_size and to_size don't need to be equal. */ __wsum ret = seed; if (from_size && to_size) ret = csum_sub(csum_partial(to, to_size, ret), csum_partial(from, from_size, 0)); else if (to_size) ret = csum_partial(to, to_size, ret); else if (from_size) ret = ~csum_partial(from, from_size, ~ret); return csum_from32to16((__force unsigned int)ret); } static const struct bpf_func_proto bpf_csum_diff_proto = { .func = bpf_csum_diff, .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, .arg5_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_csum_update, struct sk_buff *, skb, __wsum, csum) { /* The interface is to be used in combination with bpf_csum_diff() * for direct packet writes. csum rotation for alignment as well * as emulating csum_sub() can be done from the eBPF program. */ if (skb->ip_summed == CHECKSUM_COMPLETE) return (skb->csum = csum_add(skb->csum, csum)); return -ENOTSUPP; } static const struct bpf_func_proto bpf_csum_update_proto = { .func = bpf_csum_update, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_csum_level, struct sk_buff *, skb, u64, level) { /* The interface is to be used in combination with bpf_skb_adjust_room() * for encap/decap of packet headers when BPF_F_ADJ_ROOM_NO_CSUM_RESET * is passed as flags, for example. */ switch (level) { case BPF_CSUM_LEVEL_INC: __skb_incr_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_DEC: __skb_decr_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_RESET: __skb_reset_checksum_unnecessary(skb); break; case BPF_CSUM_LEVEL_QUERY: return skb->ip_summed == CHECKSUM_UNNECESSARY ? skb->csum_level : -EACCES; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_csum_level_proto = { .func = bpf_csum_level, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { return dev_forward_skb_nomtu(dev, skb); } static inline int __bpf_rx_skb_no_mac(struct net_device *dev, struct sk_buff *skb) { int ret = ____dev_forward_skb(dev, skb, false); if (likely(!ret)) { skb->dev = dev; ret = netif_rx(skb); } return ret; } static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) { int ret; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); kfree_skb(skb); return -ENETDOWN; } skb->dev = dev; skb_set_redirected_noclear(skb, skb_at_tc_ingress(skb)); skb_clear_tstamp(skb); dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); dev_xmit_recursion_dec(); return ret; } static int __bpf_redirect_no_mac(struct sk_buff *skb, struct net_device *dev, u32 flags) { unsigned int mlen = skb_network_offset(skb); if (unlikely(skb->len <= mlen)) { kfree_skb(skb); return -ERANGE; } if (mlen) { __skb_pull(skb, mlen); /* At ingress, the mac header has already been pulled once. * At egress, skb_pospull_rcsum has to be done in case that * the skb is originated from ingress (i.e. a forwarded skb) * to ensure that rcsum starts at net header. */ if (!skb_at_tc_ingress(skb)) skb_postpull_rcsum(skb, skb_mac_header(skb), mlen); } skb_pop_mac_header(skb); skb_reset_mac_len(skb); return flags & BPF_F_INGRESS ? __bpf_rx_skb_no_mac(dev, skb) : __bpf_tx_skb(dev, skb); } static int __bpf_redirect_common(struct sk_buff *skb, struct net_device *dev, u32 flags) { /* Verify that a link layer header is carried */ if (unlikely(skb->mac_header >= skb->network_header || skb->len == 0)) { kfree_skb(skb); return -ERANGE; } bpf_push_mac_rcsum(skb); return flags & BPF_F_INGRESS ? __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); } static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev, u32 flags) { if (dev_is_mac_header_xmit(dev)) return __bpf_redirect_common(skb, dev, flags); else return __bpf_redirect_no_mac(skb, dev, flags); } #if IS_ENABLED(CONFIG_IPV6) static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { u32 hh_len = LL_RESERVED_SPACE(dev); const struct in6_addr *nexthop; struct dst_entry *dst = NULL; struct neighbour *neigh; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); goto out_drop; } skb->dev = dev; skb_clear_tstamp(skb); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } rcu_read_lock(); if (!nh) { dst = skb_dst(skb); nexthop = rt6_nexthop(dst_rt6_info(dst), &ipv6_hdr(skb)->daddr); } else { nexthop = &nh->ipv6_nh; } neigh = ip_neigh_gw6(dev, nexthop); if (likely(!IS_ERR(neigh))) { int ret; sock_confirm_neigh(skb, neigh); local_bh_disable(); dev_xmit_recursion_inc(); ret = neigh_output(neigh, skb, false); dev_xmit_recursion_dec(); local_bh_enable(); rcu_read_unlock(); return ret; } rcu_read_unlock(); if (dst) IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); out_drop: kfree_skb(skb); return -ENETDOWN; } static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct net *net = dev_net(dev); int err, ret = NET_XMIT_DROP; if (!nh) { struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_flags = FLOWI_FLAG_ANYSRC, .flowi6_mark = skb->mark, .flowlabel = ip6_flowinfo(ip6h), .flowi6_oif = dev->ifindex, .flowi6_proto = ip6h->nexthdr, .daddr = ip6h->daddr, .saddr = ip6h->saddr, }; dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); if (IS_ERR(dst)) goto out_drop; skb_dst_drop(skb); skb_dst_set(skb, dst); } else if (nh->nh_family != AF_INET6) { goto out_drop; } err = bpf_out_neigh_v6(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out_xmit: return ret; } #else static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { kfree_skb(skb); return NET_XMIT_DROP; } #endif /* CONFIG_IPV6 */ #if IS_ENABLED(CONFIG_INET) static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { u32 hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; bool is_v6gw = false; if (dev_xmit_recursion()) { net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); goto out_drop; } skb->dev = dev; skb_clear_tstamp(skb); if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { skb = skb_expand_head(skb, hh_len); if (!skb) return -ENOMEM; } rcu_read_lock(); if (!nh) { struct rtable *rt = skb_rtable(skb); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); } else if (nh->nh_family == AF_INET6) { neigh = ip_neigh_gw6(dev, &nh->ipv6_nh); is_v6gw = true; } else if (nh->nh_family == AF_INET) { neigh = ip_neigh_gw4(dev, nh->ipv4_nh); } else { rcu_read_unlock(); goto out_drop; } if (likely(!IS_ERR(neigh))) { int ret; sock_confirm_neigh(skb, neigh); local_bh_disable(); dev_xmit_recursion_inc(); ret = neigh_output(neigh, skb, is_v6gw); dev_xmit_recursion_dec(); local_bh_enable(); rcu_read_unlock(); return ret; } rcu_read_unlock(); out_drop: kfree_skb(skb); return -ENETDOWN; } static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { const struct iphdr *ip4h = ip_hdr(skb); struct net *net = dev_net(dev); int err, ret = NET_XMIT_DROP; if (!nh) { struct flowi4 fl4 = { .flowi4_flags = FLOWI_FLAG_ANYSRC, .flowi4_mark = skb->mark, .flowi4_dscp = ip4h_dscp(ip4h), .flowi4_oif = dev->ifindex, .flowi4_proto = ip4h->protocol, .daddr = ip4h->daddr, .saddr = ip4h->saddr, }; struct rtable *rt; rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto out_drop; if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { ip_rt_put(rt); goto out_drop; } skb_dst_drop(skb); skb_dst_set(skb, &rt->dst); } err = bpf_out_neigh_v4(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out_xmit: return ret; } #else static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { kfree_skb(skb); return NET_XMIT_DROP; } #endif /* CONFIG_INET */ static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev, struct bpf_nh_params *nh) { struct ethhdr *ethh = eth_hdr(skb); if (unlikely(skb->mac_header >= skb->network_header)) goto out; bpf_push_mac_rcsum(skb); if (is_multicast_ether_addr(ethh->h_dest)) goto out; skb_pull(skb, sizeof(*ethh)); skb_unset_mac_header(skb); skb_reset_network_header(skb); if (skb->protocol == htons(ETH_P_IP)) return __bpf_redirect_neigh_v4(skb, dev, nh); else if (skb->protocol == htons(ETH_P_IPV6)) return __bpf_redirect_neigh_v6(skb, dev, nh); out: kfree_skb(skb); return -ENOTSUPP; } /* Internal, non-exposed redirect flags. */ enum { BPF_F_NEIGH = (1ULL << 16), BPF_F_PEER = (1ULL << 17), BPF_F_NEXTHOP = (1ULL << 18), #define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP) }; BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { struct net_device *dev; struct sk_buff *clone; int ret; BUILD_BUG_ON(BPF_F_REDIRECT_INTERNAL & BPF_F_REDIRECT_FLAGS); if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return -EINVAL; dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); if (unlikely(!dev)) return -EINVAL; clone = skb_clone(skb, GFP_ATOMIC); if (unlikely(!clone)) return -ENOMEM; /* For direct write, we need to keep the invariant that the skbs * we're dealing with need to be uncloned. Should uncloning fail * here, we need to free the just generated clone to unclone once * again. */ ret = bpf_try_make_head_writable(skb); if (unlikely(ret)) { kfree_skb(clone); return -ENOMEM; } return __bpf_redirect(clone, dev, flags); } static const struct bpf_func_proto bpf_clone_redirect_proto = { .func = bpf_clone_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static struct net_device *skb_get_peer_dev(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; if (likely(ops->ndo_get_peer_dev)) return INDIRECT_CALL_1(ops->ndo_get_peer_dev, netkit_peer_dev, dev); return NULL; } int skb_do_redirect(struct sk_buff *skb) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct net *net = dev_net(skb->dev); struct net_device *dev; u32 flags = ri->flags; dev = dev_get_by_index_rcu(net, ri->tgt_index); ri->tgt_index = 0; ri->flags = 0; if (unlikely(!dev)) goto out_drop; if (flags & BPF_F_PEER) { if (unlikely(!skb_at_tc_ingress(skb))) goto out_drop; dev = skb_get_peer_dev(dev); if (unlikely(!dev || !(dev->flags & IFF_UP) || net_eq(net, dev_net(dev)))) goto out_drop; skb->dev = dev; dev_sw_netstats_rx_add(dev, skb->len); skb_scrub_packet(skb, false); return -EAGAIN; } return flags & BPF_F_NEIGH ? __bpf_redirect_neigh(skb, dev, flags & BPF_F_NEXTHOP ? &ri->nh : NULL) : __bpf_redirect(skb, dev, flags); out_drop: kfree_skb(skb); return -EINVAL; } BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return TC_ACT_SHOT; ri->flags = flags; ri->tgt_index = ifindex; return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_proto = { .func = bpf_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags)) return TC_ACT_SHOT; ri->flags = BPF_F_PEER; ri->tgt_index = ifindex; return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_peer_proto = { .func = bpf_redirect_peer, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params, int, plen, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely((plen && plen < sizeof(*params)) || flags)) return TC_ACT_SHOT; ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0); ri->tgt_index = ifindex; BUILD_BUG_ON(sizeof(struct bpf_redir_neigh) != sizeof(struct bpf_nh_params)); if (plen) memcpy(&ri->nh, params, sizeof(ri->nh)); return TC_ACT_REDIRECT; } static const struct bpf_func_proto bpf_redirect_neigh_proto = { .func = bpf_redirect_neigh, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes) { msg->apply_bytes = bytes; return 0; } static const struct bpf_func_proto bpf_msg_apply_bytes_proto = { .func = bpf_msg_apply_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes) { msg->cork_bytes = bytes; return 0; } static void sk_msg_reset_curr(struct sk_msg *msg) { if (!msg->sg.size) { msg->sg.curr = msg->sg.start; msg->sg.copybreak = 0; } else { u32 i = msg->sg.end; sk_msg_iter_var_prev(i); msg->sg.curr = i; msg->sg.copybreak = msg->sg.data[i].length; } } static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { .func = bpf_msg_cork_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, u32, end, u64, flags) { u32 len = 0, offset = 0, copy = 0, poffset = 0, bytes = end - start; u32 first_sge, last_sge, i, shift, bytes_sg_total; struct scatterlist *sge; u8 *raw, *to, *from; struct page *page; if (unlikely(flags || end <= start)) return -EINVAL; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += len; len = sk_msg_elem(msg, i)->length; if (start < offset + len) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); if (unlikely(start >= offset + len)) return -EINVAL; first_sge = i; /* The start may point into the sg element so we need to also * account for the headroom. */ bytes_sg_total = start - offset + bytes; if (!test_bit(i, msg->sg.copy) && bytes_sg_total <= len) goto out; /* At this point we need to linearize multiple scatterlist * elements or a single shared page. Either way we need to * copy into a linear buffer exclusively owned by BPF. Then * place the buffer in the scatterlist and fixup the original * entries by removing the entries now in the linear buffer * and shifting the remaining entries. For now we do not try * to copy partial entries to avoid complexity of running out * of sg_entry slots. The downside is reading a single byte * will copy the entire sg entry. */ do { copy += sk_msg_elem(msg, i)->length; sk_msg_iter_var_next(i); if (bytes_sg_total <= copy) break; } while (i != msg->sg.end); last_sge = i; if (unlikely(bytes_sg_total > copy)) return -EINVAL; page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, get_order(copy)); if (unlikely(!page)) return -ENOMEM; raw = page_address(page); i = first_sge; do { sge = sk_msg_elem(msg, i); from = sg_virt(sge); len = sge->length; to = raw + poffset; memcpy(to, from, len); poffset += len; sge->length = 0; put_page(sg_page(sge)); sk_msg_iter_var_next(i); } while (i != last_sge); sg_set_page(&msg->sg.data[first_sge], page, copy, 0); /* To repair sg ring we need to shift entries. If we only * had a single entry though we can just replace it and * be done. Otherwise walk the ring and shift the entries. */ WARN_ON_ONCE(last_sge == first_sge); shift = last_sge > first_sge ? last_sge - first_sge - 1 : NR_MSG_FRAG_IDS - first_sge + last_sge - 1; if (!shift) goto out; i = first_sge; sk_msg_iter_var_next(i); do { u32 move_from; if (i + shift >= NR_MSG_FRAG_IDS) move_from = i + shift - NR_MSG_FRAG_IDS; else move_from = i + shift; if (move_from == msg->sg.end) break; msg->sg.data[i] = msg->sg.data[move_from]; msg->sg.data[move_from].length = 0; msg->sg.data[move_from].page_link = 0; msg->sg.data[move_from].offset = 0; sk_msg_iter_var_next(i); } while (1); msg->sg.end = msg->sg.end - shift > msg->sg.end ? msg->sg.end - shift + NR_MSG_FRAG_IDS : msg->sg.end - shift; out: sk_msg_reset_curr(msg); msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset; msg->data_end = msg->data + bytes; return 0; } static const struct bpf_func_proto bpf_msg_pull_data_proto = { .func = bpf_msg_pull_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) { struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge; u32 new, i = 0, l = 0, space, copy = 0, offset = 0; u8 *raw, *to, *from; struct page *page; if (unlikely(flags)) return -EINVAL; if (unlikely(len == 0)) return 0; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += l; l = sk_msg_elem(msg, i)->length; if (start < offset + l) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); if (start > offset + l) return -EINVAL; space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); /* If no space available will fallback to copy, we need at * least one scatterlist elem available to push data into * when start aligns to the beginning of an element or two * when it falls inside an element. We handle the start equals * offset case because its the common case for inserting a * header. */ if (!space || (space == 1 && start != offset)) copy = msg->sg.data[i].length; page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, get_order(copy + len)); if (unlikely(!page)) return -ENOMEM; if (copy) { int front, back; raw = page_address(page); if (i == msg->sg.end) sk_msg_iter_var_prev(i); psge = sk_msg_elem(msg, i); front = start - offset; back = psge->length - front; from = sg_virt(psge); if (front) memcpy(raw, from, front); if (back) { from += front; to = raw + front + len; memcpy(to, from, back); } put_page(sg_page(psge)); new = i; goto place_new; } if (start - offset) { if (i == msg->sg.end) sk_msg_iter_var_prev(i); psge = sk_msg_elem(msg, i); rsge = sk_msg_elem_cpy(msg, i); psge->length = start - offset; rsge.length -= psge->length; rsge.offset += start; sk_msg_iter_var_next(i); sg_unmark_end(psge); sg_unmark_end(&rsge); } /* Slot(s) to place newly allocated data */ sk_msg_iter_next(msg, end); new = i; sk_msg_iter_var_next(i); if (i == msg->sg.end) { if (!rsge.length) goto place_new; sk_msg_iter_next(msg, end); goto place_new; } /* Shift one or two slots as needed */ sge = sk_msg_elem_cpy(msg, new); sg_unmark_end(&sge); nsge = sk_msg_elem_cpy(msg, i); if (rsge.length) { sk_msg_iter_var_next(i); nnsge = sk_msg_elem_cpy(msg, i); sk_msg_iter_next(msg, end); } while (i != msg->sg.end) { msg->sg.data[i] = sge; sge = nsge; sk_msg_iter_var_next(i); if (rsge.length) { nsge = nnsge; nnsge = sk_msg_elem_cpy(msg, i); } else { nsge = sk_msg_elem_cpy(msg, i); } } place_new: /* Place newly allocated data buffer */ sk_mem_charge(msg->sk, len); msg->sg.size += len; __clear_bit(new, msg->sg.copy); sg_set_page(&msg->sg.data[new], page, len + copy, 0); if (rsge.length) { get_page(sg_page(&rsge)); sk_msg_iter_var_next(new); msg->sg.data[new] = rsge; } sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } static const struct bpf_func_proto bpf_msg_push_data_proto = { .func = bpf_msg_push_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; static void sk_msg_shift_left(struct sk_msg *msg, int i) { struct scatterlist *sge = sk_msg_elem(msg, i); int prev; put_page(sg_page(sge)); do { prev = i; sk_msg_iter_var_next(i); msg->sg.data[prev] = msg->sg.data[i]; } while (i != msg->sg.end); sk_msg_iter_prev(msg, end); } static void sk_msg_shift_right(struct sk_msg *msg, int i) { struct scatterlist tmp, sge; sk_msg_iter_next(msg, end); sge = sk_msg_elem_cpy(msg, i); sk_msg_iter_var_next(i); tmp = sk_msg_elem_cpy(msg, i); while (i != msg->sg.end) { msg->sg.data[i] = sge; sk_msg_iter_var_next(i); sge = tmp; tmp = sk_msg_elem_cpy(msg, i); } } BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) { u32 i = 0, l = 0, space, offset = 0; u64 last = start + len; int pop; if (unlikely(flags)) return -EINVAL; if (unlikely(len == 0)) return 0; /* First find the starting scatterlist element */ i = msg->sg.start; do { offset += l; l = sk_msg_elem(msg, i)->length; if (start < offset + l) break; sk_msg_iter_var_next(i); } while (i != msg->sg.end); /* Bounds checks: start and pop must be inside message */ if (start >= offset + l || last > msg->sg.size) return -EINVAL; space = MAX_MSG_FRAGS - sk_msg_elem_used(msg); pop = len; /* --------------| offset * -| start |-------- len -------| * * |----- a ----|-------- pop -------|----- b ----| * |______________________________________________| length * * * a: region at front of scatter element to save * b: region at back of scatter element to save when length > A + pop * pop: region to pop from element, same as input 'pop' here will be * decremented below per iteration. * * Two top-level cases to handle when start != offset, first B is non * zero and second B is zero corresponding to when a pop includes more * than one element. * * Then if B is non-zero AND there is no space allocate space and * compact A, B regions into page. If there is space shift ring to * the right free'ing the next element in ring to place B, leaving * A untouched except to reduce length. */ if (start != offset) { struct scatterlist *nsge, *sge = sk_msg_elem(msg, i); int a = start - offset; int b = sge->length - pop - a; sk_msg_iter_var_next(i); if (b > 0) { if (space) { sge->length = a; sk_msg_shift_right(msg, i); nsge = sk_msg_elem(msg, i); get_page(sg_page(sge)); sg_set_page(nsge, sg_page(sge), b, sge->offset + pop + a); } else { struct page *page, *orig; u8 *to, *from; page = alloc_pages(__GFP_NOWARN | __GFP_COMP | GFP_ATOMIC, get_order(a + b)); if (unlikely(!page)) return -ENOMEM; orig = sg_page(sge); from = sg_virt(sge); to = page_address(page); memcpy(to, from, a); memcpy(to + a, from + a + pop, b); sg_set_page(sge, page, a + b, 0); put_page(orig); } pop = 0; } else { pop -= (sge->length - a); sge->length = a; } } /* From above the current layout _must_ be as follows, * * -| offset * -| start * * |---- pop ---|---------------- b ------------| * |____________________________________________| length * * Offset and start of the current msg elem are equal because in the * previous case we handled offset != start and either consumed the * entire element and advanced to the next element OR pop == 0. * * Two cases to handle here are first pop is less than the length * leaving some remainder b above. Simply adjust the element's layout * in this case. Or pop >= length of the element so that b = 0. In this * case advance to next element decrementing pop. */ while (pop) { struct scatterlist *sge = sk_msg_elem(msg, i); if (pop < sge->length) { sge->length -= pop; sge->offset += pop; pop = 0; } else { pop -= sge->length; sk_msg_shift_left(msg, i); } } sk_mem_uncharge(msg->sk, len - pop); msg->sg.size -= (len - pop); sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } static const struct bpf_func_proto bpf_msg_pop_data_proto = { .func = bpf_msg_pop_data, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; #ifdef CONFIG_CGROUP_NET_CLASSID BPF_CALL_0(bpf_get_cgroup_classid_curr) { return __task_get_classid(current); } const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = { .func = bpf_get_cgroup_classid_curr, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_1(bpf_skb_cgroup_classid, const struct sk_buff *, skb) { struct sock *sk = skb_to_full_sk(skb); if (!sk || !sk_fullsock(sk)) return 0; return sock_cgroup_classid(&sk->sk_cgrp_data); } static const struct bpf_func_proto bpf_skb_cgroup_classid_proto = { .func = bpf_skb_cgroup_classid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; #endif BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) { return task_get_classid(skb); } static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { .func = bpf_get_cgroup_classid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_route_realm, const struct sk_buff *, skb) { return dst_tclassid(skb); } static const struct bpf_func_proto bpf_get_route_realm_proto = { .func = bpf_get_route_realm, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_hash_recalc, struct sk_buff *, skb) { /* If skb_clear_hash() was called due to mangling, we can * trigger SW recalculation here. Later access to hash * can then use the inline skb->hash via context directly * instead of calling this helper again. */ return skb_get_hash(skb); } static const struct bpf_func_proto bpf_get_hash_recalc_proto = { .func = bpf_get_hash_recalc, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_set_hash_invalid, struct sk_buff *, skb) { /* After all direct packet write, this can be used once for * triggering a lazy recalc on next skb_get_hash() invocation. */ skb_clear_hash(skb); return 0; } static const struct bpf_func_proto bpf_set_hash_invalid_proto = { .func = bpf_set_hash_invalid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_2(bpf_set_hash, struct sk_buff *, skb, u32, hash) { /* Set user specified hash as L4(+), so that it gets returned * on skb_get_hash() call unless BPF prog later on triggers a * skb_clear_hash(). */ __skb_set_sw_hash(skb, hash, true); return 0; } static const struct bpf_func_proto bpf_set_hash_proto = { .func = bpf_set_hash, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, u16, vlan_tci) { int ret; if (unlikely(vlan_proto != htons(ETH_P_8021Q) && vlan_proto != htons(ETH_P_8021AD))) vlan_proto = htons(ETH_P_8021Q); bpf_push_mac_rcsum(skb); ret = skb_vlan_push(skb, vlan_proto, vlan_tci); bpf_pull_mac_rcsum(skb); skb_reset_mac_len(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_vlan_push_proto = { .func = bpf_skb_vlan_push, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) { int ret; bpf_push_mac_rcsum(skb); ret = skb_vlan_pop(skb); bpf_pull_mac_rcsum(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_vlan_pop_proto = { .func = bpf_skb_vlan_pop, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static void bpf_skb_change_protocol(struct sk_buff *skb, u16 proto) { skb->protocol = htons(proto); if (skb_valid_dst(skb)) skb_dst_drop(skb); } static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len) { /* Caller already did skb_cow() with len as headroom, * so no need to do it here. */ skb_push(skb, len); memmove(skb->data, skb->data + len, off); memset(skb->data + off, 0, len); /* No skb_postpush_rcsum(skb, skb->data + off, len) * needed here as it does not change the skb->csum * result for checksum complete when summing over * zeroed blocks. */ return 0; } static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len) { void *old_data; /* skb_ensure_writable() is not needed here, as we're * already working on an uncloned skb. */ if (unlikely(!pskb_may_pull(skb, off + len))) return -ENOMEM; old_data = skb->data; __skb_pull(skb, len); skb_postpull_rcsum(skb, old_data + off, len); memmove(skb->data, old_data, off); return 0; } static int bpf_skb_net_hdr_push(struct sk_buff *skb, u32 off, u32 len) { bool trans_same = skb->transport_header == skb->network_header; int ret; /* There's no need for __skb_push()/__skb_pull() pair to * get to the start of the mac header as we're guaranteed * to always start from here under eBPF. */ ret = bpf_skb_generic_push(skb, off, len); if (likely(!ret)) { skb->mac_header -= len; skb->network_header -= len; if (trans_same) skb->transport_header = skb->network_header; } return ret; } static int bpf_skb_net_hdr_pop(struct sk_buff *skb, u32 off, u32 len) { bool trans_same = skb->transport_header == skb->network_header; int ret; /* Same here, __skb_push()/__skb_pull() pair not needed. */ ret = bpf_skb_generic_pop(skb, off, len); if (likely(!ret)) { skb->mac_header += len; skb->network_header += len; if (trans_same) skb->transport_header = skb->network_header; } return ret; } static int bpf_skb_proto_4_to_6(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); u32 off = skb_mac_header_len(skb); int ret; ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_push(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* SKB_GSO_TCPV4 needs to be changed into SKB_GSO_TCPV6. */ if (shinfo->gso_type & SKB_GSO_TCPV4) { shinfo->gso_type &= ~SKB_GSO_TCPV4; shinfo->gso_type |= SKB_GSO_TCPV6; } } bpf_skb_change_protocol(skb, ETH_P_IPV6); skb_clear_hash(skb); return 0; } static int bpf_skb_proto_6_to_4(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); u32 off = skb_mac_header_len(skb); int ret; ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_pop(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* SKB_GSO_TCPV6 needs to be changed into SKB_GSO_TCPV4. */ if (shinfo->gso_type & SKB_GSO_TCPV6) { shinfo->gso_type &= ~SKB_GSO_TCPV6; shinfo->gso_type |= SKB_GSO_TCPV4; } } bpf_skb_change_protocol(skb, ETH_P_IP); skb_clear_hash(skb); return 0; } static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) { __be16 from_proto = skb->protocol; if (from_proto == htons(ETH_P_IP) && to_proto == htons(ETH_P_IPV6)) return bpf_skb_proto_4_to_6(skb); if (from_proto == htons(ETH_P_IPV6) && to_proto == htons(ETH_P_IP)) return bpf_skb_proto_6_to_4(skb); return -ENOTSUPP; } BPF_CALL_3(bpf_skb_change_proto, struct sk_buff *, skb, __be16, proto, u64, flags) { int ret; if (unlikely(flags)) return -EINVAL; /* General idea is that this helper does the basic groundwork * needed for changing the protocol, and eBPF program fills the * rest through bpf_skb_store_bytes(), bpf_lX_csum_replace() * and other helpers, rather than passing a raw buffer here. * * The rationale is to keep this minimal and without a need to * deal with raw packet data. F.e. even if we would pass buffers * here, the program still needs to call the bpf_lX_csum_replace() * helpers anyway. Plus, this way we keep also separation of * concerns, since f.e. bpf_skb_store_bytes() should only take * care of stores. * * Currently, additional options and extension header space are * not supported, but flags register is reserved so we can adapt * that. For offloads, we mark packet as dodgy, so that headers * need to be verified first. */ ret = bpf_skb_proto_xlat(skb, proto); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_proto_proto = { .func = bpf_skb_change_proto, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_skb_change_type, struct sk_buff *, skb, u32, pkt_type) { /* We only allow a restricted subset to be changed for now. */ if (unlikely(!skb_pkt_type_ok(skb->pkt_type) || !skb_pkt_type_ok(pkt_type))) return -EINVAL; skb->pkt_type = pkt_type; return 0; } static const struct bpf_func_proto bpf_skb_change_type_proto = { .func = bpf_skb_change_type, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; static u32 bpf_skb_net_base_len(const struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_IP): return sizeof(struct iphdr); case htons(ETH_P_IPV6): return sizeof(struct ipv6hdr); default: return ~0U; } } #define BPF_F_ADJ_ROOM_ENCAP_L3_MASK (BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 | \ BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) #define BPF_F_ADJ_ROOM_DECAP_L3_MASK (BPF_F_ADJ_ROOM_DECAP_L3_IPV4 | \ BPF_F_ADJ_ROOM_DECAP_L3_IPV6) #define BPF_F_ADJ_ROOM_MASK (BPF_F_ADJ_ROOM_FIXED_GSO | \ BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \ BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \ BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \ BPF_F_ADJ_ROOM_ENCAP_L2_ETH | \ BPF_F_ADJ_ROOM_ENCAP_L2( \ BPF_ADJ_ROOM_ENCAP_L2_MASK) | \ BPF_F_ADJ_ROOM_DECAP_L3_MASK) static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, u64 flags) { u8 inner_mac_len = flags >> BPF_ADJ_ROOM_ENCAP_L2_SHIFT; bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK; u16 mac_len = 0, inner_net = 0, inner_trans = 0; unsigned int gso_type = SKB_GSO_DODGY; int ret; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) { /* udp gso_size delineates datagrams, only allow if fixed */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) || !(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) return -ENOTSUPP; } ret = skb_cow_head(skb, len_diff); if (unlikely(ret < 0)) return ret; if (encap) { if (skb->protocol != htons(ETH_P_IP) && skb->protocol != htons(ETH_P_IPV6)) return -ENOTSUPP; if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) return -EINVAL; if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE && flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) return -EINVAL; if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH && inner_mac_len < ETH_HLEN) return -EINVAL; if (skb->encapsulation) return -EALREADY; mac_len = skb->network_header - skb->mac_header; inner_net = skb->network_header; if (inner_mac_len > len_diff) return -EINVAL; inner_trans = skb->transport_header; } ret = bpf_skb_net_hdr_push(skb, off, len_diff); if (unlikely(ret < 0)) return ret; if (encap) { skb->inner_mac_header = inner_net - inner_mac_len; skb->inner_network_header = inner_net; skb->inner_transport_header = inner_trans; if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH) skb_set_inner_protocol(skb, htons(ETH_P_TEB)); else skb_set_inner_protocol(skb, skb->protocol); skb->encapsulation = 1; skb_set_network_header(skb, mac_len); if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) gso_type |= SKB_GSO_UDP_TUNNEL; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE) gso_type |= SKB_GSO_GRE; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) gso_type |= SKB_GSO_IPXIP6; else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) gso_type |= SKB_GSO_IPXIP4; if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE || flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) { int nh_len = flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr); skb_set_transport_header(skb, mac_len + nh_len); } /* Match skb->protocol to new outer l3 protocol */ if (skb->protocol == htons(ETH_P_IP) && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) bpf_skb_change_protocol(skb, ETH_P_IPV6); else if (skb->protocol == htons(ETH_P_IPV6) && flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) bpf_skb_change_protocol(skb, ETH_P_IP); } if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= gso_type; shinfo->gso_segs = 0; /* Due to header growth, MSS needs to be downgraded. * There is a BUG_ON() when segmenting the frag_list with * head_frag true, so linearize the skb after downgrading * the MSS. */ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) { skb_decrease_gso_size(shinfo, len_diff); if (shinfo->frag_list) return skb_linearize(skb); } } return 0; } static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff, u64 flags) { int ret; if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_DECAP_L3_MASK | BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) { /* udp gso_size delineates datagrams, only allow if fixed */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) || !(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) return -ENOTSUPP; } ret = skb_unclone(skb, GFP_ATOMIC); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_pop(skb, off, len_diff); if (unlikely(ret < 0)) return ret; /* Match skb->protocol to new outer l3 protocol */ if (skb->protocol == htons(ETH_P_IP) && flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6) bpf_skb_change_protocol(skb, ETH_P_IPV6); else if (skb->protocol == htons(ETH_P_IPV6) && flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4) bpf_skb_change_protocol(skb, ETH_P_IP); if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); /* Due to header shrink, MSS can be upgraded. */ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) skb_increase_gso_size(shinfo, len_diff); /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= SKB_GSO_DODGY; shinfo->gso_segs = 0; } return 0; } #define BPF_SKB_MAX_LEN SKB_MAX_ALLOC BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) { u32 len_diff_abs = abs(len_diff); bool shrink = len_diff < 0; int ret = 0; if (unlikely(flags || mode)) return -EINVAL; if (unlikely(len_diff_abs > 0xfffU)) return -EFAULT; if (!shrink) { ret = skb_cow(skb, len_diff); if (unlikely(ret < 0)) return ret; __skb_push(skb, len_diff_abs); memset(skb->data, 0, len_diff_abs); } else { if (unlikely(!pskb_may_pull(skb, len_diff_abs))) return -ENOMEM; __skb_pull(skb, len_diff_abs); } if (tls_sw_has_ctx_rx(skb->sk)) { struct strp_msg *rxm = strp_msg(skb); rxm->full_len += len_diff; } return ret; } static const struct bpf_func_proto sk_skb_adjust_room_proto = { .func = sk_skb_adjust_room, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) { u32 len_cur, len_diff_abs = abs(len_diff); u32 len_min = bpf_skb_net_base_len(skb); u32 len_max = BPF_SKB_MAX_LEN; __be16 proto = skb->protocol; bool shrink = len_diff < 0; u32 off; int ret; if (unlikely(flags & ~(BPF_F_ADJ_ROOM_MASK | BPF_F_ADJ_ROOM_NO_CSUM_RESET))) return -EINVAL; if (unlikely(len_diff_abs > 0xfffU)) return -EFAULT; if (unlikely(proto != htons(ETH_P_IP) && proto != htons(ETH_P_IPV6))) return -ENOTSUPP; off = skb_mac_header_len(skb); switch (mode) { case BPF_ADJ_ROOM_NET: off += bpf_skb_net_base_len(skb); break; case BPF_ADJ_ROOM_MAC: break; default: return -ENOTSUPP; } if (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) { if (!shrink) return -EINVAL; switch (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) { case BPF_F_ADJ_ROOM_DECAP_L3_IPV4: len_min = sizeof(struct iphdr); break; case BPF_F_ADJ_ROOM_DECAP_L3_IPV6: len_min = sizeof(struct ipv6hdr); break; default: return -EINVAL; } } len_cur = skb->len - skb_network_offset(skb); if ((shrink && (len_diff_abs >= len_cur || len_cur - len_diff_abs < len_min)) || (!shrink && (skb->len + len_diff_abs > len_max && !skb_is_gso(skb)))) return -ENOTSUPP; ret = shrink ? bpf_skb_net_shrink(skb, off, len_diff_abs, flags) : bpf_skb_net_grow(skb, off, len_diff_abs, flags); if (!ret && !(flags & BPF_F_ADJ_ROOM_NO_CSUM_RESET)) __skb_reset_checksum_unnecessary(skb); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_adjust_room_proto = { .func = bpf_skb_adjust_room, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; static u32 __bpf_skb_min_len(const struct sk_buff *skb) { int offset = skb_network_offset(skb); u32 min_len = 0; if (offset > 0) min_len = offset; if (skb_transport_header_was_set(skb)) { offset = skb_transport_offset(skb); if (offset > 0) min_len = offset; } if (skb->ip_summed == CHECKSUM_PARTIAL) { offset = skb_checksum_start_offset(skb) + skb->csum_offset + sizeof(__sum16); if (offset > 0) min_len = offset; } return min_len; } static int bpf_skb_grow_rcsum(struct sk_buff *skb, unsigned int new_len) { unsigned int old_len = skb->len; int ret; ret = __skb_grow_rcsum(skb, new_len); if (!ret) memset(skb->data + old_len, 0, new_len - old_len); return ret; } static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) { return __skb_trim_rcsum(skb, new_len); } static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, u64 flags) { u32 max_len = BPF_SKB_MAX_LEN; u32 min_len = __bpf_skb_min_len(skb); int ret; if (unlikely(flags || new_len > max_len || new_len < min_len)) return -EINVAL; if (skb->encapsulation) return -ENOTSUPP; /* The basic idea of this helper is that it's performing the * needed work to either grow or trim an skb, and eBPF program * rewrites the rest via helpers like bpf_skb_store_bytes(), * bpf_lX_csum_replace() and others rather than passing a raw * buffer here. This one is a slow path helper and intended * for replies with control messages. * * Like in bpf_skb_change_proto(), we want to keep this rather * minimal and without protocol specifics so that we are able * to separate concerns as in bpf_skb_store_bytes() should only * be the one responsible for writing buffers. * * It's really expected to be a slow path operation here for * control message replies, so we're implicitly linearizing, * uncloning and drop offloads from the skb by this. */ ret = __bpf_try_make_writable(skb, skb->len); if (!ret) { if (new_len > skb->len) ret = bpf_skb_grow_rcsum(skb, new_len); else if (new_len < skb->len) ret = bpf_skb_trim_rcsum(skb, new_len); if (!ret && skb_is_gso(skb)) skb_gso_reset(skb); } return ret; } BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { int ret = __bpf_skb_change_tail(skb, new_len, flags); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_tail_proto = { .func = bpf_skb_change_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { return __bpf_skb_change_tail(skb, new_len, flags); } static const struct bpf_func_proto sk_skb_change_tail_proto = { .func = sk_skb_change_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, u64 flags) { u32 max_len = BPF_SKB_MAX_LEN; u32 new_len = skb->len + head_room; int ret; if (unlikely(flags || (!skb_is_gso(skb) && new_len > max_len) || new_len < skb->len)) return -EINVAL; ret = skb_cow(skb, head_room); if (likely(!ret)) { /* Idea for this helper is that we currently only * allow to expand on mac header. This means that * skb->protocol network header, etc, stay as is. * Compared to bpf_skb_change_tail(), we're more * flexible due to not needing to linearize or * reset GSO. Intention for this helper is to be * used by an L3 skb that needs to push mac header * for redirection into L2 device. */ __skb_push(skb, head_room); memset(skb->data, 0, head_room); skb_reset_mac_header(skb); skb_reset_mac_len(skb); } return ret; } BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { int ret = __bpf_skb_change_head(skb, head_room, flags); bpf_compute_data_pointers(skb); return ret; } static const struct bpf_func_proto bpf_skb_change_head_proto = { .func = bpf_skb_change_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, u64, flags) { return __bpf_skb_change_head(skb, head_room, flags); } static const struct bpf_func_proto sk_skb_change_head_proto = { .func = sk_skb_change_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_xdp_get_buff_len, struct xdp_buff*, xdp) { return xdp_get_buff_len(xdp); } static const struct bpf_func_proto bpf_xdp_get_buff_len_proto = { .func = bpf_xdp_get_buff_len, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BTF_ID_LIST_SINGLE(bpf_xdp_get_buff_len_bpf_ids, struct, xdp_buff) const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto = { .func = bpf_xdp_get_buff_len, .gpl_only = false, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_xdp_get_buff_len_bpf_ids[0], }; static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : xdp->data - xdp->data_meta; } BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) { void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); unsigned long metalen = xdp_get_metalen(xdp); void *data_start = xdp_frame_end + metalen; void *data = xdp->data + offset; if (unlikely(data < data_start || data > xdp->data_end - ETH_HLEN)) return -EINVAL; if (metalen) memmove(xdp->data_meta + offset, xdp->data_meta, metalen); xdp->data_meta += offset; xdp->data = data; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .func = bpf_xdp_adjust_head, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush) { unsigned long ptr_len, ptr_off = 0; skb_frag_t *next_frag, *end_frag; struct skb_shared_info *sinfo; void *src, *dst; u8 *ptr_buf; if (likely(xdp->data_end - xdp->data >= off + len)) { src = flush ? buf : xdp->data + off; dst = flush ? xdp->data + off : buf; memcpy(dst, src, len); return; } sinfo = xdp_get_shared_info_from_buff(xdp); end_frag = &sinfo->frags[sinfo->nr_frags]; next_frag = &sinfo->frags[0]; ptr_len = xdp->data_end - xdp->data; ptr_buf = xdp->data; while (true) { if (off < ptr_off + ptr_len) { unsigned long copy_off = off - ptr_off; unsigned long copy_len = min(len, ptr_len - copy_off); src = flush ? buf : ptr_buf + copy_off; dst = flush ? ptr_buf + copy_off : buf; memcpy(dst, src, copy_len); off += copy_len; len -= copy_len; buf += copy_len; } if (!len || next_frag == end_frag) break; ptr_off += ptr_len; ptr_buf = skb_frag_address(next_frag); ptr_len = skb_frag_size(next_frag); next_frag++; } } void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) { u32 size = xdp->data_end - xdp->data; struct skb_shared_info *sinfo; void *addr = xdp->data; int i; if (unlikely(offset > 0xffff || len > 0xffff)) return ERR_PTR(-EFAULT); if (unlikely(offset + len > xdp_get_buff_len(xdp))) return ERR_PTR(-EINVAL); if (likely(offset < size)) /* linear area */ goto out; sinfo = xdp_get_shared_info_from_buff(xdp); offset -= size; for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */ u32 frag_size = skb_frag_size(&sinfo->frags[i]); if (offset < frag_size) { addr = skb_frag_address(&sinfo->frags[i]); size = frag_size; break; } offset -= frag_size; } out: return offset + len <= size ? addr + offset : NULL; } BPF_CALL_4(bpf_xdp_load_bytes, struct xdp_buff *, xdp, u32, offset, void *, buf, u32, len) { void *ptr; ptr = bpf_xdp_pointer(xdp, offset, len); if (IS_ERR(ptr)) return PTR_ERR(ptr); if (!ptr) bpf_xdp_copy_buf(xdp, offset, buf, len, false); else memcpy(buf, ptr, len); return 0; } static const struct bpf_func_proto bpf_xdp_load_bytes_proto = { .func = bpf_xdp_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return ____bpf_xdp_load_bytes(xdp, offset, buf, len); } BPF_CALL_4(bpf_xdp_store_bytes, struct xdp_buff *, xdp, u32, offset, void *, buf, u32, len) { void *ptr; ptr = bpf_xdp_pointer(xdp, offset, len); if (IS_ERR(ptr)) return PTR_ERR(ptr); if (!ptr) bpf_xdp_copy_buf(xdp, offset, buf, len, true); else memcpy(ptr, buf, len); return 0; } static const struct bpf_func_proto bpf_xdp_store_bytes_proto = { .func = bpf_xdp_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return ____bpf_xdp_store_bytes(xdp, offset, buf, len); } static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1]; struct xdp_rxq_info *rxq = xdp->rxq; unsigned int tailroom; if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz) return -EOPNOTSUPP; tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag); if (unlikely(offset > tailroom)) return -EINVAL; memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset); skb_frag_size_add(frag, offset); sinfo->xdp_frags_size += offset; if (rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL) xsk_buff_get_tail(xdp)->data_end += offset; return 0; } static struct xdp_buff *bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink, bool tail, bool release) { struct xdp_buff *zc_frag = tail ? xsk_buff_get_tail(xdp) : xsk_buff_get_head(xdp); if (release) { xsk_buff_del_frag(zc_frag); } else { if (tail) zc_frag->data_end -= shrink; else zc_frag->data += shrink; } return zc_frag; } static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag, int shrink, bool tail) { enum xdp_mem_type mem_type = xdp->rxq->mem.type; bool release = skb_frag_size(frag) == shrink; netmem_ref netmem = skb_frag_netmem(frag); struct xdp_buff *zc_frag = NULL; if (mem_type == MEM_TYPE_XSK_BUFF_POOL) { netmem = 0; zc_frag = bpf_xdp_shrink_data_zc(xdp, shrink, tail, release); } if (release) { __xdp_return(netmem, mem_type, false, zc_frag); } else { if (!tail) skb_frag_off_add(frag, shrink); skb_frag_size_sub(frag, shrink); } return release; } static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); int i, n_frags_free = 0, len_free = 0; if (unlikely(offset > (int)xdp_get_buff_len(xdp) - ETH_HLEN)) return -EINVAL; for (i = sinfo->nr_frags - 1; i >= 0 && offset > 0; i--) { skb_frag_t *frag = &sinfo->frags[i]; int shrink = min_t(int, offset, skb_frag_size(frag)); len_free += shrink; offset -= shrink; if (bpf_xdp_shrink_data(xdp, frag, shrink, true)) n_frags_free++; } sinfo->nr_frags -= n_frags_free; sinfo->xdp_frags_size -= len_free; if (unlikely(!sinfo->nr_frags)) { xdp_buff_clear_frags_flag(xdp); xdp_buff_clear_frag_pfmemalloc(xdp); xdp->data_end -= offset; } return 0; } BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) { void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */ void *data_end = xdp->data_end + offset; if (unlikely(xdp_buff_has_frags(xdp))) { /* non-linear xdp buff */ if (offset < 0) return bpf_xdp_frags_shrink_tail(xdp, -offset); return bpf_xdp_frags_increase_tail(xdp, offset); } /* Notice that xdp_data_hard_end have reserved some tailroom */ if (unlikely(data_end > data_hard_end)) return -EINVAL; if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; /* Clear memory area on grow, can contain uninit kernel memory */ if (offset > 0) memset(xdp->data_end, 0, offset); xdp->data_end = data_end; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_tail_proto = { .func = bpf_xdp_adjust_tail, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) { void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); void *meta = xdp->data_meta + offset; unsigned long metalen = xdp->data - meta; if (xdp_data_meta_unsupported(xdp)) return -ENOTSUPP; if (unlikely(meta < xdp_frame_end || meta > xdp->data)) return -EINVAL; if (unlikely(xdp_metalen_invalid(metalen))) return -EACCES; xdp->data_meta = meta; return 0; } static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { .func = bpf_xdp_adjust_meta, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; /** * DOC: xdp redirect * * XDP_REDIRECT works by a three-step process, implemented in the functions * below: * * 1. The bpf_redirect() and bpf_redirect_map() helpers will lookup the target * of the redirect and store it (along with some other metadata) in a per-CPU * struct bpf_redirect_info. * * 2. When the program returns the XDP_REDIRECT return code, the driver will * call xdp_do_redirect() which will use the information in struct * bpf_redirect_info to actually enqueue the frame into a map type-specific * bulk queue structure. * * 3. Before exiting its NAPI poll loop, the driver will call * xdp_do_flush(), which will flush all the different bulk queues, * thus completing the redirect. Note that xdp_do_flush() must be * called before napi_complete_done() in the driver, as the * XDP_REDIRECT logic relies on being inside a single NAPI instance * through to the xdp_do_flush() call for RCU protection of all * in-kernel data structures. */ /* * Pointers to the map entries will be kept around for this whole sequence of * steps, protected by RCU. However, there is no top-level rcu_read_lock() in * the core code; instead, the RCU protection relies on everything happening * inside a single NAPI poll sequence, which means it's between a pair of calls * to local_bh_disable()/local_bh_enable(). * * The map entries are marked as __rcu and the map code makes sure to * dereference those pointers with rcu_dereference_check() in a way that works * for both sections that to hold an rcu_read_lock() and sections that are * called from NAPI without a separate rcu_read_lock(). The code below does not * use RCU annotations, but relies on those in the map code. */ void xdp_do_flush(void) { struct list_head *lh_map, *lh_dev, *lh_xsk; bpf_net_ctx_get_all_used_flush_lists(&lh_map, &lh_dev, &lh_xsk); if (lh_dev) __dev_flush(lh_dev); if (lh_map) __cpu_map_flush(lh_map); if (lh_xsk) __xsk_map_flush(lh_xsk); } EXPORT_SYMBOL_GPL(xdp_do_flush); #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL) void xdp_do_check_flushed(struct napi_struct *napi) { struct list_head *lh_map, *lh_dev, *lh_xsk; bool missed = false; bpf_net_ctx_get_all_used_flush_lists(&lh_map, &lh_dev, &lh_xsk); if (lh_dev) { __dev_flush(lh_dev); missed = true; } if (lh_map) { __cpu_map_flush(lh_map); missed = true; } if (lh_xsk) { __xsk_map_flush(lh_xsk); missed = true; } WARN_ONCE(missed, "Missing xdp_do_flush() invocation after NAPI by %ps\n", napi->poll); } #endif DEFINE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); EXPORT_SYMBOL_GPL(bpf_master_redirect_enabled_key); u32 xdp_master_redirect(struct xdp_buff *xdp) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct net_device *master, *slave; master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev); slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp); if (slave && slave != xdp->rxq->dev) { /* The target device is different from the receiving device, so * redirect it to the new device. * Using XDP_REDIRECT gets the correct behaviour from XDP enabled * drivers to unmap the packet from their rx ring. */ ri->tgt_index = slave->ifindex; ri->map_id = INT_MAX; ri->map_type = BPF_MAP_TYPE_UNSPEC; return XDP_REDIRECT; } return XDP_TX; } EXPORT_SYMBOL_GPL(xdp_master_redirect); static inline int __xdp_do_redirect_xsk(struct bpf_redirect_info *ri, const struct net_device *dev, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; err = __xsk_map_redirect(fwd, xdp); if (unlikely(err)) goto err; _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, struct net_device *dev, struct xdp_frame *xdpf, const struct bpf_prog *xdp_prog) { enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; u32 flags = ri->flags; struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (unlikely(!xdpf)) { err = -EOVERFLOW; goto err; } switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: if (unlikely(flags & BPF_F_BROADCAST)) { map = READ_ONCE(ri->map); /* The map pointer is cleared when the map is being torn * down by dev_map_free() */ if (unlikely(!map)) { err = -ENOENT; break; } WRITE_ONCE(ri->map, NULL); err = dev_map_enqueue_multi(xdpf, dev, map, flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_enqueue(fwd, xdpf, dev); } break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_enqueue(fwd, xdpf, dev); break; case BPF_MAP_TYPE_UNSPEC: if (map_id == INT_MAX) { fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index); if (unlikely(!fwd)) { err = -EINVAL; break; } err = dev_xdp_enqueue(fwd, xdpf, dev); break; } fallthrough; default: err = -EBADRQC; } if (unlikely(err)) goto err; _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp), xdp_prog); } EXPORT_SYMBOL_GPL(xdp_do_redirect); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); return __xdp_do_redirect_frame(ri, dev, xdpf, xdp_prog); } EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog, void *fwd, enum bpf_map_type map_type, u32 map_id, u32 flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct bpf_map *map; int err; switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; case BPF_MAP_TYPE_DEVMAP_HASH: if (unlikely(flags & BPF_F_BROADCAST)) { map = READ_ONCE(ri->map); /* The map pointer is cleared when the map is being torn * down by dev_map_free() */ if (unlikely(!map)) { err = -ENOENT; break; } WRITE_ONCE(ri->map, NULL); err = dev_map_redirect_multi(dev, skb, xdp_prog, map, flags & BPF_F_EXCLUDE_INGRESS); } else { err = dev_map_generic_redirect(fwd, skb, xdp_prog); } if (unlikely(err)) goto err; break; case BPF_MAP_TYPE_XSKMAP: err = xsk_generic_rcv(fwd, xdp); if (err) goto err; consume_skb(skb); break; case BPF_MAP_TYPE_CPUMAP: err = cpu_map_generic_redirect(fwd, skb); if (unlikely(err)) goto err; break; default: err = -EBADRQC; goto err; } _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); return 0; err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; u32 flags = ri->flags; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->flags = 0; ri->map_type = BPF_MAP_TYPE_UNSPEC; if (map_type == BPF_MAP_TYPE_UNSPEC && map_id == INT_MAX) { fwd = dev_get_by_index_rcu(dev_net(dev), ri->tgt_index); if (unlikely(!fwd)) { err = -EINVAL; goto err; } err = xdp_ok_fwd_dev(fwd, skb->len); if (unlikely(err)) goto err; skb->dev = fwd; _trace_xdp_redirect(dev, xdp_prog, ri->tgt_index); generic_xdp_tx(skb, xdp_prog); return 0; } return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, fwd, map_type, map_id, flags); err: _trace_xdp_redirect_err(dev, xdp_prog, ri->tgt_index, err); return err; } BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags)) return XDP_ABORTED; /* NB! Map type UNSPEC and map_id == INT_MAX (never generated * by map_idr) is used for ifindex based XDP redirect. */ ri->tgt_index = ifindex; ri->map_id = INT_MAX; ri->map_type = BPF_MAP_TYPE_UNSPEC; return XDP_REDIRECT; } static const struct bpf_func_proto bpf_xdp_redirect_proto = { .func = bpf_xdp_redirect, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u64, key, u64, flags) { return map->ops->map_redirect(map, key, flags); } static const struct bpf_func_proto bpf_xdp_redirect_map_proto = { .func = bpf_xdp_redirect_map, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static unsigned long bpf_skb_copy(void *dst_buff, const void *skb, unsigned long off, unsigned long len) { void *ptr = skb_header_pointer(skb, off, len, dst_buff); if (unlikely(!ptr)) return len; if (ptr != dst_buff) memcpy(dst_buff, ptr, len); return 0; } BPF_CALL_5(bpf_skb_event_output, struct sk_buff *, skb, struct bpf_map *, map, u64, flags, void *, meta, u64, meta_size) { u64 skb_size = (flags & BPF_F_CTXLEN_MASK) >> 32; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; if (unlikely(!skb || skb_size > skb->len)) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, skb, skb_size, bpf_skb_copy); } static const struct bpf_func_proto bpf_skb_event_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BTF_ID_LIST_SINGLE(bpf_skb_output_btf_ids, struct, sk_buff) const struct bpf_func_proto bpf_skb_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_skb_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; static unsigned short bpf_tunnel_key_af(u64 flags) { return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET; } BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key *, to, u32, size, u64, flags) { const struct ip_tunnel_info *info = skb_tunnel_info(skb); u8 compat[sizeof(struct bpf_tunnel_key)]; void *to_orig = to; int err; if (unlikely(!info || (flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_TUNINFO_FLAGS)))) { err = -EINVAL; goto err_clear; } if (ip_tunnel_info_af(info) != bpf_tunnel_key_af(flags)) { err = -EPROTO; goto err_clear; } if (unlikely(size != sizeof(struct bpf_tunnel_key))) { err = -EINVAL; switch (size) { case offsetof(struct bpf_tunnel_key, local_ipv6[0]): case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, tunnel_ext): goto set_compat; case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ if (ip_tunnel_info_af(info) != AF_INET) goto err_clear; set_compat: to = (struct bpf_tunnel_key *)compat; break; default: goto err_clear; } } to->tunnel_id = be64_to_cpu(info->key.tun_id); to->tunnel_tos = info->key.tos; to->tunnel_ttl = info->key.ttl; if (flags & BPF_F_TUNINFO_FLAGS) to->tunnel_flags = ip_tunnel_flags_to_be16(info->key.tun_flags); else to->tunnel_ext = 0; if (flags & BPF_F_TUNINFO_IPV6) { memcpy(to->remote_ipv6, &info->key.u.ipv6.src, sizeof(to->remote_ipv6)); memcpy(to->local_ipv6, &info->key.u.ipv6.dst, sizeof(to->local_ipv6)); to->tunnel_label = be32_to_cpu(info->key.label); } else { to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src); memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); to->local_ipv4 = be32_to_cpu(info->key.u.ipv4.dst); memset(&to->local_ipv6[1], 0, sizeof(__u32) * 3); to->tunnel_label = 0; } if (unlikely(size != sizeof(struct bpf_tunnel_key))) memcpy(to_orig, to, size); return 0; err_clear: memset(to_orig, 0, size); return err; } static const struct bpf_func_proto bpf_skb_get_tunnel_key_proto = { .func = bpf_skb_get_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_get_tunnel_opt, struct sk_buff *, skb, u8 *, to, u32, size) { const struct ip_tunnel_info *info = skb_tunnel_info(skb); int err; if (unlikely(!info || !ip_tunnel_is_options_present(info->key.tun_flags))) { err = -ENOENT; goto err_clear; } if (unlikely(size < info->options_len)) { err = -ENOMEM; goto err_clear; } ip_tunnel_info_opts_get(to, info); if (size > info->options_len) memset(to + info->options_len, 0, size - info->options_len); return info->options_len; err_clear: memset(to, 0, size); return err; } static const struct bpf_func_proto bpf_skb_get_tunnel_opt_proto = { .func = bpf_skb_get_tunnel_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, }; static struct metadata_dst __percpu *md_dst; BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb, const struct bpf_tunnel_key *, from, u32, size, u64, flags) { struct metadata_dst *md = this_cpu_ptr(md_dst); u8 compat[sizeof(struct bpf_tunnel_key)]; struct ip_tunnel_info *info; if (unlikely(flags & ~(BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX | BPF_F_DONT_FRAGMENT | BPF_F_SEQ_NUMBER | BPF_F_NO_TUNNEL_KEY))) return -EINVAL; if (unlikely(size != sizeof(struct bpf_tunnel_key))) { switch (size) { case offsetof(struct bpf_tunnel_key, local_ipv6[0]): case offsetof(struct bpf_tunnel_key, tunnel_label): case offsetof(struct bpf_tunnel_key, tunnel_ext): case offsetof(struct bpf_tunnel_key, remote_ipv6[1]): /* Fixup deprecated structure layouts here, so we have * a common path later on. */ memcpy(compat, from, size); memset(compat + size, 0, sizeof(compat) - size); from = (const struct bpf_tunnel_key *) compat; break; default: return -EINVAL; } } if (unlikely((!(flags & BPF_F_TUNINFO_IPV6) && from->tunnel_label) || from->tunnel_ext)) return -EINVAL; skb_dst_drop(skb); dst_hold((struct dst_entry *) md); skb_dst_set(skb, (struct dst_entry *) md); info = &md->u.tun_info; memset(info, 0, sizeof(*info)); info->mode = IP_TUNNEL_INFO_TX; __set_bit(IP_TUNNEL_NOCACHE_BIT, info->key.tun_flags); __assign_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, info->key.tun_flags, flags & BPF_F_DONT_FRAGMENT); __assign_bit(IP_TUNNEL_CSUM_BIT, info->key.tun_flags, !(flags & BPF_F_ZERO_CSUM_TX)); __assign_bit(IP_TUNNEL_SEQ_BIT, info->key.tun_flags, flags & BPF_F_SEQ_NUMBER); __assign_bit(IP_TUNNEL_KEY_BIT, info->key.tun_flags, !(flags & BPF_F_NO_TUNNEL_KEY)); info->key.tun_id = cpu_to_be64(from->tunnel_id); info->key.tos = from->tunnel_tos; info->key.ttl = from->tunnel_ttl; if (flags & BPF_F_TUNINFO_IPV6) { info->mode |= IP_TUNNEL_INFO_IPV6; memcpy(&info->key.u.ipv6.dst, from->remote_ipv6, sizeof(from->remote_ipv6)); memcpy(&info->key.u.ipv6.src, from->local_ipv6, sizeof(from->local_ipv6)); info->key.label = cpu_to_be32(from->tunnel_label) & IPV6_FLOWLABEL_MASK; } else { info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4); info->key.u.ipv4.src = cpu_to_be32(from->local_ipv4); info->key.flow_flags = FLOWI_FLAG_ANYSRC; } return 0; } static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .func = bpf_skb_set_tunnel_key, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb, const u8 *, from, u32, size) { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct metadata_dst *md = this_cpu_ptr(md_dst); IP_TUNNEL_DECLARE_FLAGS(present) = { }; if (unlikely(info != &md->u.tun_info || (size & (sizeof(u32) - 1)))) return -EINVAL; if (unlikely(size > IP_TUNNEL_OPTS_MAX)) return -ENOMEM; ip_tunnel_set_options_present(present); ip_tunnel_info_opts_set(info, from, size, present); return 0; } static const struct bpf_func_proto bpf_skb_set_tunnel_opt_proto = { .func = bpf_skb_set_tunnel_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto * bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) { if (!md_dst) { struct metadata_dst __percpu *tmp; tmp = metadata_dst_alloc_percpu(IP_TUNNEL_OPTS_MAX, METADATA_IP_TUNNEL, GFP_KERNEL); if (!tmp) return NULL; if (cmpxchg(&md_dst, NULL, tmp)) metadata_dst_free_percpu(tmp); } switch (which) { case BPF_FUNC_skb_set_tunnel_key: return &bpf_skb_set_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_opt: return &bpf_skb_set_tunnel_opt_proto; default: return NULL; } } BPF_CALL_3(bpf_skb_under_cgroup, struct sk_buff *, skb, struct bpf_map *, map, u32, idx) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; struct sock *sk; sk = skb_to_full_sk(skb); if (!sk || !sk_fullsock(sk)) return -ENOENT; if (unlikely(idx >= array->map.max_entries)) return -E2BIG; cgrp = READ_ONCE(array->ptrs[idx]); if (unlikely(!cgrp)) return -EAGAIN; return sk_under_cgroup_hierarchy(sk, cgrp); } static const struct bpf_func_proto bpf_skb_under_cgroup_proto = { .func = bpf_skb_under_cgroup, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; #ifdef CONFIG_SOCK_CGROUP_DATA static inline u64 __bpf_sk_cgroup_id(struct sock *sk) { struct cgroup *cgrp; sk = sk_to_full_sk(sk); if (!sk || !sk_fullsock(sk)) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); return cgroup_id(cgrp); } BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) { return __bpf_sk_cgroup_id(skb->sk); } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { .func = bpf_skb_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk, int ancestor_level) { struct cgroup *ancestor; struct cgroup *cgrp; sk = sk_to_full_sk(sk); if (!sk || !sk_fullsock(sk)) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ancestor = cgroup_ancestor(cgrp, ancestor_level); if (!ancestor) return 0; return cgroup_id(ancestor); } BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, ancestor_level) { return __bpf_sk_ancestor_cgroup_id(skb->sk, ancestor_level); } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { .func = bpf_skb_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_cgroup_id, struct sock *, sk) { return __bpf_sk_cgroup_id(sk); } static const struct bpf_func_proto bpf_sk_cgroup_id_proto = { .func = bpf_sk_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level) { return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level); } static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { .func = bpf_sk_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, }; #endif static unsigned long bpf_xdp_copy(void *dst, const void *ctx, unsigned long off, unsigned long len) { struct xdp_buff *xdp = (struct xdp_buff *)ctx; bpf_xdp_copy_buf(xdp, off, dst, len, false); return 0; } BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map, u64, flags, void *, meta, u64, meta_size) { u64 xdp_size = (flags & BPF_F_CTXLEN_MASK) >> 32; if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; if (unlikely(!xdp || xdp_size > xdp_get_buff_len(xdp))) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, xdp, xdp_size, bpf_xdp_copy); } static const struct bpf_func_proto bpf_xdp_event_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BTF_ID_LIST_SINGLE(bpf_xdp_output_btf_ids, struct, xdp_buff) const struct bpf_func_proto bpf_xdp_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_xdp_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb) { return skb->sk ? __sock_gen_cookie(skb->sk) : 0; } static const struct bpf_func_proto bpf_get_socket_cookie_proto = { .func = bpf_get_socket_cookie, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { .func = bpf_get_socket_cookie_sock_addr, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx) { return __sock_gen_cookie(ctx); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { .func = bpf_get_socket_cookie_sock, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_1(bpf_get_socket_ptr_cookie, struct sock *, sk) { return sk ? sock_gen_cookie(sk) : 0; } const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto = { .func = bpf_get_socket_ptr_cookie, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON | PTR_MAYBE_NULL, }; BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { .func = bpf_get_socket_cookie_sock_ops, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static u64 __bpf_get_netns_cookie(struct sock *sk) { const struct net *net = sk ? sock_net(sk) : &init_net; return net->net_cookie; } BPF_CALL_1(bpf_get_netns_cookie, struct sk_buff *, skb) { return __bpf_get_netns_cookie(skb && skb->sk ? skb->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_proto = { .func = bpf_get_netns_cookie, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock, struct sock *, ctx) { return __bpf_get_netns_cookie(ctx); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_proto = { .func = bpf_get_netns_cookie_sock, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_addr_proto = { .func = bpf_get_netns_cookie_sock_addr, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sock_ops_proto = { .func = bpf_get_netns_cookie_sock_ops, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_netns_cookie_sk_msg, struct sk_msg *, ctx) { return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL); } static const struct bpf_func_proto bpf_get_netns_cookie_sk_msg_proto = { .func = bpf_get_netns_cookie_sk_msg, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb) { struct sock *sk = sk_to_full_sk(skb->sk); kuid_t kuid; if (!sk || !sk_fullsock(sk)) return overflowuid; kuid = sock_net_uid(sock_net(sk), sk); return from_kuid_munged(sock_net(sk)->user_ns, kuid); } static const struct bpf_func_proto bpf_get_socket_uid_proto = { .func = bpf_get_socket_uid, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; static int sk_bpf_set_get_cb_flags(struct sock *sk, char *optval, bool getopt) { u32 sk_bpf_cb_flags; if (getopt) { *(u32 *)optval = sk->sk_bpf_cb_flags; return 0; } sk_bpf_cb_flags = *(u32 *)optval; if (sk_bpf_cb_flags & ~SK_BPF_CB_MASK) return -EINVAL; sk->sk_bpf_cb_flags = sk_bpf_cb_flags; return 0; } static int sol_socket_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { switch (optname) { case SO_REUSEADDR: case SO_SNDBUF: case SO_RCVBUF: case SO_KEEPALIVE: case SO_PRIORITY: case SO_REUSEPORT: case SO_RCVLOWAT: case SO_MARK: case SO_MAX_PACING_RATE: case SO_BINDTOIFINDEX: case SO_TXREHASH: case SK_BPF_CB_FLAGS: if (*optlen != sizeof(int)) return -EINVAL; break; case SO_BINDTODEVICE: break; default: return -EINVAL; } if (optname == SK_BPF_CB_FLAGS) return sk_bpf_set_get_cb_flags(sk, optval, getopt); if (getopt) { if (optname == SO_BINDTODEVICE) return -EINVAL; return sk_getsockopt(sk, SOL_SOCKET, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); } return sk_setsockopt(sk, SOL_SOCKET, optname, KERNEL_SOCKPTR(optval), *optlen); } static int bpf_sol_tcp_getsockopt(struct sock *sk, int optname, char *optval, int optlen) { if (optlen != sizeof(int)) return -EINVAL; switch (optname) { case TCP_BPF_SOCK_OPS_CB_FLAGS: { int cb_flags = tcp_sk(sk)->bpf_sock_ops_cb_flags; memcpy(optval, &cb_flags, optlen); break; } case TCP_BPF_RTO_MIN: { int rto_min_us = jiffies_to_usecs(inet_csk(sk)->icsk_rto_min); memcpy(optval, &rto_min_us, optlen); break; } case TCP_BPF_DELACK_MAX: { int delack_max_us = jiffies_to_usecs(inet_csk(sk)->icsk_delack_max); memcpy(optval, &delack_max_us, optlen); break; } default: return -EINVAL; } return 0; } static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname, char *optval, int optlen) { struct tcp_sock *tp = tcp_sk(sk); unsigned long timeout; int val; if (optlen != sizeof(int)) return -EINVAL; val = *(int *)optval; /* Only some options are supported */ switch (optname) { case TCP_BPF_IW: if (val <= 0 || tp->data_segs_out > tp->syn_data) return -EINVAL; tcp_snd_cwnd_set(tp, val); break; case TCP_BPF_SNDCWND_CLAMP: if (val <= 0) return -EINVAL; tp->snd_cwnd_clamp = val; tp->snd_ssthresh = val; break; case TCP_BPF_DELACK_MAX: timeout = usecs_to_jiffies(val); if (timeout > TCP_DELACK_MAX || timeout < TCP_TIMEOUT_MIN) return -EINVAL; inet_csk(sk)->icsk_delack_max = timeout; break; case TCP_BPF_RTO_MIN: timeout = usecs_to_jiffies(val); if (timeout > TCP_RTO_MIN || timeout < TCP_TIMEOUT_MIN) return -EINVAL; inet_csk(sk)->icsk_rto_min = timeout; break; case TCP_BPF_SOCK_OPS_CB_FLAGS: if (val & ~(BPF_SOCK_OPS_ALL_CB_FLAGS)) return -EINVAL; tp->bpf_sock_ops_cb_flags = val; break; default: return -EINVAL; } return 0; } static int sol_tcp_sockopt_congestion(struct sock *sk, char *optval, int *optlen, bool getopt) { struct tcp_sock *tp; int ret; if (*optlen < 2) return -EINVAL; if (getopt) { if (!inet_csk(sk)->icsk_ca_ops) return -EINVAL; /* BPF expects NULL-terminated tcp-cc string */ optval[--(*optlen)] = '\0'; return do_tcp_getsockopt(sk, SOL_TCP, TCP_CONGESTION, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); } /* "cdg" is the only cc that alloc a ptr * in inet_csk_ca area. The bpf-tcp-cc may * overwrite this ptr after switching to cdg. */ if (*optlen >= sizeof("cdg") - 1 && !strncmp("cdg", optval, *optlen)) return -ENOTSUPP; /* It stops this looping * * .init => bpf_setsockopt(tcp_cc) => .init => * bpf_setsockopt(tcp_cc)" => .init => .... * * The second bpf_setsockopt(tcp_cc) is not allowed * in order to break the loop when both .init * are the same bpf prog. * * This applies even the second bpf_setsockopt(tcp_cc) * does not cause a loop. This limits only the first * '.init' can call bpf_setsockopt(TCP_CONGESTION) to * pick a fallback cc (eg. peer does not support ECN) * and the second '.init' cannot fallback to * another. */ tp = tcp_sk(sk); if (tp->bpf_chg_cc_inprogress) return -EBUSY; tp->bpf_chg_cc_inprogress = 1; ret = do_tcp_setsockopt(sk, SOL_TCP, TCP_CONGESTION, KERNEL_SOCKPTR(optval), *optlen); tp->bpf_chg_cc_inprogress = 0; return ret; } static int sol_tcp_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { if (sk->sk_protocol != IPPROTO_TCP) return -EINVAL; switch (optname) { case TCP_NODELAY: case TCP_MAXSEG: case TCP_KEEPIDLE: case TCP_KEEPINTVL: case TCP_KEEPCNT: case TCP_SYNCNT: case TCP_WINDOW_CLAMP: case TCP_THIN_LINEAR_TIMEOUTS: case TCP_USER_TIMEOUT: case TCP_NOTSENT_LOWAT: case TCP_SAVE_SYN: case TCP_RTO_MAX_MS: if (*optlen != sizeof(int)) return -EINVAL; break; case TCP_CONGESTION: return sol_tcp_sockopt_congestion(sk, optval, optlen, getopt); case TCP_SAVED_SYN: if (*optlen < 1) return -EINVAL; break; default: if (getopt) return bpf_sol_tcp_getsockopt(sk, optname, optval, *optlen); return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen); } if (getopt) { if (optname == TCP_SAVED_SYN) { struct tcp_sock *tp = tcp_sk(sk); if (!tp->saved_syn || *optlen > tcp_saved_syn_len(tp->saved_syn)) return -EINVAL; memcpy(optval, tp->saved_syn->data, *optlen); /* It cannot free tp->saved_syn here because it * does not know if the user space still needs it. */ return 0; } return do_tcp_getsockopt(sk, SOL_TCP, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); } return do_tcp_setsockopt(sk, SOL_TCP, optname, KERNEL_SOCKPTR(optval), *optlen); } static int sol_ip_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { if (sk->sk_family != AF_INET) return -EINVAL; switch (optname) { case IP_TOS: if (*optlen != sizeof(int)) return -EINVAL; break; default: return -EINVAL; } if (getopt) return do_ip_getsockopt(sk, SOL_IP, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); return do_ip_setsockopt(sk, SOL_IP, optname, KERNEL_SOCKPTR(optval), *optlen); } static int sol_ipv6_sockopt(struct sock *sk, int optname, char *optval, int *optlen, bool getopt) { if (sk->sk_family != AF_INET6) return -EINVAL; switch (optname) { case IPV6_TCLASS: case IPV6_AUTOFLOWLABEL: if (*optlen != sizeof(int)) return -EINVAL; break; default: return -EINVAL; } if (getopt) return ipv6_bpf_stub->ipv6_getsockopt(sk, SOL_IPV6, optname, KERNEL_SOCKPTR(optval), KERNEL_SOCKPTR(optlen)); return ipv6_bpf_stub->ipv6_setsockopt(sk, SOL_IPV6, optname, KERNEL_SOCKPTR(optval), *optlen); } static int __bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (!sk_fullsock(sk)) return -EINVAL; if (level == SOL_SOCKET) return sol_socket_sockopt(sk, optname, optval, &optlen, false); else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) return sol_ip_sockopt(sk, optname, optval, &optlen, false); else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) return sol_ipv6_sockopt(sk, optname, optval, &optlen, false); else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) return sol_tcp_sockopt(sk, optname, optval, &optlen, false); return -EINVAL; } static bool is_locked_tcp_sock_ops(struct bpf_sock_ops_kern *bpf_sock) { return bpf_sock->op <= BPF_SOCK_OPS_WRITE_HDR_OPT_CB; } static int _bpf_setsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (sk_fullsock(sk)) sock_owned_by_me(sk); return __bpf_setsockopt(sk, level, optname, optval, optlen); } static int __bpf_getsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { int err, saved_optlen = optlen; if (!sk_fullsock(sk)) { err = -EINVAL; goto done; } if (level == SOL_SOCKET) err = sol_socket_sockopt(sk, optname, optval, &optlen, true); else if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP) err = sol_tcp_sockopt(sk, optname, optval, &optlen, true); else if (IS_ENABLED(CONFIG_INET) && level == SOL_IP) err = sol_ip_sockopt(sk, optname, optval, &optlen, true); else if (IS_ENABLED(CONFIG_IPV6) && level == SOL_IPV6) err = sol_ipv6_sockopt(sk, optname, optval, &optlen, true); else err = -EINVAL; done: if (err) optlen = 0; if (optlen < saved_optlen) memset(optval + optlen, 0, saved_optlen - optlen); return err; } static int _bpf_getsockopt(struct sock *sk, int level, int optname, char *optval, int optlen) { if (sk_fullsock(sk)) sock_owned_by_me(sk); return __bpf_getsockopt(sk, level, optname, optval, optlen); } BPF_CALL_5(bpf_sk_setsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return _bpf_setsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_sk_setsockopt_proto = { .func = bpf_sk_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sk_getsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return _bpf_getsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_sk_getsockopt_proto = { .func = bpf_sk_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_unlocked_sk_setsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return __bpf_setsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto = { .func = bpf_unlocked_sk_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_unlocked_sk_getsockopt, struct sock *, sk, int, level, int, optname, char *, optval, int, optlen) { return __bpf_getsockopt(sk, level, optname, optval, optlen); } const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto = { .func = bpf_unlocked_sk_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = { .func = bpf_sock_addr_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_addr_getsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { return _bpf_getsockopt(ctx->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = { .func = bpf_sock_addr_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { .func = bpf_sock_ops_setsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, int optname, const u8 **start) { struct sk_buff *syn_skb = bpf_sock->syn_skb; const u8 *hdr_start; int ret; if (syn_skb) { /* sk is a request_sock here */ if (optname == TCP_BPF_SYN) { hdr_start = syn_skb->data; ret = tcp_hdrlen(syn_skb); } else if (optname == TCP_BPF_SYN_IP) { hdr_start = skb_network_header(syn_skb); ret = skb_network_header_len(syn_skb) + tcp_hdrlen(syn_skb); } else { /* optname == TCP_BPF_SYN_MAC */ hdr_start = skb_mac_header(syn_skb); ret = skb_mac_header_len(syn_skb) + skb_network_header_len(syn_skb) + tcp_hdrlen(syn_skb); } } else { struct sock *sk = bpf_sock->sk; struct saved_syn *saved_syn; if (sk->sk_state == TCP_NEW_SYN_RECV) /* synack retransmit. bpf_sock->syn_skb will * not be available. It has to resort to * saved_syn (if it is saved). */ saved_syn = inet_reqsk(sk)->saved_syn; else saved_syn = tcp_sk(sk)->saved_syn; if (!saved_syn) return -ENOENT; if (optname == TCP_BPF_SYN) { hdr_start = saved_syn->data + saved_syn->mac_hdrlen + saved_syn->network_hdrlen; ret = saved_syn->tcp_hdrlen; } else if (optname == TCP_BPF_SYN_IP) { hdr_start = saved_syn->data + saved_syn->mac_hdrlen; ret = saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; } else { /* optname == TCP_BPF_SYN_MAC */ /* TCP_SAVE_SYN may not have saved the mac hdr */ if (!saved_syn->mac_hdrlen) return -ENOENT; hdr_start = saved_syn->data; ret = saved_syn->mac_hdrlen + saved_syn->network_hdrlen + saved_syn->tcp_hdrlen; } } *start = hdr_start; return ret; } BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP && optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) { int ret, copy_len = 0; const u8 *start; ret = bpf_sock_ops_get_syn(bpf_sock, optname, &start); if (ret > 0) { copy_len = ret; if (optlen < copy_len) { copy_len = optlen; ret = -ENOSPC; } memcpy(optval, start, copy_len); } /* Zero out unused buffer at the end */ memset(optval + copy_len, 0, optlen - copy_len); return ret; } return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_ops_getsockopt_proto = { .func = bpf_sock_ops_getsockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_UNINIT_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock, int, argval) { struct sock *sk = bpf_sock->sk; int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS; if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; if (!IS_ENABLED(CONFIG_INET) || !sk_fullsock(sk)) return -EINVAL; tcp_sk(sk)->bpf_sock_ops_cb_flags = val; return argval & (~BPF_SOCK_OPS_ALL_CB_FLAGS); } static const struct bpf_func_proto bpf_sock_ops_cb_flags_set_proto = { .func = bpf_sock_ops_cb_flags_set, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, }; const struct ipv6_bpf_stub *ipv6_bpf_stub __read_mostly; EXPORT_SYMBOL_GPL(ipv6_bpf_stub); BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr, int, addr_len) { #ifdef CONFIG_INET struct sock *sk = ctx->sk; u32 flags = BIND_FROM_BPF; int err; err = -EINVAL; if (addr_len < offsetofend(struct sockaddr, sa_family)) return err; if (addr->sa_family == AF_INET) { if (addr_len < sizeof(struct sockaddr_in)) return err; if (((struct sockaddr_in *)addr)->sin_port == htons(0)) flags |= BIND_FORCE_ADDRESS_NO_PORT; return __inet_bind(sk, addr, addr_len, flags); #if IS_ENABLED(CONFIG_IPV6) } else if (addr->sa_family == AF_INET6) { if (addr_len < SIN6_LEN_RFC2133) return err; if (((struct sockaddr_in6 *)addr)->sin6_port == htons(0)) flags |= BIND_FORCE_ADDRESS_NO_PORT; /* ipv6_bpf_stub cannot be NULL, since it's called from * bpf_cgroup_inet6_connect hook and ipv6 is already loaded */ return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, flags); #endif /* CONFIG_IPV6 */ } #endif /* CONFIG_INET */ return -EAFNOSUPPORT; } static const struct bpf_func_proto bpf_bind_proto = { .func = bpf_bind, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; #ifdef CONFIG_XFRM #if (IS_BUILTIN(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) || \ (IS_MODULE(CONFIG_XFRM_INTERFACE) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) struct metadata_dst __percpu *xfrm_bpf_md_dst; EXPORT_SYMBOL_GPL(xfrm_bpf_md_dst); #endif BPF_CALL_5(bpf_skb_get_xfrm_state, struct sk_buff *, skb, u32, index, struct bpf_xfrm_state *, to, u32, size, u64, flags) { const struct sec_path *sp = skb_sec_path(skb); const struct xfrm_state *x; if (!sp || unlikely(index >= sp->len || flags)) goto err_clear; x = sp->xvec[index]; if (unlikely(size != sizeof(struct bpf_xfrm_state))) goto err_clear; to->reqid = x->props.reqid; to->spi = x->id.spi; to->family = x->props.family; to->ext = 0; if (to->family == AF_INET6) { memcpy(to->remote_ipv6, x->props.saddr.a6, sizeof(to->remote_ipv6)); } else { to->remote_ipv4 = x->props.saddr.a4; memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3); } return 0; err_clear: memset(to, 0, size); return -EINVAL; } static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { .func = bpf_skb_get_xfrm_state, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; #endif #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6) static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, u32 mtu) { params->h_vlan_TCI = 0; params->h_vlan_proto = 0; if (mtu) params->mtu_result = mtu; /* union with tot_len */ return 0; } #endif #if IS_ENABLED(CONFIG_INET) static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 flags, bool check_mtu) { struct fib_nh_common *nhc; struct in_device *in_dev; struct neighbour *neigh; struct net_device *dev; struct fib_result res; struct flowi4 fl4; u32 mtu = 0; int err; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) return -ENODEV; /* verify forwarding is enabled on this interface */ in_dev = __in_dev_get_rcu(dev); if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev))) return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl4.flowi4_iif = 1; fl4.flowi4_oif = params->ifindex; } else { fl4.flowi4_iif = params->ifindex; fl4.flowi4_oif = 0; } fl4.flowi4_dscp = inet_dsfield_to_dscp(params->tos); fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; fl4.flowi4_proto = params->l4_protocol; fl4.daddr = params->ipv4_dst; fl4.saddr = params->ipv4_src; fl4.fl4_sport = params->sport; fl4.fl4_dport = params->dport; fl4.flowi4_multipath_hash = 0; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib_table *tb; if (flags & BPF_FIB_LOOKUP_TBID) { tbid = params->tbid; /* zero out for vlan output */ params->tbid = 0; } tb = fib_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); } else { if (flags & BPF_FIB_LOOKUP_MARK) fl4.flowi4_mark = params->mark; else fl4.flowi4_mark = 0; fl4.flowi4_secid = 0; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF); } if (err) { /* map fib lookup errors to RTN_ type */ if (err == -EINVAL) return BPF_FIB_LKUP_RET_BLACKHOLE; if (err == -EHOSTUNREACH) return BPF_FIB_LKUP_RET_UNREACHABLE; if (err == -EACCES) return BPF_FIB_LKUP_RET_PROHIBIT; return BPF_FIB_LKUP_RET_NOT_FWDED; } if (res.type != RTN_UNICAST) return BPF_FIB_LKUP_RET_NOT_FWDED; if (fib_info_num_path(res.fi) > 1) fib_select_path(net, &res, &fl4, NULL); if (check_mtu) { mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); if (params->tot_len > mtu) { params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; } } nhc = res.nhc; /* do not handle lwt encaps right now */ if (nhc->nhc_lwtstate) return BPF_FIB_LKUP_RET_UNSUPP_LWT; dev = nhc->nhc_dev; params->rt_metric = res.fi->fib_priority; params->ifindex = dev->ifindex; if (flags & BPF_FIB_LOOKUP_SRC) params->ipv4_src = fib_result_prefsrc(net, &res); /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here */ if (likely(nhc->nhc_gw_family != AF_INET6)) { if (nhc->nhc_gw_family) params->ipv4_dst = nhc->nhc_gw.ipv4; } else { struct in6_addr *dst = (struct in6_addr *)params->ipv6_dst; params->family = AF_INET6; *dst = nhc->nhc_gw.ipv6; } if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params; if (likely(nhc->nhc_gw_family != AF_INET6)) neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst); else neigh = __ipv6_neigh_lookup_noref_stub(dev, params->ipv6_dst); if (!neigh || !(READ_ONCE(neigh->nud_state) & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); set_fwd_params: return bpf_fib_set_fwd_params(params, mtu); } #endif #if IS_ENABLED(CONFIG_IPV6) static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, u32 flags, bool check_mtu) { struct in6_addr *src = (struct in6_addr *) params->ipv6_src; struct in6_addr *dst = (struct in6_addr *) params->ipv6_dst; struct fib6_result res = {}; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; struct flowi6 fl6; int strict = 0; int oif, err; u32 mtu = 0; /* link local addresses are never forwarded */ if (rt6_need_strict(dst) || rt6_need_strict(src)) return BPF_FIB_LKUP_RET_NOT_FWDED; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) return -ENODEV; idev = __in6_dev_get_safely(dev); if (unlikely(!idev || !READ_ONCE(idev->cnf.forwarding))) return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl6.flowi6_iif = 1; oif = fl6.flowi6_oif = params->ifindex; } else { oif = fl6.flowi6_iif = params->ifindex; fl6.flowi6_oif = 0; strict = RT6_LOOKUP_F_HAS_SADDR; } fl6.flowlabel = params->flowinfo; fl6.flowi6_scope = 0; fl6.flowi6_flags = 0; fl6.mp_hash = 0; fl6.flowi6_proto = params->l4_protocol; fl6.daddr = *dst; fl6.saddr = *src; fl6.fl6_sport = params->sport; fl6.fl6_dport = params->dport; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; struct fib6_table *tb; if (flags & BPF_FIB_LOOKUP_TBID) { tbid = params->tbid; /* zero out for vlan output */ params->tbid = 0; } tb = ipv6_stub->fib6_get_table(net, tbid); if (unlikely(!tb)) return BPF_FIB_LKUP_RET_NOT_FWDED; err = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, &res, strict); } else { if (flags & BPF_FIB_LOOKUP_MARK) fl6.flowi6_mark = params->mark; else fl6.flowi6_mark = 0; fl6.flowi6_secid = 0; fl6.flowi6_tun_key.tun_id = 0; fl6.flowi6_uid = sock_net_uid(net, NULL); err = ipv6_stub->fib6_lookup(net, oif, &fl6, &res, strict); } if (unlikely(err || IS_ERR_OR_NULL(res.f6i) || res.f6i == net->ipv6.fib6_null_entry)) return BPF_FIB_LKUP_RET_NOT_FWDED; switch (res.fib6_type) { /* only unicast is forwarded */ case RTN_UNICAST: break; case RTN_BLACKHOLE: return BPF_FIB_LKUP_RET_BLACKHOLE; case RTN_UNREACHABLE: return BPF_FIB_LKUP_RET_UNREACHABLE; case RTN_PROHIBIT: return BPF_FIB_LKUP_RET_PROHIBIT; default: return BPF_FIB_LKUP_RET_NOT_FWDED; } ipv6_stub->fib6_select_path(net, &res, &fl6, fl6.flowi6_oif, fl6.flowi6_oif != 0, NULL, strict); if (check_mtu) { mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src); if (params->tot_len > mtu) { params->mtu_result = mtu; /* union with tot_len */ return BPF_FIB_LKUP_RET_FRAG_NEEDED; } } if (res.nh->fib_nh_lws) return BPF_FIB_LKUP_RET_UNSUPP_LWT; if (res.nh->fib_nh_gw_family) *dst = res.nh->fib_nh_gw6; dev = res.nh->fib_nh_dev; params->rt_metric = res.f6i->fib6_metric; params->ifindex = dev->ifindex; if (flags & BPF_FIB_LOOKUP_SRC) { if (res.f6i->fib6_prefsrc.plen) { *src = res.f6i->fib6_prefsrc.addr; } else { err = ipv6_bpf_stub->ipv6_dev_get_saddr(net, dev, &fl6.daddr, 0, src); if (err) return BPF_FIB_LKUP_RET_NO_SRC_ADDR; } } if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params; /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is * not needed here. */ neigh = __ipv6_neigh_lookup_noref_stub(dev, dst); if (!neigh || !(READ_ONCE(neigh->nud_state) & NUD_VALID)) return BPF_FIB_LKUP_RET_NO_NEIGH; memcpy(params->dmac, neigh->ha, ETH_ALEN); memcpy(params->smac, dev->dev_addr, ETH_ALEN); set_fwd_params: return bpf_fib_set_fwd_params(params, mtu); } #endif #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \ BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_MARK) BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) { if (plen < sizeof(*params)) return -EINVAL; if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: return bpf_ipv4_fib_lookup(dev_net(ctx->rxq->dev), params, flags, true); #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: return bpf_ipv6_fib_lookup(dev_net(ctx->rxq->dev), params, flags, true); #endif } return -EAFNOSUPPORT; } static const struct bpf_func_proto bpf_xdp_fib_lookup_proto = { .func = bpf_xdp_fib_lookup, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, struct bpf_fib_lookup *, params, int, plen, u32, flags) { struct net *net = dev_net(skb->dev); int rc = -EAFNOSUPPORT; bool check_mtu = false; if (plen < sizeof(*params)) return -EINVAL; if (flags & ~BPF_FIB_LOOKUP_MASK) return -EINVAL; if (params->tot_len) check_mtu = true; switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: rc = bpf_ipv4_fib_lookup(net, params, flags, check_mtu); break; #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: rc = bpf_ipv6_fib_lookup(net, params, flags, check_mtu); break; #endif } if (rc == BPF_FIB_LKUP_RET_SUCCESS && !check_mtu) { struct net_device *dev; /* When tot_len isn't provided by user, check skb * against MTU of FIB lookup resulting net_device */ dev = dev_get_by_index_rcu(net, params->ifindex); if (!is_skb_forwardable(dev, skb)) rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; params->mtu_result = dev->mtu; /* union with tot_len */ } return rc; } static const struct bpf_func_proto bpf_skb_fib_lookup_proto = { .func = bpf_skb_fib_lookup, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; static struct net_device *__dev_via_ifindex(struct net_device *dev_curr, u32 ifindex) { struct net *netns = dev_net(dev_curr); /* Non-redirect use-cases can use ifindex=0 and save ifindex lookup */ if (ifindex == 0) return dev_curr; return dev_get_by_index_rcu(netns, ifindex); } BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags) { int ret = BPF_MTU_CHK_RET_FRAG_NEEDED; struct net_device *dev = skb->dev; int mtu, dev_len, skb_len; if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) return -EINVAL; if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); if (unlikely(!dev)) return -ENODEV; mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; /* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ skb_len = *mtu_len ? *mtu_len + dev->hard_header_len : skb->len; skb_len += len_diff; /* minus result pass check */ if (skb_len <= dev_len) { ret = BPF_MTU_CHK_RET_SUCCESS; goto out; } /* At this point, skb->len exceed MTU, but as it include length of all * segments, it can still be below MTU. The SKB can possibly get * re-segmented in transmit path (see validate_xmit_skb). Thus, user * must choose if segs are to be MTU checked. */ if (skb_is_gso(skb)) { ret = BPF_MTU_CHK_RET_SUCCESS; if (flags & BPF_MTU_CHK_SEGS && !skb_gso_validate_network_len(skb, mtu)) ret = BPF_MTU_CHK_RET_SEGS_TOOBIG; } out: *mtu_len = mtu; return ret; } BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, u32, ifindex, u32 *, mtu_len, s32, len_diff, u64, flags) { struct net_device *dev = xdp->rxq->dev; int xdp_len = xdp->data_end - xdp->data; int ret = BPF_MTU_CHK_RET_SUCCESS; int mtu, dev_len; /* XDP variant doesn't support multi-buffer segment check (yet) */ if (unlikely(flags)) return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); if (unlikely(!dev)) return -ENODEV; mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; /* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ if (*mtu_len) xdp_len = *mtu_len + dev->hard_header_len; xdp_len += len_diff; /* minus result pass check */ if (xdp_len > dev_len) ret = BPF_MTU_CHK_RET_FRAG_NEEDED; *mtu_len = mtu; return ret; } static const struct bpf_func_proto bpf_skb_check_mtu_proto = { .func = bpf_skb_check_mtu, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; static const struct bpf_func_proto bpf_xdp_check_mtu_proto = { .func = bpf_xdp_check_mtu, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_WRITE | MEM_ALIGNED, .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len) { int err; struct ipv6_sr_hdr *srh = (struct ipv6_sr_hdr *)hdr; if (!seg6_validate_srh(srh, len, false)) return -EINVAL; switch (type) { case BPF_LWT_ENCAP_SEG6_INLINE: if (skb->protocol != htons(ETH_P_IPV6)) return -EBADMSG; err = seg6_do_srh_inline(skb, srh); break; case BPF_LWT_ENCAP_SEG6: skb_reset_inner_headers(skb); skb->encapsulation = 1; err = seg6_do_srh_encap(skb, srh, IPPROTO_IPV6); break; default: return -EINVAL; } bpf_compute_data_pointers(skb); if (err) return err; skb_set_transport_header(skb, sizeof(struct ipv6hdr)); return seg6_lookup_nexthop(skb, NULL, 0); } #endif /* CONFIG_IPV6_SEG6_BPF */ #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) static int bpf_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress) { return bpf_lwt_push_ip_encap(skb, hdr, len, ingress); } #endif BPF_CALL_4(bpf_lwt_in_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, u32, len) { switch (type) { #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_LWT_ENCAP_SEG6: case BPF_LWT_ENCAP_SEG6_INLINE: return bpf_push_seg6_encap(skb, type, hdr, len); #endif #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) case BPF_LWT_ENCAP_IP: return bpf_push_ip_encap(skb, hdr, len, true /* ingress */); #endif default: return -EINVAL; } } BPF_CALL_4(bpf_lwt_xmit_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, u32, len) { switch (type) { #if IS_ENABLED(CONFIG_LWTUNNEL_BPF) case BPF_LWT_ENCAP_IP: return bpf_push_ip_encap(skb, hdr, len, false /* egress */); #endif default: return -EINVAL; } } static const struct bpf_func_proto bpf_lwt_in_push_encap_proto = { .func = bpf_lwt_in_push_encap, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; static const struct bpf_func_proto bpf_lwt_xmit_push_encap_proto = { .func = bpf_lwt_xmit_push_encap, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh = srh_state->srh; void *srh_tlvs, *srh_end, *ptr; int srhoff = 0; lockdep_assert_held(&srh_state->bh_lock); if (srh == NULL) return -EINVAL; srh_tlvs = (void *)((char *)srh + ((srh->first_segment + 1) << 4)); srh_end = (void *)((char *)srh + sizeof(*srh) + srh_state->hdrlen); ptr = skb->data + offset; if (ptr >= srh_tlvs && ptr + len <= srh_end) srh_state->valid = false; else if (ptr < (void *)&srh->flags || ptr + len > (void *)&srh->segments) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) return -EINVAL; srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); memcpy(skb->data + offset, from, len); return 0; } static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { .func = bpf_lwt_seg6_store_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; static void bpf_update_srh_state(struct sk_buff *skb) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); int srhoff = 0; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) { srh_state->srh = NULL; } else { srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_state->hdrlen = srh_state->srh->hdrlen << 3; srh_state->valid = true; } } BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, u32, action, void *, param, u32, param_len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); int hdroff = 0; int err; lockdep_assert_held(&srh_state->bh_lock); switch (action) { case SEG6_LOCAL_ACTION_END_X: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(struct in6_addr)) return -EINVAL; return seg6_lookup_nexthop(skb, (struct in6_addr *)param, 0); case SEG6_LOCAL_ACTION_END_T: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(int)) return -EINVAL; return seg6_lookup_nexthop(skb, NULL, *(int *)param); case SEG6_LOCAL_ACTION_END_DT6: if (!seg6_bpf_has_valid_srh(skb)) return -EBADMSG; if (param_len != sizeof(int)) return -EINVAL; if (ipv6_find_hdr(skb, &hdroff, IPPROTO_IPV6, NULL, NULL) < 0) return -EBADMSG; if (!pskb_pull(skb, hdroff)) return -EBADMSG; skb_postpull_rcsum(skb, skb_network_header(skb), hdroff); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->encapsulation = 0; bpf_compute_data_pointers(skb); bpf_update_srh_state(skb); return seg6_lookup_nexthop(skb, NULL, *(int *)param); case SEG6_LOCAL_ACTION_END_B6: if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) return -EBADMSG; err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6_INLINE, param, param_len); if (!err) bpf_update_srh_state(skb); return err; case SEG6_LOCAL_ACTION_END_B6_ENCAP: if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) return -EBADMSG; err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6, param, param_len); if (!err) bpf_update_srh_state(skb); return err; default: return -EINVAL; } } static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { .func = bpf_lwt_seg6_action, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, s32, len) { struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh = srh_state->srh; void *srh_end, *srh_tlvs, *ptr; struct ipv6hdr *hdr; int srhoff = 0; int ret; lockdep_assert_held(&srh_state->bh_lock); if (unlikely(srh == NULL)) return -EINVAL; srh_tlvs = (void *)((unsigned char *)srh + sizeof(*srh) + ((srh->first_segment + 1) << 4)); srh_end = (void *)((unsigned char *)srh + sizeof(*srh) + srh_state->hdrlen); ptr = skb->data + offset; if (unlikely(ptr < srh_tlvs || ptr > srh_end)) return -EFAULT; if (unlikely(len < 0 && (void *)((char *)ptr - len) > srh_end)) return -EFAULT; if (len > 0) { ret = skb_cow_head(skb, len); if (unlikely(ret < 0)) return ret; ret = bpf_skb_net_hdr_push(skb, offset, len); } else { ret = bpf_skb_net_hdr_pop(skb, offset, -1 * len); } bpf_compute_data_pointers(skb); if (unlikely(ret < 0)) return ret; hdr = (struct ipv6hdr *)skb->data; hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) return -EINVAL; srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); srh_state->hdrlen += len; srh_state->valid = false; return 0; } static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { .func = bpf_lwt_seg6_adjust_srh, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; #endif /* CONFIG_IPV6_SEG6_BPF */ #ifdef CONFIG_INET static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, int dif, int sdif, u8 family, u8 proto) { bool refcounted = false; struct sock *sk = NULL; if (family == AF_INET) { __be32 src4 = tuple->ipv4.saddr; __be32 dst4 = tuple->ipv4.daddr; if (proto == IPPROTO_TCP) sk = __inet_lookup(net, NULL, 0, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, dif, sdif, &refcounted); else sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport, dst4, tuple->ipv4.dport, dif, sdif, net->ipv4.udp_table, NULL); #if IS_ENABLED(CONFIG_IPV6) } else { struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr; struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr; if (proto == IPPROTO_TCP) sk = __inet6_lookup(net, NULL, 0, src6, tuple->ipv6.sport, dst6, ntohs(tuple->ipv6.dport), dif, sdif, &refcounted); else if (likely(ipv6_bpf_stub)) sk = ipv6_bpf_stub->udp6_lib_lookup(net, src6, tuple->ipv6.sport, dst6, tuple->ipv6.dport, dif, sdif, net->ipv4.udp_table, NULL); #endif } if (unlikely(sk && !refcounted && !sock_flag(sk, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); sk = NULL; } return sk; } /* bpf_skc_lookup performs the core lookup for different types of sockets, * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE. */ static struct sock * __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id, u64 flags, int sdif) { struct sock *sk = NULL; struct net *net; u8 family; if (len == sizeof(tuple->ipv4)) family = AF_INET; else if (len == sizeof(tuple->ipv6)) family = AF_INET6; else return NULL; if (unlikely(flags || !((s32)netns_id < 0 || netns_id <= S32_MAX))) goto out; if (sdif < 0) { if (family == AF_INET) sdif = inet_sdif(skb); else sdif = inet6_sdif(skb); } if ((s32)netns_id < 0) { net = caller_net; sk = sk_lookup(net, tuple, ifindex, sdif, family, proto); } else { net = get_net_ns_by_id(caller_net, netns_id); if (unlikely(!net)) goto out; sk = sk_lookup(net, tuple, ifindex, sdif, family, proto); put_net(net); } out: return sk; } static struct sock * __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id, u64 flags, int sdif) { struct sock *sk = __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto, netns_id, flags, sdif); if (sk) { struct sock *sk2 = sk_to_full_sk(sk); /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk * sock refcnt is decremented to prevent a request_sock leak. */ if (sk2 != sk) { sock_gen_put(sk); /* Ensure there is no need to bump sk2 refcnt */ if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); return NULL; } sk = sk2; } } return sk; } static struct sock * bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, u8 proto, u64 netns_id, u64 flags) { struct net *caller_net; int ifindex; if (skb->dev) { caller_net = dev_net(skb->dev); ifindex = skb->dev->ifindex; } else { caller_net = sock_net(skb->sk); ifindex = 0; } return __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto, netns_id, flags, -1); } static struct sock * bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, u8 proto, u64 netns_id, u64 flags) { struct sock *sk = bpf_skc_lookup(skb, tuple, len, proto, netns_id, flags); if (sk) { struct sock *sk2 = sk_to_full_sk(sk); /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk * sock refcnt is decremented to prevent a request_sock leak. */ if (sk2 != sk) { sock_gen_put(sk); /* Ensure there is no need to bump sk2 refcnt */ if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); return NULL; } sk = sk2; } } return sk; } BPF_CALL_5(bpf_skc_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_skc_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_skc_lookup_tcp_proto = { .func = bpf_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags); } static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = { .func = bpf_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags); } static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { .func = bpf_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_tc_skc_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { struct net_device *dev = skb->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_tc_skc_lookup_tcp_proto = { .func = bpf_tc_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_tc_sk_lookup_tcp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { struct net_device *dev = skb->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_tc_sk_lookup_tcp_proto = { .func = bpf_tc_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_tc_sk_lookup_udp, struct sk_buff *, skb, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { struct net_device *dev = skb->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net, ifindex, IPPROTO_UDP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_tc_sk_lookup_udp_proto = { .func = bpf_tc_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_1(bpf_sk_release, struct sock *, sk) { if (sk && sk_is_refcounted(sk)) sock_gen_put(sk); return 0; } static const struct bpf_func_proto bpf_sk_release_proto = { .func = bpf_sk_release, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON | OBJ_RELEASE, }; BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net_device *dev = ctx->rxq->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_UDP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = { .func = bpf_xdp_sk_lookup_udp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net_device *dev = ctx->rxq->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = { .func = bpf_xdp_skc_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags) { struct net_device *dev = ctx->rxq->dev; int ifindex = dev->ifindex, sdif = dev_sdif(dev); struct net *caller_net = dev_net(dev); return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex, IPPROTO_TCP, netns_id, flags, sdif); } static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = { .func = bpf_xdp_sk_lookup_tcp, .gpl_only = false, .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_skc_lookup_tcp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_TCP, netns_id, flags, -1); } static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = { .func = bpf_sock_addr_skc_lookup_tcp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_TCP, netns_id, flags, -1); } static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = { .func = bpf_sock_addr_sk_lookup_tcp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx, struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags) { return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0, IPPROTO_UDP, netns_id, flags, -1); } static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = { .func = bpf_sock_addr_sk_lookup_udp, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, icsk_retransmits)) return false; if (off % size != 0) return false; switch (off) { case offsetof(struct bpf_tcp_sock, bytes_received): case offsetof(struct bpf_tcp_sock, bytes_acked): return size == sizeof(__u64); default: return size == sizeof(__u32); } } u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #define BPF_TCP_SOCK_GET_COMMON(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct tcp_sock, FIELD) > \ sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct tcp_sock, FIELD)); \ } while (0) #define BPF_INET_SOCK_GET_COMMON(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct inet_connection_sock, \ FIELD) > \ sizeof_field(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct inet_connection_sock, \ FIELD), \ si->dst_reg, si->src_reg, \ offsetof( \ struct inet_connection_sock, \ FIELD)); \ } while (0) BTF_TYPE_EMIT(struct bpf_tcp_sock); switch (si->off) { case offsetof(struct bpf_tcp_sock, rtt_min): BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct tcp_sock, rtt_min) + offsetof(struct minmax_sample, v)); break; case offsetof(struct bpf_tcp_sock, snd_cwnd): BPF_TCP_SOCK_GET_COMMON(snd_cwnd); break; case offsetof(struct bpf_tcp_sock, srtt_us): BPF_TCP_SOCK_GET_COMMON(srtt_us); break; case offsetof(struct bpf_tcp_sock, snd_ssthresh): BPF_TCP_SOCK_GET_COMMON(snd_ssthresh); break; case offsetof(struct bpf_tcp_sock, rcv_nxt): BPF_TCP_SOCK_GET_COMMON(rcv_nxt); break; case offsetof(struct bpf_tcp_sock, snd_nxt): BPF_TCP_SOCK_GET_COMMON(snd_nxt); break; case offsetof(struct bpf_tcp_sock, snd_una): BPF_TCP_SOCK_GET_COMMON(snd_una); break; case offsetof(struct bpf_tcp_sock, mss_cache): BPF_TCP_SOCK_GET_COMMON(mss_cache); break; case offsetof(struct bpf_tcp_sock, ecn_flags): BPF_TCP_SOCK_GET_COMMON(ecn_flags); break; case offsetof(struct bpf_tcp_sock, rate_delivered): BPF_TCP_SOCK_GET_COMMON(rate_delivered); break; case offsetof(struct bpf_tcp_sock, rate_interval_us): BPF_TCP_SOCK_GET_COMMON(rate_interval_us); break; case offsetof(struct bpf_tcp_sock, packets_out): BPF_TCP_SOCK_GET_COMMON(packets_out); break; case offsetof(struct bpf_tcp_sock, retrans_out): BPF_TCP_SOCK_GET_COMMON(retrans_out); break; case offsetof(struct bpf_tcp_sock, total_retrans): BPF_TCP_SOCK_GET_COMMON(total_retrans); break; case offsetof(struct bpf_tcp_sock, segs_in): BPF_TCP_SOCK_GET_COMMON(segs_in); break; case offsetof(struct bpf_tcp_sock, data_segs_in): BPF_TCP_SOCK_GET_COMMON(data_segs_in); break; case offsetof(struct bpf_tcp_sock, segs_out): BPF_TCP_SOCK_GET_COMMON(segs_out); break; case offsetof(struct bpf_tcp_sock, data_segs_out): BPF_TCP_SOCK_GET_COMMON(data_segs_out); break; case offsetof(struct bpf_tcp_sock, lost_out): BPF_TCP_SOCK_GET_COMMON(lost_out); break; case offsetof(struct bpf_tcp_sock, sacked_out): BPF_TCP_SOCK_GET_COMMON(sacked_out); break; case offsetof(struct bpf_tcp_sock, bytes_received): BPF_TCP_SOCK_GET_COMMON(bytes_received); break; case offsetof(struct bpf_tcp_sock, bytes_acked): BPF_TCP_SOCK_GET_COMMON(bytes_acked); break; case offsetof(struct bpf_tcp_sock, dsack_dups): BPF_TCP_SOCK_GET_COMMON(dsack_dups); break; case offsetof(struct bpf_tcp_sock, delivered): BPF_TCP_SOCK_GET_COMMON(delivered); break; case offsetof(struct bpf_tcp_sock, delivered_ce): BPF_TCP_SOCK_GET_COMMON(delivered_ce); break; case offsetof(struct bpf_tcp_sock, icsk_retransmits): BPF_INET_SOCK_GET_COMMON(icsk_retransmits); break; } return insn - insn_buf; } BPF_CALL_1(bpf_tcp_sock, struct sock *, sk) { if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_tcp_sock_proto = { .func = bpf_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_TCP_SOCK_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; BPF_CALL_1(bpf_get_listener_sock, struct sock *, sk) { sk = sk_to_full_sk(sk); if (sk && sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_RCU_FREE)) return (unsigned long)sk; return (unsigned long)NULL; } static const struct bpf_func_proto bpf_get_listener_sock_proto = { .func = bpf_get_listener_sock, .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, }; BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb) { unsigned int iphdr_len; switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): iphdr_len = sizeof(struct iphdr); break; case cpu_to_be16(ETH_P_IPV6): iphdr_len = sizeof(struct ipv6hdr); break; default: return 0; } if (skb_headlen(skb) < iphdr_len) return 0; if (skb_cloned(skb) && !skb_clone_writable(skb, iphdr_len)) return 0; return INET_ECN_set_ce(skb); } bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < 0 || off >= offsetofend(struct bpf_xdp_sock, queue_id)) return false; if (off % size != 0) return false; switch (off) { default: return size == sizeof(__u32); } } u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #define BPF_XDP_SOCK_GET(FIELD) \ do { \ BUILD_BUG_ON(sizeof_field(struct xdp_sock, FIELD) > \ sizeof_field(struct bpf_xdp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct xdp_sock, FIELD)); \ } while (0) BTF_TYPE_EMIT(struct bpf_xdp_sock); switch (si->off) { case offsetof(struct bpf_xdp_sock, queue_id): BPF_XDP_SOCK_GET(queue_id); break; } return insn - insn_buf; } static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = { .func = bpf_skb_ecn_set_ce, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len, struct tcphdr *, th, u32, th_len) { #ifdef CONFIG_SYN_COOKIES int ret; if (unlikely(!sk || th_len < sizeof(*th))) return -EINVAL; /* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */ if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -EINVAL; if (!th->ack || th->rst || th->syn) return -ENOENT; if (unlikely(iph_len < sizeof(struct iphdr))) return -EINVAL; if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; /* Both struct iphdr and struct ipv6hdr have the version field at the * same offset so we can cast to the shorter header (struct iphdr). */ switch (((struct iphdr *)iph)->version) { case 4: if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; ret = __cookie_v4_check((struct iphdr *)iph, th); break; #if IS_BUILTIN(CONFIG_IPV6) case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; if (sk->sk_family != AF_INET6) return -EINVAL; ret = __cookie_v6_check((struct ipv6hdr *)iph, th); break; #endif /* CONFIG_IPV6 */ default: return -EPROTONOSUPPORT; } if (ret > 0) return 0; return -ENOENT; #else return -ENOTSUPP; #endif } static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = { .func = bpf_tcp_check_syncookie, .gpl_only = true, .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, struct tcphdr *, th, u32, th_len) { #ifdef CONFIG_SYN_COOKIES u32 cookie; u16 mss; if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -ENOENT; if (!th->syn || th->ack || th->fin || th->rst) return -EINVAL; if (unlikely(iph_len < sizeof(struct iphdr))) return -EINVAL; /* Both struct iphdr and struct ipv6hdr have the version field at the * same offset so we can cast to the shorter header (struct iphdr). */ switch (((struct iphdr *)iph)->version) { case 4: if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; mss = tcp_v4_get_syncookie(sk, iph, th, &cookie); break; #if IS_BUILTIN(CONFIG_IPV6) case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; if (sk->sk_family != AF_INET6) return -EINVAL; mss = tcp_v6_get_syncookie(sk, iph, th, &cookie); break; #endif /* CONFIG_IPV6 */ default: return -EPROTONOSUPPORT; } if (mss == 0) return -ENOENT; return cookie | ((u64)mss << 32); #else return -EOPNOTSUPP; #endif /* CONFIG_SYN_COOKIES */ } static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { .func = bpf_tcp_gen_syncookie, .gpl_only = true, /* __cookie_v*_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) { if (!sk || flags != 0) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EOPNOTSUPP; if (unlikely(dev_net(skb->dev) != sock_net(sk))) return -ENETUNREACH; if (sk_unhashed(sk)) return -EOPNOTSUPP; if (sk_is_refcounted(sk) && unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) return -ENOENT; skb_orphan(skb); skb->sk = sk; skb->destructor = sock_pfree; return 0; } static const struct bpf_func_proto bpf_sk_assign_proto = { .func = bpf_sk_assign, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_ANYTHING, }; static const u8 *bpf_search_tcp_opt(const u8 *op, const u8 *opend, u8 search_kind, const u8 *magic, u8 magic_len, bool *eol) { u8 kind, kind_len; *eol = false; while (op < opend) { kind = op[0]; if (kind == TCPOPT_EOL) { *eol = true; return ERR_PTR(-ENOMSG); } else if (kind == TCPOPT_NOP) { op++; continue; } if (opend - op < 2 || opend - op < op[1] || op[1] < 2) /* Something is wrong in the received header. * Follow the TCP stack's tcp_parse_options() * and just bail here. */ return ERR_PTR(-EFAULT); kind_len = op[1]; if (search_kind == kind) { if (!magic_len) return op; if (magic_len > kind_len - 2) return ERR_PTR(-ENOMSG); if (!memcmp(&op[2], magic, magic_len)) return op; } op += kind_len; } return ERR_PTR(-ENOMSG); } BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, void *, search_res, u32, len, u64, flags) { bool eol, load_syn = flags & BPF_LOAD_HDR_OPT_TCP_SYN; const u8 *op, *opend, *magic, *search = search_res; u8 search_kind, search_len, copy_len, magic_len; int ret; if (!is_locked_tcp_sock_ops(bpf_sock)) return -EOPNOTSUPP; /* 2 byte is the minimal option len except TCPOPT_NOP and * TCPOPT_EOL which are useless for the bpf prog to learn * and this helper disallow loading them also. */ if (len < 2 || flags & ~BPF_LOAD_HDR_OPT_TCP_SYN) return -EINVAL; search_kind = search[0]; search_len = search[1]; if (search_len > len || search_kind == TCPOPT_NOP || search_kind == TCPOPT_EOL) return -EINVAL; if (search_kind == TCPOPT_EXP || search_kind == 253) { /* 16 or 32 bit magic. +2 for kind and kind length */ if (search_len != 4 && search_len != 6) return -EINVAL; magic = &search[2]; magic_len = search_len - 2; } else { if (search_len) return -EINVAL; magic = NULL; magic_len = 0; } if (load_syn) { ret = bpf_sock_ops_get_syn(bpf_sock, TCP_BPF_SYN, &op); if (ret < 0) return ret; opend = op + ret; op += sizeof(struct tcphdr); } else { if (!bpf_sock->skb || bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB) /* This bpf_sock->op cannot call this helper */ return -EPERM; opend = bpf_sock->skb_data_end; op = bpf_sock->skb->data + sizeof(struct tcphdr); } op = bpf_search_tcp_opt(op, opend, search_kind, magic, magic_len, &eol); if (IS_ERR(op)) return PTR_ERR(op); copy_len = op[1]; ret = copy_len; if (copy_len > len) { ret = -ENOSPC; copy_len = len; } memcpy(search_res, op, copy_len); return ret; } static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = { .func = bpf_sock_ops_load_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_sock_ops_store_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, const void *, from, u32, len, u64, flags) { u8 new_kind, new_kind_len, magic_len = 0, *opend; const u8 *op, *new_op, *magic = NULL; struct sk_buff *skb; bool eol; if (bpf_sock->op != BPF_SOCK_OPS_WRITE_HDR_OPT_CB) return -EPERM; if (len < 2 || flags) return -EINVAL; new_op = from; new_kind = new_op[0]; new_kind_len = new_op[1]; if (new_kind_len > len || new_kind == TCPOPT_NOP || new_kind == TCPOPT_EOL) return -EINVAL; if (new_kind_len > bpf_sock->remaining_opt_len) return -ENOSPC; /* 253 is another experimental kind */ if (new_kind == TCPOPT_EXP || new_kind == 253) { if (new_kind_len < 4) return -EINVAL; /* Match for the 2 byte magic also. * RFC 6994: the magic could be 2 or 4 bytes. * Hence, matching by 2 byte only is on the * conservative side but it is the right * thing to do for the 'search-for-duplication' * purpose. */ magic = &new_op[2]; magic_len = 2; } /* Check for duplication */ skb = bpf_sock->skb; op = skb->data + sizeof(struct tcphdr); opend = bpf_sock->skb_data_end; op = bpf_search_tcp_opt(op, opend, new_kind, magic, magic_len, &eol); if (!IS_ERR(op)) return -EEXIST; if (PTR_ERR(op) != -ENOMSG) return PTR_ERR(op); if (eol) /* The option has been ended. Treat it as no more * header option can be written. */ return -ENOSPC; /* No duplication found. Store the header option. */ memcpy(opend, from, new_kind_len); bpf_sock->remaining_opt_len -= new_kind_len; bpf_sock->skb_data_end += new_kind_len; return 0; } static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = { .func = bpf_sock_ops_store_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_sock_ops_reserve_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, u32, len, u64, flags) { if (bpf_sock->op != BPF_SOCK_OPS_HDR_OPT_LEN_CB) return -EPERM; if (flags || len < 2) return -EINVAL; if (len > bpf_sock->remaining_opt_len) return -ENOSPC; bpf_sock->remaining_opt_len -= len; return 0; } static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { .func = bpf_sock_ops_reserve_hdr_opt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb, u64, tstamp, u32, tstamp_type) { /* skb_clear_delivery_time() is done for inet protocol */ if (skb->protocol != htons(ETH_P_IP) && skb->protocol != htons(ETH_P_IPV6)) return -EOPNOTSUPP; switch (tstamp_type) { case BPF_SKB_CLOCK_REALTIME: skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_REALTIME; break; case BPF_SKB_CLOCK_MONOTONIC: if (!tstamp) return -EINVAL; skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_MONOTONIC; break; case BPF_SKB_CLOCK_TAI: if (!tstamp) return -EINVAL; skb->tstamp = tstamp; skb->tstamp_type = SKB_CLOCK_TAI; break; default: return -EINVAL; } return 0; } static const struct bpf_func_proto bpf_skb_set_tstamp_proto = { .func = bpf_skb_set_tstamp, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; #ifdef CONFIG_SYN_COOKIES BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv4, struct iphdr *, iph, struct tcphdr *, th, u32, th_len) { u32 cookie; u16 mss; if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; mss = tcp_parse_mss_option(th, 0) ?: TCP_MSS_DEFAULT; cookie = __cookie_v4_init_sequence(iph, th, &mss); return cookie | ((u64)mss << 32); } static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv4_proto = { .func = bpf_tcp_raw_gen_syncookie_ipv4, .gpl_only = true, /* __cookie_v4_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct iphdr), .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv6, struct ipv6hdr *, iph, struct tcphdr *, th, u32, th_len) { #if IS_BUILTIN(CONFIG_IPV6) const u16 mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); u32 cookie; u16 mss; if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; mss = tcp_parse_mss_option(th, 0) ?: mss_clamp; cookie = __cookie_v6_init_sequence(iph, th, &mss); return cookie | ((u64)mss << 32); #else return -EPROTONOSUPPORT; #endif } static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = { .func = bpf_tcp_raw_gen_syncookie_ipv6, .gpl_only = true, /* __cookie_v6_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct ipv6hdr), .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph, struct tcphdr *, th) { if (__cookie_v4_check(iph, th) > 0) return 0; return -EACCES; } static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv4_proto = { .func = bpf_tcp_raw_check_syncookie_ipv4, .gpl_only = true, /* __cookie_v4_check is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct iphdr), .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg2_size = sizeof(struct tcphdr), }; BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv6, struct ipv6hdr *, iph, struct tcphdr *, th) { #if IS_BUILTIN(CONFIG_IPV6) if (__cookie_v6_check(iph, th) > 0) return 0; return -EACCES; #else return -EPROTONOSUPPORT; #endif } static const struct bpf_func_proto bpf_tcp_raw_check_syncookie_ipv6_proto = { .func = bpf_tcp_raw_check_syncookie_ipv6, .gpl_only = true, /* __cookie_v6_check is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct ipv6hdr), .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg2_size = sizeof(struct tcphdr), }; #endif /* CONFIG_SYN_COOKIES */ #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_clone_redirect: case BPF_FUNC_l3_csum_replace: case BPF_FUNC_l4_csum_replace: case BPF_FUNC_lwt_push_encap: case BPF_FUNC_lwt_seg6_action: case BPF_FUNC_lwt_seg6_adjust_srh: case BPF_FUNC_lwt_seg6_store_bytes: case BPF_FUNC_msg_pop_data: case BPF_FUNC_msg_pull_data: case BPF_FUNC_msg_push_data: case BPF_FUNC_skb_adjust_room: case BPF_FUNC_skb_change_head: case BPF_FUNC_skb_change_proto: case BPF_FUNC_skb_change_tail: case BPF_FUNC_skb_pull_data: case BPF_FUNC_skb_store_bytes: case BPF_FUNC_skb_vlan_pop: case BPF_FUNC_skb_vlan_push: case BPF_FUNC_store_hdr_opt: case BPF_FUNC_xdp_adjust_head: case BPF_FUNC_xdp_adjust_meta: case BPF_FUNC_xdp_adjust_tail: /* tail-called program could call any of the above */ case BPF_FUNC_tail_call: return true; default: return false; } } const struct bpf_func_proto bpf_event_output_data_proto __weak; const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto __weak; static const struct bpf_func_proto * sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_cg_sock_proto; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_bind: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: return &bpf_bind_proto; default: return NULL; } case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_addr_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_addr_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sock_addr_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sock_addr_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_sock_addr_skc_lookup_tcp_proto; #endif /* CONFIG_INET */ case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_setsockopt: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_setsockopt_proto; default: return NULL; } case BPF_FUNC_getsockopt: switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_getsockopt_proto; default: return NULL; } default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } const struct bpf_func_proto bpf_sk_storage_get_proto __weak; const struct bpf_func_proto bpf_sk_storage_delete_proto __weak; static const struct bpf_func_proto * cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; case BPF_FUNC_sk_cgroup_id: return &bpf_sk_cgroup_id_proto; case BPF_FUNC_sk_ancestor_cgroup_id: return &bpf_sk_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_skc_lookup_tcp_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; case BPF_FUNC_get_listener_sock: return &bpf_get_listener_sock_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; #endif default: return sk_filter_func_proto(func_id, prog); } } static const struct bpf_func_proto * tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_skb_pull_data: return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_csum_update: return &bpf_csum_update_proto; case BPF_FUNC_csum_level: return &bpf_csum_level_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_proto; case BPF_FUNC_skb_vlan_push: return &bpf_skb_vlan_push_proto; case BPF_FUNC_skb_vlan_pop: return &bpf_skb_vlan_pop_proto; case BPF_FUNC_skb_change_proto: return &bpf_skb_change_proto_proto; case BPF_FUNC_skb_change_type: return &bpf_skb_change_type_proto; case BPF_FUNC_skb_adjust_room: return &bpf_skb_adjust_room_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &bpf_skb_change_head_proto; case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_skb_get_tunnel_opt: return &bpf_skb_get_tunnel_opt_proto; case BPF_FUNC_skb_set_tunnel_opt: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_redirect_neigh: return &bpf_redirect_neigh_proto; case BPF_FUNC_redirect_peer: return &bpf_redirect_peer_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: return &bpf_get_hash_recalc_proto; case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; case BPF_FUNC_set_hash: return &bpf_set_hash_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_fib_lookup: return &bpf_skb_fib_lookup_proto; case BPF_FUNC_check_mtu: return &bpf_skb_check_mtu_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #ifdef CONFIG_XFRM case BPF_FUNC_skb_get_xfrm_state: return &bpf_skb_get_xfrm_state_proto; #endif #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_skb_cgroup_classid: return &bpf_skb_cgroup_classid_proto; #endif #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; case BPF_FUNC_skb_ancestor_cgroup_id: return &bpf_skb_ancestor_cgroup_id_proto; #endif #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_tc_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_tc_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; case BPF_FUNC_get_listener_sock: return &bpf_get_listener_sock_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_tc_skc_lookup_tcp_proto; case BPF_FUNC_tcp_check_syncookie: return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_skb_ecn_set_ce: return &bpf_skb_ecn_set_ce_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; case BPF_FUNC_sk_assign: return &bpf_sk_assign_proto; case BPF_FUNC_skb_set_tstamp: return &bpf_skb_set_tstamp_proto; #ifdef CONFIG_SYN_COOKIES case BPF_FUNC_tcp_raw_gen_syncookie_ipv4: return &bpf_tcp_raw_gen_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_gen_syncookie_ipv6: return &bpf_tcp_raw_gen_syncookie_ipv6_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv4: return &bpf_tcp_raw_check_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv6: return &bpf_tcp_raw_check_syncookie_ipv6_proto; #endif #endif default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_xdp_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_xdp_adjust_head: return &bpf_xdp_adjust_head_proto; case BPF_FUNC_xdp_adjust_meta: return &bpf_xdp_adjust_meta_proto; case BPF_FUNC_redirect: return &bpf_xdp_redirect_proto; case BPF_FUNC_redirect_map: return &bpf_xdp_redirect_map_proto; case BPF_FUNC_xdp_adjust_tail: return &bpf_xdp_adjust_tail_proto; case BPF_FUNC_xdp_get_buff_len: return &bpf_xdp_get_buff_len_proto; case BPF_FUNC_xdp_load_bytes: return &bpf_xdp_load_bytes_proto; case BPF_FUNC_xdp_store_bytes: return &bpf_xdp_store_bytes_proto; case BPF_FUNC_fib_lookup: return &bpf_xdp_fib_lookup_proto; case BPF_FUNC_check_mtu: return &bpf_xdp_check_mtu_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_udp: return &bpf_xdp_sk_lookup_udp_proto; case BPF_FUNC_sk_lookup_tcp: return &bpf_xdp_sk_lookup_tcp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_xdp_skc_lookup_tcp_proto; case BPF_FUNC_tcp_check_syncookie: return &bpf_tcp_check_syncookie_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; #ifdef CONFIG_SYN_COOKIES case BPF_FUNC_tcp_raw_gen_syncookie_ipv4: return &bpf_tcp_raw_gen_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_gen_syncookie_ipv6: return &bpf_tcp_raw_gen_syncookie_ipv6_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv4: return &bpf_tcp_raw_check_syncookie_ipv4_proto; case BPF_FUNC_tcp_raw_check_syncookie_ipv6: return &bpf_tcp_raw_check_syncookie_ipv6_proto; #endif #endif default: return bpf_sk_base_func_proto(func_id, prog); } #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) /* The nf_conn___init type is used in the NF_CONNTRACK kfuncs. The * kfuncs are defined in two different modules, and we want to be able * to use them interchangeably with the same BTF type ID. Because modules * can't de-duplicate BTF IDs between each other, we need the type to be * referenced in the vmlinux BTF or the verifier will get confused about * the different types. So we add this dummy type reference which will * be included in vmlinux BTF, allowing both modules to refer to the * same type ID. */ BTF_TYPE_EMIT(struct nf_conn___init); #endif } const struct bpf_func_proto bpf_sock_map_update_proto __weak; const struct bpf_func_proto bpf_sock_hash_update_proto __weak; static const struct bpf_func_proto * sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_setsockopt: return &bpf_sock_ops_setsockopt_proto; case BPF_FUNC_getsockopt: return &bpf_sock_ops_getsockopt_proto; case BPF_FUNC_sock_ops_cb_flags_set: return &bpf_sock_ops_cb_flags_set_proto; case BPF_FUNC_sock_map_update: return &bpf_sock_map_update_proto; case BPF_FUNC_sock_hash_update: return &bpf_sock_hash_update_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_sock_ops_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sock_ops_proto; #ifdef CONFIG_INET case BPF_FUNC_load_hdr_opt: return &bpf_sock_ops_load_hdr_opt_proto; case BPF_FUNC_store_hdr_opt: return &bpf_sock_ops_store_hdr_opt_proto; case BPF_FUNC_reserve_hdr_opt: return &bpf_sock_ops_reserve_hdr_opt_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: return bpf_sk_base_func_proto(func_id, prog); } } const struct bpf_func_proto bpf_msg_redirect_map_proto __weak; const struct bpf_func_proto bpf_msg_redirect_hash_proto __weak; static const struct bpf_func_proto * sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_msg_redirect_map: return &bpf_msg_redirect_map_proto; case BPF_FUNC_msg_redirect_hash: return &bpf_msg_redirect_hash_proto; case BPF_FUNC_msg_apply_bytes: return &bpf_msg_apply_bytes_proto; case BPF_FUNC_msg_cork_bytes: return &bpf_msg_cork_bytes_proto; case BPF_FUNC_msg_pull_data: return &bpf_msg_pull_data_proto; case BPF_FUNC_msg_push_data: return &bpf_msg_push_data_proto; case BPF_FUNC_msg_pop_data: return &bpf_msg_pop_data_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sk_msg_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } const struct bpf_func_proto bpf_sk_redirect_map_proto __weak; const struct bpf_func_proto bpf_sk_redirect_hash_proto __weak; static const struct bpf_func_proto * sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: return &sk_skb_pull_data_proto; case BPF_FUNC_skb_change_tail: return &sk_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &sk_skb_change_head_proto; case BPF_FUNC_skb_adjust_room: return &sk_skb_adjust_room_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; case BPF_FUNC_sk_redirect_map: return &bpf_sk_redirect_map_proto; case BPF_FUNC_sk_redirect_hash: return &bpf_sk_redirect_hash_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; #ifdef CONFIG_INET case BPF_FUNC_sk_lookup_tcp: return &bpf_sk_lookup_tcp_proto; case BPF_FUNC_sk_lookup_udp: return &bpf_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; case BPF_FUNC_skc_lookup_tcp: return &bpf_skc_lookup_tcp_proto; #endif default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: return &bpf_csum_diff_proto; case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: return &bpf_get_hash_recalc_proto; case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_in_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_lwt_push_encap: return &bpf_lwt_in_push_encap_proto; default: return lwt_out_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_get_tunnel_key: return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_skb_get_tunnel_opt: return &bpf_skb_get_tunnel_opt_proto; case BPF_FUNC_skb_set_tunnel_opt: return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; case BPF_FUNC_clone_redirect: return &bpf_clone_redirect_proto; case BPF_FUNC_skb_change_tail: return &bpf_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &bpf_skb_change_head_proto; case BPF_FUNC_skb_store_bytes: return &bpf_skb_store_bytes_proto; case BPF_FUNC_csum_update: return &bpf_csum_update_proto; case BPF_FUNC_csum_level: return &bpf_csum_level_proto; case BPF_FUNC_l3_csum_replace: return &bpf_l3_csum_replace_proto; case BPF_FUNC_l4_csum_replace: return &bpf_l4_csum_replace_proto; case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; case BPF_FUNC_lwt_push_encap: return &bpf_lwt_xmit_push_encap_proto; default: return lwt_out_func_proto(func_id, prog); } } static const struct bpf_func_proto * lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_FUNC_lwt_seg6_store_bytes: return &bpf_lwt_seg6_store_bytes_proto; case BPF_FUNC_lwt_seg6_action: return &bpf_lwt_seg6_action_proto; case BPF_FUNC_lwt_seg6_adjust_srh: return &bpf_lwt_seg6_adjust_srh_proto; #endif default: return lwt_out_func_proto(func_id, prog); } } static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct __sk_buff)) return false; /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; switch (off) { case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): if (off + size > offsetofend(struct __sk_buff, cb[4])) return false; break; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): if (info->is_ldsx || size != size_default) return false; break; case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): if (size != size_default) return false; break; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; case bpf_ctx_range(struct __sk_buff, hwtstamp): if (type == BPF_WRITE || size != sizeof(__u64)) return false; break; case bpf_ctx_range(struct __sk_buff, tstamp): if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct __sk_buff, sk): if (type == BPF_WRITE || size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; break; case offsetof(struct __sk_buff, tstamp_type): return false; case offsetofend(struct __sk_buff, tstamp_type) ... offsetof(struct __sk_buff, hwtstamp) - 1: /* Explicitly prohibit access to padding in __sk_buff. */ return false; default: /* Only narrow read access allowed for now. */ if (type == BPF_WRITE) { if (size != size_default) return false; } else { bpf_ctx_record_field_size(info, size_default); if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; } } return true; } static bool sk_filter_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; } } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool cg_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, wire_len): return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; case bpf_ctx_range(struct __sk_buff, tstamp): if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool lwt_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } /* Attach type specific accesses */ static bool __sock_filter_check_attach_type(int off, enum bpf_access_type access_type, enum bpf_attach_type attach_type) { switch (off) { case offsetof(struct bpf_sock, bound_dev_if): case offsetof(struct bpf_sock, mark): case offsetof(struct bpf_sock, priority): switch (attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: goto full_access; default: return false; } case bpf_ctx_range(struct bpf_sock, src_ip4): switch (attach_type) { case BPF_CGROUP_INET4_POST_BIND: goto read_only; default: return false; } case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): switch (attach_type) { case BPF_CGROUP_INET6_POST_BIND: goto read_only; default: return false; } case bpf_ctx_range(struct bpf_sock, src_port): switch (attach_type) { case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: goto read_only; default: return false; } } read_only: return access_type == BPF_READ; full_access: return true; } bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range_till(struct bpf_sock, type, priority): return false; default: return bpf_sock_is_valid_access(off, size, type, info); } } bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); int field_size; if (off < 0 || off >= sizeof(struct bpf_sock)) return false; if (off % size != 0) return false; switch (off) { case offsetof(struct bpf_sock, state): case offsetof(struct bpf_sock, family): case offsetof(struct bpf_sock, type): case offsetof(struct bpf_sock, protocol): case offsetof(struct bpf_sock, src_port): case offsetof(struct bpf_sock, rx_queue_mapping): case bpf_ctx_range(struct bpf_sock, src_ip4): case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): case bpf_ctx_range(struct bpf_sock, dst_ip4): case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); case bpf_ctx_range(struct bpf_sock, dst_port): field_size = size == size_default ? size_default : sizeof_field(struct bpf_sock, dst_port); bpf_ctx_record_field_size(info, field_size); return bpf_ctx_narrow_access_ok(off, size, field_size); case offsetofend(struct bpf_sock, dst_port) ... offsetof(struct bpf_sock, dst_ip4) - 1: return false; } return size == size_default; } static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (!bpf_sock_is_valid_access(off, size, type, info)) return false; return __sock_filter_check_attach_type(off, type, prog->expected_attach_type); } static int bpf_noop_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { /* Neither direct read nor direct write requires any preliminary * action. */ return 0; } static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog, int drop_verdict) { struct bpf_insn *insn = insn_buf; if (!direct_write) return 0; /* if (!skb->cloned) * goto start; * * (Fast-path, otherwise approximation that we might be * a clone, do the rest in helper.) */ *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_6, CLONED_MASK); *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 7); /* ret = bpf_skb_pull_data(skb, 0); */ *insn++ = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); *insn++ = BPF_ALU64_REG(BPF_XOR, BPF_REG_2, BPF_REG_2); *insn++ = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_skb_pull_data); /* if (!ret) * goto restore; * return TC_ACT_SHOT; */ *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2); *insn++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, drop_verdict); *insn++ = BPF_EXIT_INSN(); /* restore: */ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); /* start: */ *insn++ = prog->insnsi[0]; return insn - insn_buf; } static int bpf_gen_ld_abs(const struct bpf_insn *orig, struct bpf_insn *insn_buf) { bool indirect = BPF_MODE(orig->code) == BPF_IND; struct bpf_insn *insn = insn_buf; if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm); } else { *insn++ = BPF_MOV64_REG(BPF_REG_2, orig->src_reg); if (orig->imm) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm); } /* We're guaranteed here that CTX is in R6. */ *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); switch (BPF_SIZE(orig->code)) { case BPF_B: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8_no_cache); break; case BPF_H: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16_no_cache); break; case BPF_W: *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32_no_cache); break; } *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 2); *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0); *insn++ = BPF_EXIT_INSN(); return insn - insn_buf; } static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { return bpf_unclone_prologue(insn_buf, direct_write, prog, TC_ACT_SHOT); } static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, mark): case bpf_ctx_range(struct __sk_buff, tc_index): case bpf_ctx_range(struct __sk_buff, priority): case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, queue_mapping): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_meta): info->reg_type = PTR_TO_PACKET_META; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; case offsetof(struct __sk_buff, tstamp_type): /* The convert_ctx_access() on reading and writing * __sk_buff->tstamp depends on whether the bpf prog * has used __sk_buff->tstamp_type or not. * Thus, we need to set prog->tstamp_type_access * earlier during is_valid_access() here. */ ((struct bpf_prog *)prog)->tstamp_type_access = 1; return size == sizeof(__u8); } return bpf_skb_is_valid_access(off, size, type, prog, info); } DEFINE_MUTEX(nf_conn_btf_access_lock); EXPORT_SYMBOL_GPL(nf_conn_btf_access_lock); int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size); EXPORT_SYMBOL_GPL(nfct_btf_struct_access); static int tc_cls_act_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size) { int ret = -EACCES; mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) ret = nfct_btf_struct_access(log, reg, off, size); mutex_unlock(&nf_conn_btf_access_lock); return ret; } static bool __is_valid_xdp_access(int off, int size) { if (off < 0 || off >= sizeof(struct xdp_md)) return false; if (off % size != 0) return false; if (size != sizeof(__u32)) return false; return true; } static bool xdp_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (prog->expected_attach_type != BPF_XDP_DEVMAP) { switch (off) { case offsetof(struct xdp_md, egress_ifindex): return false; } } if (type == BPF_WRITE) { if (bpf_prog_is_offloaded(prog->aux)) { switch (off) { case offsetof(struct xdp_md, rx_queue_index): return __is_valid_xdp_access(off, size); } } return false; } else { switch (off) { case offsetof(struct xdp_md, data_meta): case offsetof(struct xdp_md, data): case offsetof(struct xdp_md, data_end): if (info->is_ldsx) return false; } } switch (off) { case offsetof(struct xdp_md, data): info->reg_type = PTR_TO_PACKET; break; case offsetof(struct xdp_md, data_meta): info->reg_type = PTR_TO_PACKET_META; break; case offsetof(struct xdp_md, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return __is_valid_xdp_access(off, size); } void bpf_warn_invalid_xdp_action(const struct net_device *dev, const struct bpf_prog *prog, u32 act) { const u32 act_max = XDP_REDIRECT; pr_warn_once("%s XDP return value %u on prog %s (id %d) dev %s, expect packet loss!\n", act > act_max ? "Illegal" : "Driver unsupported", act, prog->aux->name, prog->aux->id, dev ? dev->name : "N/A"); } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); static int xdp_btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size) { int ret = -EACCES; mutex_lock(&nf_conn_btf_access_lock); if (nfct_btf_struct_access) ret = nfct_btf_struct_access(log, reg, off, size); mutex_unlock(&nf_conn_btf_access_lock); return ret; } static bool sock_addr_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct bpf_sock_addr)) return false; if (off % size != 0) return false; /* Disallow access to fields not belonging to the attach type's address * family. */ switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: break; default: return false; } break; case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): switch (prog->expected_attach_type) { case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP6_RECVMSG: break; default: return false; } break; case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): switch (prog->expected_attach_type) { case BPF_CGROUP_UDP4_SENDMSG: break; default: return false; } break; case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): switch (prog->expected_attach_type) { case BPF_CGROUP_UDP6_SENDMSG: break; default: return false; } break; } switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): case bpf_ctx_range(struct bpf_sock_addr, user_port): if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, user_ip6)) return true; if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, msg_src_ip6)) return true; if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; } else { if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, user_ip6)) return true; if (bpf_ctx_wide_access_ok(off, size, struct bpf_sock_addr, msg_src_ip6)) return true; if (size != size_default) return false; } break; case bpf_ctx_range_ptr(struct bpf_sock_addr, sk): if (type != BPF_READ) return false; if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; case bpf_ctx_range(struct bpf_sock_addr, user_family): case bpf_ctx_range(struct bpf_sock_addr, family): case bpf_ctx_range(struct bpf_sock_addr, type): case bpf_ctx_range(struct bpf_sock_addr, protocol): if (type != BPF_READ) return false; if (size != size_default) return false; break; default: return false; } return true; } static bool sock_ops_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct bpf_sock_ops)) return false; /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; if (type == BPF_WRITE) { switch (off) { case offsetof(struct bpf_sock_ops, reply): case offsetof(struct bpf_sock_ops, sk_txhash): if (size != size_default) return false; break; default: return false; } } else { switch (off) { case bpf_ctx_range_till(struct bpf_sock_ops, bytes_received, bytes_acked): if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct bpf_sock_ops, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET_OR_NULL; break; case bpf_ctx_range_ptr(struct bpf_sock_ops, skb_data): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range_ptr(struct bpf_sock_ops, skb_data_end): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET_END; break; case offsetof(struct bpf_sock_ops, skb_tcp_flags): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); case bpf_ctx_range(struct bpf_sock_ops, skb_hwtstamp): if (size != sizeof(__u64)) return false; break; default: if (size != size_default) return false; break; } } return true; } static int sk_skb_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { return bpf_unclone_prologue(insn_buf, direct_write, prog, SK_DROP); } static bool sk_skb_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } if (type == BPF_WRITE) { switch (off) { case bpf_ctx_range(struct __sk_buff, tc_index): case bpf_ctx_range(struct __sk_buff, priority): break; default: return false; } } switch (off) { case bpf_ctx_range(struct __sk_buff, mark): return false; case bpf_ctx_range(struct __sk_buff, data): info->reg_type = PTR_TO_PACKET; break; case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; } return bpf_skb_is_valid_access(off, size, type, prog, info); } static bool sk_msg_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (type == BPF_WRITE) return false; if (off % size != 0) return false; switch (off) { case bpf_ctx_range_ptr(struct sk_msg_md, data): info->reg_type = PTR_TO_PACKET; if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct sk_msg_md, data_end): info->reg_type = PTR_TO_PACKET_END; if (size != sizeof(__u64)) return false; break; case bpf_ctx_range_ptr(struct sk_msg_md, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; case bpf_ctx_range(struct sk_msg_md, family): case bpf_ctx_range(struct sk_msg_md, remote_ip4): case bpf_ctx_range(struct sk_msg_md, local_ip4): case bpf_ctx_range_till(struct sk_msg_md, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct sk_msg_md, local_ip6[0], local_ip6[3]): case bpf_ctx_range(struct sk_msg_md, remote_port): case bpf_ctx_range(struct sk_msg_md, local_port): case bpf_ctx_range(struct sk_msg_md, size): if (size != sizeof(__u32)) return false; break; default: return false; } return true; } static bool flow_dissector_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct __sk_buff)) return false; if (off % size != 0) return false; if (type == BPF_WRITE) return false; switch (off) { case bpf_ctx_range(struct __sk_buff, data): if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET; return true; case bpf_ctx_range(struct __sk_buff, data_end): if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET_END; return true; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_FLOW_KEYS; return true; default: return false; } } static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct __sk_buff, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, data)); break; case offsetof(struct __sk_buff, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data_end), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, data_end)); break; case offsetof(struct __sk_buff, flow_keys): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, flow_keys), si->dst_reg, si->src_reg, offsetof(struct bpf_flow_dissector, flow_keys)); break; } return insn - insn_buf; } static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; BUILD_BUG_ON(__SKB_CLOCK_MAX != (int)BPF_SKB_CLOCK_TAI); BUILD_BUG_ON(SKB_CLOCK_REALTIME != (int)BPF_SKB_CLOCK_REALTIME); BUILD_BUG_ON(SKB_CLOCK_MONOTONIC != (int)BPF_SKB_CLOCK_MONOTONIC); BUILD_BUG_ON(SKB_CLOCK_TAI != (int)BPF_SKB_CLOCK_TAI); *insn++ = BPF_LDX_MEM(BPF_B, value_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, value_reg, SKB_TSTAMP_TYPE_MASK); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, value_reg, SKB_TSTAMP_TYPE_RSHIFT); #else BUILD_BUG_ON(!(SKB_TSTAMP_TYPE_MASK & 0x1)); #endif return insn; } static struct bpf_insn *bpf_convert_shinfo_access(__u8 dst_reg, __u8 skb_reg, struct bpf_insn *insn) { /* si->dst_reg = skb_shinfo(SKB); */ #ifdef NET_SKBUFF_DATA_USES_OFFSET *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), BPF_REG_AX, skb_reg, offsetof(struct sk_buff, end)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), dst_reg, skb_reg, offsetof(struct sk_buff, head)); *insn++ = BPF_ALU64_REG(BPF_ADD, dst_reg, BPF_REG_AX); #else *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), dst_reg, skb_reg, offsetof(struct sk_buff, end)); #endif return insn; } static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; #ifdef CONFIG_NET_XGRESS /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. * Thus, read skb->tstamp as is if tstamp_type_access is true. */ if (!prog->tstamp_type_access) { /* AX is needed because src_reg and dst_reg could be the same */ __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); /* check if ingress mask bits is set */ *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); *insn++ = BPF_JMP_A(4); *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, SKB_TSTAMP_TYPE_MASK, 1); *insn++ = BPF_JMP_A(2); /* skb->tc_at_ingress && skb->tstamp_type, * read 0 as the (rcv) timestamp. */ *insn++ = BPF_MOV64_IMM(value_reg, 0); *insn++ = BPF_JMP_A(1); } #endif *insn++ = BPF_LDX_MEM(BPF_DW, value_reg, skb_reg, offsetof(struct sk_buff, tstamp)); return insn; } static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, const struct bpf_insn *si, struct bpf_insn *insn) { __u8 value_reg = si->src_reg; __u8 skb_reg = si->dst_reg; #ifdef CONFIG_NET_XGRESS /* If the tstamp_type is read, * the bpf prog is aware the tstamp could have delivery time. * Thus, write skb->tstamp as is if tstamp_type_access is true. * Otherwise, writing at ingress will have to clear the * skb->tstamp_type bit also. */ if (!prog->tstamp_type_access) { __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); /* Writing __sk_buff->tstamp as ingress, goto <clear> */ *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); /* goto <store> */ *insn++ = BPF_JMP_A(2); /* <clear>: skb->tstamp_type */ *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_TSTAMP_TYPE_MASK); *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET); } #endif /* <store>: skb->tstamp = tstamp */ *insn++ = BPF_RAW_INSN(BPF_CLASS(si->code) | BPF_DW | BPF_MEM, skb_reg, value_reg, offsetof(struct sk_buff, tstamp), si->imm); return insn; } #define BPF_EMIT_STORE(size, si, off) \ BPF_RAW_INSN(BPF_CLASS((si)->code) | (size) | BPF_MEM, \ (si)->dst_reg, (si)->src_reg, (off), (si)->imm) static u32 bpf_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct __sk_buff, len): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, len, 4, target_size)); break; case offsetof(struct __sk_buff, protocol): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, protocol, 2, target_size)); break; case offsetof(struct __sk_buff, vlan_proto): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_proto, 2, target_size)); break; case offsetof(struct __sk_buff, priority): if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, bpf_target_off(struct sk_buff, priority, 4, target_size)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, priority, 4, target_size)); break; case offsetof(struct __sk_buff, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, skb_iif, 4, target_size)); break; case offsetof(struct __sk_buff, ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct net_device, ifindex, 4, target_size)); break; case offsetof(struct __sk_buff, hash): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, hash, 4, target_size)); break; case offsetof(struct __sk_buff, mark): if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, bpf_target_off(struct sk_buff, mark, 4, target_size)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, mark, 4, target_size)); break; case offsetof(struct __sk_buff, pkt_type): *target_size = 1; *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg, PKT_TYPE_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, PKT_TYPE_MAX); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, 5); #endif break; case offsetof(struct __sk_buff, queue_mapping): if (type == BPF_WRITE) { u32 offset = bpf_target_off(struct sk_buff, queue_mapping, 2, target_size); if (BPF_CLASS(si->code) == BPF_ST && si->imm >= NO_QUEUE_MAPPING) { *insn++ = BPF_JMP_A(0); /* noop */ break; } if (BPF_CLASS(si->code) == BPF_STX) *insn++ = BPF_JMP_IMM(BPF_JGE, si->src_reg, NO_QUEUE_MAPPING, 1); *insn++ = BPF_EMIT_STORE(BPF_H, si, offset); } else { *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, queue_mapping, 2, target_size)); } break; case offsetof(struct __sk_buff, vlan_present): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_all, 4, target_size)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_ALU32_IMM(BPF_MOV, si->dst_reg, 1); break; case offsetof(struct __sk_buff, vlan_tci): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, vlan_tci, 2, target_size)); break; case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data)) % sizeof(__u64)); prog->cb_access = 1; off = si->off; off -= offsetof(struct __sk_buff, cb[0]); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, data); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_SIZE(si->code), si, off); else *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, tc_classid): BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, tc_classid) != 2); off = si->off; off -= offsetof(struct __sk_buff, tc_classid); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, tc_classid); *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_H, si, off); else *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), si->dst_reg, si->src_reg, offsetof(struct sk_buff, data)); break; case offsetof(struct __sk_buff, data_meta): off = si->off; off -= offsetof(struct __sk_buff, data_meta); off += offsetof(struct sk_buff, cb); off += offsetof(struct bpf_skb_data_end, data_meta); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, data_end): off = si->off; off -= offsetof(struct __sk_buff, data_end); off += offsetof(struct sk_buff, cb); off += offsetof(struct bpf_skb_data_end, data_end); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, tc_index): #ifdef CONFIG_NET_SCHED if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_H, si, bpf_target_off(struct sk_buff, tc_index, 2, target_size)); else *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, tc_index, 2, target_size)); #else *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_MOV64_REG(si->dst_reg, si->dst_reg); else *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, napi_id): #if defined(CONFIG_NET_RX_BUSY_POLL) *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct sk_buff, napi_id, 4, target_size)); *insn++ = BPF_JMP_IMM(BPF_JGE, si->dst_reg, MIN_NAPI_ID, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #else *target_size = 4; *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_family, 2, target_size)); break; case offsetof(struct __sk_buff, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_daddr, 4, target_size)); break; case offsetof(struct __sk_buff, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, 4, target_size)); break; case offsetof(struct __sk_buff, remote_ip6[0]) ... offsetof(struct __sk_buff, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct __sk_buff, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, local_ip6[0]) ... offsetof(struct __sk_buff, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct __sk_buff, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct __sk_buff, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_dport, 2, target_size)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct __sk_buff, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, bpf_target_off(struct sock_common, skc_num, 2, target_size)); break; case offsetof(struct __sk_buff, tstamp): BUILD_BUG_ON(sizeof_field(struct sk_buff, tstamp) != 8); if (type == BPF_WRITE) insn = bpf_convert_tstamp_write(prog, si, insn); else insn = bpf_convert_tstamp_read(prog, si, insn); break; case offsetof(struct __sk_buff, tstamp_type): insn = bpf_convert_tstamp_type_read(si, insn); break; case offsetof(struct __sk_buff, gso_segs): insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, gso_segs, 2, target_size)); break; case offsetof(struct __sk_buff, gso_size): insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_size), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, gso_size, 2, target_size)); break; case offsetof(struct __sk_buff, wire_len): BUILD_BUG_ON(sizeof_field(struct qdisc_skb_cb, pkt_len) != 4); off = si->off; off -= offsetof(struct __sk_buff, wire_len); off += offsetof(struct sk_buff, cb); off += offsetof(struct qdisc_skb_cb, pkt_len); *target_size = 4; *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off); break; case offsetof(struct __sk_buff, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); break; case offsetof(struct __sk_buff, hwtstamp): BUILD_BUG_ON(sizeof_field(struct skb_shared_hwtstamps, hwtstamp) != 8); BUILD_BUG_ON(offsetof(struct skb_shared_hwtstamps, hwtstamp) != 0); insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, hwtstamps, 8, target_size)); break; } return insn - insn_buf; } u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct bpf_sock, bound_dev_if): BUILD_BUG_ON(sizeof_field(struct sock, sk_bound_dev_if) != 4); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, offsetof(struct sock, sk_bound_dev_if)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_bound_dev_if)); break; case offsetof(struct bpf_sock, mark): BUILD_BUG_ON(sizeof_field(struct sock, sk_mark) != 4); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, offsetof(struct sock, sk_mark)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_mark)); break; case offsetof(struct bpf_sock, priority): BUILD_BUG_ON(sizeof_field(struct sock, sk_priority) != 4); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, offsetof(struct sock, sk_priority)); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, sk_priority)); break; case offsetof(struct bpf_sock, family): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_family), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_family, sizeof_field(struct sock_common, skc_family), target_size)); break; case offsetof(struct bpf_sock, type): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_type), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_type, sizeof_field(struct sock, sk_type), target_size)); break; case offsetof(struct bpf_sock, protocol): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_protocol), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_protocol, sizeof_field(struct sock, sk_protocol), target_size)); break; case offsetof(struct bpf_sock, src_ip4): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, sizeof_field(struct sock_common, skc_rcv_saddr), target_size)); break; case offsetof(struct bpf_sock, dst_ip4): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_daddr, sizeof_field(struct sock_common, skc_daddr), target_size)); break; case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) off = si->off; off -= offsetof(struct bpf_sock, src_ip6[0]); *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off( struct sock_common, skc_v6_rcv_saddr.s6_addr32[0], sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]), target_size) + off); #else (void)off; *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) off = si->off; off -= offsetof(struct bpf_sock, dst_ip6[0]); *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_v6_daddr.s6_addr32[0], sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]), target_size) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); *target_size = 4; #endif break; case offsetof(struct bpf_sock, src_port): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_num), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_num, sizeof_field(struct sock_common, skc_num), target_size)); break; case offsetof(struct bpf_sock, dst_port): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_dport), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_dport, sizeof_field(struct sock_common, skc_dport), target_size)); break; case offsetof(struct bpf_sock, state): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_state), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_state, sizeof_field(struct sock_common, skc_state), target_size)); break; case offsetof(struct bpf_sock, rx_queue_mapping): #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock, sk_rx_queue_mapping), si->dst_reg, si->src_reg, bpf_target_off(struct sock, sk_rx_queue_mapping, sizeof_field(struct sock, sk_rx_queue_mapping), target_size)); *insn++ = BPF_JMP_IMM(BPF_JNE, si->dst_reg, NO_QUEUE_MAPPING, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, -1); #else *insn++ = BPF_MOV64_IMM(si->dst_reg, -1); *target_size = 2; #endif break; } return insn - insn_buf; } static u32 tc_cls_act_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct __sk_buff, ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), si->dst_reg, si->src_reg, offsetof(struct sk_buff, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, bpf_target_off(struct net_device, ifindex, 4, target_size)); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); } return insn - insn_buf; } static u32 xdp_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct xdp_md, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data)); break; case offsetof(struct xdp_md, data_meta): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_meta), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data_meta)); break; case offsetof(struct xdp_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, data_end), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, data_end)); break; case offsetof(struct xdp_md, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, rxq)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_rxq_info, dev), si->dst_reg, si->dst_reg, offsetof(struct xdp_rxq_info, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; case offsetof(struct xdp_md, rx_queue_index): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, rxq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, rxq)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct xdp_rxq_info, queue_index)); break; case offsetof(struct xdp_md, egress_ifindex): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_buff, txq), si->dst_reg, si->src_reg, offsetof(struct xdp_buff, txq)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_txq_info, dev), si->dst_reg, si->dst_reg, offsetof(struct xdp_txq_info, dev)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct net_device, ifindex)); break; } return insn - insn_buf; } /* SOCK_ADDR_LOAD_NESTED_FIELD() loads Nested Field S.F.NF where S is type of * context Structure, F is Field in context structure that contains a pointer * to Nested Structure of type NS that has the field NF. * * SIZE encodes the load size (BPF_B, BPF_H, etc). It's up to caller to make * sure that SIZE is not greater than actual size of S.F.NF. * * If offset OFF is provided, the load happens from that offset relative to * offset of NF. */ #define SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, SIZE, OFF) \ do { \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), si->dst_reg, \ si->src_reg, offsetof(S, F)); \ *insn++ = BPF_LDX_MEM( \ SIZE, si->dst_reg, si->dst_reg, \ bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF); \ } while (0) #define SOCK_ADDR_LOAD_NESTED_FIELD(S, NS, F, NF) \ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, \ BPF_FIELD_SIZEOF(NS, NF), 0) /* SOCK_ADDR_STORE_NESTED_FIELD_OFF() has semantic similar to * SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF() but for store operation. * * In addition it uses Temporary Field TF (member of struct S) as the 3rd * "register" since two registers available in convert_ctx_access are not * enough: we can't override neither SRC, since it contains value to store, nor * DST since it contains pointer to context that may be used by later * instructions. But we need a temporary place to save pointer to nested * structure whose field we want to store to. */ #define SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, OFF, TF) \ do { \ int tmp_reg = BPF_REG_9; \ if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg) \ --tmp_reg; \ if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg) \ --tmp_reg; \ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, tmp_reg, \ offsetof(S, TF)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg, \ si->dst_reg, offsetof(S, F)); \ *insn++ = BPF_RAW_INSN(SIZE | BPF_MEM | BPF_CLASS(si->code), \ tmp_reg, si->src_reg, \ bpf_target_off(NS, NF, sizeof_field(NS, NF), \ target_size) \ + OFF, \ si->imm); \ *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, si->dst_reg, \ offsetof(S, TF)); \ } while (0) #define SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(S, NS, F, NF, SIZE, OFF, \ TF) \ do { \ if (type == BPF_WRITE) { \ SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, \ OFF, TF); \ } else { \ SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF( \ S, NS, F, NF, SIZE, OFF); \ } \ } while (0) static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { int off, port_size = sizeof_field(struct sockaddr_in6, sin6_port); struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_sock_addr, user_family): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sockaddr, uaddr, sa_family); break; case offsetof(struct bpf_sock_addr, user_ip4): SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in, uaddr, sin_addr, BPF_SIZE(si->code), 0, tmp_reg); break; case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): off = si->off; off -= offsetof(struct bpf_sock_addr, user_ip6[0]); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_addr.s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); break; case offsetof(struct bpf_sock_addr, user_port): /* To get port we need to know sa_family first and then treat * sockaddr as either sockaddr_in or sockaddr_in6. * Though we can simplify since port field has same offset and * size in both structures. * Here we check this invariant and use just one of the * structures if it's true. */ BUILD_BUG_ON(offsetof(struct sockaddr_in, sin_port) != offsetof(struct sockaddr_in6, sin6_port)); BUILD_BUG_ON(sizeof_field(struct sockaddr_in, sin_port) != sizeof_field(struct sockaddr_in6, sin6_port)); /* Account for sin6_port being smaller than user_port. */ port_size = min(port_size, BPF_LDST_BYTES(si)); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_port, bytes_to_bpf_size(port_size), 0, tmp_reg); break; case offsetof(struct bpf_sock_addr, family): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_family); break; case offsetof(struct bpf_sock_addr, type): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_type); break; case offsetof(struct bpf_sock_addr, protocol): SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, struct sock, sk, sk_protocol); break; case offsetof(struct bpf_sock_addr, msg_src_ip4): /* Treat t_ctx as struct in_addr for msg_src_ip4. */ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct in_addr, t_ctx, s_addr, BPF_SIZE(si->code), 0, tmp_reg); break; case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], msg_src_ip6[3]): off = si->off; off -= offsetof(struct bpf_sock_addr, msg_src_ip6[0]); /* Treat t_ctx as struct in6_addr for msg_src_ip6. */ SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( struct bpf_sock_addr_kern, struct in6_addr, t_ctx, s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); break; case offsetof(struct bpf_sock_addr, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_addr_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_addr_kern, sk)); break; } return insn - insn_buf; } static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 2; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ fullsock_reg = reg; \ jmp += 2; \ } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_locked_tcp_sock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_locked_tcp_sock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(OBJ, \ OBJ_FIELD), \ si->dst_reg, si->dst_reg, \ offsetof(OBJ, OBJ_FIELD)); \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_JMP_A(1); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } \ } while (0) #define SOCK_OPS_GET_SK() \ do { \ int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 1; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ fullsock_reg = reg; \ jmp += 2; \ } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_fullsock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ if (si->dst_reg == si->src_reg) \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ if (si->dst_reg == si->src_reg) { \ *insn++ = BPF_JMP_A(1); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } \ } while (0) #define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \ SOCK_OPS_GET_FIELD(FIELD, FIELD, struct tcp_sock) /* Helper macro for adding write access to tcp_sock or sock fields. * The macro is called with two registers, dst_reg which contains a pointer * to ctx (context) and src_reg which contains the value that should be * stored. However, we need an additional register since we cannot overwrite * dst_reg because it may be used later in the program. * Instead we "borrow" one of the other register. We first save its value * into a new (temp) field in bpf_sock_ops_kern, use it, and then restore * it at the end of the macro. */ #define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int reg = BPF_REG_9; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_locked_tcp_sock), \ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_locked_tcp_sock)); \ *insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, sk));\ *insn++ = BPF_RAW_INSN(BPF_FIELD_SIZEOF(OBJ, OBJ_FIELD) | \ BPF_MEM | BPF_CLASS(si->code), \ reg, si->src_reg, \ offsetof(OBJ, OBJ_FIELD), \ si->imm); \ *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->dst_reg, \ offsetof(struct bpf_sock_ops_kern, \ temp)); \ } while (0) #define SOCK_OPS_GET_OR_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ, TYPE) \ do { \ if (TYPE == BPF_WRITE) \ SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ else \ SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ } while (0) switch (si->off) { case offsetof(struct bpf_sock_ops, op): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, op), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, op)); break; case offsetof(struct bpf_sock_ops, replylong[0]) ... offsetof(struct bpf_sock_ops, replylong[3]): BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) != sizeof_field(struct bpf_sock_ops_kern, reply)); BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) != sizeof_field(struct bpf_sock_ops_kern, replylong)); off = si->off; off -= offsetof(struct bpf_sock_ops, replylong[0]); off += offsetof(struct bpf_sock_ops_kern, replylong[0]); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_W, si, off); else *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off); break; case offsetof(struct bpf_sock_ops, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_family)); break; case offsetof(struct bpf_sock_ops, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_daddr)); break; case offsetof(struct bpf_sock_ops, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_rcv_saddr)); break; case offsetof(struct bpf_sock_ops, remote_ip6[0]) ... offsetof(struct bpf_sock_ops, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct bpf_sock_ops, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct bpf_sock_ops, local_ip6[0]) ... offsetof(struct bpf_sock_ops, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct bpf_sock_ops, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct bpf_sock_ops, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_dport)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct bpf_sock_ops, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_num)); break; case offsetof(struct bpf_sock_ops, is_fullsock): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, is_fullsock), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, is_fullsock)); break; case offsetof(struct bpf_sock_ops, state): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_state) != 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_state)); break; case offsetof(struct bpf_sock_ops, rtt_min): BUILD_BUG_ON(sizeof_field(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct tcp_sock, rtt_min) + sizeof_field(struct minmax_sample, t)); break; case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags): SOCK_OPS_GET_FIELD(bpf_sock_ops_cb_flags, bpf_sock_ops_cb_flags, struct tcp_sock); break; case offsetof(struct bpf_sock_ops, sk_txhash): SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash, struct sock, type); break; case offsetof(struct bpf_sock_ops, snd_cwnd): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_cwnd); break; case offsetof(struct bpf_sock_ops, srtt_us): SOCK_OPS_GET_TCP_SOCK_FIELD(srtt_us); break; case offsetof(struct bpf_sock_ops, snd_ssthresh): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_ssthresh); break; case offsetof(struct bpf_sock_ops, rcv_nxt): SOCK_OPS_GET_TCP_SOCK_FIELD(rcv_nxt); break; case offsetof(struct bpf_sock_ops, snd_nxt): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_nxt); break; case offsetof(struct bpf_sock_ops, snd_una): SOCK_OPS_GET_TCP_SOCK_FIELD(snd_una); break; case offsetof(struct bpf_sock_ops, mss_cache): SOCK_OPS_GET_TCP_SOCK_FIELD(mss_cache); break; case offsetof(struct bpf_sock_ops, ecn_flags): SOCK_OPS_GET_TCP_SOCK_FIELD(ecn_flags); break; case offsetof(struct bpf_sock_ops, rate_delivered): SOCK_OPS_GET_TCP_SOCK_FIELD(rate_delivered); break; case offsetof(struct bpf_sock_ops, rate_interval_us): SOCK_OPS_GET_TCP_SOCK_FIELD(rate_interval_us); break; case offsetof(struct bpf_sock_ops, packets_out): SOCK_OPS_GET_TCP_SOCK_FIELD(packets_out); break; case offsetof(struct bpf_sock_ops, retrans_out): SOCK_OPS_GET_TCP_SOCK_FIELD(retrans_out); break; case offsetof(struct bpf_sock_ops, total_retrans): SOCK_OPS_GET_TCP_SOCK_FIELD(total_retrans); break; case offsetof(struct bpf_sock_ops, segs_in): SOCK_OPS_GET_TCP_SOCK_FIELD(segs_in); break; case offsetof(struct bpf_sock_ops, data_segs_in): SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_in); break; case offsetof(struct bpf_sock_ops, segs_out): SOCK_OPS_GET_TCP_SOCK_FIELD(segs_out); break; case offsetof(struct bpf_sock_ops, data_segs_out): SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_out); break; case offsetof(struct bpf_sock_ops, lost_out): SOCK_OPS_GET_TCP_SOCK_FIELD(lost_out); break; case offsetof(struct bpf_sock_ops, sacked_out): SOCK_OPS_GET_TCP_SOCK_FIELD(sacked_out); break; case offsetof(struct bpf_sock_ops, bytes_received): SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_received); break; case offsetof(struct bpf_sock_ops, bytes_acked): SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked); break; case offsetof(struct bpf_sock_ops, sk): SOCK_OPS_GET_SK(); break; case offsetof(struct bpf_sock_ops, skb_data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb_data_end), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb_data_end)); break; case offsetof(struct bpf_sock_ops, skb_data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), si->dst_reg, si->dst_reg, offsetof(struct sk_buff, data)); break; case offsetof(struct bpf_sock_ops, skb_len): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), si->dst_reg, si->dst_reg, offsetof(struct sk_buff, len)); break; case offsetof(struct bpf_sock_ops, skb_tcp_flags): off = offsetof(struct sk_buff, cb); off += offsetof(struct tcp_skb_cb, tcp_flags); *target_size = sizeof_field(struct tcp_skb_cb, tcp_flags); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_skb_cb, tcp_flags), si->dst_reg, si->dst_reg, off); break; case offsetof(struct bpf_sock_ops, skb_hwtstamp): { struct bpf_insn *jmp_on_null_skb; *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, skb), si->dst_reg, si->src_reg, offsetof(struct bpf_sock_ops_kern, skb)); /* Reserve one insn to test skb == NULL */ jmp_on_null_skb = insn++; insn = bpf_convert_shinfo_access(si->dst_reg, si->dst_reg, insn); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, hwtstamps, 8, target_size)); *jmp_on_null_skb = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, insn - jmp_on_null_skb - 1); break; } } return insn - insn_buf; } /* data_end = skb->data + skb_headlen() */ static struct bpf_insn *bpf_convert_data_end_access(const struct bpf_insn *si, struct bpf_insn *insn) { int reg; int temp_reg_off = offsetof(struct sk_buff, cb) + offsetof(struct sk_skb_cb, temp_reg); if (si->src_reg == si->dst_reg) { /* We need an extra register, choose and save a register. */ reg = BPF_REG_9; if (si->src_reg == reg || si->dst_reg == reg) reg--; if (si->src_reg == reg || si->dst_reg == reg) reg--; *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, temp_reg_off); } else { reg = si->dst_reg; } /* reg = skb->data */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), reg, si->src_reg, offsetof(struct sk_buff, data)); /* AX = skb->len */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, len)); /* reg = skb->data + skb->len */ *insn++ = BPF_ALU64_REG(BPF_ADD, reg, BPF_REG_AX); /* AX = skb->data_len */ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data_len), BPF_REG_AX, si->src_reg, offsetof(struct sk_buff, data_len)); /* reg = skb->data + skb->len - skb->data_len */ *insn++ = BPF_ALU64_REG(BPF_SUB, reg, BPF_REG_AX); if (si->src_reg == si->dst_reg) { /* Restore the saved register */ *insn++ = BPF_MOV64_REG(BPF_REG_AX, si->src_reg); *insn++ = BPF_MOV64_REG(si->dst_reg, reg); *insn++ = BPF_LDX_MEM(BPF_DW, reg, BPF_REG_AX, temp_reg_off); } return insn; } static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; int off; switch (si->off) { case offsetof(struct __sk_buff, data_end): insn = bpf_convert_data_end_access(si, insn); break; case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: BUILD_BUG_ON(sizeof_field(struct sk_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct sk_skb_cb, data)) % sizeof(__u64)); prog->cb_access = 1; off = si->off; off -= offsetof(struct __sk_buff, cb[0]); off += offsetof(struct sk_buff, cb); off += offsetof(struct sk_skb_cb, data); if (type == BPF_WRITE) *insn++ = BPF_EMIT_STORE(BPF_SIZE(si->code), si, off); else *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, si->src_reg, off); break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); } return insn - insn_buf; } static u32 sk_msg_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; #if IS_ENABLED(CONFIG_IPV6) int off; #endif /* convert ctx uses the fact sg element is first in struct */ BUILD_BUG_ON(offsetof(struct sk_msg, sg) != 0); switch (si->off) { case offsetof(struct sk_msg_md, data): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data), si->dst_reg, si->src_reg, offsetof(struct sk_msg, data)); break; case offsetof(struct sk_msg_md, data_end): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, data_end), si->dst_reg, si->src_reg, offsetof(struct sk_msg, data_end)); break; case offsetof(struct sk_msg_md, family): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_family) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_family)); break; case offsetof(struct sk_msg_md, remote_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_daddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_daddr)); break; case offsetof(struct sk_msg_md, local_ip4): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_rcv_saddr) != 4); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_rcv_saddr)); break; case offsetof(struct sk_msg_md, remote_ip6[0]) ... offsetof(struct sk_msg_md, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct sk_msg_md, remote_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_daddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct sk_msg_md, local_ip6[0]) ... offsetof(struct sk_msg_md, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) BUILD_BUG_ON(sizeof_field(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4); off = si->off; off -= offsetof(struct sk_msg_md, local_ip6[0]); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) + off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; case offsetof(struct sk_msg_md, remote_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_dport) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_dport)); #ifndef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_LSH, si->dst_reg, 16); #endif break; case offsetof(struct sk_msg_md, local_port): BUILD_BUG_ON(sizeof_field(struct sock_common, skc_num) != 2); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->dst_reg, offsetof(struct sock_common, skc_num)); break; case offsetof(struct sk_msg_md, size): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_sg, size), si->dst_reg, si->src_reg, offsetof(struct sk_msg_sg, size)); break; case offsetof(struct sk_msg_md, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg, sk), si->dst_reg, si->src_reg, offsetof(struct sk_msg, sk)); break; } return insn - insn_buf; } const struct bpf_verifier_ops sk_filter_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_ld_abs = bpf_gen_ld_abs, }; const struct bpf_prog_ops sk_filter_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .get_func_proto = tc_cls_act_func_proto, .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, .gen_ld_abs = bpf_gen_ld_abs, .btf_struct_access = tc_cls_act_btf_struct_access, }; const struct bpf_prog_ops tc_cls_act_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops xdp_verifier_ops = { .get_func_proto = xdp_func_proto, .is_valid_access = xdp_is_valid_access, .convert_ctx_access = xdp_convert_ctx_access, .gen_prologue = bpf_noop_prologue, .btf_struct_access = xdp_btf_struct_access, }; const struct bpf_prog_ops xdp_prog_ops = { .test_run = bpf_prog_test_run_xdp, }; const struct bpf_verifier_ops cg_skb_verifier_ops = { .get_func_proto = cg_skb_func_proto, .is_valid_access = cg_skb_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops cg_skb_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_in_verifier_ops = { .get_func_proto = lwt_in_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_in_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_out_verifier_ops = { .get_func_proto = lwt_out_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_out_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_xmit_verifier_ops = { .get_func_proto = lwt_xmit_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, }; const struct bpf_prog_ops lwt_xmit_prog_ops = { .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops lwt_seg6local_verifier_ops = { .get_func_proto = lwt_seg6local_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; const struct bpf_prog_ops lwt_seg6local_prog_ops = { }; const struct bpf_verifier_ops cg_sock_verifier_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, .convert_ctx_access = bpf_sock_convert_ctx_access, }; const struct bpf_prog_ops cg_sock_prog_ops = { }; const struct bpf_verifier_ops cg_sock_addr_verifier_ops = { .get_func_proto = sock_addr_func_proto, .is_valid_access = sock_addr_is_valid_access, .convert_ctx_access = sock_addr_convert_ctx_access, }; const struct bpf_prog_ops cg_sock_addr_prog_ops = { }; const struct bpf_verifier_ops sock_ops_verifier_ops = { .get_func_proto = sock_ops_func_proto, .is_valid_access = sock_ops_is_valid_access, .convert_ctx_access = sock_ops_convert_ctx_access, }; const struct bpf_prog_ops sock_ops_prog_ops = { }; const struct bpf_verifier_ops sk_skb_verifier_ops = { .get_func_proto = sk_skb_func_proto, .is_valid_access = sk_skb_is_valid_access, .convert_ctx_access = sk_skb_convert_ctx_access, .gen_prologue = sk_skb_prologue, }; const struct bpf_prog_ops sk_skb_prog_ops = { }; const struct bpf_verifier_ops sk_msg_verifier_ops = { .get_func_proto = sk_msg_func_proto, .is_valid_access = sk_msg_is_valid_access, .convert_ctx_access = sk_msg_convert_ctx_access, .gen_prologue = bpf_noop_prologue, }; const struct bpf_prog_ops sk_msg_prog_ops = { }; const struct bpf_verifier_ops flow_dissector_verifier_ops = { .get_func_proto = flow_dissector_func_proto, .is_valid_access = flow_dissector_is_valid_access, .convert_ctx_access = flow_dissector_convert_ctx_access, }; const struct bpf_prog_ops flow_dissector_prog_ops = { .test_run = bpf_prog_test_run_flow_dissector, }; int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; struct sk_filter *filter; if (sock_flag(sk, SOCK_FILTER_LOCKED)) return -EPERM; filter = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); if (filter) { RCU_INIT_POINTER(sk->sk_filter, NULL); sk_filter_uncharge(sk, filter); ret = 0; } return ret; } EXPORT_SYMBOL_GPL(sk_detach_filter); int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len) { struct sock_fprog_kern *fprog; struct sk_filter *filter; int ret = 0; sockopt_lock_sock(sk); filter = rcu_dereference_protected(sk->sk_filter, lockdep_sock_is_held(sk)); if (!filter) goto out; /* We're copying the filter that has been originally attached, * so no conversion/decode needed anymore. eBPF programs that * have no original program cannot be dumped through this. */ ret = -EACCES; fprog = filter->prog->orig_prog; if (!fprog) goto out; ret = fprog->len; if (!len) /* User space only enquires number of filter blocks. */ goto out; ret = -EINVAL; if (len < fprog->len) goto out; ret = -EFAULT; if (copy_to_sockptr(optval, fprog->filter, bpf_classic_proglen(fprog))) goto out; /* Instead of bytes, the API requests to return the number * of filter blocks. */ ret = fprog->len; out: sockopt_release_sock(sk); return ret; } #ifdef CONFIG_INET static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock_reuseport *reuse, struct sock *sk, struct sk_buff *skb, struct sock *migrating_sk, u32 hash) { reuse_kern->skb = skb; reuse_kern->sk = sk; reuse_kern->selected_sk = NULL; reuse_kern->migrating_sk = migrating_sk; reuse_kern->data_end = skb->data + skb_headlen(skb); reuse_kern->hash = hash; reuse_kern->reuseport_id = reuse->reuseport_id; reuse_kern->bind_inany = reuse->bind_inany; } struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash) { struct sk_reuseport_kern reuse_kern; enum sk_action action; bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, migrating_sk, hash); action = bpf_prog_run(prog, &reuse_kern); if (action == SK_PASS) return reuse_kern.selected_sk; else return ERR_PTR(-ECONNREFUSED); } BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, struct bpf_map *, map, void *, key, u32, flags) { bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY; struct sock_reuseport *reuse; struct sock *selected_sk; int err; selected_sk = map->ops->map_lookup_elem(map, key); if (!selected_sk) return -ENOENT; reuse = rcu_dereference(selected_sk->sk_reuseport_cb); if (!reuse) { /* reuseport_array has only sk with non NULL sk_reuseport_cb. * The only (!reuse) case here is - the sk has already been * unhashed (e.g. by close()), so treat it as -ENOENT. * * Other maps (e.g. sock_map) do not provide this guarantee and * the sk may never be in the reuseport group to begin with. */ err = is_sockarray ? -ENOENT : -EINVAL; goto error; } if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) { struct sock *sk = reuse_kern->sk; if (sk->sk_protocol != selected_sk->sk_protocol) { err = -EPROTOTYPE; } else if (sk->sk_family != selected_sk->sk_family) { err = -EAFNOSUPPORT; } else { /* Catch all. Likely bound to a different sockaddr. */ err = -EBADFD; } goto error; } reuse_kern->selected_sk = selected_sk; return 0; error: /* Lookup in sock_map can return TCP ESTABLISHED sockets. */ if (sk_is_refcounted(selected_sk)) sock_put(selected_sk); return err; } static const struct bpf_func_proto sk_select_reuseport_proto = { .func = sk_select_reuseport, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_PTR_TO_MAP_KEY, .arg4_type = ARG_ANYTHING, }; BPF_CALL_4(sk_reuseport_load_bytes, const struct sk_reuseport_kern *, reuse_kern, u32, offset, void *, to, u32, len) { return ____bpf_skb_load_bytes(reuse_kern->skb, offset, to, len); } static const struct bpf_func_proto sk_reuseport_load_bytes_proto = { .func = sk_reuseport_load_bytes, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, }; BPF_CALL_5(sk_reuseport_load_bytes_relative, const struct sk_reuseport_kern *, reuse_kern, u32, offset, void *, to, u32, len, u32, start_header) { return ____bpf_skb_load_bytes_relative(reuse_kern->skb, offset, to, len, start_header); } static const struct bpf_func_proto sk_reuseport_load_bytes_relative_proto = { .func = sk_reuseport_load_bytes_relative, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_UNINIT_MEM, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; static const struct bpf_func_proto * sk_reuseport_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sk_select_reuseport: return &sk_select_reuseport_proto; case BPF_FUNC_skb_load_bytes: return &sk_reuseport_load_bytes_proto; case BPF_FUNC_skb_load_bytes_relative: return &sk_reuseport_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_ptr_cookie_proto; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id, prog); } } static bool sk_reuseport_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const u32 size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct sk_reuseport_md) || off % size || type != BPF_READ) return false; switch (off) { case offsetof(struct sk_reuseport_md, data): info->reg_type = PTR_TO_PACKET; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, data_end): info->reg_type = PTR_TO_PACKET_END; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, hash): return size == size_default; case offsetof(struct sk_reuseport_md, sk): info->reg_type = PTR_TO_SOCKET; return size == sizeof(__u64); case offsetof(struct sk_reuseport_md, migrating_sk): info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; return size == sizeof(__u64); /* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): if (size < sizeof_field(struct sk_buff, protocol)) return false; fallthrough; case bpf_ctx_range(struct sk_reuseport_md, ip_protocol): case bpf_ctx_range(struct sk_reuseport_md, bind_inany): case bpf_ctx_range(struct sk_reuseport_md, len): bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); default: return false; } } #define SK_REUSEPORT_LOAD_FIELD(F) ({ \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \ si->dst_reg, si->src_reg, \ bpf_target_off(struct sk_reuseport_kern, F, \ sizeof_field(struct sk_reuseport_kern, F), \ target_size)); \ }) #define SK_REUSEPORT_LOAD_SKB_FIELD(SKB_FIELD) \ SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ struct sk_buff, \ skb, \ SKB_FIELD) #define SK_REUSEPORT_LOAD_SK_FIELD(SK_FIELD) \ SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ struct sock, \ sk, \ SK_FIELD) static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct sk_reuseport_md, data): SK_REUSEPORT_LOAD_SKB_FIELD(data); break; case offsetof(struct sk_reuseport_md, len): SK_REUSEPORT_LOAD_SKB_FIELD(len); break; case offsetof(struct sk_reuseport_md, eth_protocol): SK_REUSEPORT_LOAD_SKB_FIELD(protocol); break; case offsetof(struct sk_reuseport_md, ip_protocol): SK_REUSEPORT_LOAD_SK_FIELD(sk_protocol); break; case offsetof(struct sk_reuseport_md, data_end): SK_REUSEPORT_LOAD_FIELD(data_end); break; case offsetof(struct sk_reuseport_md, hash): SK_REUSEPORT_LOAD_FIELD(hash); break; case offsetof(struct sk_reuseport_md, bind_inany): SK_REUSEPORT_LOAD_FIELD(bind_inany); break; case offsetof(struct sk_reuseport_md, sk): SK_REUSEPORT_LOAD_FIELD(sk); break; case offsetof(struct sk_reuseport_md, migrating_sk): SK_REUSEPORT_LOAD_FIELD(migrating_sk); break; } return insn - insn_buf; } const struct bpf_verifier_ops sk_reuseport_verifier_ops = { .get_func_proto = sk_reuseport_func_proto, .is_valid_access = sk_reuseport_is_valid_access, .convert_ctx_access = sk_reuseport_convert_ctx_access, }; const struct bpf_prog_ops sk_reuseport_prog_ops = { }; DEFINE_STATIC_KEY_FALSE(bpf_sk_lookup_enabled); EXPORT_SYMBOL(bpf_sk_lookup_enabled); BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx, struct sock *, sk, u64, flags) { if (unlikely(flags & ~(BPF_SK_LOOKUP_F_REPLACE | BPF_SK_LOOKUP_F_NO_REUSEPORT))) return -EINVAL; if (unlikely(sk && sk_is_refcounted(sk))) return -ESOCKTNOSUPPORT; /* reject non-RCU freed sockets */ if (unlikely(sk && sk_is_tcp(sk) && sk->sk_state != TCP_LISTEN)) return -ESOCKTNOSUPPORT; /* only accept TCP socket in LISTEN */ if (unlikely(sk && sk_is_udp(sk) && sk->sk_state != TCP_CLOSE)) return -ESOCKTNOSUPPORT; /* only accept UDP socket in CLOSE */ /* Check if socket is suitable for packet L3/L4 protocol */ if (sk && sk->sk_protocol != ctx->protocol) return -EPROTOTYPE; if (sk && sk->sk_family != ctx->family && (sk->sk_family == AF_INET || ipv6_only_sock(sk))) return -EAFNOSUPPORT; if (ctx->selected_sk && !(flags & BPF_SK_LOOKUP_F_REPLACE)) return -EEXIST; /* Select socket as lookup result */ ctx->selected_sk = sk; ctx->no_reuseport = flags & BPF_SK_LOOKUP_F_NO_REUSEPORT; return 0; } static const struct bpf_func_proto bpf_sk_lookup_assign_proto = { .func = bpf_sk_lookup_assign, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_SOCKET_OR_NULL, .arg3_type = ARG_ANYTHING, }; static const struct bpf_func_proto * sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; case BPF_FUNC_sk_assign: return &bpf_sk_lookup_assign_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: return bpf_sk_base_func_proto(func_id, prog); } } static bool sk_lookup_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct bpf_sk_lookup)) return false; if (off % size != 0) return false; if (type != BPF_READ) return false; switch (off) { case bpf_ctx_range_ptr(struct bpf_sk_lookup, sk): info->reg_type = PTR_TO_SOCKET_OR_NULL; return size == sizeof(__u64); case bpf_ctx_range(struct bpf_sk_lookup, family): case bpf_ctx_range(struct bpf_sk_lookup, protocol): case bpf_ctx_range(struct bpf_sk_lookup, remote_ip4): case bpf_ctx_range(struct bpf_sk_lookup, local_ip4): case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): case bpf_ctx_range(struct bpf_sk_lookup, local_port): case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex): bpf_ctx_record_field_size(info, sizeof(__u32)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32)); case bpf_ctx_range(struct bpf_sk_lookup, remote_port): /* Allow 4-byte access to 2-byte field for backward compatibility */ if (size == sizeof(__u32)) return true; bpf_ctx_record_field_size(info, sizeof(__be16)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__be16)); case offsetofend(struct bpf_sk_lookup, remote_port) ... offsetof(struct bpf_sk_lookup, local_ip4) - 1: /* Allow access to zero padding for backward compatibility */ bpf_ctx_record_field_size(info, sizeof(__u16)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__u16)); default: return false; } } static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_sk_lookup, sk): *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, selected_sk)); break; case offsetof(struct bpf_sk_lookup, family): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, family, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, protocol): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, protocol, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, remote_ip4): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, v4.saddr, 4, target_size)); break; case offsetof(struct bpf_sk_lookup, local_ip4): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, v4.daddr, 4, target_size)); break; case bpf_ctx_range_till(struct bpf_sk_lookup, remote_ip6[0], remote_ip6[3]): { #if IS_ENABLED(CONFIG_IPV6) int off = si->off; off -= offsetof(struct bpf_sk_lookup, remote_ip6[0]); off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, v6.saddr)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; } case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): { #if IS_ENABLED(CONFIG_IPV6) int off = si->off; off -= offsetof(struct bpf_sk_lookup, local_ip6[0]); off += bpf_target_off(struct in6_addr, s6_addr32[0], 4, target_size); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, offsetof(struct bpf_sk_lookup_kern, v6.daddr)); *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, off); #else *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); #endif break; } case offsetof(struct bpf_sk_lookup, remote_port): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, sport, 2, target_size)); break; case offsetofend(struct bpf_sk_lookup, remote_port): *target_size = 2; *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); break; case offsetof(struct bpf_sk_lookup, local_port): *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, dport, 2, target_size)); break; case offsetof(struct bpf_sk_lookup, ingress_ifindex): *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sk_lookup_kern, ingress_ifindex, 4, target_size)); break; } return insn - insn_buf; } const struct bpf_prog_ops sk_lookup_prog_ops = { .test_run = bpf_prog_test_run_sk_lookup, }; const struct bpf_verifier_ops sk_lookup_verifier_ops = { .get_func_proto = sk_lookup_func_proto, .is_valid_access = sk_lookup_is_valid_access, .convert_ctx_access = sk_lookup_convert_ctx_access, }; #endif /* CONFIG_INET */ DEFINE_BPF_DISPATCHER(xdp) void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog) { bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(xdp), prev_prog, prog); } BTF_ID_LIST_GLOBAL(btf_sock_ids, MAX_BTF_SOCK_TYPE) #define BTF_SOCK_TYPE(name, type) BTF_ID(struct, type) BTF_SOCK_TYPE_xxx #undef BTF_SOCK_TYPE BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk) { /* tcp6_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct tcp6_sock); if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk->sk_family == AF_INET6) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = { .func = bpf_skc_to_tcp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP6], }; BPF_CALL_1(bpf_skc_to_tcp_sock, struct sock *, sk) { if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = { .func = bpf_skc_to_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP], }; BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk) { /* BTF types for tcp_timewait_sock and inet_timewait_sock are not * generated if CONFIG_INET=n. Trigger an explicit generation here. */ BTF_TYPE_EMIT(struct inet_timewait_sock); BTF_TYPE_EMIT(struct tcp_timewait_sock); #ifdef CONFIG_INET if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif #if IS_BUILTIN(CONFIG_IPV6) if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = { .func = bpf_skc_to_tcp_timewait_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW], }; BPF_CALL_1(bpf_skc_to_tcp_request_sock, struct sock *, sk) { #ifdef CONFIG_INET if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif #if IS_BUILTIN(CONFIG_IPV6) if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = { .func = bpf_skc_to_tcp_request_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ], }; BPF_CALL_1(bpf_skc_to_udp6_sock, struct sock *, sk) { /* udp6_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct udp6_sock); if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP && sk->sk_type == SOCK_DGRAM && sk->sk_family == AF_INET6) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { .func = bpf_skc_to_udp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; BPF_CALL_1(bpf_skc_to_unix_sock, struct sock *, sk) { /* unix_sock type is not generated in dwarf and hence btf, * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct unix_sock); if (sk && sk_fullsock(sk) && sk->sk_family == AF_UNIX) return (unsigned long)sk; return (unsigned long)NULL; } const struct bpf_func_proto bpf_skc_to_unix_sock_proto = { .func = bpf_skc_to_unix_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UNIX], }; BPF_CALL_1(bpf_skc_to_mptcp_sock, struct sock *, sk) { BTF_TYPE_EMIT(struct mptcp_sock); return (unsigned long)bpf_mptcp_sock_from_subflow(sk); } const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto = { .func = bpf_skc_to_mptcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .arg1_type = ARG_PTR_TO_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_MPTCP], }; BPF_CALL_1(bpf_sock_from_file, struct file *, file) { return (unsigned long)sock_from_file(file); } BTF_ID_LIST(bpf_sock_from_file_btf_ids) BTF_ID(struct, socket) BTF_ID(struct, file) const struct bpf_func_proto bpf_sock_from_file_proto = { .func = bpf_sock_from_file, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, .ret_btf_id = &bpf_sock_from_file_btf_ids[0], .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &bpf_sock_from_file_btf_ids[1], }; static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func; switch (func_id) { case BPF_FUNC_skc_to_tcp6_sock: func = &bpf_skc_to_tcp6_sock_proto; break; case BPF_FUNC_skc_to_tcp_sock: func = &bpf_skc_to_tcp_sock_proto; break; case BPF_FUNC_skc_to_tcp_timewait_sock: func = &bpf_skc_to_tcp_timewait_sock_proto; break; case BPF_FUNC_skc_to_tcp_request_sock: func = &bpf_skc_to_tcp_request_sock_proto; break; case BPF_FUNC_skc_to_udp6_sock: func = &bpf_skc_to_udp6_sock_proto; break; case BPF_FUNC_skc_to_unix_sock: func = &bpf_skc_to_unix_sock_proto; break; case BPF_FUNC_skc_to_mptcp_sock: func = &bpf_skc_to_mptcp_sock_proto; break; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: return bpf_base_func_proto(func_id, prog); } if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; return func; } /** * bpf_skb_meta_pointer() - Gets a mutable pointer within the skb metadata area. * @skb: socket buffer carrying the metadata * @offset: offset into the metadata area, must be <= skb_metadata_len() */ void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset) { return skb_metadata_end(skb) - skb_metadata_len(skb) + offset; } __bpf_kfunc_start_defs(); __bpf_kfunc int bpf_dynptr_from_skb(struct __sk_buff *s, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; struct sk_buff *skb = (struct sk_buff *)s; if (flags) { bpf_dynptr_set_null(ptr); return -EINVAL; } bpf_dynptr_init(ptr, skb, BPF_DYNPTR_TYPE_SKB, 0, skb->len); return 0; } /** * bpf_dynptr_from_skb_meta() - Initialize a dynptr to the skb metadata area. * @skb_: socket buffer carrying the metadata * @flags: future use, must be zero * @ptr__uninit: dynptr to initialize * * Set up a dynptr for access to the metadata area earlier allocated from the * XDP context with bpf_xdp_adjust_meta(). Serves as an alternative to * &__sk_buff->data_meta. * * If passed @skb_ is a clone which shares the data with the original, the * dynptr will be read-only. This limitation may be lifted in the future. * * Return: * * %0 - dynptr ready to use * * %-EINVAL - invalid flags, dynptr set to null */ __bpf_kfunc int bpf_dynptr_from_skb_meta(struct __sk_buff *skb_, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; struct sk_buff *skb = (struct sk_buff *)skb_; if (flags) { bpf_dynptr_set_null(ptr); return -EINVAL; } bpf_dynptr_init(ptr, skb, BPF_DYNPTR_TYPE_SKB_META, 0, skb_metadata_len(skb)); if (skb_cloned(skb)) bpf_dynptr_set_rdonly(ptr); return 0; } __bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_md *x, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; struct xdp_buff *xdp = (struct xdp_buff *)x; if (flags) { bpf_dynptr_set_null(ptr); return -EINVAL; } bpf_dynptr_init(ptr, xdp, BPF_DYNPTR_TYPE_XDP, 0, xdp_get_buff_len(xdp)); return 0; } __bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern, const u8 *sun_path, u32 sun_path__sz) { struct sockaddr_un *un; if (sa_kern->sk->sk_family != AF_UNIX) return -EINVAL; /* We do not allow changing the address to unnamed or larger than the * maximum allowed address size for a unix sockaddr. */ if (sun_path__sz == 0 || sun_path__sz > UNIX_PATH_MAX) return -EINVAL; un = (struct sockaddr_un *)sa_kern->uaddr; memcpy(un->sun_path, sun_path, sun_path__sz); sa_kern->uaddrlen = offsetof(struct sockaddr_un, sun_path) + sun_path__sz; return 0; } __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk, struct bpf_tcp_req_attrs *attrs, int attrs__sz) { #if IS_ENABLED(CONFIG_SYN_COOKIES) struct sk_buff *skb = (struct sk_buff *)s; const struct request_sock_ops *ops; struct inet_request_sock *ireq; struct tcp_request_sock *treq; struct request_sock *req; struct net *net; __u16 min_mss; u32 tsoff = 0; if (attrs__sz != sizeof(*attrs) || attrs->reserved[0] || attrs->reserved[1] || attrs->reserved[2]) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EINVAL; net = dev_net(skb->dev); if (net != sock_net(sk)) return -ENETUNREACH; switch (skb->protocol) { case htons(ETH_P_IP): ops = &tcp_request_sock_ops; min_mss = 536; break; #if IS_BUILTIN(CONFIG_IPV6) case htons(ETH_P_IPV6): ops = &tcp6_request_sock_ops; min_mss = IPV6_MIN_MTU - 60; break; #endif default: return -EINVAL; } if (sk->sk_type != SOCK_STREAM || sk->sk_state != TCP_LISTEN || sk_is_mptcp(sk)) return -EINVAL; if (attrs->mss < min_mss) return -EINVAL; if (attrs->wscale_ok) { if (!READ_ONCE(net->ipv4.sysctl_tcp_window_scaling)) return -EINVAL; if (attrs->snd_wscale > TCP_MAX_WSCALE || attrs->rcv_wscale > TCP_MAX_WSCALE) return -EINVAL; } if (attrs->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack)) return -EINVAL; if (attrs->tstamp_ok) { if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps)) return -EINVAL; tsoff = attrs->rcv_tsecr - tcp_ns_to_ts(attrs->usec_ts_ok, tcp_clock_ns()); } req = inet_reqsk_alloc(ops, sk, false); if (!req) return -ENOMEM; ireq = inet_rsk(req); treq = tcp_rsk(req); req->rsk_listener = sk; req->syncookie = 1; req->mss = attrs->mss; req->ts_recent = attrs->rcv_tsval; ireq->snd_wscale = attrs->snd_wscale; ireq->rcv_wscale = attrs->rcv_wscale; ireq->tstamp_ok = !!attrs->tstamp_ok; ireq->sack_ok = !!attrs->sack_ok; ireq->wscale_ok = !!attrs->wscale_ok; ireq->ecn_ok = !!attrs->ecn_ok; treq->req_usec_ts = !!attrs->usec_ts_ok; treq->ts_off = tsoff; skb_orphan(skb); skb->sk = req_to_sk(req); skb->destructor = sock_pfree; return 0; #else return -EOPNOTSUPP; #endif } __bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops, u64 flags) { struct sk_buff *skb; if (skops->op != BPF_SOCK_OPS_TSTAMP_SENDMSG_CB) return -EOPNOTSUPP; if (flags) return -EINVAL; skb = skops->skb; skb_shinfo(skb)->tx_flags |= SKBTX_BPF; TCP_SKB_CB(skb)->txstamp_ack |= TSTAMP_ACK_BPF; skb_shinfo(skb)->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; return 0; } /** * bpf_xdp_pull_data() - Pull in non-linear xdp data. * @x: &xdp_md associated with the XDP buffer * @len: length of data to be made directly accessible in the linear part * * Pull in data in case the XDP buffer associated with @x is non-linear and * not all @len are in the linear data area. * * Direct packet access allows reading and writing linear XDP data through * packet pointers (i.e., &xdp_md->data + offsets). The amount of data which * ends up in the linear part of the xdp_buff depends on the NIC and its * configuration. When a frag-capable XDP program wants to directly access * headers that may be in the non-linear area, call this kfunc to make sure * the data is available in the linear area. Alternatively, use dynptr or * bpf_xdp_{load,store}_bytes() to access data without pulling. * * This kfunc can also be used with bpf_xdp_adjust_head() to decapsulate * headers in the non-linear data area. * * A call to this kfunc may reduce headroom. If there is not enough tailroom * in the linear data area, metadata and data will be shifted down. * * A call to this kfunc is susceptible to change the buffer geometry. * Therefore, at load time, all checks on pointers previously done by the * verifier are invalidated and must be performed again, if the kfunc is used * in combination with direct packet access. * * Return: * * %0 - success * * %-EINVAL - invalid len */ __bpf_kfunc int bpf_xdp_pull_data(struct xdp_md *x, u32 len) { struct xdp_buff *xdp = (struct xdp_buff *)x; struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); int i, delta, shift, headroom, tailroom, n_frags_free = 0; void *data_hard_end = xdp_data_hard_end(xdp); int data_len = xdp->data_end - xdp->data; void *start; if (len <= data_len) return 0; if (unlikely(len > xdp_get_buff_len(xdp))) return -EINVAL; start = xdp_data_meta_unsupported(xdp) ? xdp->data : xdp->data_meta; headroom = start - xdp->data_hard_start - sizeof(struct xdp_frame); tailroom = data_hard_end - xdp->data_end; delta = len - data_len; if (unlikely(delta > tailroom + headroom)) return -EINVAL; shift = delta - tailroom; if (shift > 0) { memmove(start - shift, start, xdp->data_end - start); xdp->data_meta -= shift; xdp->data -= shift; xdp->data_end -= shift; } for (i = 0; i < sinfo->nr_frags && delta; i++) { skb_frag_t *frag = &sinfo->frags[i]; u32 shrink = min_t(u32, delta, skb_frag_size(frag)); memcpy(xdp->data_end, skb_frag_address(frag), shrink); xdp->data_end += shrink; sinfo->xdp_frags_size -= shrink; delta -= shrink; if (bpf_xdp_shrink_data(xdp, frag, shrink, false)) n_frags_free++; } if (unlikely(n_frags_free)) { memmove(sinfo->frags, sinfo->frags + n_frags_free, (sinfo->nr_frags - n_frags_free) * sizeof(skb_frag_t)); sinfo->nr_frags -= n_frags_free; if (!sinfo->nr_frags) { xdp_buff_clear_frags_flag(xdp); xdp_buff_clear_frag_pfmemalloc(xdp); } } return 0; } __bpf_kfunc_end_defs(); int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, struct bpf_dynptr *ptr__uninit) { struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; int err; err = bpf_dynptr_from_skb(skb, flags, ptr__uninit); if (err) return err; bpf_dynptr_set_rdonly(ptr); return 0; } BTF_KFUNCS_START(bpf_kfunc_check_set_skb) BTF_ID_FLAGS(func, bpf_dynptr_from_skb, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_skb) BTF_KFUNCS_START(bpf_kfunc_check_set_skb_meta) BTF_ID_FLAGS(func, bpf_dynptr_from_skb_meta, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_skb_meta) BTF_KFUNCS_START(bpf_kfunc_check_set_xdp) BTF_ID_FLAGS(func, bpf_dynptr_from_xdp) BTF_ID_FLAGS(func, bpf_xdp_pull_data) BTF_KFUNCS_END(bpf_kfunc_check_set_xdp) BTF_KFUNCS_START(bpf_kfunc_check_set_sock_addr) BTF_ID_FLAGS(func, bpf_sock_addr_set_sun_path) BTF_KFUNCS_END(bpf_kfunc_check_set_sock_addr) BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk) BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_tcp_reqsk) BTF_KFUNCS_START(bpf_kfunc_check_set_sock_ops) BTF_ID_FLAGS(func, bpf_sock_ops_enable_tx_tstamp, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_sock_ops) static const struct btf_kfunc_id_set bpf_kfunc_set_skb = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_skb, }; static const struct btf_kfunc_id_set bpf_kfunc_set_skb_meta = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_skb_meta, }; static const struct btf_kfunc_id_set bpf_kfunc_set_xdp = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_xdp, }; static const struct btf_kfunc_id_set bpf_kfunc_set_sock_addr = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_sock_addr, }; static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_tcp_reqsk, }; static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_sock_ops, }; static int __init bpf_kfunc_init(void) { int ret; ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_ACT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SK_SKB, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCKET_FILTER, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SKB, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_OUT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_IN, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_XMIT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_skb_meta); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_ACT, &bpf_kfunc_set_skb_meta); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, &bpf_kfunc_set_sock_addr); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk); return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCK_OPS, &bpf_kfunc_set_sock_ops); } late_initcall(bpf_kfunc_init); __bpf_kfunc_start_defs(); /* bpf_sock_destroy: Destroy the given socket with ECONNABORTED error code. * * The function expects a non-NULL pointer to a socket, and invokes the * protocol specific socket destroy handlers. * * The helper can only be called from BPF contexts that have acquired the socket * locks. * * Parameters: * @sock: Pointer to socket to be destroyed * * Return: * On error, may return EPROTONOSUPPORT, EINVAL. * EPROTONOSUPPORT if protocol specific destroy handler is not supported. * 0 otherwise */ __bpf_kfunc int bpf_sock_destroy(struct sock_common *sock) { struct sock *sk = (struct sock *)sock; /* The locking semantics that allow for synchronous execution of the * destroy handlers are only supported for TCP and UDP. * Supporting protocols will need to acquire sock lock in the BPF context * prior to invoking this kfunc. */ if (!sk->sk_prot->diag_destroy || (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_UDP)) return -EOPNOTSUPP; return sk->sk_prot->diag_destroy(sk, ECONNABORTED); } __bpf_kfunc_end_defs(); BTF_KFUNCS_START(bpf_sk_iter_kfunc_ids) BTF_ID_FLAGS(func, bpf_sock_destroy, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_sk_iter_kfunc_ids) static int tracing_iter_filter(const struct bpf_prog *prog, u32 kfunc_id) { if (btf_id_set8_contains(&bpf_sk_iter_kfunc_ids, kfunc_id) && prog->expected_attach_type != BPF_TRACE_ITER) return -EACCES; return 0; } static const struct btf_kfunc_id_set bpf_sk_iter_kfunc_set = { .owner = THIS_MODULE, .set = &bpf_sk_iter_kfunc_ids, .filter = tracing_iter_filter, }; static int init_subsystem(void) { return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_sk_iter_kfunc_set); } late_initcall(init_subsystem); |
| 302 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM sock #if !defined(_TRACE_SOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SOCK_H #include <net/sock.h> #include <net/ipv6.h> #include <linux/tracepoint.h> #include <linux/ipv6.h> #include <linux/tcp.h> #include <trace/events/net_probe_common.h> #define family_names \ EM(AF_INET) \ EMe(AF_INET6) /* The protocol traced by inet_sock_set_state */ #define inet_protocol_names \ EM(IPPROTO_TCP) \ EM(IPPROTO_SCTP) \ EMe(IPPROTO_MPTCP) #define tcp_state_names \ EM(TCP_ESTABLISHED) \ EM(TCP_SYN_SENT) \ EM(TCP_SYN_RECV) \ EM(TCP_FIN_WAIT1) \ EM(TCP_FIN_WAIT2) \ EM(TCP_TIME_WAIT) \ EM(TCP_CLOSE) \ EM(TCP_CLOSE_WAIT) \ EM(TCP_LAST_ACK) \ EM(TCP_LISTEN) \ EM(TCP_CLOSING) \ EMe(TCP_NEW_SYN_RECV) #define skmem_kind_names \ EM(SK_MEM_SEND) \ EMe(SK_MEM_RECV) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); family_names inet_protocol_names tcp_state_names skmem_kind_names #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } #define show_family_name(val) \ __print_symbolic(val, family_names) #define show_inet_protocol_name(val) \ __print_symbolic(val, inet_protocol_names) #define show_tcp_state_name(val) \ __print_symbolic(val, tcp_state_names) #define show_skmem_kind_names(val) \ __print_symbolic(val, skmem_kind_names) TRACE_EVENT(sock_rcvqueue_full, TP_PROTO(struct sock *sk, struct sk_buff *skb), TP_ARGS(sk, skb), TP_STRUCT__entry( __field(int, rmem_alloc) __field(unsigned int, truesize) __field(int, sk_rcvbuf) ), TP_fast_assign( __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->truesize = skb->truesize; __entry->sk_rcvbuf = READ_ONCE(sk->sk_rcvbuf); ), TP_printk("rmem_alloc=%d truesize=%u sk_rcvbuf=%d", __entry->rmem_alloc, __entry->truesize, __entry->sk_rcvbuf) ); TRACE_EVENT(sock_exceed_buf_limit, TP_PROTO(struct sock *sk, struct proto *prot, long allocated, int kind), TP_ARGS(sk, prot, allocated, kind), TP_STRUCT__entry( __array(char, name, 32) __array(long, sysctl_mem, 3) __field(long, allocated) __field(int, sysctl_rmem) __field(int, rmem_alloc) __field(int, sysctl_wmem) __field(int, wmem_alloc) __field(int, wmem_queued) __field(int, kind) ), TP_fast_assign( strscpy(__entry->name, prot->name, 32); __entry->sysctl_mem[0] = READ_ONCE(prot->sysctl_mem[0]); __entry->sysctl_mem[1] = READ_ONCE(prot->sysctl_mem[1]); __entry->sysctl_mem[2] = READ_ONCE(prot->sysctl_mem[2]); __entry->allocated = allocated; __entry->sysctl_rmem = sk_get_rmem0(sk, prot); __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->sysctl_wmem = sk_get_wmem0(sk, prot); __entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc); __entry->wmem_queued = READ_ONCE(sk->sk_wmem_queued); __entry->kind = kind; ), TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld sysctl_rmem=%d rmem_alloc=%d sysctl_wmem=%d wmem_alloc=%d wmem_queued=%d kind=%s", __entry->name, __entry->sysctl_mem[0], __entry->sysctl_mem[1], __entry->sysctl_mem[2], __entry->allocated, __entry->sysctl_rmem, __entry->rmem_alloc, __entry->sysctl_wmem, __entry->wmem_alloc, __entry->wmem_queued, show_skmem_kind_names(__entry->kind) ) ); TRACE_EVENT(inet_sock_set_state, TP_PROTO(const struct sock *sk, const int oldstate, const int newstate), TP_ARGS(sk, oldstate, newstate), TP_STRUCT__entry( __field(const void *, skaddr) __field(int, oldstate) __field(int, newstate) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u16, protocol) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skaddr = sk; __entry->oldstate = oldstate; __entry->newstate = newstate; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s", show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, show_tcp_state_name(__entry->oldstate), show_tcp_state_name(__entry->newstate)) ); TRACE_EVENT(inet_sk_error_report, TP_PROTO(const struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(int, error) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u16, protocol) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->error = sk->sk_err; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c error=%d", show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, __entry->error) ); TRACE_EVENT(sk_data_ready, TP_PROTO(const struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(const void *, skaddr) __field(__u16, family) __field(__u16, protocol) __field(unsigned long, ip) ), TP_fast_assign( __entry->skaddr = sk; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->ip = _RET_IP_; ), TP_printk("family=%u protocol=%u func=%ps", __entry->family, __entry->protocol, (void *)__entry->ip) ); /* * sock send/recv msg length */ DECLARE_EVENT_CLASS(sock_msg_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags), TP_STRUCT__entry( __field(void *, sk) __field(__u16, family) __field(__u16, protocol) __field(int, ret) __field(int, flags) ), TP_fast_assign( __entry->sk = sk; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->ret = ret; __entry->flags = flags; ), TP_printk("sk address = %p, family = %s protocol = %s, length = %d, error = %d, flags = 0x%x", __entry->sk, show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), !(__entry->flags & MSG_PEEK) ? (__entry->ret > 0 ? __entry->ret : 0) : 0, __entry->ret < 0 ? __entry->ret : 0, __entry->flags) ); DEFINE_EVENT(sock_msg_length, sock_send_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags) ); DEFINE_EVENT(sock_msg_length, sock_recv_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags) ); #endif /* _TRACE_SOCK_H */ /* 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _linux_POSIX_TIMERS_H #define _linux_POSIX_TIMERS_H #include <linux/alarmtimer.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/pid.h> #include <linux/posix-timers_types.h> #include <linux/rcuref.h> #include <linux/spinlock.h> #include <linux/timerqueue.h> struct kernel_siginfo; struct task_struct; struct sigqueue; struct k_itimer; static inline clockid_t make_process_cpuclock(const unsigned int pid, const clockid_t clock) { return ((~pid) << 3) | clock; } static inline clockid_t make_thread_cpuclock(const unsigned int tid, const clockid_t clock) { return make_process_cpuclock(tid, clock | CPUCLOCK_PERTHREAD_MASK); } static inline clockid_t fd_to_clockid(const int fd) { return make_process_cpuclock((unsigned int) fd, CLOCKFD); } static inline int clockid_to_fd(const clockid_t clk) { return ~(clk >> 3); } static inline bool clockid_aux_valid(clockid_t id) { return IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS) && id >= CLOCK_AUX && id <= CLOCK_AUX_LAST; } #ifdef CONFIG_POSIX_TIMERS #include <linux/signal_types.h> /** * cpu_timer - Posix CPU timer representation for k_itimer * @node: timerqueue node to queue in the task/sig * @head: timerqueue head on which this timer is queued * @pid: Pointer to target task PID * @elist: List head for the expiry list * @firing: Timer is currently firing * @nanosleep: Timer is used for nanosleep and is not a regular posix-timer * @handling: Pointer to the task which handles expiry */ struct cpu_timer { struct timerqueue_node node; struct timerqueue_head *head; struct pid *pid; struct list_head elist; bool firing; bool nanosleep; struct task_struct __rcu *handling; }; static inline bool cpu_timer_enqueue(struct timerqueue_head *head, struct cpu_timer *ctmr) { ctmr->head = head; return timerqueue_add(head, &ctmr->node); } static inline bool cpu_timer_queued(struct cpu_timer *ctmr) { return !!ctmr->head; } static inline bool cpu_timer_dequeue(struct cpu_timer *ctmr) { if (cpu_timer_queued(ctmr)) { timerqueue_del(ctmr->head, &ctmr->node); ctmr->head = NULL; return true; } return false; } static inline u64 cpu_timer_getexpires(struct cpu_timer *ctmr) { return ctmr->node.expires; } static inline void cpu_timer_setexpires(struct cpu_timer *ctmr, u64 exp) { ctmr->node.expires = exp; } static inline void posix_cputimers_init(struct posix_cputimers *pct) { memset(pct, 0, sizeof(*pct)); pct->bases[0].nextevt = U64_MAX; pct->bases[1].nextevt = U64_MAX; pct->bases[2].nextevt = U64_MAX; } void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit); static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, u64 runtime) { pct->bases[CPUCLOCK_SCHED].nextevt = runtime; } void posixtimer_rearm_itimer(struct task_struct *p); bool posixtimer_init_sigqueue(struct sigqueue *q); void posixtimer_send_sigqueue(struct k_itimer *tmr); bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq); void posixtimer_free_timer(struct k_itimer *timer); long posixtimer_create_prctl(unsigned long ctrl); /* Init task static initializer */ #define INIT_CPU_TIMERBASE(b) { \ .nextevt = U64_MAX, \ } #define INIT_CPU_TIMERBASES(b) { \ INIT_CPU_TIMERBASE(b[0]), \ INIT_CPU_TIMERBASE(b[1]), \ INIT_CPU_TIMERBASE(b[2]), \ } #define INIT_CPU_TIMERS(s) \ .posix_cputimers = { \ .bases = INIT_CPU_TIMERBASES(s.posix_cputimers.bases), \ }, #else struct cpu_timer { }; #define INIT_CPU_TIMERS(s) static inline void posix_cputimers_init(struct posix_cputimers *pct) { } static inline void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { } static inline void posixtimer_rearm_itimer(struct task_struct *p) { } static inline bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq) { return false; } static inline void posixtimer_free_timer(struct k_itimer *timer) { } static inline long posixtimer_create_prctl(unsigned long ctrl) { return -EINVAL; } #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK void clear_posix_cputimers_work(struct task_struct *p); void posix_cputimers_init_work(void); #else static inline void clear_posix_cputimers_work(struct task_struct *p) { } static inline void posix_cputimers_init_work(void) { } #endif /** * struct k_itimer - POSIX.1b interval timer structure. * @list: List node for binding the timer to tsk::signal::posix_timers * @ignored_list: List node for tracking ignored timers in tsk::signal::ignored_posix_timers * @t_hash: Entry in the posix timer hash table * @it_lock: Lock protecting the timer * @kclock: Pointer to the k_clock struct handling this timer * @it_clock: The posix timer clock id * @it_id: The posix timer id for identifying the timer * @it_status: The status of the timer * @it_sig_periodic: The periodic status at signal delivery * @it_overrun: The overrun counter for pending signals * @it_overrun_last: The overrun at the time of the last delivered signal * @it_signal_seq: Sequence count to control signal delivery * @it_sigqueue_seq: The sequence count at the point where the signal was queued * @it_sigev_notify: The notify word of sigevent struct for signal delivery * @it_interval: The interval for periodic timers * @it_signal: Pointer to the creators signal struct * @it_pid: The pid of the process/task targeted by the signal * @it_process: The task to wakeup on clock_nanosleep (CPU timers) * @rcuref: Reference count for life time management * @sigq: Embedded sigqueue * @it: Union representing the various posix timer type * internals. * @rcu: RCU head for freeing the timer. */ struct k_itimer { /* 1st cacheline contains read-mostly fields */ struct hlist_node t_hash; struct hlist_node list; timer_t it_id; clockid_t it_clock; int it_sigev_notify; enum pid_type it_pid_type; struct signal_struct *it_signal; const struct k_clock *kclock; /* 2nd cacheline and above contain fields which are modified regularly */ spinlock_t it_lock; int it_status; bool it_sig_periodic; s64 it_overrun; s64 it_overrun_last; unsigned int it_signal_seq; unsigned int it_sigqueue_seq; ktime_t it_interval; struct hlist_node ignored_list; union { struct pid *it_pid; struct task_struct *it_process; }; struct sigqueue sigq; rcuref_t rcuref; union { struct { struct hrtimer timer; } real; struct cpu_timer cpu; struct { struct alarm alarmtimer; } alarm; } it; struct rcu_head rcu; } ____cacheline_aligned_in_smp; void run_posix_cpu_timers(void); void posix_cpu_timers_exit(struct task_struct *task); void posix_cpu_timers_exit_group(struct task_struct *task); void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, u64 *newval, u64 *oldval); int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); #ifdef CONFIG_POSIX_TIMERS static inline void posixtimer_putref(struct k_itimer *tmr) { if (rcuref_put(&tmr->rcuref)) posixtimer_free_timer(tmr); } static inline void posixtimer_sigqueue_getref(struct sigqueue *q) { struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); WARN_ON_ONCE(!rcuref_get(&tmr->rcuref)); } static inline void posixtimer_sigqueue_putref(struct sigqueue *q) { struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); posixtimer_putref(tmr); } static inline bool posixtimer_valid(const struct k_itimer *timer) { unsigned long val = (unsigned long)timer->it_signal; return !(val & 0x1UL); } #else /* CONFIG_POSIX_TIMERS */ static inline void posixtimer_sigqueue_getref(struct sigqueue *q) { } static inline void posixtimer_sigqueue_putref(struct sigqueue *q) { } #endif /* !CONFIG_POSIX_TIMERS */ #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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2023 Isovalent */ #ifndef __NET_TCX_H #define __NET_TCX_H #include <linux/bpf.h> #include <linux/bpf_mprog.h> #include <net/sch_generic.h> struct mini_Qdisc; struct tcx_entry { struct mini_Qdisc __rcu *miniq; struct bpf_mprog_bundle bundle; u32 miniq_active; struct rcu_head rcu; }; struct tcx_link { struct bpf_link link; struct net_device *dev; }; static inline void tcx_set_ingress(struct sk_buff *skb, bool ingress) { #ifdef CONFIG_NET_XGRESS skb->tc_at_ingress = ingress; #endif } #ifdef CONFIG_NET_XGRESS static inline struct tcx_entry *tcx_entry(struct bpf_mprog_entry *entry) { struct bpf_mprog_bundle *bundle = entry->parent; return container_of(bundle, struct tcx_entry, bundle); } static inline struct tcx_link *tcx_link(const struct bpf_link *link) { return container_of(link, struct tcx_link, link); } void tcx_inc(void); void tcx_dec(void); static inline void tcx_entry_sync(void) { /* bpf_mprog_entry got a/b swapped, therefore ensure that * there are no inflight users on the old one anymore. */ synchronize_rcu(); } static inline void tcx_entry_update(struct net_device *dev, struct bpf_mprog_entry *entry, bool ingress) { ASSERT_RTNL(); if (ingress) rcu_assign_pointer(dev->tcx_ingress, entry); else rcu_assign_pointer(dev->tcx_egress, entry); } static inline struct bpf_mprog_entry * tcx_entry_fetch(struct net_device *dev, bool ingress) { ASSERT_RTNL(); if (ingress) return rcu_dereference_rtnl(dev->tcx_ingress); else return rcu_dereference_rtnl(dev->tcx_egress); } static inline struct bpf_mprog_entry *tcx_entry_create_noprof(void) { struct tcx_entry *tcx = kzalloc_noprof(sizeof(*tcx), GFP_KERNEL); if (tcx) { bpf_mprog_bundle_init(&tcx->bundle); return &tcx->bundle.a; } return NULL; } #define tcx_entry_create(...) alloc_hooks(tcx_entry_create_noprof(__VA_ARGS__)) static inline void tcx_entry_free(struct bpf_mprog_entry *entry) { kfree_rcu(tcx_entry(entry), rcu); } static inline struct bpf_mprog_entry * tcx_entry_fetch_or_create(struct net_device *dev, bool ingress, bool *created) { struct bpf_mprog_entry *entry = tcx_entry_fetch(dev, ingress); *created = false; if (!entry) { entry = tcx_entry_create(); if (!entry) return NULL; *created = true; } return entry; } static inline void tcx_skeys_inc(bool ingress) { tcx_inc(); if (ingress) net_inc_ingress_queue(); else net_inc_egress_queue(); } static inline void tcx_skeys_dec(bool ingress) { if (ingress) net_dec_ingress_queue(); else net_dec_egress_queue(); tcx_dec(); } static inline void tcx_miniq_inc(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active++; } static inline void tcx_miniq_dec(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); tcx_entry(entry)->miniq_active--; } static inline bool tcx_entry_is_active(struct bpf_mprog_entry *entry) { ASSERT_RTNL(); return bpf_mprog_total(entry) || tcx_entry(entry)->miniq_active; } static inline enum tcx_action_base tcx_action_code(struct sk_buff *skb, int code) { switch (code) { case TCX_PASS: skb->tc_index = qdisc_skb_cb(skb)->tc_classid; fallthrough; case TCX_DROP: case TCX_REDIRECT: return code; case TCX_NEXT: default: return TCX_NEXT; } } #endif /* CONFIG_NET_XGRESS */ #if defined(CONFIG_NET_XGRESS) && defined(CONFIG_BPF_SYSCALL) int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); void tcx_uninstall(struct net_device *dev, bool ingress); int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); static inline void dev_tcx_uninstall(struct net_device *dev) { ASSERT_RTNL(); tcx_uninstall(dev, true); tcx_uninstall(dev, false); } #else static inline int tcx_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } static inline void dev_tcx_uninstall(struct net_device *dev) { } #endif /* CONFIG_NET_XGRESS && CONFIG_BPF_SYSCALL */ #endif /* __NET_TCX_H */ |
| 28 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/path.h> #include <linux/fcntl.h> #include <linux/errno.h> enum { MAX_NESTED_LINKS = 8 }; #define MAXSYMLINKS 40 /* * Type of the last component on LOOKUP_PARENT */ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* pathwalk mode */ #define LOOKUP_FOLLOW BIT(0) /* follow links at the end */ #define LOOKUP_DIRECTORY BIT(1) /* require a directory */ #define LOOKUP_AUTOMOUNT BIT(2) /* force terminal automount */ #define LOOKUP_EMPTY BIT(3) /* accept empty path [user_... only] */ #define LOOKUP_LINKAT_EMPTY BIT(4) /* Linkat request with empty path. */ #define LOOKUP_DOWN BIT(5) /* follow mounts in the starting point */ #define LOOKUP_MOUNTPOINT BIT(6) /* follow mounts in the end */ #define LOOKUP_REVAL BIT(7) /* tell ->d_revalidate() to trust no cache */ #define LOOKUP_RCU BIT(8) /* RCU pathwalk mode; semi-internal */ #define LOOKUP_CACHED BIT(9) /* Only do cached lookup */ #define LOOKUP_PARENT BIT(10) /* Looking up final parent in path */ /* 5 spare bits for pathwalk */ /* These tell filesystem methods that we are dealing with the final component... */ #define LOOKUP_OPEN BIT(16) /* ... in open */ #define LOOKUP_CREATE BIT(17) /* ... in object creation */ #define LOOKUP_EXCL BIT(18) /* ... in target must not exist */ #define LOOKUP_RENAME_TARGET BIT(19) /* ... in destination of rename() */ /* 4 spare bits for intent */ /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS BIT(24) /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS BIT(25) /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV BIT(26) /* No mountpoint crossing. */ #define LOOKUP_BENEATH BIT(27) /* No escaping from starting point. */ #define LOOKUP_IN_ROOT BIT(28) /* Treat dirfd as fs root. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) /* 3 spare bits for scoping */ extern int path_pts(struct path *path); extern int user_path_at(int, const char __user *, unsigned, struct path *); struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); struct dentry *kern_path_parent(const char *name, struct path *parent); extern struct dentry *start_creating_path(int, const char *, struct path *, unsigned int); extern struct dentry *start_creating_user_path(int, const char __user *, struct path *, unsigned int); extern void end_creating_path(const struct path *, struct dentry *); extern struct dentry *start_removing_path(const char *, struct path *); extern struct dentry *start_removing_user_path_at(int , const char __user *, struct path *); static inline void end_removing_path(const struct path *path , struct dentry *dentry) { end_creating_path(path, dentry); } int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); extern struct dentry *try_lookup_noperm(struct qstr *, struct dentry *); extern struct dentry *lookup_noperm(struct qstr *, struct dentry *); extern struct dentry *lookup_noperm_unlocked(struct qstr *, struct dentry *); extern struct dentry *lookup_noperm_positive_unlocked(struct qstr *, struct dentry *); struct dentry *lookup_one(struct mnt_idmap *, struct qstr *, struct dentry *); struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); struct dentry *lookup_one_positive_killable(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); /** * mode_strip_umask - handle vfs umask stripping * @dir: parent directory of the new inode * @mode: mode of the new inode to be created in @dir * * In most filesystems, umask stripping depends on whether or not the * filesystem supports POSIX ACLs. If the filesystem doesn't support it umask * stripping is done directly in here. If the filesystem does support POSIX * ACLs umask stripping is deferred until the filesystem calls * posix_acl_create(). * * Some filesystems (like NFSv4) also want to avoid umask stripping by the * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK * to get this effect without declaring that they support POSIX ACLs. * * Returns: mode */ static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK)) mode &= ~current_umask(); return mode; } extern int __must_check nd_jump_link(const struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { ((char *) name)[min(len, maxlen)] = '\0'; } /** * retry_estale - determine whether the caller should retry an operation * @error: the error that would currently be returned * @flags: flags being used for next lookup attempt * * Check to see if the error code was -ESTALE, and then determine whether * to retry the call based on whether "flags" already has LOOKUP_REVAL set. * * Returns true if the caller should try the operation again. */ static inline bool retry_estale(const long error, const unsigned int flags) { return unlikely(error == -ESTALE && !(flags & LOOKUP_REVAL)); } #endif /* _LINUX_NAMEI_H */ |
| 288 288 288 288 267 268 | 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 | /* 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__ */ |
| 36 35 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu-vm.c - vmalloc area based chunk allocation * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * Chunks are mapped into vmalloc areas and populated page by page. * This is the default chunk allocator. */ #include "internal.h" static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { /* must not be used on pre-mapped chunk */ WARN_ON(chunk->immutable); return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); } /** * pcpu_get_pages - get temp pages array * * Returns pointer to array of pointers to struct page which can be indexed * with pcpu_page_idx(). Note that there is only one array and accesses * should be serialized by pcpu_alloc_mutex. * * RETURNS: * Pointer to temp pages array on success. */ static struct page **pcpu_get_pages(void) { static struct page **pages; size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); lockdep_assert_held(&pcpu_alloc_mutex); if (!pages) pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL); return pages; } /** * pcpu_free_pages - free pages which were allocated for @chunk * @chunk: chunk pages were allocated for * @pages: array of pages to be freed, indexed by pcpu_page_idx() * @page_start: page index of the first page to be freed * @page_end: page index of the last page to be freed + 1 * * Free pages [@page_start and @page_end) in @pages for all units. * The pages were allocated for @chunk. */ static void pcpu_free_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu; int i; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page *page = pages[pcpu_page_idx(cpu, i)]; if (page) __free_page(page); } } } /** * pcpu_alloc_pages - allocates pages for @chunk * @chunk: target chunk * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() * @page_start: page index of the first page to be allocated * @page_end: page index of the last page to be allocated + 1 * @gfp: allocation flags passed to the underlying allocator * * Allocate pages [@page_start,@page_end) into @pages for all units. * The allocation is for @chunk. Percpu core doesn't care about the * content of @pages and will pass it verbatim to pcpu_map_pages(). */ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end, gfp_t gfp) { unsigned int cpu, tcpu; int i; gfp |= __GFP_HIGHMEM; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); if (!*pagep) goto err; } } return 0; err: while (--i >= page_start) __free_page(pages[pcpu_page_idx(cpu, i)]); for_each_possible_cpu(tcpu) { if (tcpu == cpu) break; for (i = page_start; i < page_end; i++) __free_page(pages[pcpu_page_idx(tcpu, i)]); } return -ENOMEM; } /** * pcpu_pre_unmap_flush - flush cache prior to unmapping * @chunk: chunk the regions to be flushed belongs to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages in [@page_start,@page_end) of @chunk are about to be * unmapped. Flush cache. As each flushing trial can be very * expensive, issue flush on the whole region at once rather than * doing it for each cpu. This could be an overkill but is more * scalable. */ static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_cache_vunmap( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) { vunmap_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT)); } /** * pcpu_unmap_pages - unmap pages out of a pcpu_chunk * @chunk: chunk of interest * @pages: pages array which can be used to pass information to free * @page_start: page index of the first page to unmap * @page_end: page index of the last page to unmap + 1 * * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. * Corresponding elements in @pages were cleared by the caller and can * be used to carry information to pcpu_free_pages() which will be * called after all unmaps are finished. The caller should call * proper pre/post flush functions. */ static void pcpu_unmap_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu; int i; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page *page; page = pcpu_chunk_page(chunk, cpu, i); WARN_ON(!page); pages[pcpu_page_idx(cpu, i)] = page; } __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start), page_end - page_start); } } /** * pcpu_post_unmap_tlb_flush - flush TLB after unmapping * @chunk: pcpu_chunk the regions to be flushed belong to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush * TLB for the regions. This can be skipped if the area is to be * returned to vmalloc as vmalloc will handle TLB flushing lazily. * * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once * for the whole region. */ static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_tlb_kernel_range( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } static int __pcpu_map_pages(unsigned long addr, struct page **pages, int nr_pages) { return vmap_pages_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT), PAGE_KERNEL, pages, PAGE_SHIFT); } /** * pcpu_map_pages - map pages into a pcpu_chunk * @chunk: chunk of interest * @pages: pages array containing pages to be mapped * @page_start: page index of the first page to map * @page_end: page index of the last page to map + 1 * * For each cpu, map pages [@page_start,@page_end) into @chunk. The * caller is responsible for calling pcpu_post_map_flush() after all * mappings are complete. * * This function is responsible for setting up whatever is necessary for * reverse lookup (addr -> chunk). */ static int pcpu_map_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu, tcpu; int i, err; for_each_possible_cpu(cpu) { err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start), &pages[pcpu_page_idx(cpu, page_start)], page_end - page_start); if (err < 0) goto err; for (i = page_start; i < page_end; i++) pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)], chunk); } return 0; err: for_each_possible_cpu(tcpu) { __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), page_end - page_start); if (tcpu == cpu) break; } pcpu_post_unmap_tlb_flush(chunk, page_start, page_end); return err; } /** * pcpu_post_map_flush - flush cache after mapping * @chunk: pcpu_chunk the regions to be flushed belong to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages [@page_start,@page_end) of @chunk have been mapped. Flush * cache. * * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once * for the whole region. */ static void pcpu_post_map_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_cache_vmap( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } /** * pcpu_populate_chunk - populate and map an area of a pcpu_chunk * @chunk: chunk of interest * @page_start: the start page * @page_end: the end page * @gfp: allocation flags passed to the underlying memory allocator * * For each cpu, populate and map pages [@page_start,@page_end) into * @chunk. * * CONTEXT: * pcpu_alloc_mutex, does GFP_KERNEL allocation. */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp) { struct page **pages; pages = pcpu_get_pages(); if (!pages) return -ENOMEM; if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp)) return -ENOMEM; if (pcpu_map_pages(chunk, pages, page_start, page_end)) { pcpu_free_pages(chunk, pages, page_start, page_end); return -ENOMEM; } pcpu_post_map_flush(chunk, page_start, page_end); return 0; } /** * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk * @chunk: chunk to depopulate * @page_start: the start page * @page_end: the end page * * For each cpu, depopulate and unmap pages [@page_start,@page_end) * from @chunk. * * Caller is required to call pcpu_post_unmap_tlb_flush() if not returning the * region back to vmalloc() which will lazily flush the tlb. * * CONTEXT: * pcpu_alloc_mutex. */ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end) { struct page **pages; /* * If control reaches here, there must have been at least one * successful population attempt so the temp pages array must * be available now. */ pages = pcpu_get_pages(); BUG_ON(!pages); /* unmap and free */ pcpu_pre_unmap_flush(chunk, page_start, page_end); pcpu_unmap_pages(chunk, pages, page_start, page_end); pcpu_free_pages(chunk, pages, page_start, page_end); } static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; struct vm_struct **vms; chunk = pcpu_alloc_chunk(gfp); if (!chunk) return NULL; vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, pcpu_nr_groups, pcpu_atom_size); if (!vms) { pcpu_free_chunk(chunk); return NULL; } chunk->data = vms; chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0]; pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(chunk->base_addr); return chunk; } static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; pcpu_stats_chunk_dealloc(); trace_percpu_destroy_chunk(chunk->base_addr); if (chunk->data) pcpu_free_vm_areas(chunk->data, pcpu_nr_groups); pcpu_free_chunk(chunk); } static struct page *pcpu_addr_to_page(void *addr) { return vmalloc_to_page(addr); } static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) { /* no extra restriction */ return 0; } /** * pcpu_should_reclaim_chunk - determine if a chunk should go into reclaim * @chunk: chunk of interest * * This is the entry point for percpu reclaim. If a chunk qualifies, it is then * isolated and managed in separate lists at the back of pcpu_slot: sidelined * and to_depopulate respectively. The to_depopulate list holds chunks slated * for depopulation. They no longer contribute to pcpu_nr_empty_pop_pages once * they are on this list. Once depopulated, they are moved onto the sidelined * list which enables them to be pulled back in for allocation if no other chunk * can suffice the allocation. */ static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk) { /* do not reclaim either the first chunk or reserved chunk */ if (chunk == pcpu_first_chunk || chunk == pcpu_reserved_chunk) return false; /* * If it is isolated, it may be on the sidelined list so move it back to * the to_depopulate list. If we hit at least 1/4 pages empty pages AND * there is no system-wide shortage of empty pages aside from this * chunk, move it to the to_depopulate list. */ return ((chunk->isolated && chunk->nr_empty_pop_pages) || (pcpu_nr_empty_pop_pages > (PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages) && chunk->nr_empty_pop_pages >= chunk->nr_pages / 4)); } |
| 56 38 38 50 17 17 37 50 17 17 37 4 14 13 4 14 32 25 10 69 30 16 16 16 16 16 16 16 16 16 16 16 38 38 45 7 7 96 95 38 38 38 38 9 45 7 46 42 53 52 52 56 15 44 42 42 42 16 16 16 16 16 16 16 42 42 36 6 6 42 42 42 42 42 42 42 42 42 42 42 42 37 38 16 18 18 18 5 18 18 18 18 18 4 14 14 18 18 33 17 18 18 18 33 17 18 18 42 42 12 6 36 42 53 52 52 53 53 53 95 91 96 10 7 10 7 16 16 16 16 10 7 7 38 38 34 32 2 18 14 14 2 12 | 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 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/workqueue.h> #include <linux/spinlock.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_tables.h> #include <net/ip.h> #include <net/flow.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_flow_table.h> struct nft_flow_offload { struct nft_flowtable *flowtable; }; static enum flow_offload_xmit_type nft_xmit_type(struct dst_entry *dst) { if (dst_xfrm(dst)) return FLOW_OFFLOAD_XMIT_XFRM; return FLOW_OFFLOAD_XMIT_NEIGH; } static void nft_default_forward_path(struct nf_flow_route *route, struct dst_entry *dst_cache, enum ip_conntrack_dir dir) { route->tuple[!dir].in.ifindex = dst_cache->dev->ifindex; route->tuple[dir].dst = dst_cache; route->tuple[dir].xmit_type = nft_xmit_type(dst_cache); } static bool nft_is_valid_ether_device(const struct net_device *dev) { if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER || dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr)) return false; return true; } static int nft_dev_fill_forward_path(const struct nf_flow_route *route, const struct dst_entry *dst_cache, const struct nf_conn *ct, enum ip_conntrack_dir dir, u8 *ha, struct net_device_path_stack *stack) { const void *daddr = &ct->tuplehash[!dir].tuple.src.u3; struct net_device *dev = dst_cache->dev; struct neighbour *n; u8 nud_state; if (!nft_is_valid_ether_device(dev)) goto out; n = dst_neigh_lookup(dst_cache, daddr); if (!n) return -1; read_lock_bh(&n->lock); nud_state = n->nud_state; ether_addr_copy(ha, n->ha); read_unlock_bh(&n->lock); neigh_release(n); if (!(nud_state & NUD_VALID)) return -1; out: return dev_fill_forward_path(dev, ha, stack); } struct nft_forward_info { const struct net_device *indev; const struct net_device *outdev; const struct net_device *hw_outdev; struct id { __u16 id; __be16 proto; } encap[NF_FLOW_TABLE_ENCAP_MAX]; u8 num_encaps; u8 ingress_vlans; u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; enum flow_offload_xmit_type xmit_type; }; static void nft_dev_path_info(const struct net_device_path_stack *stack, struct nft_forward_info *info, unsigned char *ha, struct nf_flowtable *flowtable) { const struct net_device_path *path; int i; memcpy(info->h_dest, ha, ETH_ALEN); for (i = 0; i < stack->num_paths; i++) { path = &stack->path[i]; switch (path->type) { case DEV_PATH_ETHERNET: case DEV_PATH_DSA: case DEV_PATH_VLAN: case DEV_PATH_PPPOE: info->indev = path->dev; if (is_zero_ether_addr(info->h_source)) memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); if (path->type == DEV_PATH_ETHERNET) break; if (path->type == DEV_PATH_DSA) { i = stack->num_paths; break; } /* DEV_PATH_VLAN and DEV_PATH_PPPOE */ if (info->num_encaps >= NF_FLOW_TABLE_ENCAP_MAX) { info->indev = NULL; break; } if (!info->outdev) info->outdev = path->dev; info->encap[info->num_encaps].id = path->encap.id; info->encap[info->num_encaps].proto = path->encap.proto; info->num_encaps++; if (path->type == DEV_PATH_PPPOE) memcpy(info->h_dest, path->encap.h_dest, ETH_ALEN); break; case DEV_PATH_BRIDGE: if (is_zero_ether_addr(info->h_source)) memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN); switch (path->bridge.vlan_mode) { case DEV_PATH_BR_VLAN_UNTAG_HW: info->ingress_vlans |= BIT(info->num_encaps - 1); break; case DEV_PATH_BR_VLAN_TAG: info->encap[info->num_encaps].id = path->bridge.vlan_id; info->encap[info->num_encaps].proto = path->bridge.vlan_proto; info->num_encaps++; break; case DEV_PATH_BR_VLAN_UNTAG: info->num_encaps--; break; case DEV_PATH_BR_VLAN_KEEP: break; } info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; break; default: info->indev = NULL; break; } } if (!info->outdev) info->outdev = info->indev; info->hw_outdev = info->indev; if (nf_flowtable_hw_offload(flowtable) && nft_is_valid_ether_device(info->indev)) info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT; } static bool nft_flowtable_find_dev(const struct net_device *dev, struct nft_flowtable *ft) { struct nft_hook *hook; bool found = false; list_for_each_entry_rcu(hook, &ft->hook_list, list) { if (!nft_hook_find_ops_rcu(hook, dev)) continue; found = true; break; } return found; } static void nft_dev_forward_path(struct nf_flow_route *route, const struct nf_conn *ct, enum ip_conntrack_dir dir, struct nft_flowtable *ft) { const struct dst_entry *dst = route->tuple[dir].dst; struct net_device_path_stack stack; struct nft_forward_info info = {}; unsigned char ha[ETH_ALEN]; int i; if (nft_dev_fill_forward_path(route, dst, ct, dir, ha, &stack) >= 0) nft_dev_path_info(&stack, &info, ha, &ft->data); if (!info.indev || !nft_flowtable_find_dev(info.indev, ft)) return; route->tuple[!dir].in.ifindex = info.indev->ifindex; for (i = 0; i < info.num_encaps; i++) { route->tuple[!dir].in.encap[i].id = info.encap[i].id; route->tuple[!dir].in.encap[i].proto = info.encap[i].proto; } route->tuple[!dir].in.num_encaps = info.num_encaps; route->tuple[!dir].in.ingress_vlans = info.ingress_vlans; if (info.xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) { memcpy(route->tuple[dir].out.h_source, info.h_source, ETH_ALEN); memcpy(route->tuple[dir].out.h_dest, info.h_dest, ETH_ALEN); route->tuple[dir].out.ifindex = info.outdev->ifindex; route->tuple[dir].out.hw_ifindex = info.hw_outdev->ifindex; route->tuple[dir].xmit_type = info.xmit_type; } } static int nft_flow_route(const struct nft_pktinfo *pkt, const struct nf_conn *ct, struct nf_flow_route *route, enum ip_conntrack_dir dir, struct nft_flowtable *ft) { struct dst_entry *this_dst = skb_dst(pkt->skb); struct dst_entry *other_dst = NULL; struct flowi fl; memset(&fl, 0, sizeof(fl)); switch (nft_pf(pkt)) { case NFPROTO_IPV4: fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip; fl.u.ip4.saddr = ct->tuplehash[!dir].tuple.src.u3.ip; fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex; fl.u.ip4.flowi4_iif = this_dst->dev->ifindex; fl.u.ip4.flowi4_dscp = ip4h_dscp(ip_hdr(pkt->skb)); fl.u.ip4.flowi4_mark = pkt->skb->mark; fl.u.ip4.flowi4_flags = FLOWI_FLAG_ANYSRC; break; case NFPROTO_IPV6: fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6; fl.u.ip6.saddr = ct->tuplehash[!dir].tuple.src.u3.in6; fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex; fl.u.ip6.flowi6_iif = this_dst->dev->ifindex; fl.u.ip6.flowlabel = ip6_flowinfo(ipv6_hdr(pkt->skb)); fl.u.ip6.flowi6_mark = pkt->skb->mark; fl.u.ip6.flowi6_flags = FLOWI_FLAG_ANYSRC; break; } if (!dst_hold_safe(this_dst)) return -ENOENT; nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt)); if (!other_dst) { dst_release(this_dst); return -ENOENT; } nft_default_forward_path(route, this_dst, dir); nft_default_forward_path(route, other_dst, !dir); if (route->tuple[dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH && route->tuple[!dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH) { nft_dev_forward_path(route, ct, dir, ft); nft_dev_forward_path(route, ct, !dir, ft); } return 0; } static bool nft_flow_offload_skip(struct sk_buff *skb, int family) { if (skb_sec_path(skb)) return true; if (family == NFPROTO_IPV4) { const struct ip_options *opt; opt = &(IPCB(skb)->opt); if (unlikely(opt->optlen)) return true; } return false; } static void flow_offload_ct_tcp(struct nf_conn *ct) { /* conntrack will not see all packets, disable tcp window validation. */ spin_lock_bh(&ct->lock); ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; spin_unlock_bh(&ct->lock); } static void nft_flow_offload_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; struct tcphdr _tcph, *tcph = NULL; struct nf_flow_route route = {}; enum ip_conntrack_info ctinfo; struct flow_offload *flow; enum ip_conntrack_dir dir; struct nf_conn *ct; int ret; if (nft_flow_offload_skip(pkt->skb, nft_pf(pkt))) goto out; ct = nf_ct_get(pkt->skb, &ctinfo); if (!ct) goto out; switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) { case IPPROTO_TCP: tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(_tcph), &_tcph); if (unlikely(!tcph || tcph->fin || tcph->rst || !nf_conntrack_tcp_established(ct))) goto out; break; case IPPROTO_UDP: break; #ifdef CONFIG_NF_CT_PROTO_GRE case IPPROTO_GRE: { struct nf_conntrack_tuple *tuple; if (ct->status & IPS_NAT_MASK) goto out; tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; /* No support for GRE v1 */ if (tuple->src.u.gre.key || tuple->dst.u.gre.key) goto out; break; } #endif default: goto out; } if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) || ct->status & (IPS_SEQ_ADJUST | IPS_NAT_CLASH)) goto out; if (!nf_ct_is_confirmed(ct)) goto out; if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status)) goto out; dir = CTINFO2DIR(ctinfo); if (nft_flow_route(pkt, ct, &route, dir, priv->flowtable) < 0) goto err_flow_route; flow = flow_offload_alloc(ct); if (!flow) goto err_flow_alloc; flow_offload_route_init(flow, &route); if (tcph) flow_offload_ct_tcp(ct); __set_bit(NF_FLOW_HW_BIDIRECTIONAL, &flow->flags); ret = flow_offload_add(flowtable, flow); if (ret < 0) goto err_flow_add; return; err_flow_add: flow_offload_free(flow); err_flow_alloc: dst_release(route.tuple[dir].dst); dst_release(route.tuple[!dir].dst); err_flow_route: clear_bit(IPS_OFFLOAD_BIT, &ct->status); out: regs->verdict.code = NFT_BREAK; } static int nft_flow_offload_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { unsigned int hook_mask = (1 << NF_INET_FORWARD); if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && ctx->family != NFPROTO_INET) return -EOPNOTSUPP; return nft_chain_validate_hooks(ctx->chain, hook_mask); } static const struct nla_policy nft_flow_offload_policy[NFTA_FLOW_MAX + 1] = { [NFTA_FLOW_TABLE_NAME] = { .type = NLA_STRING, .len = NFT_NAME_MAXLEN - 1 }, }; static int nft_flow_offload_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_flow_offload *priv = nft_expr_priv(expr); u8 genmask = nft_genmask_next(ctx->net); struct nft_flowtable *flowtable; if (!tb[NFTA_FLOW_TABLE_NAME]) return -EINVAL; flowtable = nft_flowtable_lookup(ctx->net, ctx->table, tb[NFTA_FLOW_TABLE_NAME], genmask); if (IS_ERR(flowtable)) return PTR_ERR(flowtable); if (!nft_use_inc(&flowtable->use)) return -EMFILE; priv->flowtable = flowtable; return nf_ct_netns_get(ctx->net, ctx->family); } static void nft_flow_offload_deactivate(const struct nft_ctx *ctx, const struct nft_expr *expr, enum nft_trans_phase phase) { struct nft_flow_offload *priv = nft_expr_priv(expr); nf_tables_deactivate_flowtable(ctx, priv->flowtable, phase); } static void nft_flow_offload_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_flow_offload *priv = nft_expr_priv(expr); nft_use_inc_restore(&priv->flowtable->use); } static void nft_flow_offload_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { nf_ct_netns_put(ctx->net, ctx->family); } static int nft_flow_offload_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_flow_offload *priv = nft_expr_priv(expr); if (nla_put_string(skb, NFTA_FLOW_TABLE_NAME, priv->flowtable->name)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static struct nft_expr_type nft_flow_offload_type; static const struct nft_expr_ops nft_flow_offload_ops = { .type = &nft_flow_offload_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_flow_offload)), .eval = nft_flow_offload_eval, .init = nft_flow_offload_init, .activate = nft_flow_offload_activate, .deactivate = nft_flow_offload_deactivate, .destroy = nft_flow_offload_destroy, .validate = nft_flow_offload_validate, .dump = nft_flow_offload_dump, .reduce = NFT_REDUCE_READONLY, }; static struct nft_expr_type nft_flow_offload_type __read_mostly = { .name = "flow_offload", .ops = &nft_flow_offload_ops, .policy = nft_flow_offload_policy, .maxattr = NFTA_FLOW_MAX, .owner = THIS_MODULE, }; static int flow_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); if (event != NETDEV_DOWN) return NOTIFY_DONE; nf_flow_table_cleanup(dev); return NOTIFY_DONE; } static struct notifier_block flow_offload_netdev_notifier = { .notifier_call = flow_offload_netdev_event, }; static int __init nft_flow_offload_module_init(void) { int err; err = register_netdevice_notifier(&flow_offload_netdev_notifier); if (err) goto err; err = nft_register_expr(&nft_flow_offload_type); if (err < 0) goto register_expr; return 0; register_expr: unregister_netdevice_notifier(&flow_offload_netdev_notifier); err: return err; } static void __exit nft_flow_offload_module_exit(void) { nft_unregister_expr(&nft_flow_offload_type); unregister_netdevice_notifier(&flow_offload_netdev_notifier); } module_init(nft_flow_offload_module_init); module_exit(nft_flow_offload_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("flow_offload"); MODULE_DESCRIPTION("nftables hardware flow offload module"); |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 4 3 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 | // SPDX-License-Identifier: GPL-2.0-only #include <net/netdev_lock.h> #include <net/netdev_queues.h> #include <net/sock.h> #include <linux/ethtool_netlink.h> #include <linux/phy_link_topology.h> #include <linux/pm_runtime.h> #include "netlink.h" #include "module_fw.h" static struct genl_family ethtool_genl_family; static bool ethnl_ok __read_mostly; static u32 ethnl_bcast_seq; #define ETHTOOL_FLAGS_BASIC (ETHTOOL_FLAG_COMPACT_BITSETS | \ ETHTOOL_FLAG_OMIT_REPLY) #define ETHTOOL_FLAGS_STATS (ETHTOOL_FLAGS_BASIC | ETHTOOL_FLAG_STATS) const struct nla_policy ethnl_header_policy[] = { [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_BASIC), }; const struct nla_policy ethnl_header_policy_stats[] = { [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_STATS), }; const struct nla_policy ethnl_header_policy_phy[] = { [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_BASIC), [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; const struct nla_policy ethnl_header_policy_phy_stats[] = { [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, .len = ALTIFNAMSIZ - 1 }, [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, ETHTOOL_FLAGS_STATS), [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; int ethnl_sock_priv_set(struct sk_buff *skb, struct net_device *dev, u32 portid, enum ethnl_sock_type type) { struct ethnl_sock_priv *sk_priv; sk_priv = genl_sk_priv_get(ðtool_genl_family, NETLINK_CB(skb).sk); if (IS_ERR(sk_priv)) return PTR_ERR(sk_priv); sk_priv->dev = dev; sk_priv->portid = portid; sk_priv->type = type; return 0; } static void ethnl_sock_priv_destroy(void *priv) { struct ethnl_sock_priv *sk_priv = priv; switch (sk_priv->type) { case ETHTOOL_SOCK_TYPE_MODULE_FW_FLASH: ethnl_module_fw_flash_sock_destroy(sk_priv); break; default: break; } } u32 ethnl_bcast_seq_next(void) { ASSERT_RTNL(); return ++ethnl_bcast_seq; } int ethnl_ops_begin(struct net_device *dev) { int ret; if (!dev) return -ENODEV; if (dev->dev.parent) pm_runtime_get_sync(dev->dev.parent); netdev_ops_assert_locked(dev); if (!netif_device_present(dev) || dev->reg_state >= NETREG_UNREGISTERING) { ret = -ENODEV; goto err; } if (dev->ethtool_ops->begin) { ret = dev->ethtool_ops->begin(dev); if (ret) goto err; } return 0; err: if (dev->dev.parent) pm_runtime_put(dev->dev.parent); return ret; } void ethnl_ops_complete(struct net_device *dev) { if (dev->ethtool_ops->complete) dev->ethtool_ops->complete(dev); if (dev->dev.parent) pm_runtime_put(dev->dev.parent); } /** * ethnl_parse_header_dev_get() - parse request header * @req_info: structure to put results into * @header: nest attribute with request header * @net: request netns * @extack: netlink extack for error reporting * @require_dev: fail if no device identified in header * * Parse request header in nested attribute @nest and puts results into * the structure pointed to by @req_info. Extack from @info is used for error * reporting. If req_info->dev is not null on return, reference to it has * been taken. If error is returned, *req_info is null initialized and no * reference is held. * * Return: 0 on success or negative error code */ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, const struct nlattr *header, struct net *net, struct netlink_ext_ack *extack, bool require_dev) { struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy_phy)]; const struct nlattr *devname_attr; struct net_device *dev = NULL; u32 flags = 0; int ret; if (!header) { if (!require_dev) return 0; NL_SET_ERR_MSG(extack, "request header missing"); return -EINVAL; } /* No validation here, command policy should have a nested policy set * for the header, therefore validation should have already been done. */ ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy_phy) - 1, header, NULL, extack); if (ret < 0) return ret; if (tb[ETHTOOL_A_HEADER_FLAGS]) flags = nla_get_u32(tb[ETHTOOL_A_HEADER_FLAGS]); devname_attr = tb[ETHTOOL_A_HEADER_DEV_NAME]; if (tb[ETHTOOL_A_HEADER_DEV_INDEX]) { u32 ifindex = nla_get_u32(tb[ETHTOOL_A_HEADER_DEV_INDEX]); dev = netdev_get_by_index(net, ifindex, &req_info->dev_tracker, GFP_KERNEL); if (!dev) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_HEADER_DEV_INDEX], "no device matches ifindex"); return -ENODEV; } /* if both ifindex and ifname are passed, they must match */ if (devname_attr && strncmp(dev->name, nla_data(devname_attr), IFNAMSIZ)) { netdev_put(dev, &req_info->dev_tracker); NL_SET_ERR_MSG_ATTR(extack, header, "ifindex and name do not match"); return -ENODEV; } } else if (devname_attr) { dev = netdev_get_by_name(net, nla_data(devname_attr), &req_info->dev_tracker, GFP_KERNEL); if (!dev) { NL_SET_ERR_MSG_ATTR(extack, devname_attr, "no device matches name"); return -ENODEV; } } else if (require_dev) { NL_SET_ERR_MSG_ATTR(extack, header, "neither ifindex nor name specified"); return -EINVAL; } if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) { if (dev) { req_info->phy_index = nla_get_u32(tb[ETHTOOL_A_HEADER_PHY_INDEX]); } else { NL_SET_ERR_MSG_ATTR(extack, header, "phy_index set without a netdev"); return -EINVAL; } } req_info->dev = dev; req_info->flags = flags; return 0; } struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info, struct nlattr **tb, unsigned int header, struct netlink_ext_ack *extack) { struct phy_device *phydev; ASSERT_RTNL(); if (!req_info->dev) return NULL; if (!req_info->phy_index) return req_info->dev->phydev; phydev = phy_link_topo_get_phy(req_info->dev, req_info->phy_index); if (!phydev && tb) { NL_SET_ERR_MSG_ATTR(extack, tb[header], "no phy matching phyindex"); return ERR_PTR(-ENODEV); } return phydev; } /** * ethnl_fill_reply_header() - Put common header into a reply message * @skb: skb with the message * @dev: network device to describe in header * @attrtype: attribute type to use for the nest * * Create a nested attribute with attributes describing given network device. * * Return: 0 on success, error value (-EMSGSIZE only) on error */ int ethnl_fill_reply_header(struct sk_buff *skb, struct net_device *dev, u16 attrtype) { struct nlattr *nest; if (!dev) return 0; nest = nla_nest_start(skb, attrtype); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_HEADER_DEV_INDEX, (u32)dev->ifindex) || nla_put_string(skb, ETHTOOL_A_HEADER_DEV_NAME, dev->name)) goto nla_put_failure; /* If more attributes are put into reply header, ethnl_header_size() * must be updated to account for them. */ nla_nest_end(skb, nest); return 0; nla_put_failure: nla_nest_cancel(skb, nest); return -EMSGSIZE; } /** * ethnl_reply_init() - Create skb for a reply and fill device identification * @payload: payload length (without netlink and genetlink header) * @dev: device the reply is about (may be null) * @cmd: ETHTOOL_MSG_* message type for reply * @hdr_attrtype: attribute type for common header * @info: genetlink info of the received packet we respond to * @ehdrp: place to store payload pointer returned by genlmsg_new() * * Return: pointer to allocated skb on success, NULL on error */ struct sk_buff *ethnl_reply_init(size_t payload, struct net_device *dev, u8 cmd, u16 hdr_attrtype, struct genl_info *info, void **ehdrp) { struct sk_buff *skb; skb = genlmsg_new(payload, GFP_KERNEL); if (!skb) goto err; *ehdrp = genlmsg_put_reply(skb, info, ðtool_genl_family, 0, cmd); if (!*ehdrp) goto err_free; if (dev) { int ret; ret = ethnl_fill_reply_header(skb, dev, hdr_attrtype); if (ret < 0) goto err_free; } return skb; err_free: nlmsg_free(skb); err: if (info) GENL_SET_ERR_MSG(info, "failed to setup reply message"); return NULL; } void *ethnl_dump_put(struct sk_buff *skb, struct netlink_callback *cb, u8 cmd) { return genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, ðtool_genl_family, 0, cmd); } void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd) { return genlmsg_put(skb, 0, ++ethnl_bcast_seq, ðtool_genl_family, 0, cmd); } void *ethnl_unicast_put(struct sk_buff *skb, u32 portid, u32 seq, u8 cmd) { return genlmsg_put(skb, portid, seq, ðtool_genl_family, 0, cmd); } int ethnl_multicast(struct sk_buff *skb, struct net_device *dev) { return genlmsg_multicast_netns(ðtool_genl_family, dev_net(dev), skb, 0, ETHNL_MCGRP_MONITOR, GFP_KERNEL); } /* GET request helpers */ /** * struct ethnl_dump_ctx - context structure for generic dumpit() callback * @ops: request ops of currently processed message type * @req_info: parsed request header of processed request * @reply_data: data needed to compose the reply * @pos_ifindex: saved iteration position - ifindex * * These parameters are kept in struct netlink_callback as context preserved * between iterations. They are initialized by ethnl_default_start() and used * in ethnl_default_dumpit() and ethnl_default_done(). */ struct ethnl_dump_ctx { const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; struct ethnl_reply_data *reply_data; unsigned long pos_ifindex; }; /** * struct ethnl_perphy_dump_ctx - context for dumpit() PHY-aware callbacks * @ethnl_ctx: generic ethnl context * @ifindex: For Filtered DUMP requests, the ifindex of the targeted netdev * @pos_phyindex: iterator position for multi-msg DUMP */ struct ethnl_perphy_dump_ctx { struct ethnl_dump_ctx ethnl_ctx; unsigned int ifindex; unsigned long pos_phyindex; }; static const struct ethnl_request_ops * ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_STRSET_GET] = ðnl_strset_request_ops, [ETHTOOL_MSG_LINKINFO_GET] = ðnl_linkinfo_request_ops, [ETHTOOL_MSG_LINKINFO_SET] = ðnl_linkinfo_request_ops, [ETHTOOL_MSG_LINKMODES_GET] = ðnl_linkmodes_request_ops, [ETHTOOL_MSG_LINKMODES_SET] = ðnl_linkmodes_request_ops, [ETHTOOL_MSG_LINKSTATE_GET] = ðnl_linkstate_request_ops, [ETHTOOL_MSG_DEBUG_GET] = ðnl_debug_request_ops, [ETHTOOL_MSG_DEBUG_SET] = ðnl_debug_request_ops, [ETHTOOL_MSG_WOL_GET] = ðnl_wol_request_ops, [ETHTOOL_MSG_WOL_SET] = ðnl_wol_request_ops, [ETHTOOL_MSG_FEATURES_GET] = ðnl_features_request_ops, [ETHTOOL_MSG_PRIVFLAGS_GET] = ðnl_privflags_request_ops, [ETHTOOL_MSG_PRIVFLAGS_SET] = ðnl_privflags_request_ops, [ETHTOOL_MSG_RINGS_GET] = ðnl_rings_request_ops, [ETHTOOL_MSG_RINGS_SET] = ðnl_rings_request_ops, [ETHTOOL_MSG_CHANNELS_GET] = ðnl_channels_request_ops, [ETHTOOL_MSG_CHANNELS_SET] = ðnl_channels_request_ops, [ETHTOOL_MSG_COALESCE_GET] = ðnl_coalesce_request_ops, [ETHTOOL_MSG_COALESCE_SET] = ðnl_coalesce_request_ops, [ETHTOOL_MSG_PAUSE_GET] = ðnl_pause_request_ops, [ETHTOOL_MSG_PAUSE_SET] = ðnl_pause_request_ops, [ETHTOOL_MSG_EEE_GET] = ðnl_eee_request_ops, [ETHTOOL_MSG_EEE_SET] = ðnl_eee_request_ops, [ETHTOOL_MSG_FEC_GET] = ðnl_fec_request_ops, [ETHTOOL_MSG_FEC_SET] = ðnl_fec_request_ops, [ETHTOOL_MSG_TSINFO_GET] = ðnl_tsinfo_request_ops, [ETHTOOL_MSG_MODULE_EEPROM_GET] = ðnl_module_eeprom_request_ops, [ETHTOOL_MSG_STATS_GET] = ðnl_stats_request_ops, [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops, [ETHTOOL_MSG_MODULE_GET] = ðnl_module_request_ops, [ETHTOOL_MSG_MODULE_SET] = ðnl_module_request_ops, [ETHTOOL_MSG_PSE_GET] = ðnl_pse_request_ops, [ETHTOOL_MSG_PSE_SET] = ðnl_pse_request_ops, [ETHTOOL_MSG_RSS_GET] = ðnl_rss_request_ops, [ETHTOOL_MSG_RSS_SET] = ðnl_rss_request_ops, [ETHTOOL_MSG_PLCA_GET_CFG] = ðnl_plca_cfg_request_ops, [ETHTOOL_MSG_PLCA_SET_CFG] = ðnl_plca_cfg_request_ops, [ETHTOOL_MSG_PLCA_GET_STATUS] = ðnl_plca_status_request_ops, [ETHTOOL_MSG_MM_GET] = ðnl_mm_request_ops, [ETHTOOL_MSG_MM_SET] = ðnl_mm_request_ops, [ETHTOOL_MSG_TSCONFIG_GET] = ðnl_tsconfig_request_ops, [ETHTOOL_MSG_TSCONFIG_SET] = ðnl_tsconfig_request_ops, [ETHTOOL_MSG_PHY_GET] = ðnl_phy_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) { return (struct ethnl_dump_ctx *)cb->ctx; } static struct ethnl_perphy_dump_ctx * ethnl_perphy_dump_context(struct netlink_callback *cb) { return (struct ethnl_perphy_dump_ctx *)cb->ctx; } /** * ethnl_default_parse() - Parse request message * @req_info: pointer to structure to put data into * @info: genl_info from the request * @request_ops: struct request_ops for request type * @require_dev: fail if no device identified in header * * Parse universal request header and call request specific ->parse_request() * callback (if defined) to parse the rest of the message. * * Return: 0 on success or negative error code */ static int ethnl_default_parse(struct ethnl_req_info *req_info, const struct genl_info *info, const struct ethnl_request_ops *request_ops, bool require_dev) { struct nlattr **tb = info->attrs; int ret; ret = ethnl_parse_header_dev_get(req_info, tb[request_ops->hdr_attr], genl_info_net(info), info->extack, require_dev); if (ret < 0) return ret; if (request_ops->parse_request) { ret = request_ops->parse_request(req_info, tb, info->extack); if (ret < 0) goto err_dev; } return 0; err_dev: netdev_put(req_info->dev, &req_info->dev_tracker); req_info->dev = NULL; return ret; } /** * ethnl_init_reply_data() - Initialize reply data for GET request * @reply_data: pointer to embedded struct ethnl_reply_data * @ops: instance of struct ethnl_request_ops describing the layout * @dev: network device to initialize the reply for * * Fills the reply data part with zeros and sets the dev member. Must be called * before calling the ->fill_reply() callback (for each iteration when handling * dump requests). */ static void ethnl_init_reply_data(struct ethnl_reply_data *reply_data, const struct ethnl_request_ops *ops, struct net_device *dev) { memset(reply_data, 0, ops->reply_data_size); reply_data->dev = dev; } /* default ->doit() handler for GET type requests */ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) { struct ethnl_reply_data *reply_data = NULL; struct ethnl_req_info *req_info = NULL; const u8 cmd = info->genlhdr->cmd; const struct ethnl_request_ops *ops; int hdr_len, reply_len; struct sk_buff *rskb; void *reply_payload; int ret; ops = ethnl_default_requests[cmd]; if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", cmd)) return -EOPNOTSUPP; if (GENL_REQ_ATTR_CHECK(info, ops->hdr_attr)) return -EINVAL; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return -ENOMEM; reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); if (!reply_data) { kfree(req_info); return -ENOMEM; } ret = ethnl_default_parse(req_info, info, ops, !ops->allow_nodev_do); if (ret < 0) goto err_free; ethnl_init_reply_data(reply_data, ops, req_info->dev); rtnl_lock(); if (req_info->dev) netdev_lock_ops(req_info->dev); ret = ops->prepare_data(req_info, reply_data, info); if (req_info->dev) netdev_unlock_ops(req_info->dev); rtnl_unlock(); if (ret < 0) goto err_dev; ret = ops->reply_size(req_info, reply_data); if (ret < 0) goto err_cleanup; reply_len = ret; ret = -ENOMEM; rskb = ethnl_reply_init(reply_len + ethnl_reply_header_size(), req_info->dev, ops->reply_cmd, ops->hdr_attr, info, &reply_payload); if (!rskb) goto err_cleanup; hdr_len = rskb->len; ret = ops->fill_reply(rskb, req_info, reply_data); if (ret < 0) goto err_msg; WARN_ONCE(rskb->len - hdr_len > reply_len, "ethnl cmd %d: calculated reply length %d, but consumed %d\n", cmd, reply_len, rskb->len - hdr_len); if (ops->cleanup_data) ops->cleanup_data(reply_data); genlmsg_end(rskb, reply_payload); netdev_put(req_info->dev, &req_info->dev_tracker); kfree(reply_data); kfree(req_info); return genlmsg_reply(rskb, info); err_msg: WARN_ONCE(ret == -EMSGSIZE, "calculated message payload length (%d) not sufficient\n", reply_len); nlmsg_free(rskb); err_cleanup: if (ops->cleanup_data) ops->cleanup_data(reply_data); err_dev: netdev_put(req_info->dev, &req_info->dev_tracker); err_free: kfree(reply_data); kfree(req_info); return ret; } static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev, const struct ethnl_dump_ctx *ctx, const struct genl_info *info) { void *ehdr; int ret; ehdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, ðtool_genl_family, NLM_F_MULTI, ctx->ops->reply_cmd); if (!ehdr) return -EMSGSIZE; ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev); rtnl_lock(); netdev_lock_ops(dev); ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, info); netdev_unlock_ops(dev); rtnl_unlock(); if (ret < 0) goto out_cancel; ret = ethnl_fill_reply_header(skb, dev, ctx->ops->hdr_attr); if (ret < 0) goto out; ret = ctx->ops->fill_reply(skb, ctx->req_info, ctx->reply_data); out: if (ctx->ops->cleanup_data) ctx->ops->cleanup_data(ctx->reply_data); out_cancel: ctx->reply_data->dev = NULL; if (ret < 0) genlmsg_cancel(skb, ehdr); else genlmsg_end(skb, ehdr); return ret; } /* Default ->dumpit() handler for GET requests. */ static int ethnl_default_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); struct net *net = sock_net(skb->sk); netdevice_tracker dev_tracker; struct net_device *dev; int ret = 0; rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->pos_ifindex) { netdev_hold(dev, &dev_tracker, GFP_ATOMIC); rcu_read_unlock(); ret = ethnl_default_dump_one(skb, dev, ctx, genl_info_dump(cb)); rcu_read_lock(); netdev_put(dev, &dev_tracker); if (ret < 0 && ret != -EOPNOTSUPP) { if (likely(skb->len)) ret = skb->len; break; } ret = 0; } rcu_read_unlock(); return ret; } /* generic ->start() handler for GET requests */ static int ethnl_default_start(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); struct ethnl_reply_data *reply_data; const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; struct genlmsghdr *ghdr; int ret; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); ghdr = nlmsg_data(cb->nlh); ops = ethnl_default_requests[ghdr->cmd]; if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", ghdr->cmd)) return -EOPNOTSUPP; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return -ENOMEM; reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); if (!reply_data) { ret = -ENOMEM; goto free_req_info; } ret = ethnl_default_parse(req_info, &info->info, ops, false); if (ret < 0) goto free_reply_data; if (req_info->dev) { /* We ignore device specification in dump requests but as the * same parser as for non-dump (doit) requests is used, it * would take reference to the device if it finds one */ netdev_put(req_info->dev, &req_info->dev_tracker); req_info->dev = NULL; } ctx->ops = ops; ctx->req_info = req_info; ctx->reply_data = reply_data; ctx->pos_ifindex = 0; return 0; free_reply_data: kfree(reply_data); free_req_info: kfree(req_info); return ret; } /* per-PHY ->start() handler for GET requests */ static int ethnl_perphy_start(struct netlink_callback *cb) { struct ethnl_perphy_dump_ctx *phy_ctx = ethnl_perphy_dump_context(cb); const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ethnl_dump_ctx *ctx = &phy_ctx->ethnl_ctx; struct ethnl_reply_data *reply_data; const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; struct genlmsghdr *ghdr; int ret; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); ghdr = nlmsg_data(cb->nlh); ops = ethnl_default_requests[ghdr->cmd]; if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", ghdr->cmd)) return -EOPNOTSUPP; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return -ENOMEM; reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); if (!reply_data) { ret = -ENOMEM; goto free_req_info; } /* Unlike per-dev dump, don't ignore dev. The dump handler * will notice it and dump PHYs from given dev. We only keep track of * the dev's ifindex, .dumpit() will grab and release the netdev itself. */ ret = ethnl_default_parse(req_info, &info->info, ops, false); if (ret < 0) goto free_reply_data; if (req_info->dev) { phy_ctx->ifindex = req_info->dev->ifindex; netdev_put(req_info->dev, &req_info->dev_tracker); req_info->dev = NULL; } ctx->ops = ops; ctx->req_info = req_info; ctx->reply_data = reply_data; ctx->pos_ifindex = 0; return 0; free_reply_data: kfree(reply_data); free_req_info: kfree(req_info); return ret; } static int ethnl_perphy_dump_one_dev(struct sk_buff *skb, struct ethnl_perphy_dump_ctx *ctx, const struct genl_info *info) { struct ethnl_dump_ctx *ethnl_ctx = &ctx->ethnl_ctx; struct net_device *dev = ethnl_ctx->req_info->dev; struct phy_device_node *pdn; int ret; if (!dev->link_topo) return 0; xa_for_each_start(&dev->link_topo->phys, ctx->pos_phyindex, pdn, ctx->pos_phyindex) { ethnl_ctx->req_info->phy_index = ctx->pos_phyindex; /* We can re-use the original dump_one as ->prepare_data in * commands use ethnl_req_get_phydev(), which gets the PHY from * the req_info->phy_index */ ret = ethnl_default_dump_one(skb, dev, ethnl_ctx, info); if (ret) return ret; } ctx->pos_phyindex = 0; return 0; } static int ethnl_perphy_dump_all_dev(struct sk_buff *skb, struct ethnl_perphy_dump_ctx *ctx, const struct genl_info *info) { struct ethnl_dump_ctx *ethnl_ctx = &ctx->ethnl_ctx; struct net *net = sock_net(skb->sk); netdevice_tracker dev_tracker; struct net_device *dev; int ret = 0; rcu_read_lock(); for_each_netdev_dump(net, dev, ethnl_ctx->pos_ifindex) { netdev_hold(dev, &dev_tracker, GFP_ATOMIC); rcu_read_unlock(); /* per-PHY commands use ethnl_req_get_phydev(), which needs the * net_device in the req_info */ ethnl_ctx->req_info->dev = dev; ret = ethnl_perphy_dump_one_dev(skb, ctx, info); rcu_read_lock(); netdev_put(dev, &dev_tracker); ethnl_ctx->req_info->dev = NULL; if (ret < 0 && ret != -EOPNOTSUPP) { if (likely(skb->len)) ret = skb->len; break; } ret = 0; } rcu_read_unlock(); return ret; } /* per-PHY ->dumpit() handler for GET requests. */ static int ethnl_perphy_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct ethnl_perphy_dump_ctx *ctx = ethnl_perphy_dump_context(cb); const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct ethnl_dump_ctx *ethnl_ctx = &ctx->ethnl_ctx; int ret = 0; if (ctx->ifindex) { netdevice_tracker dev_tracker; struct net_device *dev; dev = netdev_get_by_index(genl_info_net(&info->info), ctx->ifindex, &dev_tracker, GFP_KERNEL); if (!dev) return -ENODEV; ethnl_ctx->req_info->dev = dev; ret = ethnl_perphy_dump_one_dev(skb, ctx, genl_info_dump(cb)); if (ret < 0 && ret != -EOPNOTSUPP && likely(skb->len)) ret = skb->len; netdev_put(dev, &dev_tracker); } else { ret = ethnl_perphy_dump_all_dev(skb, ctx, genl_info_dump(cb)); } return ret; } /* per-PHY ->done() handler for GET requests */ static int ethnl_perphy_done(struct netlink_callback *cb) { struct ethnl_perphy_dump_ctx *ctx = ethnl_perphy_dump_context(cb); struct ethnl_dump_ctx *ethnl_ctx = &ctx->ethnl_ctx; kfree(ethnl_ctx->reply_data); kfree(ethnl_ctx->req_info); return 0; } /* default ->done() handler for GET requests */ static int ethnl_default_done(struct netlink_callback *cb) { struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb); kfree(ctx->reply_data); kfree(ctx->req_info); return 0; } static int ethnl_default_set_doit(struct sk_buff *skb, struct genl_info *info) { const struct ethnl_request_ops *ops; const u8 cmd = info->genlhdr->cmd; struct ethnl_req_info *req_info; struct net_device *dev; int ret; ops = ethnl_default_requests[cmd]; if (WARN_ONCE(!ops, "cmd %u has no ethnl_request_ops\n", cmd)) return -EOPNOTSUPP; if (GENL_REQ_ATTR_CHECK(info, ops->hdr_attr)) return -EINVAL; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return -ENOMEM; ret = ethnl_default_parse(req_info, info, ops, true); if (ret < 0) goto out_free_req; if (ops->set_validate) { ret = ops->set_validate(req_info, info); /* 0 means nothing to do */ if (ret <= 0) goto out_dev; } dev = req_info->dev; rtnl_lock(); netdev_lock_ops(dev); dev->cfg_pending = kmemdup(dev->cfg, sizeof(*dev->cfg), GFP_KERNEL_ACCOUNT); if (!dev->cfg_pending) { ret = -ENOMEM; goto out_tie_cfg; } ret = ethnl_ops_begin(dev); if (ret < 0) goto out_free_cfg; ret = ops->set(req_info, info); if (ret < 0) goto out_ops; swap(dev->cfg, dev->cfg_pending); if (!ret) goto out_ops; ethnl_notify(dev, ops->set_ntf_cmd, req_info); ret = 0; out_ops: ethnl_ops_complete(dev); out_free_cfg: kfree(dev->cfg_pending); out_tie_cfg: dev->cfg_pending = dev->cfg; netdev_unlock_ops(dev); rtnl_unlock(); out_dev: ethnl_parse_header_dev_put(req_info); out_free_req: kfree(req_info); return ret; } static const struct ethnl_request_ops * ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { [ETHTOOL_MSG_LINKINFO_NTF] = ðnl_linkinfo_request_ops, [ETHTOOL_MSG_LINKMODES_NTF] = ðnl_linkmodes_request_ops, [ETHTOOL_MSG_DEBUG_NTF] = ðnl_debug_request_ops, [ETHTOOL_MSG_WOL_NTF] = ðnl_wol_request_ops, [ETHTOOL_MSG_FEATURES_NTF] = ðnl_features_request_ops, [ETHTOOL_MSG_PRIVFLAGS_NTF] = ðnl_privflags_request_ops, [ETHTOOL_MSG_RINGS_NTF] = ðnl_rings_request_ops, [ETHTOOL_MSG_CHANNELS_NTF] = ðnl_channels_request_ops, [ETHTOOL_MSG_COALESCE_NTF] = ðnl_coalesce_request_ops, [ETHTOOL_MSG_PAUSE_NTF] = ðnl_pause_request_ops, [ETHTOOL_MSG_EEE_NTF] = ðnl_eee_request_ops, [ETHTOOL_MSG_FEC_NTF] = ðnl_fec_request_ops, [ETHTOOL_MSG_MODULE_NTF] = ðnl_module_request_ops, [ETHTOOL_MSG_PLCA_NTF] = ðnl_plca_cfg_request_ops, [ETHTOOL_MSG_MM_NTF] = ðnl_mm_request_ops, [ETHTOOL_MSG_RSS_NTF] = ðnl_rss_request_ops, [ETHTOOL_MSG_RSS_CREATE_NTF] = ðnl_rss_request_ops, }; /* default notification handler */ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd, const struct ethnl_req_info *orig_req_info) { struct ethnl_reply_data *reply_data; const struct ethnl_request_ops *ops; struct ethnl_req_info *req_info; struct genl_info info; struct sk_buff *skb; void *reply_payload; int reply_len; int ret; genl_info_init_ntf(&info, ðtool_genl_family, cmd); if (WARN_ONCE(cmd > ETHTOOL_MSG_KERNEL_MAX || !ethnl_default_notify_ops[cmd], "unexpected notification type %u\n", cmd)) return; ops = ethnl_default_notify_ops[cmd]; req_info = kzalloc(ops->req_info_size, GFP_KERNEL); if (!req_info) return; reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); if (!reply_data) { kfree(req_info); return; } req_info->dev = dev; req_info->flags |= ETHTOOL_FLAG_COMPACT_BITSETS; if (orig_req_info) { req_info->phy_index = orig_req_info->phy_index; memcpy(&req_info[1], &orig_req_info[1], ops->req_info_size - sizeof(*req_info)); } netdev_ops_assert_locked(dev); ethnl_init_reply_data(reply_data, ops, dev); ret = ops->prepare_data(req_info, reply_data, &info); if (ret < 0) goto err_rep; ret = ops->reply_size(req_info, reply_data); if (ret < 0) goto err_cleanup; reply_len = ret + ethnl_reply_header_size(); skb = genlmsg_new(reply_len, GFP_KERNEL); if (!skb) goto err_cleanup; reply_payload = ethnl_bcastmsg_put(skb, cmd); if (!reply_payload) goto err_skb; ret = ethnl_fill_reply_header(skb, dev, ops->hdr_attr); if (ret < 0) goto err_msg; ret = ops->fill_reply(skb, req_info, reply_data); if (ret < 0) goto err_msg; if (ops->cleanup_data) ops->cleanup_data(reply_data); genlmsg_end(skb, reply_payload); kfree(reply_data); kfree(req_info); ethnl_multicast(skb, dev); return; err_msg: WARN_ONCE(ret == -EMSGSIZE, "calculated message payload length (%d) not sufficient\n", reply_len); err_skb: nlmsg_free(skb); err_cleanup: if (ops->cleanup_data) ops->cleanup_data(reply_data); err_rep: kfree(reply_data); kfree(req_info); return; } /* notifications */ typedef void (*ethnl_notify_handler_t)(struct net_device *dev, unsigned int cmd, const struct ethnl_req_info *req_info); static const ethnl_notify_handler_t ethnl_notify_handlers[] = { [ETHTOOL_MSG_LINKINFO_NTF] = ethnl_default_notify, [ETHTOOL_MSG_LINKMODES_NTF] = ethnl_default_notify, [ETHTOOL_MSG_DEBUG_NTF] = ethnl_default_notify, [ETHTOOL_MSG_WOL_NTF] = ethnl_default_notify, [ETHTOOL_MSG_FEATURES_NTF] = ethnl_default_notify, [ETHTOOL_MSG_PRIVFLAGS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_RINGS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_CHANNELS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_COALESCE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_PAUSE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_EEE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_FEC_NTF] = ethnl_default_notify, [ETHTOOL_MSG_MODULE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_PLCA_NTF] = ethnl_default_notify, [ETHTOOL_MSG_MM_NTF] = ethnl_default_notify, [ETHTOOL_MSG_RSS_NTF] = ethnl_default_notify, [ETHTOOL_MSG_RSS_CREATE_NTF] = ethnl_default_notify, }; void ethnl_notify(struct net_device *dev, unsigned int cmd, const struct ethnl_req_info *req_info) { if (unlikely(!ethnl_ok)) return; ASSERT_RTNL(); if (likely(cmd < ARRAY_SIZE(ethnl_notify_handlers) && ethnl_notify_handlers[cmd])) ethnl_notify_handlers[cmd](dev, cmd, req_info); else WARN_ONCE(1, "notification %u not implemented (dev=%s)\n", cmd, netdev_name(dev)); } void ethtool_notify(struct net_device *dev, unsigned int cmd) { ethnl_notify(dev, cmd, NULL); } EXPORT_SYMBOL(ethtool_notify); static void ethnl_notify_features(struct netdev_notifier_info *info) { struct net_device *dev = netdev_notifier_info_to_dev(info); ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF); } static int ethnl_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netdev_notifier_info *info = ptr; struct netlink_ext_ack *extack; struct net_device *dev; dev = netdev_notifier_info_to_dev(info); extack = netdev_notifier_info_to_extack(info); switch (event) { case NETDEV_FEAT_CHANGE: ethnl_notify_features(ptr); break; case NETDEV_PRE_UP: if (dev->ethtool->module_fw_flash_in_progress) { NL_SET_ERR_MSG(extack, "Can't set port up while flashing module firmware"); return NOTIFY_BAD; } } return NOTIFY_DONE; } static struct notifier_block ethnl_netdev_notifier = { .notifier_call = ethnl_netdev_event, }; /* genetlink setup */ static const struct genl_ops ethtool_genl_ops[] = { { .cmd = ETHTOOL_MSG_STRSET_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_strset_get_policy, .maxattr = ARRAY_SIZE(ethnl_strset_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKINFO_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_linkinfo_get_policy, .maxattr = ARRAY_SIZE(ethnl_linkinfo_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKINFO_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_linkinfo_set_policy, .maxattr = ARRAY_SIZE(ethnl_linkinfo_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKMODES_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_linkmodes_get_policy, .maxattr = ARRAY_SIZE(ethnl_linkmodes_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKMODES_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_linkmodes_set_policy, .maxattr = ARRAY_SIZE(ethnl_linkmodes_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_LINKSTATE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_linkstate_get_policy, .maxattr = ARRAY_SIZE(ethnl_linkstate_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_DEBUG_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_debug_get_policy, .maxattr = ARRAY_SIZE(ethnl_debug_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_DEBUG_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_debug_set_policy, .maxattr = ARRAY_SIZE(ethnl_debug_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_WOL_GET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_wol_get_policy, .maxattr = ARRAY_SIZE(ethnl_wol_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_WOL_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_wol_set_policy, .maxattr = ARRAY_SIZE(ethnl_wol_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEATURES_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_features_get_policy, .maxattr = ARRAY_SIZE(ethnl_features_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEATURES_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_set_features, .policy = ethnl_features_set_policy, .maxattr = ARRAY_SIZE(ethnl_features_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_PRIVFLAGS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_privflags_get_policy, .maxattr = ARRAY_SIZE(ethnl_privflags_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PRIVFLAGS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_privflags_set_policy, .maxattr = ARRAY_SIZE(ethnl_privflags_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_RINGS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_rings_get_policy, .maxattr = ARRAY_SIZE(ethnl_rings_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_RINGS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_rings_set_policy, .maxattr = ARRAY_SIZE(ethnl_rings_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_CHANNELS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_channels_get_policy, .maxattr = ARRAY_SIZE(ethnl_channels_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_CHANNELS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_channels_set_policy, .maxattr = ARRAY_SIZE(ethnl_channels_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_COALESCE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_coalesce_get_policy, .maxattr = ARRAY_SIZE(ethnl_coalesce_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_COALESCE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_coalesce_set_policy, .maxattr = ARRAY_SIZE(ethnl_coalesce_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_PAUSE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_pause_get_policy, .maxattr = ARRAY_SIZE(ethnl_pause_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PAUSE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_pause_set_policy, .maxattr = ARRAY_SIZE(ethnl_pause_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_EEE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_eee_get_policy, .maxattr = ARRAY_SIZE(ethnl_eee_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_EEE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_eee_set_policy, .maxattr = ARRAY_SIZE(ethnl_eee_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_TSINFO_GET, .doit = ethnl_default_doit, .start = ethnl_tsinfo_start, .dumpit = ethnl_tsinfo_dumpit, .done = ethnl_tsinfo_done, .policy = ethnl_tsinfo_get_policy, .maxattr = ARRAY_SIZE(ethnl_tsinfo_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_CABLE_TEST_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_act_cable_test, .policy = ethnl_cable_test_act_policy, .maxattr = ARRAY_SIZE(ethnl_cable_test_act_policy) - 1, }, { .cmd = ETHTOOL_MSG_CABLE_TEST_TDR_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_act_cable_test_tdr, .policy = ethnl_cable_test_tdr_act_policy, .maxattr = ARRAY_SIZE(ethnl_cable_test_tdr_act_policy) - 1, }, { .cmd = ETHTOOL_MSG_TUNNEL_INFO_GET, .doit = ethnl_tunnel_info_doit, .start = ethnl_tunnel_info_start, .dumpit = ethnl_tunnel_info_dumpit, .policy = ethnl_tunnel_info_get_policy, .maxattr = ARRAY_SIZE(ethnl_tunnel_info_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEC_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_fec_get_policy, .maxattr = ARRAY_SIZE(ethnl_fec_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_FEC_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_fec_set_policy, .maxattr = ARRAY_SIZE(ethnl_fec_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_MODULE_EEPROM_GET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_module_eeprom_get_policy, .maxattr = ARRAY_SIZE(ethnl_module_eeprom_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_STATS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_stats_get_policy, .maxattr = ARRAY_SIZE(ethnl_stats_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_phc_vclocks_get_policy, .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_MODULE_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_module_get_policy, .maxattr = ARRAY_SIZE(ethnl_module_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_MODULE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_module_set_policy, .maxattr = ARRAY_SIZE(ethnl_module_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_PSE_GET, .doit = ethnl_default_doit, .start = ethnl_perphy_start, .dumpit = ethnl_perphy_dumpit, .done = ethnl_perphy_done, .policy = ethnl_pse_get_policy, .maxattr = ARRAY_SIZE(ethnl_pse_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PSE_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_pse_set_policy, .maxattr = ARRAY_SIZE(ethnl_pse_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_RSS_GET, .doit = ethnl_default_doit, .start = ethnl_rss_dump_start, .dumpit = ethnl_rss_dumpit, .policy = ethnl_rss_get_policy, .maxattr = ARRAY_SIZE(ethnl_rss_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_PLCA_GET_CFG, .doit = ethnl_default_doit, .start = ethnl_perphy_start, .dumpit = ethnl_perphy_dumpit, .done = ethnl_perphy_done, .policy = ethnl_plca_get_cfg_policy, .maxattr = ARRAY_SIZE(ethnl_plca_get_cfg_policy) - 1, }, { .cmd = ETHTOOL_MSG_PLCA_SET_CFG, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_plca_set_cfg_policy, .maxattr = ARRAY_SIZE(ethnl_plca_set_cfg_policy) - 1, }, { .cmd = ETHTOOL_MSG_PLCA_GET_STATUS, .doit = ethnl_default_doit, .start = ethnl_perphy_start, .dumpit = ethnl_perphy_dumpit, .done = ethnl_perphy_done, .policy = ethnl_plca_get_status_policy, .maxattr = ARRAY_SIZE(ethnl_plca_get_status_policy) - 1, }, { .cmd = ETHTOOL_MSG_MM_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_mm_get_policy, .maxattr = ARRAY_SIZE(ethnl_mm_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_MM_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_mm_set_policy, .maxattr = ARRAY_SIZE(ethnl_mm_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_MODULE_FW_FLASH_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_act_module_fw_flash, .policy = ethnl_module_fw_flash_act_policy, .maxattr = ARRAY_SIZE(ethnl_module_fw_flash_act_policy) - 1, }, { .cmd = ETHTOOL_MSG_PHY_GET, .doit = ethnl_default_doit, .start = ethnl_perphy_start, .dumpit = ethnl_perphy_dumpit, .done = ethnl_perphy_done, .policy = ethnl_phy_get_policy, .maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_TSCONFIG_GET, .doit = ethnl_default_doit, .start = ethnl_default_start, .dumpit = ethnl_default_dumpit, .done = ethnl_default_done, .policy = ethnl_tsconfig_get_policy, .maxattr = ARRAY_SIZE(ethnl_tsconfig_get_policy) - 1, }, { .cmd = ETHTOOL_MSG_TSCONFIG_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_tsconfig_set_policy, .maxattr = ARRAY_SIZE(ethnl_tsconfig_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_RSS_SET, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_default_set_doit, .policy = ethnl_rss_set_policy, .maxattr = ARRAY_SIZE(ethnl_rss_set_policy) - 1, }, { .cmd = ETHTOOL_MSG_RSS_CREATE_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_rss_create_doit, .policy = ethnl_rss_create_policy, .maxattr = ARRAY_SIZE(ethnl_rss_create_policy) - 1, }, { .cmd = ETHTOOL_MSG_RSS_DELETE_ACT, .flags = GENL_UNS_ADMIN_PERM, .doit = ethnl_rss_delete_doit, .policy = ethnl_rss_delete_policy, .maxattr = ARRAY_SIZE(ethnl_rss_delete_policy) - 1, }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { [ETHNL_MCGRP_MONITOR] = { .name = ETHTOOL_MCGRP_MONITOR_NAME }, }; static struct genl_family ethtool_genl_family __ro_after_init = { .name = ETHTOOL_GENL_NAME, .version = ETHTOOL_GENL_VERSION, .netnsok = true, .parallel_ops = true, .ops = ethtool_genl_ops, .n_ops = ARRAY_SIZE(ethtool_genl_ops), .resv_start_op = ETHTOOL_MSG_MODULE_GET + 1, .mcgrps = ethtool_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(ethtool_nl_mcgrps), .sock_priv_size = sizeof(struct ethnl_sock_priv), .sock_priv_destroy = ethnl_sock_priv_destroy, }; /* module setup */ static int __init ethnl_init(void) { int ret; ret = genl_register_family(ðtool_genl_family); if (WARN(ret < 0, "ethtool: genetlink family registration failed")) return ret; ethnl_ok = true; ret = register_netdevice_notifier(ðnl_netdev_notifier); WARN(ret < 0, "ethtool: net device notifier registration failed"); return ret; } subsys_initcall(ethnl_init); |
| 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 | /* 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 |
| 17 17 17 17 17 17 17 17 17 100 4 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 | // SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) /* * Copyright (C) 2017-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005 * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All rights reserved. * * This driver produces cryptographically secure pseudorandom data. It is divided * into roughly six sections, each with a section header: * * - Initialization and readiness waiting. * - Fast key erasure RNG, the "crng". * - Entropy accumulation and extraction routines. * - Entropy collection routines. * - Userspace reader/writer interfaces. * - Sysctl interface. * * The high level overview is that there is one input pool, into which * various pieces of data are hashed. Prior to initialization, some of that * data is then "credited" as having a certain number of bits of entropy. * When enough bits of entropy are available, the hash is finalized and * handed as a key to a stream cipher that expands it indefinitely for * various consumers. This key is periodically refreshed as the various * entropy collectors, described below, add data to the input pool. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/utsname.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/major.h> #include <linux/string.h> #include <linux/fcntl.h> #include <linux/slab.h> #include <linux/random.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/blkdev.h> #include <linux/interrupt.h> #include <linux/mm.h> #include <linux/nodemask.h> #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/percpu.h> #include <linux/ptrace.h> #include <linux/workqueue.h> #include <linux/irq.h> #include <linux/ratelimit.h> #include <linux/syscalls.h> #include <linux/completion.h> #include <linux/uuid.h> #include <linux/uaccess.h> #include <linux/suspend.h> #include <linux/siphash.h> #include <linux/sched/isolation.h> #include <crypto/chacha.h> #include <crypto/blake2s.h> #ifdef CONFIG_VDSO_GETRANDOM #include <vdso/getrandom.h> #include <vdso/datapage.h> #include <vdso/vsyscall.h> #endif #include <asm/archrandom.h> #include <asm/processor.h> #include <asm/irq.h> #include <asm/irq_regs.h> #include <asm/io.h> /********************************************************************* * * Initialization and readiness waiting. * * Much of the RNG infrastructure is devoted to various dependencies * being able to wait until the RNG has collected enough entropy and * is ready for safe consumption. * *********************************************************************/ /* * crng_init is protected by base_crng->lock, and only increases * its value (from empty->early->ready). */ static enum { CRNG_EMPTY = 0, /* Little to no entropy collected */ CRNG_EARLY = 1, /* At least POOL_EARLY_BITS collected */ CRNG_READY = 2 /* Fully initialized with POOL_READY_BITS collected */ } crng_init __read_mostly = CRNG_EMPTY; static DEFINE_STATIC_KEY_FALSE(crng_is_ready); #define crng_ready() (static_branch_likely(&crng_is_ready) || crng_init >= CRNG_READY) /* Various types of waiters for crng_init->CRNG_READY transition. */ static DECLARE_WAIT_QUEUE_HEAD(crng_init_wait); static struct fasync_struct *fasync; static ATOMIC_NOTIFIER_HEAD(random_ready_notifier); /* Control how we warn userspace. */ static struct ratelimit_state urandom_warning = RATELIMIT_STATE_INIT_FLAGS("urandom_warning", HZ, 3, RATELIMIT_MSG_ON_RELEASE); static int ratelimit_disable __read_mostly = IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM); module_param_named(ratelimit_disable, ratelimit_disable, int, 0644); MODULE_PARM_DESC(ratelimit_disable, "Disable random ratelimit suppression"); /* * Returns whether or not the input pool has been seeded and thus guaranteed * to supply cryptographically secure random numbers. This applies to: the * /dev/urandom device, the get_random_bytes function, and the get_random_{u8, * u16,u32,u64,long} family of functions. * * Returns: true if the input pool has been seeded. * false if the input pool has not been seeded. */ bool rng_is_initialized(void) { return crng_ready(); } EXPORT_SYMBOL(rng_is_initialized); static void __cold crng_set_ready(struct work_struct *work) { static_branch_enable(&crng_is_ready); } /* Used by wait_for_random_bytes(), and considered an entropy collector, below. */ static void try_to_generate_entropy(void); /* * Wait for the input pool to be seeded and thus guaranteed to supply * cryptographically secure random numbers. This applies to: the /dev/urandom * device, the get_random_bytes function, and the get_random_{u8,u16,u32,u64, * long} family of functions. Using any of these functions without first * calling this function forfeits the guarantee of security. * * Returns: 0 if the input pool has been seeded. * -ERESTARTSYS if the function was interrupted by a signal. */ int wait_for_random_bytes(void) { while (!crng_ready()) { int ret; try_to_generate_entropy(); ret = wait_event_interruptible_timeout(crng_init_wait, crng_ready(), HZ); if (ret) return ret > 0 ? 0 : ret; } return 0; } EXPORT_SYMBOL(wait_for_random_bytes); /* * Add a callback function that will be invoked when the crng is initialised, * or immediately if it already has been. Only use this is you are absolutely * sure it is required. Most users should instead be able to test * `rng_is_initialized()` on demand, or make use of `get_random_bytes_wait()`. */ int __cold execute_with_initialized_rng(struct notifier_block *nb) { unsigned long flags; int ret = 0; spin_lock_irqsave(&random_ready_notifier.lock, flags); if (crng_ready()) nb->notifier_call(nb, 0, NULL); else ret = raw_notifier_chain_register((struct raw_notifier_head *)&random_ready_notifier.head, nb); spin_unlock_irqrestore(&random_ready_notifier.lock, flags); return ret; } #define warn_unseeded_randomness() \ if (IS_ENABLED(CONFIG_WARN_ALL_UNSEEDED_RANDOM) && !crng_ready()) \ printk_deferred(KERN_NOTICE "random: %s called from %pS with crng_init=%d\n", \ __func__, (void *)_RET_IP_, crng_init) /********************************************************************* * * Fast key erasure RNG, the "crng". * * These functions expand entropy from the entropy extractor into * long streams for external consumption using the "fast key erasure" * RNG described at <https://blog.cr.yp.to/20170723-random.html>. * * There are a few exported interfaces for use by other drivers: * * void get_random_bytes(void *buf, size_t len) * u8 get_random_u8() * u16 get_random_u16() * u32 get_random_u32() * u32 get_random_u32_below(u32 ceil) * u32 get_random_u32_above(u32 floor) * u32 get_random_u32_inclusive(u32 floor, u32 ceil) * u64 get_random_u64() * unsigned long get_random_long() * * These interfaces will return the requested number of random bytes * into the given buffer or as a return value. This is equivalent to * a read from /dev/urandom. The u8, u16, u32, u64, long family of * functions may be higher performance for one-off random integers, * because they do a bit of buffering and do not invoke reseeding * until the buffer is emptied. * *********************************************************************/ enum { CRNG_RESEED_START_INTERVAL = HZ, CRNG_RESEED_INTERVAL = 60 * HZ }; static struct { u8 key[CHACHA_KEY_SIZE] __aligned(__alignof__(long)); unsigned long generation; spinlock_t lock; } base_crng = { .lock = __SPIN_LOCK_UNLOCKED(base_crng.lock) }; struct crng { u8 key[CHACHA_KEY_SIZE]; unsigned long generation; local_lock_t lock; }; static DEFINE_PER_CPU(struct crng, crngs) = { .generation = ULONG_MAX, .lock = INIT_LOCAL_LOCK(crngs.lock), }; /* * Return the interval until the next reseeding, which is normally * CRNG_RESEED_INTERVAL, but during early boot, it is at an interval * proportional to the uptime. */ static unsigned int crng_reseed_interval(void) { static bool early_boot = true; if (unlikely(READ_ONCE(early_boot))) { time64_t uptime = ktime_get_seconds(); if (uptime >= CRNG_RESEED_INTERVAL / HZ * 2) WRITE_ONCE(early_boot, false); else return max_t(unsigned int, CRNG_RESEED_START_INTERVAL, (unsigned int)uptime / 2 * HZ); } return CRNG_RESEED_INTERVAL; } /* Used by crng_reseed() and crng_make_state() to extract a new seed from the input pool. */ static void extract_entropy(void *buf, size_t len); /* This extracts a new crng key from the input pool. */ static void crng_reseed(struct work_struct *work) { static DECLARE_DELAYED_WORK(next_reseed, crng_reseed); unsigned long flags; unsigned long next_gen; u8 key[CHACHA_KEY_SIZE]; /* Immediately schedule the next reseeding, so that it fires sooner rather than later. */ if (likely(system_unbound_wq)) queue_delayed_work(system_unbound_wq, &next_reseed, crng_reseed_interval()); extract_entropy(key, sizeof(key)); /* * We copy the new key into the base_crng, overwriting the old one, * and update the generation counter. We avoid hitting ULONG_MAX, * because the per-cpu crngs are initialized to ULONG_MAX, so this * forces new CPUs that come online to always initialize. */ spin_lock_irqsave(&base_crng.lock, flags); memcpy(base_crng.key, key, sizeof(base_crng.key)); next_gen = base_crng.generation + 1; if (next_gen == ULONG_MAX) ++next_gen; WRITE_ONCE(base_crng.generation, next_gen); #ifdef CONFIG_VDSO_GETRANDOM /* base_crng.generation's invalid value is ULONG_MAX, while * vdso_k_rng_data->generation's invalid value is 0, so add one to the * former to arrive at the latter. Use smp_store_release so that this * is ordered with the write above to base_crng.generation. Pairs with * the smp_rmb() before the syscall in the vDSO code. * * Cast to unsigned long for 32-bit architectures, since atomic 64-bit * operations are not supported on those architectures. This is safe * because base_crng.generation is a 32-bit value. On big-endian * architectures it will be stored in the upper 32 bits, but that's okay * because the vDSO side only checks whether the value changed, without * actually using or interpreting the value. */ smp_store_release((unsigned long *)&vdso_k_rng_data->generation, next_gen + 1); #endif if (!static_branch_likely(&crng_is_ready)) crng_init = CRNG_READY; spin_unlock_irqrestore(&base_crng.lock, flags); memzero_explicit(key, sizeof(key)); } /* * This generates a ChaCha block using the provided key, and then * immediately overwrites that key with half the block. It returns * the resultant ChaCha state to the user, along with the second * half of the block containing 32 bytes of random data that may * be used; random_data_len may not be greater than 32. * * The returned ChaCha state contains within it a copy of the old * key value, at index 4, so the state should always be zeroed out * immediately after using in order to maintain forward secrecy. * If the state cannot be erased in a timely manner, then it is * safer to set the random_data parameter to &chacha_state->x[4] * so that this function overwrites it before returning. */ static void crng_fast_key_erasure(u8 key[CHACHA_KEY_SIZE], struct chacha_state *chacha_state, u8 *random_data, size_t random_data_len) { u8 first_block[CHACHA_BLOCK_SIZE]; BUG_ON(random_data_len > 32); chacha_init_consts(chacha_state); memcpy(&chacha_state->x[4], key, CHACHA_KEY_SIZE); memset(&chacha_state->x[12], 0, sizeof(u32) * 4); chacha20_block(chacha_state, first_block); memcpy(key, first_block, CHACHA_KEY_SIZE); memcpy(random_data, first_block + CHACHA_KEY_SIZE, random_data_len); memzero_explicit(first_block, sizeof(first_block)); } /* * This function returns a ChaCha state that you may use for generating * random data. It also returns up to 32 bytes on its own of random data * that may be used; random_data_len may not be greater than 32. */ static void crng_make_state(struct chacha_state *chacha_state, u8 *random_data, size_t random_data_len) { unsigned long flags; struct crng *crng; BUG_ON(random_data_len > 32); /* * For the fast path, we check whether we're ready, unlocked first, and * then re-check once locked later. In the case where we're really not * ready, we do fast key erasure with the base_crng directly, extracting * when crng_init is CRNG_EMPTY. */ if (!crng_ready()) { bool ready; spin_lock_irqsave(&base_crng.lock, flags); ready = crng_ready(); if (!ready) { if (crng_init == CRNG_EMPTY) extract_entropy(base_crng.key, sizeof(base_crng.key)); crng_fast_key_erasure(base_crng.key, chacha_state, random_data, random_data_len); } spin_unlock_irqrestore(&base_crng.lock, flags); if (!ready) return; } local_lock_irqsave(&crngs.lock, flags); crng = raw_cpu_ptr(&crngs); /* * If our per-cpu crng is older than the base_crng, then it means * somebody reseeded the base_crng. In that case, we do fast key * erasure on the base_crng, and use its output as the new key * for our per-cpu crng. This brings us up to date with base_crng. */ if (unlikely(crng->generation != READ_ONCE(base_crng.generation))) { spin_lock(&base_crng.lock); crng_fast_key_erasure(base_crng.key, chacha_state, crng->key, sizeof(crng->key)); crng->generation = base_crng.generation; spin_unlock(&base_crng.lock); } /* * Finally, when we've made it this far, our per-cpu crng has an up * to date key, and we can do fast key erasure with it to produce * some random data and a ChaCha state for the caller. All other * branches of this function are "unlikely", so most of the time we * should wind up here immediately. */ crng_fast_key_erasure(crng->key, chacha_state, random_data, random_data_len); local_unlock_irqrestore(&crngs.lock, flags); } static void _get_random_bytes(void *buf, size_t len) { struct chacha_state chacha_state; u8 tmp[CHACHA_BLOCK_SIZE]; size_t first_block_len; if (!len) return; first_block_len = min_t(size_t, 32, len); crng_make_state(&chacha_state, buf, first_block_len); len -= first_block_len; buf += first_block_len; while (len) { if (len < CHACHA_BLOCK_SIZE) { chacha20_block(&chacha_state, tmp); memcpy(buf, tmp, len); memzero_explicit(tmp, sizeof(tmp)); break; } chacha20_block(&chacha_state, buf); if (unlikely(chacha_state.x[12] == 0)) ++chacha_state.x[13]; len -= CHACHA_BLOCK_SIZE; buf += CHACHA_BLOCK_SIZE; } chacha_zeroize_state(&chacha_state); } /* * This returns random bytes in arbitrary quantities. The quality of the * random bytes is good as /dev/urandom. In order to ensure that the * randomness provided by this function is okay, the function * wait_for_random_bytes() should be called and return 0 at least once * at any point prior. */ void get_random_bytes(void *buf, size_t len) { warn_unseeded_randomness(); _get_random_bytes(buf, len); } EXPORT_SYMBOL(get_random_bytes); static ssize_t get_random_bytes_user(struct iov_iter *iter) { struct chacha_state chacha_state; u8 block[CHACHA_BLOCK_SIZE]; size_t ret = 0, copied; if (unlikely(!iov_iter_count(iter))) return 0; /* * Immediately overwrite the ChaCha key at index 4 with random * bytes, in case userspace causes copy_to_iter() below to sleep * forever, so that we still retain forward secrecy in that case. */ crng_make_state(&chacha_state, (u8 *)&chacha_state.x[4], CHACHA_KEY_SIZE); /* * However, if we're doing a read of len <= 32, we don't need to * use chacha_state after, so we can simply return those bytes to * the user directly. */ if (iov_iter_count(iter) <= CHACHA_KEY_SIZE) { ret = copy_to_iter(&chacha_state.x[4], CHACHA_KEY_SIZE, iter); goto out_zero_chacha; } for (;;) { chacha20_block(&chacha_state, block); if (unlikely(chacha_state.x[12] == 0)) ++chacha_state.x[13]; copied = copy_to_iter(block, sizeof(block), iter); ret += copied; if (!iov_iter_count(iter) || copied != sizeof(block)) break; BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); if (ret % PAGE_SIZE == 0) { if (signal_pending(current)) break; cond_resched(); } } memzero_explicit(block, sizeof(block)); out_zero_chacha: chacha_zeroize_state(&chacha_state); return ret ? ret : -EFAULT; } /* * Batched entropy returns random integers. The quality of the random * number is good as /dev/urandom. In order to ensure that the randomness * provided by this function is okay, the function wait_for_random_bytes() * should be called and return 0 at least once at any point prior. */ #define DEFINE_BATCHED_ENTROPY(type) \ struct batch_ ##type { \ /* \ * We make this 1.5x a ChaCha block, so that we get the \ * remaining 32 bytes from fast key erasure, plus one full \ * block from the detached ChaCha state. We can increase \ * the size of this later if needed so long as we keep the \ * formula of (integer_blocks + 0.5) * CHACHA_BLOCK_SIZE. \ */ \ type entropy[CHACHA_BLOCK_SIZE * 3 / (2 * sizeof(type))]; \ local_lock_t lock; \ unsigned long generation; \ unsigned int position; \ }; \ \ static DEFINE_PER_CPU(struct batch_ ##type, batched_entropy_ ##type) = { \ .lock = INIT_LOCAL_LOCK(batched_entropy_ ##type.lock), \ .position = UINT_MAX \ }; \ \ type get_random_ ##type(void) \ { \ type ret; \ unsigned long flags; \ struct batch_ ##type *batch; \ unsigned long next_gen; \ \ warn_unseeded_randomness(); \ \ if (!crng_ready()) { \ _get_random_bytes(&ret, sizeof(ret)); \ return ret; \ } \ \ local_lock_irqsave(&batched_entropy_ ##type.lock, flags); \ batch = raw_cpu_ptr(&batched_entropy_##type); \ \ next_gen = READ_ONCE(base_crng.generation); \ if (batch->position >= ARRAY_SIZE(batch->entropy) || \ next_gen != batch->generation) { \ _get_random_bytes(batch->entropy, sizeof(batch->entropy)); \ batch->position = 0; \ batch->generation = next_gen; \ } \ \ ret = batch->entropy[batch->position]; \ batch->entropy[batch->position] = 0; \ ++batch->position; \ local_unlock_irqrestore(&batched_entropy_ ##type.lock, flags); \ return ret; \ } \ EXPORT_SYMBOL(get_random_ ##type); DEFINE_BATCHED_ENTROPY(u8) DEFINE_BATCHED_ENTROPY(u16) DEFINE_BATCHED_ENTROPY(u32) DEFINE_BATCHED_ENTROPY(u64) u32 __get_random_u32_below(u32 ceil) { /* * This is the slow path for variable ceil. It is still fast, most of * the time, by doing traditional reciprocal multiplication and * opportunistically comparing the lower half to ceil itself, before * falling back to computing a larger bound, and then rejecting samples * whose lower half would indicate a range indivisible by ceil. The use * of `-ceil % ceil` is analogous to `2^32 % ceil`, but is computable * in 32-bits. */ u32 rand = get_random_u32(); u64 mult; /* * This function is technically undefined for ceil == 0, and in fact * for the non-underscored constant version in the header, we build bug * on that. But for the non-constant case, it's convenient to have that * evaluate to being a straight call to get_random_u32(), so that * get_random_u32_inclusive() can work over its whole range without * undefined behavior. */ if (unlikely(!ceil)) return rand; mult = (u64)ceil * rand; if (unlikely((u32)mult < ceil)) { u32 bound = -ceil % ceil; while (unlikely((u32)mult < bound)) mult = (u64)ceil * get_random_u32(); } return mult >> 32; } EXPORT_SYMBOL(__get_random_u32_below); #ifdef CONFIG_SMP /* * This function is called when the CPU is coming up, with entry * CPUHP_RANDOM_PREPARE, which comes before CPUHP_WORKQUEUE_PREP. */ int __cold random_prepare_cpu(unsigned int cpu) { /* * When the cpu comes back online, immediately invalidate both * the per-cpu crng and all batches, so that we serve fresh * randomness. */ per_cpu_ptr(&crngs, cpu)->generation = ULONG_MAX; per_cpu_ptr(&batched_entropy_u8, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u16, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u32, cpu)->position = UINT_MAX; per_cpu_ptr(&batched_entropy_u64, cpu)->position = UINT_MAX; return 0; } #endif /********************************************************************** * * Entropy accumulation and extraction routines. * * Callers may add entropy via: * * static void mix_pool_bytes(const void *buf, size_t len) * * After which, if added entropy should be credited: * * static void credit_init_bits(size_t bits) * * Finally, extract entropy via: * * static void extract_entropy(void *buf, size_t len) * **********************************************************************/ enum { POOL_BITS = BLAKE2S_HASH_SIZE * 8, POOL_READY_BITS = POOL_BITS, /* When crng_init->CRNG_READY */ POOL_EARLY_BITS = POOL_READY_BITS / 2 /* When crng_init->CRNG_EARLY */ }; static struct { struct blake2s_state hash; spinlock_t lock; unsigned int init_bits; } input_pool = { .hash.h = { BLAKE2S_IV0 ^ (0x01010000 | BLAKE2S_HASH_SIZE), BLAKE2S_IV1, BLAKE2S_IV2, BLAKE2S_IV3, BLAKE2S_IV4, BLAKE2S_IV5, BLAKE2S_IV6, BLAKE2S_IV7 }, .hash.outlen = BLAKE2S_HASH_SIZE, .lock = __SPIN_LOCK_UNLOCKED(input_pool.lock), }; static void _mix_pool_bytes(const void *buf, size_t len) { blake2s_update(&input_pool.hash, buf, len); } /* * This function adds bytes into the input pool. It does not * update the initialization bit counter; the caller should call * credit_init_bits if this is appropriate. */ static void mix_pool_bytes(const void *buf, size_t len) { unsigned long flags; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(buf, len); spin_unlock_irqrestore(&input_pool.lock, flags); } /* * This is an HKDF-like construction for using the hashed collected entropy * as a PRF key, that's then expanded block-by-block. */ static void extract_entropy(void *buf, size_t len) { unsigned long flags; u8 seed[BLAKE2S_HASH_SIZE], next_key[BLAKE2S_HASH_SIZE]; struct { unsigned long rdseed[32 / sizeof(long)]; size_t counter; } block; size_t i, longs; for (i = 0; i < ARRAY_SIZE(block.rdseed);) { longs = arch_get_random_seed_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i); if (longs) { i += longs; continue; } longs = arch_get_random_longs(&block.rdseed[i], ARRAY_SIZE(block.rdseed) - i); if (longs) { i += longs; continue; } block.rdseed[i++] = random_get_entropy(); } spin_lock_irqsave(&input_pool.lock, flags); /* seed = HASHPRF(last_key, entropy_input) */ blake2s_final(&input_pool.hash, seed); /* next_key = HASHPRF(seed, RDSEED || 0) */ block.counter = 0; blake2s(next_key, (u8 *)&block, seed, sizeof(next_key), sizeof(block), sizeof(seed)); blake2s_init_key(&input_pool.hash, BLAKE2S_HASH_SIZE, next_key, sizeof(next_key)); spin_unlock_irqrestore(&input_pool.lock, flags); memzero_explicit(next_key, sizeof(next_key)); while (len) { i = min_t(size_t, len, BLAKE2S_HASH_SIZE); /* output = HASHPRF(seed, RDSEED || ++counter) */ ++block.counter; blake2s(buf, (u8 *)&block, seed, i, sizeof(block), sizeof(seed)); len -= i; buf += i; } memzero_explicit(seed, sizeof(seed)); memzero_explicit(&block, sizeof(block)); } #define credit_init_bits(bits) if (!crng_ready()) _credit_init_bits(bits) static void __cold _credit_init_bits(size_t bits) { static DECLARE_WORK(set_ready, crng_set_ready); unsigned int new, orig, add; unsigned long flags; int m; if (!bits) return; add = min_t(size_t, bits, POOL_BITS); orig = READ_ONCE(input_pool.init_bits); do { new = min_t(unsigned int, POOL_BITS, orig + add); } while (!try_cmpxchg(&input_pool.init_bits, &orig, new)); if (orig < POOL_READY_BITS && new >= POOL_READY_BITS) { crng_reseed(NULL); /* Sets crng_init to CRNG_READY under base_crng.lock. */ if (static_key_initialized && system_unbound_wq) queue_work(system_unbound_wq, &set_ready); atomic_notifier_call_chain(&random_ready_notifier, 0, NULL); #ifdef CONFIG_VDSO_GETRANDOM WRITE_ONCE(vdso_k_rng_data->is_ready, true); #endif wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); pr_notice("crng init done\n"); m = ratelimit_state_get_miss(&urandom_warning); if (m) pr_notice("%d urandom warning(s) missed due to ratelimiting\n", m); } else if (orig < POOL_EARLY_BITS && new >= POOL_EARLY_BITS) { spin_lock_irqsave(&base_crng.lock, flags); /* Check if crng_init is CRNG_EMPTY, to avoid race with crng_reseed(). */ if (crng_init == CRNG_EMPTY) { extract_entropy(base_crng.key, sizeof(base_crng.key)); crng_init = CRNG_EARLY; } spin_unlock_irqrestore(&base_crng.lock, flags); } } /********************************************************************** * * Entropy collection routines. * * The following exported functions are used for pushing entropy into * the above entropy accumulation routines: * * void add_device_randomness(const void *buf, size_t len); * void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after); * void add_bootloader_randomness(const void *buf, size_t len); * void add_vmfork_randomness(const void *unique_vm_id, size_t len); * void add_interrupt_randomness(int irq); * void add_input_randomness(unsigned int type, unsigned int code, unsigned int value); * void add_disk_randomness(struct gendisk *disk); * * add_device_randomness() adds data to the input pool that * is likely to differ between two devices (or possibly even per boot). * This would be things like MAC addresses or serial numbers, or the * read-out of the RTC. This does *not* credit any actual entropy to * the pool, but it initializes the pool to different values for devices * that might otherwise be identical and have very little entropy * available to them (particularly common in the embedded world). * * add_hwgenerator_randomness() is for true hardware RNGs, and will credit * entropy as specified by the caller. If the entropy pool is full it will * block until more entropy is needed. * * add_bootloader_randomness() is called by bootloader drivers, such as EFI * and device tree, and credits its input depending on whether or not the * command line option 'random.trust_bootloader'. * * add_vmfork_randomness() adds a unique (but not necessarily secret) ID * representing the current instance of a VM to the pool, without crediting, * and then force-reseeds the crng so that it takes effect immediately. * * add_interrupt_randomness() uses the interrupt timing as random * inputs to the entropy pool. Using the cycle counters and the irq source * as inputs, it feeds the input pool roughly once a second or after 64 * interrupts, crediting 1 bit of entropy for whichever comes first. * * add_input_randomness() uses the input layer interrupt timing, as well * as the event type information from the hardware. * * add_disk_randomness() uses what amounts to the seek time of block * layer request events, on a per-disk_devt basis, as input to the * entropy pool. Note that high-speed solid state drives with very low * seek times do not make for good sources of entropy, as their seek * times are usually fairly consistent. * * The last two routines try to estimate how many bits of entropy * to credit. They do this by keeping track of the first and second * order deltas of the event timings. * **********************************************************************/ static bool trust_cpu __initdata = true; static bool trust_bootloader __initdata = true; static int __init parse_trust_cpu(char *arg) { return kstrtobool(arg, &trust_cpu); } static int __init parse_trust_bootloader(char *arg) { return kstrtobool(arg, &trust_bootloader); } early_param("random.trust_cpu", parse_trust_cpu); early_param("random.trust_bootloader", parse_trust_bootloader); static int random_pm_notification(struct notifier_block *nb, unsigned long action, void *data) { unsigned long flags, entropy = random_get_entropy(); /* * Encode a representation of how long the system has been suspended, * in a way that is distinct from prior system suspends. */ ktime_t stamps[] = { ktime_get(), ktime_get_boottime(), ktime_get_real() }; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&action, sizeof(action)); _mix_pool_bytes(stamps, sizeof(stamps)); _mix_pool_bytes(&entropy, sizeof(entropy)); spin_unlock_irqrestore(&input_pool.lock, flags); if (crng_ready() && (action == PM_RESTORE_PREPARE || (action == PM_POST_SUSPEND && !IS_ENABLED(CONFIG_PM_AUTOSLEEP) && !IS_ENABLED(CONFIG_PM_USERSPACE_AUTOSLEEP)))) { crng_reseed(NULL); pr_notice("crng reseeded on system resumption\n"); } return 0; } static struct notifier_block pm_notifier = { .notifier_call = random_pm_notification }; /* * This is called extremely early, before time keeping functionality is * available, but arch randomness is. Interrupts are not yet enabled. */ void __init random_init_early(const char *command_line) { unsigned long entropy[BLAKE2S_BLOCK_SIZE / sizeof(long)]; size_t i, longs, arch_bits; #if defined(LATENT_ENTROPY_PLUGIN) static const u8 compiletime_seed[BLAKE2S_BLOCK_SIZE] __initconst __latent_entropy; _mix_pool_bytes(compiletime_seed, sizeof(compiletime_seed)); #endif for (i = 0, arch_bits = sizeof(entropy) * 8; i < ARRAY_SIZE(entropy);) { longs = arch_get_random_seed_longs(entropy, ARRAY_SIZE(entropy) - i); if (longs) { _mix_pool_bytes(entropy, sizeof(*entropy) * longs); i += longs; continue; } longs = arch_get_random_longs(entropy, ARRAY_SIZE(entropy) - i); if (longs) { _mix_pool_bytes(entropy, sizeof(*entropy) * longs); i += longs; continue; } arch_bits -= sizeof(*entropy) * 8; ++i; } _mix_pool_bytes(init_utsname(), sizeof(*(init_utsname()))); _mix_pool_bytes(command_line, strlen(command_line)); /* Reseed if already seeded by earlier phases. */ if (crng_ready()) crng_reseed(NULL); else if (trust_cpu) _credit_init_bits(arch_bits); } /* * This is called a little bit after the prior function, and now there is * access to timestamps counters. Interrupts are not yet enabled. */ void __init random_init(void) { unsigned long entropy = random_get_entropy(); ktime_t now = ktime_get_real(); _mix_pool_bytes(&now, sizeof(now)); _mix_pool_bytes(&entropy, sizeof(entropy)); add_latent_entropy(); /* * If we were initialized by the cpu or bootloader before jump labels * or workqueues are initialized, then we should enable the static * branch here, where it's guaranteed that these have been initialized. */ if (!static_branch_likely(&crng_is_ready) && crng_init >= CRNG_READY) crng_set_ready(NULL); /* Reseed if already seeded by earlier phases. */ if (crng_ready()) crng_reseed(NULL); WARN_ON(register_pm_notifier(&pm_notifier)); WARN(!entropy, "Missing cycle counter and fallback timer; RNG " "entropy collection will consequently suffer."); } /* * Add device- or boot-specific data to the input pool to help * initialize it. * * None of this adds any entropy; it is meant to avoid the problem of * the entropy pool having similar initial state across largely * identical devices. */ void add_device_randomness(const void *buf, size_t len) { unsigned long entropy = random_get_entropy(); unsigned long flags; spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&entropy, sizeof(entropy)); _mix_pool_bytes(buf, len); spin_unlock_irqrestore(&input_pool.lock, flags); } EXPORT_SYMBOL(add_device_randomness); /* * Interface for in-kernel drivers of true hardware RNGs. Those devices * may produce endless random bits, so this function will sleep for * some amount of time after, if the sleep_after parameter is true. */ void add_hwgenerator_randomness(const void *buf, size_t len, size_t entropy, bool sleep_after) { mix_pool_bytes(buf, len); credit_init_bits(entropy); /* * Throttle writing to once every reseed interval, unless we're not yet * initialized or no entropy is credited. */ if (sleep_after && !kthread_should_stop() && (crng_ready() || !entropy)) schedule_timeout_interruptible(crng_reseed_interval()); } EXPORT_SYMBOL_GPL(add_hwgenerator_randomness); /* * Handle random seed passed by bootloader, and credit it depending * on the command line option 'random.trust_bootloader'. */ void __init add_bootloader_randomness(const void *buf, size_t len) { mix_pool_bytes(buf, len); if (trust_bootloader) credit_init_bits(len * 8); } #if IS_ENABLED(CONFIG_VMGENID) static BLOCKING_NOTIFIER_HEAD(vmfork_chain); /* * Handle a new unique VM ID, which is unique, not secret, so we * don't credit it, but we do immediately force a reseed after so * that it's used by the crng posthaste. */ void __cold add_vmfork_randomness(const void *unique_vm_id, size_t len) { add_device_randomness(unique_vm_id, len); if (crng_ready()) { crng_reseed(NULL); pr_notice("crng reseeded due to virtual machine fork\n"); } blocking_notifier_call_chain(&vmfork_chain, 0, NULL); } #if IS_MODULE(CONFIG_VMGENID) EXPORT_SYMBOL_GPL(add_vmfork_randomness); #endif int __cold register_random_vmfork_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&vmfork_chain, nb); } EXPORT_SYMBOL_GPL(register_random_vmfork_notifier); int __cold unregister_random_vmfork_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&vmfork_chain, nb); } EXPORT_SYMBOL_GPL(unregister_random_vmfork_notifier); #endif struct fast_pool { unsigned long pool[4]; unsigned long last; unsigned int count; struct timer_list mix; }; static void mix_interrupt_randomness(struct timer_list *work); static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = { #ifdef CONFIG_64BIT #define FASTMIX_PERM SIPHASH_PERMUTATION .pool = { SIPHASH_CONST_0, SIPHASH_CONST_1, SIPHASH_CONST_2, SIPHASH_CONST_3 }, #else #define FASTMIX_PERM HSIPHASH_PERMUTATION .pool = { HSIPHASH_CONST_0, HSIPHASH_CONST_1, HSIPHASH_CONST_2, HSIPHASH_CONST_3 }, #endif .mix = __TIMER_INITIALIZER(mix_interrupt_randomness, 0) }; /* * This is [Half]SipHash-1-x, starting from an empty key. Because * the key is fixed, it assumes that its inputs are non-malicious, * and therefore this has no security on its own. s represents the * four-word SipHash state, while v represents a two-word input. */ static void fast_mix(unsigned long s[4], unsigned long v1, unsigned long v2) { s[3] ^= v1; FASTMIX_PERM(s[0], s[1], s[2], s[3]); s[0] ^= v1; s[3] ^= v2; FASTMIX_PERM(s[0], s[1], s[2], s[3]); s[0] ^= v2; } #ifdef CONFIG_SMP /* * This function is called when the CPU has just come online, with * entry CPUHP_AP_RANDOM_ONLINE, just after CPUHP_AP_WORKQUEUE_ONLINE. */ int __cold random_online_cpu(unsigned int cpu) { /* * During CPU shutdown and before CPU onlining, add_interrupt_ * randomness() may schedule mix_interrupt_randomness(), and * set the MIX_INFLIGHT flag. However, because the worker can * be scheduled on a different CPU during this period, that * flag will never be cleared. For that reason, we zero out * the flag here, which runs just after workqueues are onlined * for the CPU again. This also has the effect of setting the * irq randomness count to zero so that new accumulated irqs * are fresh. */ per_cpu_ptr(&irq_randomness, cpu)->count = 0; return 0; } #endif static void mix_interrupt_randomness(struct timer_list *work) { struct fast_pool *fast_pool = container_of(work, struct fast_pool, mix); /* * The size of the copied stack pool is explicitly 2 longs so that we * only ever ingest half of the siphash output each time, retaining * the other half as the next "key" that carries over. The entropy is * supposed to be sufficiently dispersed between bits so on average * we don't wind up "losing" some. */ unsigned long pool[2]; unsigned int count; /* Check to see if we're running on the wrong CPU due to hotplug. */ local_irq_disable(); if (fast_pool != this_cpu_ptr(&irq_randomness)) { local_irq_enable(); return; } /* * Copy the pool to the stack so that the mixer always has a * consistent view, before we reenable irqs again. */ memcpy(pool, fast_pool->pool, sizeof(pool)); count = fast_pool->count; fast_pool->count = 0; fast_pool->last = jiffies; local_irq_enable(); mix_pool_bytes(pool, sizeof(pool)); credit_init_bits(clamp_t(unsigned int, (count & U16_MAX) / 64, 1, sizeof(pool) * 8)); memzero_explicit(pool, sizeof(pool)); } void add_interrupt_randomness(int irq) { enum { MIX_INFLIGHT = 1U << 31 }; unsigned long entropy = random_get_entropy(); struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); struct pt_regs *regs = get_irq_regs(); unsigned int new_count; fast_mix(fast_pool->pool, entropy, (regs ? instruction_pointer(regs) : _RET_IP_) ^ swab(irq)); new_count = ++fast_pool->count; if (new_count & MIX_INFLIGHT) return; if (new_count < 1024 && !time_is_before_jiffies(fast_pool->last + HZ)) return; fast_pool->count |= MIX_INFLIGHT; if (!timer_pending(&fast_pool->mix)) { fast_pool->mix.expires = jiffies; add_timer_on(&fast_pool->mix, raw_smp_processor_id()); } } EXPORT_SYMBOL_GPL(add_interrupt_randomness); /* There is one of these per entropy source */ struct timer_rand_state { unsigned long last_time; long last_delta, last_delta2; }; /* * This function adds entropy to the entropy "pool" by using timing * delays. It uses the timer_rand_state structure to make an estimate * of how many bits of entropy this call has added to the pool. The * value "num" is also added to the pool; it should somehow describe * the type of event that just happened. */ static void add_timer_randomness(struct timer_rand_state *state, unsigned int num) { unsigned long entropy = random_get_entropy(), now = jiffies, flags; long delta, delta2, delta3; unsigned int bits; /* * If we're in a hard IRQ, add_interrupt_randomness() will be called * sometime after, so mix into the fast pool. */ if (in_hardirq()) { fast_mix(this_cpu_ptr(&irq_randomness)->pool, entropy, num); } else { spin_lock_irqsave(&input_pool.lock, flags); _mix_pool_bytes(&entropy, sizeof(entropy)); _mix_pool_bytes(&num, sizeof(num)); spin_unlock_irqrestore(&input_pool.lock, flags); } if (crng_ready()) return; /* * Calculate number of bits of randomness we probably added. * We take into account the first, second and third-order deltas * in order to make our estimate. */ delta = now - READ_ONCE(state->last_time); WRITE_ONCE(state->last_time, now); delta2 = delta - READ_ONCE(state->last_delta); WRITE_ONCE(state->last_delta, delta); delta3 = delta2 - READ_ONCE(state->last_delta2); WRITE_ONCE(state->last_delta2, delta2); if (delta < 0) delta = -delta; if (delta2 < 0) delta2 = -delta2; if (delta3 < 0) delta3 = -delta3; if (delta > delta2) delta = delta2; if (delta > delta3) delta = delta3; /* * delta is now minimum absolute delta. Round down by 1 bit * on general principles, and limit entropy estimate to 11 bits. */ bits = min(fls(delta >> 1), 11); /* * As mentioned above, if we're in a hard IRQ, add_interrupt_randomness() * will run after this, which uses a different crediting scheme of 1 bit * per every 64 interrupts. In order to let that function do accounting * close to the one in this function, we credit a full 64/64 bit per bit, * and then subtract one to account for the extra one added. */ if (in_hardirq()) this_cpu_ptr(&irq_randomness)->count += max(1u, bits * 64) - 1; else _credit_init_bits(bits); } void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) { static unsigned char last_value; static struct timer_rand_state input_timer_state = { INITIAL_JIFFIES }; /* Ignore autorepeat and the like. */ if (value == last_value) return; last_value = value; add_timer_randomness(&input_timer_state, (type << 4) ^ code ^ (code >> 4) ^ value); } EXPORT_SYMBOL_GPL(add_input_randomness); #ifdef CONFIG_BLOCK void add_disk_randomness(struct gendisk *disk) { if (!disk || !disk->random) return; /* First major is 1, so we get >= 0x200 here. */ add_timer_randomness(disk->random, 0x100 + disk_devt(disk)); } EXPORT_SYMBOL_GPL(add_disk_randomness); void __cold rand_initialize_disk(struct gendisk *disk) { struct timer_rand_state *state; /* * If kzalloc returns null, we just won't use that entropy * source. */ state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL); if (state) { state->last_time = INITIAL_JIFFIES; disk->random = state; } } #endif struct entropy_timer_state { unsigned long entropy; struct timer_list timer; atomic_t samples; unsigned int samples_per_bit; }; /* * Each time the timer fires, we expect that we got an unpredictable jump in * the cycle counter. Even if the timer is running on another CPU, the timer * activity will be touching the stack of the CPU that is generating entropy. * * Note that we don't re-arm the timer in the timer itself - we are happy to be * scheduled away, since that just makes the load more complex, but we do not * want the timer to keep ticking unless the entropy loop is running. * * So the re-arming always happens in the entropy loop itself. */ static void __cold entropy_timer(struct timer_list *timer) { struct entropy_timer_state *state = container_of(timer, struct entropy_timer_state, timer); unsigned long entropy = random_get_entropy(); mix_pool_bytes(&entropy, sizeof(entropy)); if (atomic_inc_return(&state->samples) % state->samples_per_bit == 0) credit_init_bits(1); } /* * If we have an actual cycle counter, see if we can generate enough entropy * with timing noise. */ static void __cold try_to_generate_entropy(void) { enum { NUM_TRIAL_SAMPLES = 8192, MAX_SAMPLES_PER_BIT = HZ / 15 }; u8 stack_bytes[sizeof(struct entropy_timer_state) + SMP_CACHE_BYTES - 1]; struct entropy_timer_state *stack = PTR_ALIGN((void *)stack_bytes, SMP_CACHE_BYTES); unsigned int i, num_different = 0; unsigned long last = random_get_entropy(); int cpu = -1; for (i = 0; i < NUM_TRIAL_SAMPLES - 1; ++i) { stack->entropy = random_get_entropy(); if (stack->entropy != last) ++num_different; last = stack->entropy; } stack->samples_per_bit = DIV_ROUND_UP(NUM_TRIAL_SAMPLES, num_different + 1); if (stack->samples_per_bit > MAX_SAMPLES_PER_BIT) return; atomic_set(&stack->samples, 0); timer_setup_on_stack(&stack->timer, entropy_timer, 0); while (!crng_ready() && !signal_pending(current)) { /* * Check !timer_pending() and then ensure that any previous callback has finished * executing by checking timer_delete_sync_try(), before queueing the next one. */ if (!timer_pending(&stack->timer) && timer_delete_sync_try(&stack->timer) >= 0) { struct cpumask timer_cpus; unsigned int num_cpus; /* * Preemption must be disabled here, both to read the current CPU number * and to avoid scheduling a timer on a dead CPU. */ preempt_disable(); /* Only schedule callbacks on timer CPUs that are online. */ cpumask_and(&timer_cpus, housekeeping_cpumask(HK_TYPE_TIMER), cpu_online_mask); num_cpus = cpumask_weight(&timer_cpus); /* In very bizarre case of misconfiguration, fallback to all online. */ if (unlikely(num_cpus == 0)) { timer_cpus = *cpu_online_mask; num_cpus = cpumask_weight(&timer_cpus); } /* Basic CPU round-robin, which avoids the current CPU. */ do { cpu = cpumask_next(cpu, &timer_cpus); if (cpu >= nr_cpu_ids) cpu = cpumask_first(&timer_cpus); } while (cpu == smp_processor_id() && num_cpus > 1); /* Expiring the timer at `jiffies` means it's the next tick. */ stack->timer.expires = jiffies; add_timer_on(&stack->timer, cpu); preempt_enable(); } mix_pool_bytes(&stack->entropy, sizeof(stack->entropy)); schedule(); stack->entropy = random_get_entropy(); } mix_pool_bytes(&stack->entropy, sizeof(stack->entropy)); timer_delete_sync(&stack->timer); timer_destroy_on_stack(&stack->timer); } /********************************************************************** * * Userspace reader/writer interfaces. * * getrandom(2) is the primary modern interface into the RNG and should * be used in preference to anything else. * * Reading from /dev/random has the same functionality as calling * getrandom(2) with flags=0. In earlier versions, however, it had * vastly different semantics and should therefore be avoided, to * prevent backwards compatibility issues. * * Reading from /dev/urandom has the same functionality as calling * getrandom(2) with flags=GRND_INSECURE. Because it does not block * waiting for the RNG to be ready, it should not be used. * * Writing to either /dev/random or /dev/urandom adds entropy to * the input pool but does not credit it. * * Polling on /dev/random indicates when the RNG is initialized, on * the read side, and when it wants new entropy, on the write side. * * Both /dev/random and /dev/urandom have the same set of ioctls for * adding entropy, getting the entropy count, zeroing the count, and * reseeding the crng. * **********************************************************************/ SYSCALL_DEFINE3(getrandom, char __user *, ubuf, size_t, len, unsigned int, flags) { struct iov_iter iter; int ret; if (flags & ~(GRND_NONBLOCK | GRND_RANDOM | GRND_INSECURE)) return -EINVAL; /* * Requesting insecure and blocking randomness at the same time makes * no sense. */ if ((flags & (GRND_INSECURE | GRND_RANDOM)) == (GRND_INSECURE | GRND_RANDOM)) return -EINVAL; if (!crng_ready() && !(flags & GRND_INSECURE)) { if (flags & GRND_NONBLOCK) return -EAGAIN; ret = wait_for_random_bytes(); if (unlikely(ret)) return ret; } ret = import_ubuf(ITER_DEST, ubuf, len, &iter); if (unlikely(ret)) return ret; return get_random_bytes_user(&iter); } static __poll_t random_poll(struct file *file, poll_table *wait) { poll_wait(file, &crng_init_wait, wait); return crng_ready() ? EPOLLIN | EPOLLRDNORM : EPOLLOUT | EPOLLWRNORM; } static ssize_t write_pool_user(struct iov_iter *iter) { u8 block[BLAKE2S_BLOCK_SIZE]; ssize_t ret = 0; size_t copied; if (unlikely(!iov_iter_count(iter))) return 0; for (;;) { copied = copy_from_iter(block, sizeof(block), iter); ret += copied; mix_pool_bytes(block, copied); if (!iov_iter_count(iter) || copied != sizeof(block)) break; BUILD_BUG_ON(PAGE_SIZE % sizeof(block) != 0); if (ret % PAGE_SIZE == 0) { if (signal_pending(current)) break; cond_resched(); } } memzero_explicit(block, sizeof(block)); return ret ? ret : -EFAULT; } static ssize_t random_write_iter(struct kiocb *kiocb, struct iov_iter *iter) { return write_pool_user(iter); } static ssize_t urandom_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { static int maxwarn = 10; /* * Opportunistically attempt to initialize the RNG on platforms that * have fast cycle counters, but don't (for now) require it to succeed. */ if (!crng_ready()) try_to_generate_entropy(); if (!crng_ready()) { if (!ratelimit_disable && maxwarn <= 0) ratelimit_state_inc_miss(&urandom_warning); else if (ratelimit_disable || __ratelimit(&urandom_warning)) { --maxwarn; pr_notice("%s: uninitialized urandom read (%zu bytes read)\n", current->comm, iov_iter_count(iter)); } } return get_random_bytes_user(iter); } static ssize_t random_read_iter(struct kiocb *kiocb, struct iov_iter *iter) { int ret; if (!crng_ready() && ((kiocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) || (kiocb->ki_filp->f_flags & O_NONBLOCK))) return -EAGAIN; ret = wait_for_random_bytes(); if (ret != 0) return ret; return get_random_bytes_user(iter); } static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) { int __user *p = (int __user *)arg; int ent_count; switch (cmd) { case RNDGETENTCNT: /* Inherently racy, no point locking. */ if (put_user(input_pool.init_bits, p)) return -EFAULT; return 0; case RNDADDTOENTCNT: if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(ent_count, p)) return -EFAULT; if (ent_count < 0) return -EINVAL; credit_init_bits(ent_count); return 0; case RNDADDENTROPY: { struct iov_iter iter; ssize_t ret; int len; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(ent_count, p++)) return -EFAULT; if (ent_count < 0) return -EINVAL; if (get_user(len, p++)) return -EFAULT; ret = import_ubuf(ITER_SOURCE, p, len, &iter); if (unlikely(ret)) return ret; ret = write_pool_user(&iter); if (unlikely(ret < 0)) return ret; /* Since we're crediting, enforce that it was all written into the pool. */ if (unlikely(ret != len)) return -EFAULT; credit_init_bits(ent_count); return 0; } case RNDZAPENTCNT: case RNDCLEARPOOL: /* No longer has any effect. */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 0; case RNDRESEEDCRNG: if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!crng_ready()) return -ENODATA; crng_reseed(NULL); return 0; default: return -EINVAL; } } static int random_fasync(int fd, struct file *filp, int on) { return fasync_helper(fd, filp, on, &fasync); } const struct file_operations random_fops = { .read_iter = random_read_iter, .write_iter = random_write_iter, .poll = random_poll, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; const struct file_operations urandom_fops = { .read_iter = urandom_read_iter, .write_iter = random_write_iter, .unlocked_ioctl = random_ioctl, .compat_ioctl = compat_ptr_ioctl, .fasync = random_fasync, .llseek = noop_llseek, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, }; /******************************************************************** * * Sysctl interface. * * These are partly unused legacy knobs with dummy values to not break * userspace and partly still useful things. They are usually accessible * in /proc/sys/kernel/random/ and are as follows: * * - boot_id - a UUID representing the current boot. * * - uuid - a random UUID, different each time the file is read. * * - poolsize - the number of bits of entropy that the input pool can * hold, tied to the POOL_BITS constant. * * - entropy_avail - the number of bits of entropy currently in the * input pool. Always <= poolsize. * * - write_wakeup_threshold - the amount of entropy in the input pool * below which write polls to /dev/random will unblock, requesting * more entropy, tied to the POOL_READY_BITS constant. It is writable * to avoid breaking old userspaces, but writing to it does not * change any behavior of the RNG. * * - urandom_min_reseed_secs - fixed to the value CRNG_RESEED_INTERVAL. * It is writable to avoid breaking old userspaces, but writing * to it does not change any behavior of the RNG. * ********************************************************************/ #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static int sysctl_random_min_urandom_seed = CRNG_RESEED_INTERVAL / HZ; static int sysctl_random_write_wakeup_bits = POOL_READY_BITS; static int sysctl_poolsize = POOL_BITS; static u8 sysctl_bootid[UUID_SIZE]; /* * This function is used to return both the bootid UUID, and random * UUID. The difference is in whether table->data is NULL; if it is, * then a new UUID is generated and returned to the user. */ static int proc_do_uuid(const struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { u8 tmp_uuid[UUID_SIZE], *uuid; char uuid_string[UUID_STRING_LEN + 1]; struct ctl_table fake_table = { .data = uuid_string, .maxlen = UUID_STRING_LEN }; if (write) return -EPERM; uuid = table->data; if (!uuid) { uuid = tmp_uuid; generate_random_uuid(uuid); } else { static DEFINE_SPINLOCK(bootid_spinlock); spin_lock(&bootid_spinlock); if (!uuid[8]) generate_random_uuid(uuid); spin_unlock(&bootid_spinlock); } snprintf(uuid_string, sizeof(uuid_string), "%pU", uuid); return proc_dostring(&fake_table, 0, buf, lenp, ppos); } /* The same as proc_dointvec, but writes don't change anything. */ static int proc_do_rointvec(const struct ctl_table *table, int write, void *buf, size_t *lenp, loff_t *ppos) { return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos); } static const struct ctl_table random_table[] = { { .procname = "poolsize", .data = &sysctl_poolsize, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, { .procname = "entropy_avail", .data = &input_pool.init_bits, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, { .procname = "write_wakeup_threshold", .data = &sysctl_random_write_wakeup_bits, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_rointvec, }, { .procname = "urandom_min_reseed_secs", .data = &sysctl_random_min_urandom_seed, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_rointvec, }, { .procname = "boot_id", .data = &sysctl_bootid, .mode = 0444, .proc_handler = proc_do_uuid, }, { .procname = "uuid", .mode = 0444, .proc_handler = proc_do_uuid, }, }; /* * random_init() is called before sysctl_init(), * so we cannot call register_sysctl_init() in random_init() */ static int __init random_sysctls_init(void) { register_sysctl_init("kernel/random", random_table); return 0; } device_initcall(random_sysctls_init); #endif |
| 12 12 12 12 12 9 10 9 10 10 10 10 10 10 10 10 10 12 12 12 12 12 12 10 10 12 10 12 12 12 12 11 12 12 12 12 12 12 12 12 6 6 6 57 6 57 57 57 57 57 31 57 57 55 32 25 32 25 126 125 126 126 126 126 126 126 125 125 125 100 25 125 126 126 126 98 125 126 125 306 306 306 306 306 306 306 305 305 306 306 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Implementation of the security services. * * Authors : Stephen Smalley, <stephen.smalley.work@gmail.com> * James Morris <jmorris@redhat.com> * * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * * Support for enhanced MLS infrastructure. * Support for context based audit filters. * * Updated: Frank Mayer <mayerf@tresys.com> and Karl MacMillan <kmacmillan@tresys.com> * * Added conditional policy language extensions * * Updated: Hewlett-Packard <paul@paul-moore.com> * * Added support for NetLabel * Added support for the policy capability bitmap * * Updated: Chad Sellers <csellers@tresys.com> * * Added validation of kernel classes and permissions * * Updated: KaiGai Kohei <kaigai@ak.jp.nec.com> * * Added support for bounds domain and audit messaged on masked permissions * * Updated: Guido Trentalancia <guido@trentalancia.com> * * Added support for runtime switching of the policy type * * Copyright (C) 2008, 2009 NEC Corporation * Copyright (C) 2006, 2007 Hewlett-Packard Development Company, L.P. * Copyright (C) 2004-2006 Trusted Computer Solutions, Inc. * Copyright (C) 2003 - 2004, 2006 Tresys Technology, LLC * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/sched.h> #include <linux/audit.h> #include <linux/parser.h> #include <linux/vmalloc.h> #include <linux/lsm_hooks.h> #include <net/netlabel.h> #include "flask.h" #include "avc.h" #include "avc_ss.h" #include "security.h" #include "context.h" #include "policydb.h" #include "sidtab.h" #include "services.h" #include "conditional.h" #include "mls.h" #include "objsec.h" #include "netlabel.h" #include "xfrm.h" #include "ebitmap.h" #include "audit.h" #include "policycap_names.h" #include "ima.h" struct selinux_policy_convert_data { struct convert_context_args args; struct sidtab_convert_params sidtab_params; }; /* Forward declaration. */ static int context_struct_to_string(struct policydb *policydb, struct context *context, char **scontext, u32 *scontext_len); static int sidtab_entry_to_string(struct policydb *policydb, struct sidtab *sidtab, struct sidtab_entry *entry, char **scontext, u32 *scontext_len); static void context_struct_compute_av(struct policydb *policydb, struct context *scontext, struct context *tcontext, u16 tclass, struct av_decision *avd, struct extended_perms *xperms); static int selinux_set_mapping(struct policydb *pol, const struct security_class_mapping *map, struct selinux_map *out_map) { u16 i, j; bool print_unknown_handle = false; /* Find number of classes in the input mapping */ if (!map) return -EINVAL; i = 0; while (map[i].name) i++; /* Allocate space for the class records, plus one for class zero */ out_map->mapping = kcalloc(++i, sizeof(*out_map->mapping), GFP_ATOMIC); if (!out_map->mapping) return -ENOMEM; /* Store the raw class and permission values */ j = 0; while (map[j].name) { const struct security_class_mapping *p_in = map + (j++); struct selinux_mapping *p_out = out_map->mapping + j; u16 k; /* An empty class string skips ahead */ if (!strcmp(p_in->name, "")) { p_out->num_perms = 0; continue; } p_out->value = string_to_security_class(pol, p_in->name); if (!p_out->value) { pr_info("SELinux: Class %s not defined in policy.\n", p_in->name); if (pol->reject_unknown) goto err; p_out->num_perms = 0; print_unknown_handle = true; continue; } k = 0; while (p_in->perms[k]) { /* An empty permission string skips ahead */ if (!*p_in->perms[k]) { k++; continue; } p_out->perms[k] = string_to_av_perm(pol, p_out->value, p_in->perms[k]); if (!p_out->perms[k]) { pr_info("SELinux: Permission %s in class %s not defined in policy.\n", p_in->perms[k], p_in->name); if (pol->reject_unknown) goto err; print_unknown_handle = true; } k++; } p_out->num_perms = k; } if (print_unknown_handle) pr_info("SELinux: the above unknown classes and permissions will be %s\n", pol->allow_unknown ? "allowed" : "denied"); out_map->size = i; return 0; err: kfree(out_map->mapping); out_map->mapping = NULL; return -EINVAL; } /* * Get real, policy values from mapped values */ static u16 unmap_class(struct selinux_map *map, u16 tclass) { if (tclass < map->size) return map->mapping[tclass].value; return tclass; } /* * Get kernel value for class from its policy value */ static u16 map_class(struct selinux_map *map, u16 pol_value) { u16 i; for (i = 1; i < map->size; i++) { if (map->mapping[i].value == pol_value) return i; } return SECCLASS_NULL; } static void map_decision(struct selinux_map *map, u16 tclass, struct av_decision *avd, int allow_unknown) { if (tclass < map->size) { struct selinux_mapping *mapping = &map->mapping[tclass]; unsigned int i, n = mapping->num_perms; u32 result; for (i = 0, result = 0; i < n; i++) { if (avd->allowed & mapping->perms[i]) result |= (u32)1<<i; if (allow_unknown && !mapping->perms[i]) result |= (u32)1<<i; } avd->allowed = result; for (i = 0, result = 0; i < n; i++) if (avd->auditallow & mapping->perms[i]) result |= (u32)1<<i; avd->auditallow = result; for (i = 0, result = 0; i < n; i++) { if (avd->auditdeny & mapping->perms[i]) result |= (u32)1<<i; if (!allow_unknown && !mapping->perms[i]) result |= (u32)1<<i; } /* * In case the kernel has a bug and requests a permission * between num_perms and the maximum permission number, we * should audit that denial */ for (; i < (sizeof(u32)*8); i++) result |= (u32)1<<i; avd->auditdeny = result; } } int security_mls_enabled(void) { int mls_enabled; struct selinux_policy *policy; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); mls_enabled = policy->policydb.mls_enabled; rcu_read_unlock(); return mls_enabled; } /* * Return the boolean value of a constraint expression * when it is applied to the specified source and target * security contexts. * * xcontext is a special beast... It is used by the validatetrans rules * only. For these rules, scontext is the context before the transition, * tcontext is the context after the transition, and xcontext is the context * of the process performing the transition. All other callers of * constraint_expr_eval should pass in NULL for xcontext. */ static int constraint_expr_eval(struct policydb *policydb, struct context *scontext, struct context *tcontext, struct context *xcontext, struct constraint_expr *cexpr) { u32 val1, val2; struct context *c; struct role_datum *r1, *r2; struct mls_level *l1, *l2; struct constraint_expr *e; int s[CEXPR_MAXDEPTH]; int sp = -1; for (e = cexpr; e; e = e->next) { switch (e->expr_type) { case CEXPR_NOT: BUG_ON(sp < 0); s[sp] = !s[sp]; break; case CEXPR_AND: BUG_ON(sp < 1); sp--; s[sp] &= s[sp + 1]; break; case CEXPR_OR: BUG_ON(sp < 1); sp--; s[sp] |= s[sp + 1]; break; case CEXPR_ATTR: if (sp == (CEXPR_MAXDEPTH - 1)) return 0; switch (e->attr) { case CEXPR_USER: val1 = scontext->user; val2 = tcontext->user; break; case CEXPR_TYPE: val1 = scontext->type; val2 = tcontext->type; break; case CEXPR_ROLE: val1 = scontext->role; val2 = tcontext->role; r1 = policydb->role_val_to_struct[val1 - 1]; r2 = policydb->role_val_to_struct[val2 - 1]; switch (e->op) { case CEXPR_DOM: s[++sp] = ebitmap_get_bit(&r1->dominates, val2 - 1); continue; case CEXPR_DOMBY: s[++sp] = ebitmap_get_bit(&r2->dominates, val1 - 1); continue; case CEXPR_INCOMP: s[++sp] = (!ebitmap_get_bit(&r1->dominates, val2 - 1) && !ebitmap_get_bit(&r2->dominates, val1 - 1)); continue; default: break; } break; case CEXPR_L1L2: l1 = &(scontext->range.level[0]); l2 = &(tcontext->range.level[0]); goto mls_ops; case CEXPR_L1H2: l1 = &(scontext->range.level[0]); l2 = &(tcontext->range.level[1]); goto mls_ops; case CEXPR_H1L2: l1 = &(scontext->range.level[1]); l2 = &(tcontext->range.level[0]); goto mls_ops; case CEXPR_H1H2: l1 = &(scontext->range.level[1]); l2 = &(tcontext->range.level[1]); goto mls_ops; case CEXPR_L1H1: l1 = &(scontext->range.level[0]); l2 = &(scontext->range.level[1]); goto mls_ops; case CEXPR_L2H2: l1 = &(tcontext->range.level[0]); l2 = &(tcontext->range.level[1]); goto mls_ops; mls_ops: switch (e->op) { case CEXPR_EQ: s[++sp] = mls_level_eq(l1, l2); continue; case CEXPR_NEQ: s[++sp] = !mls_level_eq(l1, l2); continue; case CEXPR_DOM: s[++sp] = mls_level_dom(l1, l2); continue; case CEXPR_DOMBY: s[++sp] = mls_level_dom(l2, l1); continue; case CEXPR_INCOMP: s[++sp] = mls_level_incomp(l2, l1); continue; default: BUG(); return 0; } break; default: BUG(); return 0; } switch (e->op) { case CEXPR_EQ: s[++sp] = (val1 == val2); break; case CEXPR_NEQ: s[++sp] = (val1 != val2); break; default: BUG(); return 0; } break; case CEXPR_NAMES: if (sp == (CEXPR_MAXDEPTH-1)) return 0; c = scontext; if (e->attr & CEXPR_TARGET) c = tcontext; else if (e->attr & CEXPR_XTARGET) { c = xcontext; if (!c) { BUG(); return 0; } } if (e->attr & CEXPR_USER) val1 = c->user; else if (e->attr & CEXPR_ROLE) val1 = c->role; else if (e->attr & CEXPR_TYPE) val1 = c->type; else { BUG(); return 0; } switch (e->op) { case CEXPR_EQ: s[++sp] = ebitmap_get_bit(&e->names, val1 - 1); break; case CEXPR_NEQ: s[++sp] = !ebitmap_get_bit(&e->names, val1 - 1); break; default: BUG(); return 0; } break; default: BUG(); return 0; } } BUG_ON(sp != 0); return s[0]; } /* * security_dump_masked_av - dumps masked permissions during * security_compute_av due to RBAC, MLS/Constraint and Type bounds. */ static int dump_masked_av_helper(void *k, void *d, void *args) { struct perm_datum *pdatum = d; char **permission_names = args; BUG_ON(pdatum->value < 1 || pdatum->value > 32); permission_names[pdatum->value - 1] = (char *)k; return 0; } static void security_dump_masked_av(struct policydb *policydb, struct context *scontext, struct context *tcontext, u16 tclass, u32 permissions, const char *reason) { struct common_datum *common_dat; struct class_datum *tclass_dat; struct audit_buffer *ab; char *tclass_name; char *scontext_name = NULL; char *tcontext_name = NULL; char *permission_names[32]; int index; u32 length; bool need_comma = false; if (!permissions) return; tclass_name = sym_name(policydb, SYM_CLASSES, tclass - 1); tclass_dat = policydb->class_val_to_struct[tclass - 1]; common_dat = tclass_dat->comdatum; /* init permission_names */ if (common_dat && hashtab_map(&common_dat->permissions.table, dump_masked_av_helper, permission_names) < 0) goto out; if (hashtab_map(&tclass_dat->permissions.table, dump_masked_av_helper, permission_names) < 0) goto out; /* get scontext/tcontext in text form */ if (context_struct_to_string(policydb, scontext, &scontext_name, &length) < 0) goto out; if (context_struct_to_string(policydb, tcontext, &tcontext_name, &length) < 0) goto out; /* audit a message */ ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) goto out; audit_log_format(ab, "op=security_compute_av reason=%s " "scontext=%s tcontext=%s tclass=%s perms=", reason, scontext_name, tcontext_name, tclass_name); for (index = 0; index < 32; index++) { u32 mask = (1 << index); if ((mask & permissions) == 0) continue; audit_log_format(ab, "%s%s", need_comma ? "," : "", permission_names[index] ? permission_names[index] : "????"); need_comma = true; } audit_log_end(ab); out: /* release scontext/tcontext */ kfree(tcontext_name); kfree(scontext_name); } /* * security_boundary_permission - drops violated permissions * on boundary constraint. */ static void type_attribute_bounds_av(struct policydb *policydb, struct context *scontext, struct context *tcontext, u16 tclass, struct av_decision *avd) { struct context lo_scontext; struct context lo_tcontext, *tcontextp = tcontext; struct av_decision lo_avd; struct type_datum *source; struct type_datum *target; u32 masked = 0; source = policydb->type_val_to_struct[scontext->type - 1]; BUG_ON(!source); if (!source->bounds) return; target = policydb->type_val_to_struct[tcontext->type - 1]; BUG_ON(!target); memset(&lo_avd, 0, sizeof(lo_avd)); memcpy(&lo_scontext, scontext, sizeof(lo_scontext)); lo_scontext.type = source->bounds; if (target->bounds) { memcpy(&lo_tcontext, tcontext, sizeof(lo_tcontext)); lo_tcontext.type = target->bounds; tcontextp = &lo_tcontext; } context_struct_compute_av(policydb, &lo_scontext, tcontextp, tclass, &lo_avd, NULL); masked = ~lo_avd.allowed & avd->allowed; if (likely(!masked)) return; /* no masked permission */ /* mask violated permissions */ avd->allowed &= ~masked; /* audit masked permissions */ security_dump_masked_av(policydb, scontext, tcontext, tclass, masked, "bounds"); } /* * Flag which drivers have permissions and which base permissions are covered. */ void services_compute_xperms_drivers( struct extended_perms *xperms, struct avtab_node *node) { unsigned int i; switch (node->datum.u.xperms->specified) { case AVTAB_XPERMS_IOCTLDRIVER: xperms->base_perms |= AVC_EXT_IOCTL; /* if one or more driver has all permissions allowed */ for (i = 0; i < ARRAY_SIZE(xperms->drivers.p); i++) xperms->drivers.p[i] |= node->datum.u.xperms->perms.p[i]; break; case AVTAB_XPERMS_IOCTLFUNCTION: xperms->base_perms |= AVC_EXT_IOCTL; /* if allowing permissions within a driver */ security_xperm_set(xperms->drivers.p, node->datum.u.xperms->driver); break; case AVTAB_XPERMS_NLMSG: xperms->base_perms |= AVC_EXT_NLMSG; /* if allowing permissions within a driver */ security_xperm_set(xperms->drivers.p, node->datum.u.xperms->driver); break; } xperms->len = 1; } /* * Compute access vectors and extended permissions based on a context * structure pair for the permissions in a particular class. */ static void context_struct_compute_av(struct policydb *policydb, struct context *scontext, struct context *tcontext, u16 tclass, struct av_decision *avd, struct extended_perms *xperms) { struct constraint_node *constraint; struct role_allow *ra; struct avtab_key avkey; struct avtab_node *node; struct class_datum *tclass_datum; struct ebitmap *sattr, *tattr; struct ebitmap_node *snode, *tnode; unsigned int i, j; avd->allowed = 0; avd->auditallow = 0; avd->auditdeny = 0xffffffff; if (xperms) { memset(xperms, 0, sizeof(*xperms)); } if (unlikely(!tclass || tclass > policydb->p_classes.nprim)) { pr_warn_ratelimited("SELinux: Invalid class %u\n", tclass); return; } tclass_datum = policydb->class_val_to_struct[tclass - 1]; /* * If a specific type enforcement rule was defined for * this permission check, then use it. */ avkey.target_class = tclass; avkey.specified = AVTAB_AV | AVTAB_XPERMS; sattr = &policydb->type_attr_map_array[scontext->type - 1]; tattr = &policydb->type_attr_map_array[tcontext->type - 1]; ebitmap_for_each_positive_bit(sattr, snode, i) { ebitmap_for_each_positive_bit(tattr, tnode, j) { avkey.source_type = i + 1; avkey.target_type = j + 1; for (node = avtab_search_node(&policydb->te_avtab, &avkey); node; node = avtab_search_node_next(node, avkey.specified)) { if (node->key.specified == AVTAB_ALLOWED) avd->allowed |= node->datum.u.data; else if (node->key.specified == AVTAB_AUDITALLOW) avd->auditallow |= node->datum.u.data; else if (node->key.specified == AVTAB_AUDITDENY) avd->auditdeny &= node->datum.u.data; else if (xperms && (node->key.specified & AVTAB_XPERMS)) services_compute_xperms_drivers(xperms, node); } /* Check conditional av table for additional permissions */ cond_compute_av(&policydb->te_cond_avtab, &avkey, avd, xperms); } } /* * Remove any permissions prohibited by a constraint (this includes * the MLS policy). */ constraint = tclass_datum->constraints; while (constraint) { if ((constraint->permissions & (avd->allowed)) && !constraint_expr_eval(policydb, scontext, tcontext, NULL, constraint->expr)) { avd->allowed &= ~(constraint->permissions); } constraint = constraint->next; } /* * If checking process transition permission and the * role is changing, then check the (current_role, new_role) * pair. */ if (tclass == policydb->process_class && (avd->allowed & policydb->process_trans_perms) && scontext->role != tcontext->role) { for (ra = policydb->role_allow; ra; ra = ra->next) { if (scontext->role == ra->role && tcontext->role == ra->new_role) break; } if (!ra) avd->allowed &= ~policydb->process_trans_perms; } /* * If the given source and target types have boundary * constraint, lazy checks have to mask any violated * permission and notice it to userspace via audit. */ type_attribute_bounds_av(policydb, scontext, tcontext, tclass, avd); } static int security_validtrans_handle_fail(struct selinux_policy *policy, struct sidtab_entry *oentry, struct sidtab_entry *nentry, struct sidtab_entry *tentry, u16 tclass) { struct policydb *p = &policy->policydb; struct sidtab *sidtab = policy->sidtab; char *o = NULL, *n = NULL, *t = NULL; u32 olen, nlen, tlen; if (sidtab_entry_to_string(p, sidtab, oentry, &o, &olen)) goto out; if (sidtab_entry_to_string(p, sidtab, nentry, &n, &nlen)) goto out; if (sidtab_entry_to_string(p, sidtab, tentry, &t, &tlen)) goto out; audit_log(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR, "op=security_validate_transition seresult=denied" " oldcontext=%s newcontext=%s taskcontext=%s tclass=%s", o, n, t, sym_name(p, SYM_CLASSES, tclass-1)); out: kfree(o); kfree(n); kfree(t); if (!enforcing_enabled()) return 0; return -EPERM; } static int security_compute_validatetrans(u32 oldsid, u32 newsid, u32 tasksid, u16 orig_tclass, bool user) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct sidtab_entry *oentry; struct sidtab_entry *nentry; struct sidtab_entry *tentry; struct class_datum *tclass_datum; struct constraint_node *constraint; u16 tclass; int rc = 0; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; if (!user) tclass = unmap_class(&policy->map, orig_tclass); else tclass = orig_tclass; if (!tclass || tclass > policydb->p_classes.nprim) { rc = -EINVAL; goto out; } tclass_datum = policydb->class_val_to_struct[tclass - 1]; oentry = sidtab_search_entry(sidtab, oldsid); if (!oentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, oldsid); rc = -EINVAL; goto out; } nentry = sidtab_search_entry(sidtab, newsid); if (!nentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, newsid); rc = -EINVAL; goto out; } tentry = sidtab_search_entry(sidtab, tasksid); if (!tentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tasksid); rc = -EINVAL; goto out; } constraint = tclass_datum->validatetrans; while (constraint) { if (!constraint_expr_eval(policydb, &oentry->context, &nentry->context, &tentry->context, constraint->expr)) { if (user) rc = -EPERM; else rc = security_validtrans_handle_fail(policy, oentry, nentry, tentry, tclass); goto out; } constraint = constraint->next; } out: rcu_read_unlock(); return rc; } int security_validate_transition_user(u32 oldsid, u32 newsid, u32 tasksid, u16 tclass) { return security_compute_validatetrans(oldsid, newsid, tasksid, tclass, true); } int security_validate_transition(u32 oldsid, u32 newsid, u32 tasksid, u16 orig_tclass) { return security_compute_validatetrans(oldsid, newsid, tasksid, orig_tclass, false); } /* * security_bounded_transition - check whether the given * transition is directed to bounded, or not. * It returns 0, if @newsid is bounded by @oldsid. * Otherwise, it returns error code. * * @oldsid : current security identifier * @newsid : destinated security identifier */ int security_bounded_transition(u32 old_sid, u32 new_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct sidtab_entry *old_entry, *new_entry; struct type_datum *type; u32 index; int rc; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; rc = -EINVAL; old_entry = sidtab_search_entry(sidtab, old_sid); if (!old_entry) { pr_err("SELinux: %s: unrecognized SID %u\n", __func__, old_sid); goto out; } rc = -EINVAL; new_entry = sidtab_search_entry(sidtab, new_sid); if (!new_entry) { pr_err("SELinux: %s: unrecognized SID %u\n", __func__, new_sid); goto out; } rc = 0; /* type/domain unchanged */ if (old_entry->context.type == new_entry->context.type) goto out; index = new_entry->context.type; while (true) { type = policydb->type_val_to_struct[index - 1]; BUG_ON(!type); /* not bounded anymore */ rc = -EPERM; if (!type->bounds) break; /* @newsid is bounded by @oldsid */ rc = 0; if (type->bounds == old_entry->context.type) break; index = type->bounds; } if (rc) { char *old_name = NULL; char *new_name = NULL; u32 length; if (!sidtab_entry_to_string(policydb, sidtab, old_entry, &old_name, &length) && !sidtab_entry_to_string(policydb, sidtab, new_entry, &new_name, &length)) { audit_log(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR, "op=security_bounded_transition " "seresult=denied " "oldcontext=%s newcontext=%s", old_name, new_name); } kfree(new_name); kfree(old_name); } out: rcu_read_unlock(); return rc; } static void avd_init(struct selinux_policy *policy, struct av_decision *avd) { avd->allowed = 0; avd->auditallow = 0; avd->auditdeny = 0xffffffff; if (policy) avd->seqno = policy->latest_granting; else avd->seqno = 0; avd->flags = 0; } static void update_xperms_extended_data(u8 specified, const struct extended_perms_data *from, struct extended_perms_data *xp_data) { unsigned int i; switch (specified) { case AVTAB_XPERMS_IOCTLDRIVER: memset(xp_data->p, 0xff, sizeof(xp_data->p)); break; case AVTAB_XPERMS_IOCTLFUNCTION: case AVTAB_XPERMS_NLMSG: for (i = 0; i < ARRAY_SIZE(xp_data->p); i++) xp_data->p[i] |= from->p[i]; break; } } void services_compute_xperms_decision(struct extended_perms_decision *xpermd, struct avtab_node *node) { u16 specified; switch (node->datum.u.xperms->specified) { case AVTAB_XPERMS_IOCTLFUNCTION: if (xpermd->base_perm != AVC_EXT_IOCTL || xpermd->driver != node->datum.u.xperms->driver) return; break; case AVTAB_XPERMS_IOCTLDRIVER: if (xpermd->base_perm != AVC_EXT_IOCTL || !security_xperm_test(node->datum.u.xperms->perms.p, xpermd->driver)) return; break; case AVTAB_XPERMS_NLMSG: if (xpermd->base_perm != AVC_EXT_NLMSG || xpermd->driver != node->datum.u.xperms->driver) return; break; default: pr_warn_once( "SELinux: unknown extended permission (%u) will be ignored\n", node->datum.u.xperms->specified); return; } specified = node->key.specified & ~(AVTAB_ENABLED | AVTAB_ENABLED_OLD); if (specified == AVTAB_XPERMS_ALLOWED) { xpermd->used |= XPERMS_ALLOWED; update_xperms_extended_data(node->datum.u.xperms->specified, &node->datum.u.xperms->perms, xpermd->allowed); } else if (specified == AVTAB_XPERMS_AUDITALLOW) { xpermd->used |= XPERMS_AUDITALLOW; update_xperms_extended_data(node->datum.u.xperms->specified, &node->datum.u.xperms->perms, xpermd->auditallow); } else if (specified == AVTAB_XPERMS_DONTAUDIT) { xpermd->used |= XPERMS_DONTAUDIT; update_xperms_extended_data(node->datum.u.xperms->specified, &node->datum.u.xperms->perms, xpermd->dontaudit); } else { pr_warn_once("SELinux: unknown specified key (%u)\n", node->key.specified); } } void security_compute_xperms_decision(u32 ssid, u32 tsid, u16 orig_tclass, u8 driver, u8 base_perm, struct extended_perms_decision *xpermd) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; u16 tclass; struct context *scontext, *tcontext; struct avtab_key avkey; struct avtab_node *node; struct ebitmap *sattr, *tattr; struct ebitmap_node *snode, *tnode; unsigned int i, j; xpermd->base_perm = base_perm; xpermd->driver = driver; xpermd->used = 0; memset(xpermd->allowed->p, 0, sizeof(xpermd->allowed->p)); memset(xpermd->auditallow->p, 0, sizeof(xpermd->auditallow->p)); memset(xpermd->dontaudit->p, 0, sizeof(xpermd->dontaudit->p)); rcu_read_lock(); if (!selinux_initialized()) goto allow; policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; scontext = sidtab_search(sidtab, ssid); if (!scontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, ssid); goto out; } tcontext = sidtab_search(sidtab, tsid); if (!tcontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tsid); goto out; } tclass = unmap_class(&policy->map, orig_tclass); if (unlikely(orig_tclass && !tclass)) { if (policydb->allow_unknown) goto allow; goto out; } if (unlikely(!tclass || tclass > policydb->p_classes.nprim)) { pr_warn_ratelimited("SELinux: Invalid class %hu\n", tclass); goto out; } avkey.target_class = tclass; avkey.specified = AVTAB_XPERMS; sattr = &policydb->type_attr_map_array[scontext->type - 1]; tattr = &policydb->type_attr_map_array[tcontext->type - 1]; ebitmap_for_each_positive_bit(sattr, snode, i) { ebitmap_for_each_positive_bit(tattr, tnode, j) { avkey.source_type = i + 1; avkey.target_type = j + 1; for (node = avtab_search_node(&policydb->te_avtab, &avkey); node; node = avtab_search_node_next(node, avkey.specified)) services_compute_xperms_decision(xpermd, node); cond_compute_xperms(&policydb->te_cond_avtab, &avkey, xpermd); } } out: rcu_read_unlock(); return; allow: memset(xpermd->allowed->p, 0xff, sizeof(xpermd->allowed->p)); goto out; } /** * security_compute_av - Compute access vector decisions. * @ssid: source security identifier * @tsid: target security identifier * @orig_tclass: target security class * @avd: access vector decisions * @xperms: extended permissions * * Compute a set of access vector decisions based on the * SID pair (@ssid, @tsid) for the permissions in @tclass. */ void security_compute_av(u32 ssid, u32 tsid, u16 orig_tclass, struct av_decision *avd, struct extended_perms *xperms) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; u16 tclass; struct context *scontext = NULL, *tcontext = NULL; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); avd_init(policy, avd); xperms->len = 0; if (!selinux_initialized()) goto allow; policydb = &policy->policydb; sidtab = policy->sidtab; scontext = sidtab_search(sidtab, ssid); if (!scontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, ssid); goto out; } /* permissive domain? */ if (ebitmap_get_bit(&policydb->permissive_map, scontext->type)) avd->flags |= AVD_FLAGS_PERMISSIVE; /* neveraudit domain? */ if (ebitmap_get_bit(&policydb->neveraudit_map, scontext->type)) avd->flags |= AVD_FLAGS_NEVERAUDIT; /* both permissive and neveraudit => allow */ if (avd->flags == (AVD_FLAGS_PERMISSIVE|AVD_FLAGS_NEVERAUDIT)) goto allow; tcontext = sidtab_search(sidtab, tsid); if (!tcontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tsid); goto out; } tclass = unmap_class(&policy->map, orig_tclass); if (unlikely(orig_tclass && !tclass)) { if (policydb->allow_unknown) goto allow; goto out; } context_struct_compute_av(policydb, scontext, tcontext, tclass, avd, xperms); map_decision(&policy->map, orig_tclass, avd, policydb->allow_unknown); out: rcu_read_unlock(); if (avd->flags & AVD_FLAGS_NEVERAUDIT) avd->auditallow = avd->auditdeny = 0; return; allow: avd->allowed = 0xffffffff; goto out; } void security_compute_av_user(u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct context *scontext = NULL, *tcontext = NULL; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); avd_init(policy, avd); if (!selinux_initialized()) goto allow; policydb = &policy->policydb; sidtab = policy->sidtab; scontext = sidtab_search(sidtab, ssid); if (!scontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, ssid); goto out; } /* permissive domain? */ if (ebitmap_get_bit(&policydb->permissive_map, scontext->type)) avd->flags |= AVD_FLAGS_PERMISSIVE; /* neveraudit domain? */ if (ebitmap_get_bit(&policydb->neveraudit_map, scontext->type)) avd->flags |= AVD_FLAGS_NEVERAUDIT; /* both permissive and neveraudit => allow */ if (avd->flags == (AVD_FLAGS_PERMISSIVE|AVD_FLAGS_NEVERAUDIT)) goto allow; tcontext = sidtab_search(sidtab, tsid); if (!tcontext) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tsid); goto out; } if (unlikely(!tclass)) { if (policydb->allow_unknown) goto allow; goto out; } context_struct_compute_av(policydb, scontext, tcontext, tclass, avd, NULL); out: rcu_read_unlock(); if (avd->flags & AVD_FLAGS_NEVERAUDIT) avd->auditallow = avd->auditdeny = 0; return; allow: avd->allowed = 0xffffffff; goto out; } /* * Write the security context string representation of * the context structure `context' into a dynamically * allocated string of the correct size. Set `*scontext' * to point to this string and set `*scontext_len' to * the length of the string. */ static int context_struct_to_string(struct policydb *p, struct context *context, char **scontext, u32 *scontext_len) { char *scontextp; if (scontext) *scontext = NULL; *scontext_len = 0; if (context->len) { *scontext_len = context->len; if (scontext) { *scontext = kstrdup(context->str, GFP_ATOMIC); if (!(*scontext)) return -ENOMEM; } return 0; } /* Compute the size of the context. */ *scontext_len += strlen(sym_name(p, SYM_USERS, context->user - 1)) + 1; *scontext_len += strlen(sym_name(p, SYM_ROLES, context->role - 1)) + 1; *scontext_len += strlen(sym_name(p, SYM_TYPES, context->type - 1)) + 1; *scontext_len += mls_compute_context_len(p, context); if (!scontext) return 0; /* Allocate space for the context; caller must free this space. */ scontextp = kmalloc(*scontext_len, GFP_ATOMIC); if (!scontextp) return -ENOMEM; *scontext = scontextp; /* * Copy the user name, role name and type name into the context. */ scontextp += sprintf(scontextp, "%s:%s:%s", sym_name(p, SYM_USERS, context->user - 1), sym_name(p, SYM_ROLES, context->role - 1), sym_name(p, SYM_TYPES, context->type - 1)); mls_sid_to_context(p, context, &scontextp); *scontextp = 0; return 0; } static int sidtab_entry_to_string(struct policydb *p, struct sidtab *sidtab, struct sidtab_entry *entry, char **scontext, u32 *scontext_len) { int rc = sidtab_sid2str_get(sidtab, entry, scontext, scontext_len); if (rc != -ENOENT) return rc; rc = context_struct_to_string(p, &entry->context, scontext, scontext_len); if (!rc && scontext) sidtab_sid2str_put(sidtab, entry, *scontext, *scontext_len); return rc; } #include "initial_sid_to_string.h" int security_sidtab_hash_stats(char *page) { struct selinux_policy *policy; int rc; if (!selinux_initialized()) { pr_err("SELinux: %s: called before initial load_policy\n", __func__); return -EINVAL; } rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); rc = sidtab_hash_stats(policy->sidtab, page); rcu_read_unlock(); return rc; } const char *security_get_initial_sid_context(u32 sid) { if (unlikely(sid > SECINITSID_NUM)) return NULL; return initial_sid_to_string[sid]; } static int security_sid_to_context_core(u32 sid, char **scontext, u32 *scontext_len, int force, int only_invalid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct sidtab_entry *entry; int rc = 0; if (scontext) *scontext = NULL; *scontext_len = 0; if (!selinux_initialized()) { if (sid <= SECINITSID_NUM) { char *scontextp; const char *s; /* * Before the policy is loaded, translate * SECINITSID_INIT to "kernel", because systemd and * libselinux < 2.6 take a getcon_raw() result that is * both non-null and not "kernel" to mean that a policy * is already loaded. */ if (sid == SECINITSID_INIT) sid = SECINITSID_KERNEL; s = initial_sid_to_string[sid]; if (!s) return -EINVAL; *scontext_len = strlen(s) + 1; if (!scontext) return 0; scontextp = kmemdup(s, *scontext_len, GFP_ATOMIC); if (!scontextp) return -ENOMEM; *scontext = scontextp; return 0; } pr_err("SELinux: %s: called before initial " "load_policy on unknown SID %d\n", __func__, sid); return -EINVAL; } rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; if (force) entry = sidtab_search_entry_force(sidtab, sid); else entry = sidtab_search_entry(sidtab, sid); if (!entry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, sid); rc = -EINVAL; goto out_unlock; } if (only_invalid && !entry->context.len) goto out_unlock; rc = sidtab_entry_to_string(policydb, sidtab, entry, scontext, scontext_len); out_unlock: rcu_read_unlock(); return rc; } /** * security_sid_to_context - Obtain a context for a given SID. * @sid: security identifier, SID * @scontext: security context * @scontext_len: length in bytes * * Write the string representation of the context associated with @sid * into a dynamically allocated string of the correct size. Set @scontext * to point to this string and set @scontext_len to the length of the string. */ int security_sid_to_context(u32 sid, char **scontext, u32 *scontext_len) { return security_sid_to_context_core(sid, scontext, scontext_len, 0, 0); } int security_sid_to_context_force(u32 sid, char **scontext, u32 *scontext_len) { return security_sid_to_context_core(sid, scontext, scontext_len, 1, 0); } /** * security_sid_to_context_inval - Obtain a context for a given SID if it * is invalid. * @sid: security identifier, SID * @scontext: security context * @scontext_len: length in bytes * * Write the string representation of the context associated with @sid * into a dynamically allocated string of the correct size, but only if the * context is invalid in the current policy. Set @scontext to point to * this string (or NULL if the context is valid) and set @scontext_len to * the length of the string (or 0 if the context is valid). */ int security_sid_to_context_inval(u32 sid, char **scontext, u32 *scontext_len) { return security_sid_to_context_core(sid, scontext, scontext_len, 1, 1); } /* * Caveat: Mutates scontext. */ static int string_to_context_struct(struct policydb *pol, struct sidtab *sidtabp, char *scontext, struct context *ctx, u32 def_sid) { struct role_datum *role; struct type_datum *typdatum; struct user_datum *usrdatum; char *scontextp, *p, oldc; int rc = 0; context_init(ctx); /* Parse the security context. */ rc = -EINVAL; scontextp = scontext; /* Extract the user. */ p = scontextp; while (*p && *p != ':') p++; if (*p == 0) goto out; *p++ = 0; usrdatum = symtab_search(&pol->p_users, scontextp); if (!usrdatum) goto out; ctx->user = usrdatum->value; /* Extract role. */ scontextp = p; while (*p && *p != ':') p++; if (*p == 0) goto out; *p++ = 0; role = symtab_search(&pol->p_roles, scontextp); if (!role) goto out; ctx->role = role->value; /* Extract type. */ scontextp = p; while (*p && *p != ':') p++; oldc = *p; *p++ = 0; typdatum = symtab_search(&pol->p_types, scontextp); if (!typdatum || typdatum->attribute) goto out; ctx->type = typdatum->value; rc = mls_context_to_sid(pol, oldc, p, ctx, sidtabp, def_sid); if (rc) goto out; /* Check the validity of the new context. */ rc = -EINVAL; if (!policydb_context_isvalid(pol, ctx)) goto out; rc = 0; out: if (rc) context_destroy(ctx); return rc; } static int security_context_to_sid_core(const char *scontext, u32 scontext_len, u32 *sid, u32 def_sid, gfp_t gfp_flags, int force) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; char *scontext2, *str = NULL; struct context context; int rc = 0; /* An empty security context is never valid. */ if (!scontext_len) return -EINVAL; /* Copy the string to allow changes and ensure a NUL terminator */ scontext2 = kmemdup_nul(scontext, scontext_len, gfp_flags); if (!scontext2) return -ENOMEM; if (!selinux_initialized()) { u32 i; for (i = 1; i < SECINITSID_NUM; i++) { const char *s = initial_sid_to_string[i]; if (s && !strcmp(s, scontext2)) { *sid = i; goto out; } } *sid = SECINITSID_KERNEL; goto out; } *sid = SECSID_NULL; if (force) { /* Save another copy for storing in uninterpreted form */ rc = -ENOMEM; str = kstrdup(scontext2, gfp_flags); if (!str) goto out; } retry: rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; rc = string_to_context_struct(policydb, sidtab, scontext2, &context, def_sid); if (rc == -EINVAL && force) { context.str = str; context.len = strlen(str) + 1; str = NULL; } else if (rc) goto out_unlock; rc = sidtab_context_to_sid(sidtab, &context, sid); if (rc == -ESTALE) { rcu_read_unlock(); if (context.str) { str = context.str; context.str = NULL; } context_destroy(&context); goto retry; } context_destroy(&context); out_unlock: rcu_read_unlock(); out: kfree(scontext2); kfree(str); return rc; } /** * security_context_to_sid - Obtain a SID for a given security context. * @scontext: security context * @scontext_len: length in bytes * @sid: security identifier, SID * @gfp: context for the allocation * * Obtains a SID associated with the security context that * has the string representation specified by @scontext. * Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient * memory is available, or 0 on success. */ int security_context_to_sid(const char *scontext, u32 scontext_len, u32 *sid, gfp_t gfp) { return security_context_to_sid_core(scontext, scontext_len, sid, SECSID_NULL, gfp, 0); } int security_context_str_to_sid(const char *scontext, u32 *sid, gfp_t gfp) { return security_context_to_sid(scontext, strlen(scontext), sid, gfp); } /** * security_context_to_sid_default - Obtain a SID for a given security context, * falling back to specified default if needed. * * @scontext: security context * @scontext_len: length in bytes * @sid: security identifier, SID * @def_sid: default SID to assign on error * @gfp_flags: the allocator get-free-page (GFP) flags * * Obtains a SID associated with the security context that * has the string representation specified by @scontext. * The default SID is passed to the MLS layer to be used to allow * kernel labeling of the MLS field if the MLS field is not present * (for upgrading to MLS without full relabel). * Implicitly forces adding of the context even if it cannot be mapped yet. * Returns -%EINVAL if the context is invalid, -%ENOMEM if insufficient * memory is available, or 0 on success. */ int security_context_to_sid_default(const char *scontext, u32 scontext_len, u32 *sid, u32 def_sid, gfp_t gfp_flags) { return security_context_to_sid_core(scontext, scontext_len, sid, def_sid, gfp_flags, 1); } int security_context_to_sid_force(const char *scontext, u32 scontext_len, u32 *sid) { return security_context_to_sid_core(scontext, scontext_len, sid, SECSID_NULL, GFP_KERNEL, 1); } static int compute_sid_handle_invalid_context( struct selinux_policy *policy, struct sidtab_entry *sentry, struct sidtab_entry *tentry, u16 tclass, struct context *newcontext) { struct policydb *policydb = &policy->policydb; struct sidtab *sidtab = policy->sidtab; char *s = NULL, *t = NULL, *n = NULL; u32 slen, tlen, nlen; struct audit_buffer *ab; if (sidtab_entry_to_string(policydb, sidtab, sentry, &s, &slen)) goto out; if (sidtab_entry_to_string(policydb, sidtab, tentry, &t, &tlen)) goto out; if (context_struct_to_string(policydb, newcontext, &n, &nlen)) goto out; ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); if (!ab) goto out; audit_log_format(ab, "op=security_compute_sid invalid_context="); /* no need to record the NUL with untrusted strings */ audit_log_n_untrustedstring(ab, n, nlen - 1); audit_log_format(ab, " scontext=%s tcontext=%s tclass=%s", s, t, sym_name(policydb, SYM_CLASSES, tclass-1)); audit_log_end(ab); out: kfree(s); kfree(t); kfree(n); if (!enforcing_enabled()) return 0; return -EACCES; } static void filename_compute_type(struct policydb *policydb, struct context *newcontext, u32 stype, u32 ttype, u16 tclass, const char *objname) { struct filename_trans_key ft; struct filename_trans_datum *datum; /* * Most filename trans rules are going to live in specific directories * like /dev or /var/run. This bitmap will quickly skip rule searches * if the ttype does not contain any rules. */ if (!ebitmap_get_bit(&policydb->filename_trans_ttypes, ttype)) return; ft.ttype = ttype; ft.tclass = tclass; ft.name = objname; datum = policydb_filenametr_search(policydb, &ft); while (datum) { if (ebitmap_get_bit(&datum->stypes, stype - 1)) { newcontext->type = datum->otype; return; } datum = datum->next; } } static int security_compute_sid(u32 ssid, u32 tsid, u16 orig_tclass, u16 specified, const char *objname, u32 *out_sid, bool kern) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct class_datum *cladatum; struct context *scontext, *tcontext, newcontext; struct sidtab_entry *sentry, *tentry; struct avtab_key avkey; struct avtab_node *avnode, *node; u16 tclass; int rc = 0; bool sock; if (!selinux_initialized()) { switch (orig_tclass) { case SECCLASS_PROCESS: /* kernel value */ *out_sid = ssid; break; default: *out_sid = tsid; break; } goto out; } retry: cladatum = NULL; context_init(&newcontext); rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); if (kern) { tclass = unmap_class(&policy->map, orig_tclass); sock = security_is_socket_class(orig_tclass); } else { tclass = orig_tclass; sock = security_is_socket_class(map_class(&policy->map, tclass)); } policydb = &policy->policydb; sidtab = policy->sidtab; sentry = sidtab_search_entry(sidtab, ssid); if (!sentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, ssid); rc = -EINVAL; goto out_unlock; } tentry = sidtab_search_entry(sidtab, tsid); if (!tentry) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, tsid); rc = -EINVAL; goto out_unlock; } scontext = &sentry->context; tcontext = &tentry->context; if (tclass && tclass <= policydb->p_classes.nprim) cladatum = policydb->class_val_to_struct[tclass - 1]; /* Set the user identity. */ switch (specified) { case AVTAB_TRANSITION: case AVTAB_CHANGE: if (cladatum && cladatum->default_user == DEFAULT_TARGET) { newcontext.user = tcontext->user; } else { /* notice this gets both DEFAULT_SOURCE and unset */ /* Use the process user identity. */ newcontext.user = scontext->user; } break; case AVTAB_MEMBER: /* Use the related object owner. */ newcontext.user = tcontext->user; break; } /* Set the role to default values. */ if (cladatum && cladatum->default_role == DEFAULT_SOURCE) { newcontext.role = scontext->role; } else if (cladatum && cladatum->default_role == DEFAULT_TARGET) { newcontext.role = tcontext->role; } else { if ((tclass == policydb->process_class) || sock) newcontext.role = scontext->role; else newcontext.role = OBJECT_R_VAL; } /* Set the type. * Look for a type transition/member/change rule. */ avkey.source_type = scontext->type; avkey.target_type = tcontext->type; avkey.target_class = tclass; avkey.specified = specified; avnode = avtab_search_node(&policydb->te_avtab, &avkey); /* If no permanent rule, also check for enabled conditional rules */ if (!avnode) { node = avtab_search_node(&policydb->te_cond_avtab, &avkey); for (; node; node = avtab_search_node_next(node, specified)) { if (node->key.specified & AVTAB_ENABLED) { avnode = node; break; } } } /* If a permanent rule is found, use the type from * the type transition/member/change rule. Otherwise, * set the type to its default values. */ if (avnode) { newcontext.type = avnode->datum.u.data; } else if (cladatum && cladatum->default_type == DEFAULT_SOURCE) { newcontext.type = scontext->type; } else if (cladatum && cladatum->default_type == DEFAULT_TARGET) { newcontext.type = tcontext->type; } else { if ((tclass == policydb->process_class) || sock) { /* Use the type of process. */ newcontext.type = scontext->type; } else { /* Use the type of the related object. */ newcontext.type = tcontext->type; } } /* if we have a objname this is a file trans check so check those rules */ if (objname) filename_compute_type(policydb, &newcontext, scontext->type, tcontext->type, tclass, objname); /* Check for class-specific changes. */ if (specified & AVTAB_TRANSITION) { /* Look for a role transition rule. */ struct role_trans_datum *rtd; struct role_trans_key rtk = { .role = scontext->role, .type = tcontext->type, .tclass = tclass, }; rtd = policydb_roletr_search(policydb, &rtk); if (rtd) newcontext.role = rtd->new_role; } /* Set the MLS attributes. This is done last because it may allocate memory. */ rc = mls_compute_sid(policydb, scontext, tcontext, tclass, specified, &newcontext, sock); if (rc) goto out_unlock; /* Check the validity of the context. */ if (!policydb_context_isvalid(policydb, &newcontext)) { rc = compute_sid_handle_invalid_context(policy, sentry, tentry, tclass, &newcontext); if (rc) goto out_unlock; } /* Obtain the sid for the context. */ if (context_equal(scontext, &newcontext)) *out_sid = ssid; else if (context_equal(tcontext, &newcontext)) *out_sid = tsid; else { rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); context_destroy(&newcontext); goto retry; } } out_unlock: rcu_read_unlock(); context_destroy(&newcontext); out: return rc; } /** * security_transition_sid - Compute the SID for a new subject/object. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @qstr: object name * @out_sid: security identifier for new subject/object * * Compute a SID to use for labeling a new subject or object in the * class @tclass based on a SID pair (@ssid, @tsid). * Return -%EINVAL if any of the parameters are invalid, -%ENOMEM * if insufficient memory is available, or %0 if the new SID was * computed successfully. */ int security_transition_sid(u32 ssid, u32 tsid, u16 tclass, const struct qstr *qstr, u32 *out_sid) { return security_compute_sid(ssid, tsid, tclass, AVTAB_TRANSITION, qstr ? qstr->name : NULL, out_sid, true); } int security_transition_sid_user(u32 ssid, u32 tsid, u16 tclass, const char *objname, u32 *out_sid) { return security_compute_sid(ssid, tsid, tclass, AVTAB_TRANSITION, objname, out_sid, false); } /** * security_member_sid - Compute the SID for member selection. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @out_sid: security identifier for selected member * * Compute a SID to use when selecting a member of a polyinstantiated * object of class @tclass based on a SID pair (@ssid, @tsid). * Return -%EINVAL if any of the parameters are invalid, -%ENOMEM * if insufficient memory is available, or %0 if the SID was * computed successfully. */ int security_member_sid(u32 ssid, u32 tsid, u16 tclass, u32 *out_sid) { return security_compute_sid(ssid, tsid, tclass, AVTAB_MEMBER, NULL, out_sid, false); } /** * security_change_sid - Compute the SID for object relabeling. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @out_sid: security identifier for selected member * * Compute a SID to use for relabeling an object of class @tclass * based on a SID pair (@ssid, @tsid). * Return -%EINVAL if any of the parameters are invalid, -%ENOMEM * if insufficient memory is available, or %0 if the SID was * computed successfully. */ int security_change_sid(u32 ssid, u32 tsid, u16 tclass, u32 *out_sid) { return security_compute_sid(ssid, tsid, tclass, AVTAB_CHANGE, NULL, out_sid, false); } static inline int convert_context_handle_invalid_context( struct policydb *policydb, struct context *context) { char *s; u32 len; if (enforcing_enabled()) return -EINVAL; if (!context_struct_to_string(policydb, context, &s, &len)) { pr_warn("SELinux: Context %s would be invalid if enforcing\n", s); kfree(s); } return 0; } /** * services_convert_context - Convert a security context across policies. * @args: populated convert_context_args struct * @oldc: original context * @newc: converted context * @gfp_flags: allocation flags * * Convert the values in the security context structure @oldc from the values * specified in the policy @args->oldp to the values specified in the policy * @args->newp, storing the new context in @newc, and verifying that the * context is valid under the new policy. */ int services_convert_context(struct convert_context_args *args, struct context *oldc, struct context *newc, gfp_t gfp_flags) { struct ocontext *oc; struct role_datum *role; struct type_datum *typdatum; struct user_datum *usrdatum; char *s; u32 len; int rc; if (oldc->str) { s = kstrdup(oldc->str, gfp_flags); if (!s) return -ENOMEM; rc = string_to_context_struct(args->newp, NULL, s, newc, SECSID_NULL); if (rc == -EINVAL) { /* * Retain string representation for later mapping. * * IMPORTANT: We need to copy the contents of oldc->str * back into s again because string_to_context_struct() * may have garbled it. */ memcpy(s, oldc->str, oldc->len); context_init(newc); newc->str = s; newc->len = oldc->len; return 0; } kfree(s); if (rc) { /* Other error condition, e.g. ENOMEM. */ pr_err("SELinux: Unable to map context %s, rc = %d.\n", oldc->str, -rc); return rc; } pr_info("SELinux: Context %s became valid (mapped).\n", oldc->str); return 0; } context_init(newc); /* Convert the user. */ usrdatum = symtab_search(&args->newp->p_users, sym_name(args->oldp, SYM_USERS, oldc->user - 1)); if (!usrdatum) goto bad; newc->user = usrdatum->value; /* Convert the role. */ role = symtab_search(&args->newp->p_roles, sym_name(args->oldp, SYM_ROLES, oldc->role - 1)); if (!role) goto bad; newc->role = role->value; /* Convert the type. */ typdatum = symtab_search(&args->newp->p_types, sym_name(args->oldp, SYM_TYPES, oldc->type - 1)); if (!typdatum) goto bad; newc->type = typdatum->value; /* Convert the MLS fields if dealing with MLS policies */ if (args->oldp->mls_enabled && args->newp->mls_enabled) { rc = mls_convert_context(args->oldp, args->newp, oldc, newc); if (rc) goto bad; } else if (!args->oldp->mls_enabled && args->newp->mls_enabled) { /* * Switching between non-MLS and MLS policy: * ensure that the MLS fields of the context for all * existing entries in the sidtab are filled in with a * suitable default value, likely taken from one of the * initial SIDs. */ oc = args->newp->ocontexts[OCON_ISID]; while (oc && oc->sid[0] != SECINITSID_UNLABELED) oc = oc->next; if (!oc) { pr_err("SELinux: unable to look up" " the initial SIDs list\n"); goto bad; } rc = mls_range_set(newc, &oc->context[0].range); if (rc) goto bad; } /* Check the validity of the new context. */ if (!policydb_context_isvalid(args->newp, newc)) { rc = convert_context_handle_invalid_context(args->oldp, oldc); if (rc) goto bad; } return 0; bad: /* Map old representation to string and save it. */ rc = context_struct_to_string(args->oldp, oldc, &s, &len); if (rc) return rc; context_destroy(newc); newc->str = s; newc->len = len; pr_info("SELinux: Context %s became invalid (unmapped).\n", newc->str); return 0; } static void security_load_policycaps(struct selinux_policy *policy) { struct policydb *p; unsigned int i; struct ebitmap_node *node; p = &policy->policydb; for (i = 0; i < ARRAY_SIZE(selinux_state.policycap); i++) WRITE_ONCE(selinux_state.policycap[i], ebitmap_get_bit(&p->policycaps, i)); for (i = 0; i < ARRAY_SIZE(selinux_policycap_names); i++) pr_info("SELinux: policy capability %s=%d\n", selinux_policycap_names[i], ebitmap_get_bit(&p->policycaps, i)); ebitmap_for_each_positive_bit(&p->policycaps, node, i) { if (i >= ARRAY_SIZE(selinux_policycap_names)) pr_info("SELinux: unknown policy capability %u\n", i); } } static int security_preserve_bools(struct selinux_policy *oldpolicy, struct selinux_policy *newpolicy); static void selinux_policy_free(struct selinux_policy *policy) { if (!policy) return; sidtab_destroy(policy->sidtab); kfree(policy->map.mapping); policydb_destroy(&policy->policydb); kfree(policy->sidtab); kfree(policy); } static void selinux_policy_cond_free(struct selinux_policy *policy) { cond_policydb_destroy_dup(&policy->policydb); kfree(policy); } void selinux_policy_cancel(struct selinux_load_state *load_state) { struct selinux_state *state = &selinux_state; struct selinux_policy *oldpolicy; oldpolicy = rcu_dereference_protected(state->policy, lockdep_is_held(&state->policy_mutex)); sidtab_cancel_convert(oldpolicy->sidtab); selinux_policy_free(load_state->policy); kfree(load_state->convert_data); } static void selinux_notify_policy_change(u32 seqno) { /* Flush external caches and notify userspace of policy load */ avc_ss_reset(seqno); selnl_notify_policyload(seqno); selinux_status_update_policyload(seqno); selinux_netlbl_cache_invalidate(); selinux_xfrm_notify_policyload(); selinux_ima_measure_state_locked(); } void selinux_policy_commit(struct selinux_load_state *load_state) { struct selinux_state *state = &selinux_state; struct selinux_policy *oldpolicy, *newpolicy = load_state->policy; unsigned long flags; u32 seqno; oldpolicy = rcu_dereference_protected(state->policy, lockdep_is_held(&state->policy_mutex)); /* If switching between different policy types, log MLS status */ if (oldpolicy) { if (oldpolicy->policydb.mls_enabled && !newpolicy->policydb.mls_enabled) pr_info("SELinux: Disabling MLS support...\n"); else if (!oldpolicy->policydb.mls_enabled && newpolicy->policydb.mls_enabled) pr_info("SELinux: Enabling MLS support...\n"); } /* Set latest granting seqno for new policy. */ if (oldpolicy) newpolicy->latest_granting = oldpolicy->latest_granting + 1; else newpolicy->latest_granting = 1; seqno = newpolicy->latest_granting; /* Install the new policy. */ if (oldpolicy) { sidtab_freeze_begin(oldpolicy->sidtab, &flags); rcu_assign_pointer(state->policy, newpolicy); sidtab_freeze_end(oldpolicy->sidtab, &flags); } else { rcu_assign_pointer(state->policy, newpolicy); } /* Load the policycaps from the new policy */ security_load_policycaps(newpolicy); if (!selinux_initialized()) { /* * After first policy load, the security server is * marked as initialized and ready to handle requests and * any objects created prior to policy load are then labeled. */ selinux_mark_initialized(); selinux_complete_init(); } /* Free the old policy */ synchronize_rcu(); selinux_policy_free(oldpolicy); kfree(load_state->convert_data); /* Notify others of the policy change */ selinux_notify_policy_change(seqno); } /** * security_load_policy - Load a security policy configuration. * @data: binary policy data * @len: length of data in bytes * @load_state: policy load state * * Load a new set of security policy configuration data, * validate it and convert the SID table as necessary. * This function will flush the access vector cache after * loading the new policy. */ int security_load_policy(void *data, size_t len, struct selinux_load_state *load_state) { struct selinux_state *state = &selinux_state; struct selinux_policy *newpolicy, *oldpolicy; struct selinux_policy_convert_data *convert_data; int rc = 0; struct policy_file file = { data, len }, *fp = &file; newpolicy = kzalloc(sizeof(*newpolicy), GFP_KERNEL); if (!newpolicy) return -ENOMEM; newpolicy->sidtab = kzalloc(sizeof(*newpolicy->sidtab), GFP_KERNEL); if (!newpolicy->sidtab) { rc = -ENOMEM; goto err_policy; } rc = policydb_read(&newpolicy->policydb, fp); if (rc) goto err_sidtab; newpolicy->policydb.len = len; rc = selinux_set_mapping(&newpolicy->policydb, secclass_map, &newpolicy->map); if (rc) goto err_policydb; rc = policydb_load_isids(&newpolicy->policydb, newpolicy->sidtab); if (rc) { pr_err("SELinux: unable to load the initial SIDs\n"); goto err_mapping; } if (!selinux_initialized()) { /* First policy load, so no need to preserve state from old policy */ load_state->policy = newpolicy; load_state->convert_data = NULL; return 0; } oldpolicy = rcu_dereference_protected(state->policy, lockdep_is_held(&state->policy_mutex)); /* Preserve active boolean values from the old policy */ rc = security_preserve_bools(oldpolicy, newpolicy); if (rc) { pr_err("SELinux: unable to preserve booleans\n"); goto err_free_isids; } /* * Convert the internal representations of contexts * in the new SID table. */ convert_data = kmalloc(sizeof(*convert_data), GFP_KERNEL); if (!convert_data) { rc = -ENOMEM; goto err_free_isids; } convert_data->args.oldp = &oldpolicy->policydb; convert_data->args.newp = &newpolicy->policydb; convert_data->sidtab_params.args = &convert_data->args; convert_data->sidtab_params.target = newpolicy->sidtab; rc = sidtab_convert(oldpolicy->sidtab, &convert_data->sidtab_params); if (rc) { pr_err("SELinux: unable to convert the internal" " representation of contexts in the new SID" " table\n"); goto err_free_convert_data; } load_state->policy = newpolicy; load_state->convert_data = convert_data; return 0; err_free_convert_data: kfree(convert_data); err_free_isids: sidtab_destroy(newpolicy->sidtab); err_mapping: kfree(newpolicy->map.mapping); err_policydb: policydb_destroy(&newpolicy->policydb); err_sidtab: kfree(newpolicy->sidtab); err_policy: kfree(newpolicy); return rc; } /** * ocontext_to_sid - Helper to safely get sid for an ocontext * @sidtab: SID table * @c: ocontext structure * @index: index of the context entry (0 or 1) * @out_sid: pointer to the resulting SID value * * For all ocontexts except OCON_ISID the SID fields are populated * on-demand when needed. Since updating the SID value is an SMP-sensitive * operation, this helper must be used to do that safely. * * WARNING: This function may return -ESTALE, indicating that the caller * must retry the operation after re-acquiring the policy pointer! */ static int ocontext_to_sid(struct sidtab *sidtab, struct ocontext *c, size_t index, u32 *out_sid) { int rc; u32 sid; /* Ensure the associated sidtab entry is visible to this thread. */ sid = smp_load_acquire(&c->sid[index]); if (!sid) { rc = sidtab_context_to_sid(sidtab, &c->context[index], &sid); if (rc) return rc; /* * Ensure the new sidtab entry is visible to other threads * when they see the SID. */ smp_store_release(&c->sid[index], sid); } *out_sid = sid; return 0; } /** * security_port_sid - Obtain the SID for a port. * @protocol: protocol number * @port: port number * @out_sid: security identifier */ int security_port_sid(u8 protocol, u16 port, u32 *out_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; int rc; if (!selinux_initialized()) { *out_sid = SECINITSID_PORT; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_PORT]; while (c) { if (c->u.port.protocol == protocol && c->u.port.low_port <= port && c->u.port.high_port >= port) break; c = c->next; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else { *out_sid = SECINITSID_PORT; } out: rcu_read_unlock(); return rc; } /** * security_ib_pkey_sid - Obtain the SID for a pkey. * @subnet_prefix: Subnet Prefix * @pkey_num: pkey number * @out_sid: security identifier */ int security_ib_pkey_sid(u64 subnet_prefix, u16 pkey_num, u32 *out_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; int rc; if (!selinux_initialized()) { *out_sid = SECINITSID_UNLABELED; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_IBPKEY]; while (c) { if (c->u.ibpkey.low_pkey <= pkey_num && c->u.ibpkey.high_pkey >= pkey_num && c->u.ibpkey.subnet_prefix == subnet_prefix) break; c = c->next; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else *out_sid = SECINITSID_UNLABELED; out: rcu_read_unlock(); return rc; } /** * security_ib_endport_sid - Obtain the SID for a subnet management interface. * @dev_name: device name * @port_num: port number * @out_sid: security identifier */ int security_ib_endport_sid(const char *dev_name, u8 port_num, u32 *out_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; int rc; if (!selinux_initialized()) { *out_sid = SECINITSID_UNLABELED; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_IBENDPORT]; while (c) { if (c->u.ibendport.port == port_num && !strncmp(c->u.ibendport.dev_name, dev_name, IB_DEVICE_NAME_MAX)) break; c = c->next; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else *out_sid = SECINITSID_UNLABELED; out: rcu_read_unlock(); return rc; } /** * security_netif_sid - Obtain the SID for a network interface. * @name: interface name * @if_sid: interface SID */ int security_netif_sid(const char *name, u32 *if_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct ocontext *c; bool wildcard_support; if (!selinux_initialized()) { *if_sid = SECINITSID_NETIF; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; wildcard_support = ebitmap_get_bit(&policydb->policycaps, POLICYDB_CAP_NETIF_WILDCARD); c = policydb->ocontexts[OCON_NETIF]; while (c) { if (wildcard_support) { if (match_wildcard(c->u.name, name)) break; } else { if (strcmp(c->u.name, name) == 0) break; } c = c->next; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, if_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else *if_sid = SECINITSID_NETIF; out: rcu_read_unlock(); return rc; } static bool match_ipv6_addrmask(const u32 input[4], const u32 addr[4], const u32 mask[4]) { int i; for (i = 0; i < 4; i++) if (addr[i] != (input[i] & mask[i])) return false; return true; } /** * security_node_sid - Obtain the SID for a node (host). * @domain: communication domain aka address family * @addrp: address * @addrlen: address length in bytes * @out_sid: security identifier */ int security_node_sid(u16 domain, const void *addrp, u32 addrlen, u32 *out_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct ocontext *c; if (!selinux_initialized()) { *out_sid = SECINITSID_NODE; return 0; } retry: rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; switch (domain) { case AF_INET: { u32 addr; rc = -EINVAL; if (addrlen != sizeof(u32)) goto out; addr = *((const u32 *)addrp); c = policydb->ocontexts[OCON_NODE]; while (c) { if (c->u.node.addr == (addr & c->u.node.mask)) break; c = c->next; } break; } case AF_INET6: rc = -EINVAL; if (addrlen != sizeof(u64) * 2) goto out; c = policydb->ocontexts[OCON_NODE6]; while (c) { if (match_ipv6_addrmask(addrp, c->u.node6.addr, c->u.node6.mask)) break; c = c->next; } break; default: rc = 0; *out_sid = SECINITSID_NODE; goto out; } if (c) { rc = ocontext_to_sid(sidtab, c, 0, out_sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else { *out_sid = SECINITSID_NODE; } rc = 0; out: rcu_read_unlock(); return rc; } #define SIDS_NEL 25 /** * security_get_user_sids - Obtain reachable SIDs for a user. * @fromsid: starting SID * @username: username * @sids: array of reachable SIDs for user * @nel: number of elements in @sids * * Generate the set of SIDs for legal security contexts * for a given user that can be reached by @fromsid. * Set *@sids to point to a dynamically allocated * array containing the set of SIDs. Set *@nel to the * number of elements in the array. */ int security_get_user_sids(u32 fromsid, const char *username, u32 **sids, u32 *nel) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct context *fromcon, usercon; u32 *mysids = NULL, *mysids2, sid; u32 i, j, mynel, maxnel = SIDS_NEL; struct user_datum *user; struct role_datum *role; struct ebitmap_node *rnode, *tnode; int rc; *sids = NULL; *nel = 0; if (!selinux_initialized()) return 0; mysids = kcalloc(maxnel, sizeof(*mysids), GFP_KERNEL); if (!mysids) return -ENOMEM; retry: mynel = 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; context_init(&usercon); rc = -EINVAL; fromcon = sidtab_search(sidtab, fromsid); if (!fromcon) goto out_unlock; rc = -EINVAL; user = symtab_search(&policydb->p_users, username); if (!user) goto out_unlock; usercon.user = user->value; ebitmap_for_each_positive_bit(&user->roles, rnode, i) { role = policydb->role_val_to_struct[i]; usercon.role = i + 1; ebitmap_for_each_positive_bit(&role->types, tnode, j) { usercon.type = j + 1; if (mls_setup_user_range(policydb, fromcon, user, &usercon)) continue; rc = sidtab_context_to_sid(sidtab, &usercon, &sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out_unlock; if (mynel < maxnel) { mysids[mynel++] = sid; } else { rc = -ENOMEM; maxnel += SIDS_NEL; mysids2 = kcalloc(maxnel, sizeof(*mysids2), GFP_ATOMIC); if (!mysids2) goto out_unlock; memcpy(mysids2, mysids, mynel * sizeof(*mysids2)); kfree(mysids); mysids = mysids2; mysids[mynel++] = sid; } } } rc = 0; out_unlock: rcu_read_unlock(); if (rc || !mynel) { kfree(mysids); return rc; } rc = -ENOMEM; mysids2 = kcalloc(mynel, sizeof(*mysids2), GFP_KERNEL); if (!mysids2) { kfree(mysids); return rc; } for (i = 0, j = 0; i < mynel; i++) { struct av_decision dummy_avd; rc = avc_has_perm_noaudit(fromsid, mysids[i], SECCLASS_PROCESS, /* kernel value */ PROCESS__TRANSITION, AVC_STRICT, &dummy_avd); if (!rc) mysids2[j++] = mysids[i]; cond_resched(); } kfree(mysids); *sids = mysids2; *nel = j; return 0; } /** * __security_genfs_sid - Helper to obtain a SID for a file in a filesystem * @policy: policy * @fstype: filesystem type * @path: path from root of mount * @orig_sclass: file security class * @sid: SID for path * * Obtain a SID to use for a file in a filesystem that * cannot support xattr or use a fixed labeling behavior like * transition SIDs or task SIDs. * * WARNING: This function may return -ESTALE, indicating that the caller * must retry the operation after re-acquiring the policy pointer! */ static inline int __security_genfs_sid(struct selinux_policy *policy, const char *fstype, const char *path, u16 orig_sclass, u32 *sid) { struct policydb *policydb = &policy->policydb; struct sidtab *sidtab = policy->sidtab; u16 sclass; struct genfs *genfs; struct ocontext *c; int cmp = 0; bool wildcard; while (path[0] == '/' && path[1] == '/') path++; sclass = unmap_class(&policy->map, orig_sclass); *sid = SECINITSID_UNLABELED; for (genfs = policydb->genfs; genfs; genfs = genfs->next) { cmp = strcmp(fstype, genfs->fstype); if (cmp <= 0) break; } if (!genfs || cmp) return -ENOENT; wildcard = ebitmap_get_bit(&policy->policydb.policycaps, POLICYDB_CAP_GENFS_SECLABEL_WILDCARD); for (c = genfs->head; c; c = c->next) { if (!c->v.sclass || sclass == c->v.sclass) { if (wildcard) { if (match_wildcard(c->u.name, path)) break; } else { size_t len = strlen(c->u.name); if ((strncmp(c->u.name, path, len)) == 0) break; } } } if (!c) return -ENOENT; return ocontext_to_sid(sidtab, c, 0, sid); } /** * security_genfs_sid - Obtain a SID for a file in a filesystem * @fstype: filesystem type * @path: path from root of mount * @orig_sclass: file security class * @sid: SID for path * * Acquire policy_rwlock before calling __security_genfs_sid() and release * it afterward. */ int security_genfs_sid(const char *fstype, const char *path, u16 orig_sclass, u32 *sid) { struct selinux_policy *policy; int retval; if (!selinux_initialized()) { *sid = SECINITSID_UNLABELED; return 0; } do { rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); retval = __security_genfs_sid(policy, fstype, path, orig_sclass, sid); rcu_read_unlock(); } while (retval == -ESTALE); return retval; } int selinux_policy_genfs_sid(struct selinux_policy *policy, const char *fstype, const char *path, u16 orig_sclass, u32 *sid) { /* no lock required, policy is not yet accessible by other threads */ return __security_genfs_sid(policy, fstype, path, orig_sclass, sid); } /** * security_fs_use - Determine how to handle labeling for a filesystem. * @sb: superblock in question */ int security_fs_use(struct super_block *sb) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct ocontext *c; struct superblock_security_struct *sbsec = selinux_superblock(sb); const char *fstype = sb->s_type->name; if (!selinux_initialized()) { sbsec->behavior = SECURITY_FS_USE_NONE; sbsec->sid = SECINITSID_UNLABELED; return 0; } retry: rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; c = policydb->ocontexts[OCON_FSUSE]; while (c) { if (strcmp(fstype, c->u.name) == 0) break; c = c->next; } if (c) { sbsec->behavior = c->v.behavior; rc = ocontext_to_sid(sidtab, c, 0, &sbsec->sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; } else { rc = __security_genfs_sid(policy, fstype, "/", SECCLASS_DIR, &sbsec->sid); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) { sbsec->behavior = SECURITY_FS_USE_NONE; rc = 0; } else { sbsec->behavior = SECURITY_FS_USE_GENFS; } } out: rcu_read_unlock(); return rc; } int security_get_bools(struct selinux_policy *policy, u32 *len, char ***names, int **values) { struct policydb *policydb; u32 i; int rc; policydb = &policy->policydb; *names = NULL; *values = NULL; rc = 0; *len = policydb->p_bools.nprim; if (!*len) goto out; rc = -ENOMEM; *names = kcalloc(*len, sizeof(char *), GFP_ATOMIC); if (!*names) goto err; rc = -ENOMEM; *values = kcalloc(*len, sizeof(int), GFP_ATOMIC); if (!*values) goto err; for (i = 0; i < *len; i++) { (*values)[i] = policydb->bool_val_to_struct[i]->state; rc = -ENOMEM; (*names)[i] = kstrdup(sym_name(policydb, SYM_BOOLS, i), GFP_ATOMIC); if (!(*names)[i]) goto err; } rc = 0; out: return rc; err: if (*names) { for (i = 0; i < *len; i++) kfree((*names)[i]); kfree(*names); } kfree(*values); *len = 0; *names = NULL; *values = NULL; goto out; } int security_set_bools(u32 len, const int *values) { struct selinux_state *state = &selinux_state; struct selinux_policy *newpolicy, *oldpolicy; int rc; u32 i, seqno = 0; if (!selinux_initialized()) return -EINVAL; oldpolicy = rcu_dereference_protected(state->policy, lockdep_is_held(&state->policy_mutex)); /* Consistency check on number of booleans, should never fail */ if (WARN_ON(len != oldpolicy->policydb.p_bools.nprim)) return -EINVAL; newpolicy = kmemdup(oldpolicy, sizeof(*newpolicy), GFP_KERNEL); if (!newpolicy) return -ENOMEM; /* * Deep copy only the parts of the policydb that might be * modified as a result of changing booleans. */ rc = cond_policydb_dup(&newpolicy->policydb, &oldpolicy->policydb); if (rc) { kfree(newpolicy); return -ENOMEM; } /* Update the boolean states in the copy */ for (i = 0; i < len; i++) { int new_state = !!values[i]; int old_state = newpolicy->policydb.bool_val_to_struct[i]->state; if (new_state != old_state) { audit_log(audit_context(), GFP_ATOMIC, AUDIT_MAC_CONFIG_CHANGE, "bool=%s val=%d old_val=%d auid=%u ses=%u", sym_name(&newpolicy->policydb, SYM_BOOLS, i), new_state, old_state, from_kuid(&init_user_ns, audit_get_loginuid(current)), audit_get_sessionid(current)); newpolicy->policydb.bool_val_to_struct[i]->state = new_state; } } /* Re-evaluate the conditional rules in the copy */ evaluate_cond_nodes(&newpolicy->policydb); /* Set latest granting seqno for new policy */ newpolicy->latest_granting = oldpolicy->latest_granting + 1; seqno = newpolicy->latest_granting; /* Install the new policy */ rcu_assign_pointer(state->policy, newpolicy); /* * Free the conditional portions of the old policydb * that were copied for the new policy, and the oldpolicy * structure itself but not what it references. */ synchronize_rcu(); selinux_policy_cond_free(oldpolicy); /* Notify others of the policy change */ selinux_notify_policy_change(seqno); return 0; } int security_get_bool_value(u32 index) { struct selinux_policy *policy; struct policydb *policydb; int rc; u32 len; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; rc = -EFAULT; len = policydb->p_bools.nprim; if (index >= len) goto out; rc = policydb->bool_val_to_struct[index]->state; out: rcu_read_unlock(); return rc; } static int security_preserve_bools(struct selinux_policy *oldpolicy, struct selinux_policy *newpolicy) { int rc, *bvalues = NULL; char **bnames = NULL; struct cond_bool_datum *booldatum; u32 i, nbools = 0; rc = security_get_bools(oldpolicy, &nbools, &bnames, &bvalues); if (rc) goto out; for (i = 0; i < nbools; i++) { booldatum = symtab_search(&newpolicy->policydb.p_bools, bnames[i]); if (booldatum) booldatum->state = bvalues[i]; } evaluate_cond_nodes(&newpolicy->policydb); out: if (bnames) { for (i = 0; i < nbools; i++) kfree(bnames[i]); } kfree(bnames); kfree(bvalues); return rc; } /* * security_sid_mls_copy() - computes a new sid based on the given * sid and the mls portion of mls_sid. */ int security_sid_mls_copy(u32 sid, u32 mls_sid, u32 *new_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; struct context *context1; struct context *context2; struct context newcon; char *s; u32 len; int rc; if (!selinux_initialized()) { *new_sid = sid; return 0; } retry: rc = 0; context_init(&newcon); rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; if (!policydb->mls_enabled) { *new_sid = sid; goto out_unlock; } rc = -EINVAL; context1 = sidtab_search(sidtab, sid); if (!context1) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, sid); goto out_unlock; } rc = -EINVAL; context2 = sidtab_search(sidtab, mls_sid); if (!context2) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, mls_sid); goto out_unlock; } newcon.user = context1->user; newcon.role = context1->role; newcon.type = context1->type; rc = mls_context_cpy(&newcon, context2); if (rc) goto out_unlock; /* Check the validity of the new context. */ if (!policydb_context_isvalid(policydb, &newcon)) { rc = convert_context_handle_invalid_context(policydb, &newcon); if (rc) { if (!context_struct_to_string(policydb, &newcon, &s, &len)) { struct audit_buffer *ab; ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR); audit_log_format(ab, "op=security_sid_mls_copy invalid_context="); /* don't record NUL with untrusted strings */ audit_log_n_untrustedstring(ab, s, len - 1); audit_log_end(ab); kfree(s); } goto out_unlock; } } rc = sidtab_context_to_sid(sidtab, &newcon, new_sid); if (rc == -ESTALE) { rcu_read_unlock(); context_destroy(&newcon); goto retry; } out_unlock: rcu_read_unlock(); context_destroy(&newcon); return rc; } /** * security_net_peersid_resolve - Compare and resolve two network peer SIDs * @nlbl_sid: NetLabel SID * @nlbl_type: NetLabel labeling protocol type * @xfrm_sid: XFRM SID * @peer_sid: network peer sid * * Description: * Compare the @nlbl_sid and @xfrm_sid values and if the two SIDs can be * resolved into a single SID it is returned via @peer_sid and the function * returns zero. Otherwise @peer_sid is set to SECSID_NULL and the function * returns a negative value. A table summarizing the behavior is below: * * | function return | @sid * ------------------------------+-----------------+----------------- * no peer labels | 0 | SECSID_NULL * single peer label | 0 | <peer_label> * multiple, consistent labels | 0 | <peer_label> * multiple, inconsistent labels | -<errno> | SECSID_NULL * */ int security_net_peersid_resolve(u32 nlbl_sid, u32 nlbl_type, u32 xfrm_sid, u32 *peer_sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct context *nlbl_ctx; struct context *xfrm_ctx; *peer_sid = SECSID_NULL; /* handle the common (which also happens to be the set of easy) cases * right away, these two if statements catch everything involving a * single or absent peer SID/label */ if (xfrm_sid == SECSID_NULL) { *peer_sid = nlbl_sid; return 0; } /* NOTE: an nlbl_type == NETLBL_NLTYPE_UNLABELED is a "fallback" label * and is treated as if nlbl_sid == SECSID_NULL when a XFRM SID/label * is present */ if (nlbl_sid == SECSID_NULL || nlbl_type == NETLBL_NLTYPE_UNLABELED) { *peer_sid = xfrm_sid; return 0; } if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; /* * We don't need to check initialized here since the only way both * nlbl_sid and xfrm_sid are not equal to SECSID_NULL would be if the * security server was initialized and state->initialized was true. */ if (!policydb->mls_enabled) { rc = 0; goto out; } rc = -EINVAL; nlbl_ctx = sidtab_search(sidtab, nlbl_sid); if (!nlbl_ctx) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, nlbl_sid); goto out; } rc = -EINVAL; xfrm_ctx = sidtab_search(sidtab, xfrm_sid); if (!xfrm_ctx) { pr_err("SELinux: %s: unrecognized SID %d\n", __func__, xfrm_sid); goto out; } rc = (mls_context_equal(nlbl_ctx, xfrm_ctx) ? 0 : -EACCES); if (rc) goto out; /* at present NetLabel SIDs/labels really only carry MLS * information so if the MLS portion of the NetLabel SID * matches the MLS portion of the labeled XFRM SID/label * then pass along the XFRM SID as it is the most * expressive */ *peer_sid = xfrm_sid; out: rcu_read_unlock(); return rc; } static int get_classes_callback(void *k, void *d, void *args) { struct class_datum *datum = d; char *name = k, **classes = args; u32 value = datum->value - 1; classes[value] = kstrdup(name, GFP_ATOMIC); if (!classes[value]) return -ENOMEM; return 0; } int security_get_classes(struct selinux_policy *policy, char ***classes, u32 *nclasses) { struct policydb *policydb; int rc; policydb = &policy->policydb; rc = -ENOMEM; *nclasses = policydb->p_classes.nprim; *classes = kcalloc(*nclasses, sizeof(**classes), GFP_ATOMIC); if (!*classes) goto out; rc = hashtab_map(&policydb->p_classes.table, get_classes_callback, *classes); if (rc) { u32 i; for (i = 0; i < *nclasses; i++) kfree((*classes)[i]); kfree(*classes); } out: return rc; } static int get_permissions_callback(void *k, void *d, void *args) { struct perm_datum *datum = d; char *name = k, **perms = args; u32 value = datum->value - 1; perms[value] = kstrdup(name, GFP_ATOMIC); if (!perms[value]) return -ENOMEM; return 0; } int security_get_permissions(struct selinux_policy *policy, const char *class, char ***perms, u32 *nperms) { struct policydb *policydb; u32 i; int rc; struct class_datum *match; policydb = &policy->policydb; rc = -EINVAL; match = symtab_search(&policydb->p_classes, class); if (!match) { pr_err("SELinux: %s: unrecognized class %s\n", __func__, class); goto out; } rc = -ENOMEM; *nperms = match->permissions.nprim; *perms = kcalloc(*nperms, sizeof(**perms), GFP_ATOMIC); if (!*perms) goto out; if (match->comdatum) { rc = hashtab_map(&match->comdatum->permissions.table, get_permissions_callback, *perms); if (rc) goto err; } rc = hashtab_map(&match->permissions.table, get_permissions_callback, *perms); if (rc) goto err; out: return rc; err: for (i = 0; i < *nperms; i++) kfree((*perms)[i]); kfree(*perms); return rc; } int security_get_reject_unknown(void) { struct selinux_policy *policy; int value; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); value = policy->policydb.reject_unknown; rcu_read_unlock(); return value; } int security_get_allow_unknown(void) { struct selinux_policy *policy; int value; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); value = policy->policydb.allow_unknown; rcu_read_unlock(); return value; } /** * security_policycap_supported - Check for a specific policy capability * @req_cap: capability * * Description: * This function queries the currently loaded policy to see if it supports the * capability specified by @req_cap. Returns true (1) if the capability is * supported, false (0) if it isn't supported. * */ int security_policycap_supported(unsigned int req_cap) { struct selinux_policy *policy; int rc; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); rc = ebitmap_get_bit(&policy->policydb.policycaps, req_cap); rcu_read_unlock(); return rc; } struct selinux_audit_rule { u32 au_seqno; struct context au_ctxt; }; void selinux_audit_rule_free(void *vrule) { struct selinux_audit_rule *rule = vrule; if (rule) { context_destroy(&rule->au_ctxt); kfree(rule); } } int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, gfp_t gfp) { struct selinux_state *state = &selinux_state; struct selinux_policy *policy; struct policydb *policydb; struct selinux_audit_rule *tmprule; struct role_datum *roledatum; struct type_datum *typedatum; struct user_datum *userdatum; struct selinux_audit_rule **rule = (struct selinux_audit_rule **)vrule; int rc = 0; *rule = NULL; if (!selinux_initialized()) return -EOPNOTSUPP; switch (field) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: /* only 'equals' and 'not equals' fit user, role, and type */ if (op != Audit_equal && op != Audit_not_equal) return -EINVAL; break; case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: /* we do not allow a range, indicated by the presence of '-' */ if (strchr(rulestr, '-')) return -EINVAL; break; default: /* only the above fields are valid */ return -EINVAL; } tmprule = kzalloc(sizeof(struct selinux_audit_rule), gfp); if (!tmprule) return -ENOMEM; context_init(&tmprule->au_ctxt); rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; tmprule->au_seqno = policy->latest_granting; switch (field) { case AUDIT_SUBJ_USER: case AUDIT_OBJ_USER: userdatum = symtab_search(&policydb->p_users, rulestr); if (!userdatum) { rc = -EINVAL; goto err; } tmprule->au_ctxt.user = userdatum->value; break; case AUDIT_SUBJ_ROLE: case AUDIT_OBJ_ROLE: roledatum = symtab_search(&policydb->p_roles, rulestr); if (!roledatum) { rc = -EINVAL; goto err; } tmprule->au_ctxt.role = roledatum->value; break; case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_TYPE: typedatum = symtab_search(&policydb->p_types, rulestr); if (!typedatum) { rc = -EINVAL; goto err; } tmprule->au_ctxt.type = typedatum->value; break; case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: rc = mls_from_string(policydb, rulestr, &tmprule->au_ctxt, GFP_ATOMIC); if (rc) goto err; break; } rcu_read_unlock(); *rule = tmprule; return 0; err: rcu_read_unlock(); selinux_audit_rule_free(tmprule); *rule = NULL; return rc; } /* Check to see if the rule contains any selinux fields */ int selinux_audit_rule_known(struct audit_krule *rule) { u32 i; for (i = 0; i < rule->field_count; i++) { struct audit_field *f = &rule->fields[i]; switch (f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: return 1; } } return 0; } int selinux_audit_rule_match(struct lsm_prop *prop, u32 field, u32 op, void *vrule) { struct selinux_state *state = &selinux_state; struct selinux_policy *policy; struct context *ctxt; struct mls_level *level; struct selinux_audit_rule *rule = vrule; int match = 0; if (unlikely(!rule)) { WARN_ONCE(1, "selinux_audit_rule_match: missing rule\n"); return -ENOENT; } if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(state->policy); if (rule->au_seqno < policy->latest_granting) { match = -ESTALE; goto out; } ctxt = sidtab_search(policy->sidtab, prop->selinux.secid); if (unlikely(!ctxt)) { WARN_ONCE(1, "selinux_audit_rule_match: unrecognized SID %d\n", prop->selinux.secid); match = -ENOENT; goto out; } /* a field/op pair that is not caught here will simply fall through without a match */ switch (field) { case AUDIT_SUBJ_USER: case AUDIT_OBJ_USER: switch (op) { case Audit_equal: match = (ctxt->user == rule->au_ctxt.user); break; case Audit_not_equal: match = (ctxt->user != rule->au_ctxt.user); break; } break; case AUDIT_SUBJ_ROLE: case AUDIT_OBJ_ROLE: switch (op) { case Audit_equal: match = (ctxt->role == rule->au_ctxt.role); break; case Audit_not_equal: match = (ctxt->role != rule->au_ctxt.role); break; } break; case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_TYPE: switch (op) { case Audit_equal: match = (ctxt->type == rule->au_ctxt.type); break; case Audit_not_equal: match = (ctxt->type != rule->au_ctxt.type); break; } break; case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: level = ((field == AUDIT_SUBJ_SEN || field == AUDIT_OBJ_LEV_LOW) ? &ctxt->range.level[0] : &ctxt->range.level[1]); switch (op) { case Audit_equal: match = mls_level_eq(&rule->au_ctxt.range.level[0], level); break; case Audit_not_equal: match = !mls_level_eq(&rule->au_ctxt.range.level[0], level); break; case Audit_lt: match = (mls_level_dom(&rule->au_ctxt.range.level[0], level) && !mls_level_eq(&rule->au_ctxt.range.level[0], level)); break; case Audit_le: match = mls_level_dom(&rule->au_ctxt.range.level[0], level); break; case Audit_gt: match = (mls_level_dom(level, &rule->au_ctxt.range.level[0]) && !mls_level_eq(level, &rule->au_ctxt.range.level[0])); break; case Audit_ge: match = mls_level_dom(level, &rule->au_ctxt.range.level[0]); break; } } out: rcu_read_unlock(); return match; } static int aurule_avc_callback(u32 event) { if (event == AVC_CALLBACK_RESET) return audit_update_lsm_rules(); return 0; } static int __init aurule_init(void) { int err; err = avc_add_callback(aurule_avc_callback, AVC_CALLBACK_RESET); if (err) panic("avc_add_callback() failed, error %d\n", err); return err; } __initcall(aurule_init); #ifdef CONFIG_NETLABEL /** * security_netlbl_cache_add - Add an entry to the NetLabel cache * @secattr: the NetLabel packet security attributes * @sid: the SELinux SID * * Description: * Attempt to cache the context in @ctx, which was derived from the packet in * @skb, in the NetLabel subsystem cache. This function assumes @secattr has * already been initialized. * */ static void security_netlbl_cache_add(struct netlbl_lsm_secattr *secattr, u32 sid) { u32 *sid_cache; sid_cache = kmalloc(sizeof(*sid_cache), GFP_ATOMIC); if (sid_cache == NULL) return; secattr->cache = netlbl_secattr_cache_alloc(GFP_ATOMIC); if (secattr->cache == NULL) { kfree(sid_cache); return; } *sid_cache = sid; secattr->cache->free = kfree; secattr->cache->data = sid_cache; secattr->flags |= NETLBL_SECATTR_CACHE; } /** * security_netlbl_secattr_to_sid - Convert a NetLabel secattr to a SELinux SID * @secattr: the NetLabel packet security attributes * @sid: the SELinux SID * * Description: * Convert the given NetLabel security attributes in @secattr into a * SELinux SID. If the @secattr field does not contain a full SELinux * SID/context then use SECINITSID_NETMSG as the foundation. If possible the * 'cache' field of @secattr is set and the CACHE flag is set; this is to * allow the @secattr to be used by NetLabel to cache the secattr to SID * conversion for future lookups. Returns zero on success, negative values on * failure. * */ int security_netlbl_secattr_to_sid(struct netlbl_lsm_secattr *secattr, u32 *sid) { struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; int rc; struct context *ctx; struct context ctx_new; if (!selinux_initialized()) { *sid = SECSID_NULL; return 0; } retry: rc = 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; sidtab = policy->sidtab; if (secattr->flags & NETLBL_SECATTR_CACHE) *sid = *(u32 *)secattr->cache->data; else if (secattr->flags & NETLBL_SECATTR_SECID) *sid = secattr->attr.secid; else if (secattr->flags & NETLBL_SECATTR_MLS_LVL) { rc = -EIDRM; ctx = sidtab_search(sidtab, SECINITSID_NETMSG); if (ctx == NULL) goto out; context_init(&ctx_new); ctx_new.user = ctx->user; ctx_new.role = ctx->role; ctx_new.type = ctx->type; mls_import_netlbl_lvl(policydb, &ctx_new, secattr); if (secattr->flags & NETLBL_SECATTR_MLS_CAT) { rc = mls_import_netlbl_cat(policydb, &ctx_new, secattr); if (rc) goto out; } rc = -EIDRM; if (!mls_context_isvalid(policydb, &ctx_new)) { ebitmap_destroy(&ctx_new.range.level[0].cat); goto out; } rc = sidtab_context_to_sid(sidtab, &ctx_new, sid); ebitmap_destroy(&ctx_new.range.level[0].cat); if (rc == -ESTALE) { rcu_read_unlock(); goto retry; } if (rc) goto out; security_netlbl_cache_add(secattr, *sid); } else *sid = SECSID_NULL; out: rcu_read_unlock(); return rc; } /** * security_netlbl_sid_to_secattr - Convert a SELinux SID to a NetLabel secattr * @sid: the SELinux SID * @secattr: the NetLabel packet security attributes * * Description: * Convert the given SELinux SID in @sid into a NetLabel security attribute. * Returns zero on success, negative values on failure. * */ int security_netlbl_sid_to_secattr(u32 sid, struct netlbl_lsm_secattr *secattr) { struct selinux_policy *policy; struct policydb *policydb; int rc; struct context *ctx; if (!selinux_initialized()) return 0; rcu_read_lock(); policy = rcu_dereference(selinux_state.policy); policydb = &policy->policydb; rc = -ENOENT; ctx = sidtab_search(policy->sidtab, sid); if (ctx == NULL) goto out; rc = -ENOMEM; secattr->domain = kstrdup(sym_name(policydb, SYM_TYPES, ctx->type - 1), GFP_ATOMIC); if (secattr->domain == NULL) goto out; secattr->attr.secid = sid; secattr->flags |= NETLBL_SECATTR_DOMAIN_CPY | NETLBL_SECATTR_SECID; mls_export_netlbl_lvl(policydb, ctx, secattr); rc = mls_export_netlbl_cat(policydb, ctx, secattr); out: rcu_read_unlock(); return rc; } #endif /* CONFIG_NETLABEL */ /** * __security_read_policy - read the policy. * @policy: SELinux policy * @data: binary policy data * @len: length of data in bytes * */ static int __security_read_policy(struct selinux_policy *policy, void *data, size_t *len) { int rc; struct policy_file fp; fp.data = data; fp.len = *len; rc = policydb_write(&policy->policydb, &fp); if (rc) return rc; *len = (unsigned long)fp.data - (unsigned long)data; return 0; } /** * security_read_policy - read the policy. * @data: binary policy data * @len: length of data in bytes * */ int security_read_policy(void **data, size_t *len) { struct selinux_state *state = &selinux_state; struct selinux_policy *policy; policy = rcu_dereference_protected( state->policy, lockdep_is_held(&state->policy_mutex)); if (!policy) return -EINVAL; *len = policy->policydb.len; *data = vmalloc_user(*len); if (!*data) return -ENOMEM; return __security_read_policy(policy, *data, len); } /** * security_read_state_kernel - read the policy. * @data: binary policy data * @len: length of data in bytes * * Allocates kernel memory for reading SELinux policy. * This function is for internal use only and should not * be used for returning data to user space. * * This function must be called with policy_mutex held. */ int security_read_state_kernel(void **data, size_t *len) { int err; struct selinux_state *state = &selinux_state; struct selinux_policy *policy; policy = rcu_dereference_protected( state->policy, lockdep_is_held(&state->policy_mutex)); if (!policy) return -EINVAL; *len = policy->policydb.len; *data = vmalloc(*len); if (!*data) return -ENOMEM; err = __security_read_policy(policy, *data, len); if (err) { vfree(*data); *data = NULL; *len = 0; } return err; } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (C) 2019 Arm Ltd. */ #ifndef __KVM_ARM_HYPERCALLS_H #define __KVM_ARM_HYPERCALLS_H #include <asm/kvm_emulate.h> int kvm_smccc_call_handler(struct kvm_vcpu *vcpu); static inline u32 smccc_get_function(struct kvm_vcpu *vcpu) { return vcpu_get_reg(vcpu, 0); } static inline unsigned long smccc_get_arg1(struct kvm_vcpu *vcpu) { return vcpu_get_reg(vcpu, 1); } static inline unsigned long smccc_get_arg2(struct kvm_vcpu *vcpu) { return vcpu_get_reg(vcpu, 2); } static inline unsigned long smccc_get_arg3(struct kvm_vcpu *vcpu) { return vcpu_get_reg(vcpu, 3); } static inline void smccc_set_retval(struct kvm_vcpu *vcpu, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) { vcpu_set_reg(vcpu, 0, a0); vcpu_set_reg(vcpu, 1, a1); vcpu_set_reg(vcpu, 2, a2); vcpu_set_reg(vcpu, 3, a3); } struct kvm_one_reg; void kvm_arm_init_hypercalls(struct kvm *kvm); void kvm_arm_teardown_hypercalls(struct kvm *kvm); int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); int kvm_vm_smccc_has_attr(struct kvm *kvm, struct kvm_device_attr *attr); int kvm_vm_smccc_set_attr(struct kvm *kvm, struct kvm_device_attr *attr); #endif |
| 69 68 69 69 1134 1134 1131 1136 1130 59 1133 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/irq_work.h> #include <linux/spinlock.h> #include <linux/task_work.h> #include <linux/resume_user_mode.h> static struct callback_head work_exited; /* all we need is ->next == NULL */ #ifdef CONFIG_IRQ_WORK static void task_work_set_notify_irq(struct irq_work *entry) { test_and_set_tsk_thread_flag(current, TIF_NOTIFY_RESUME); } static DEFINE_PER_CPU(struct irq_work, irq_work_NMI_resume) = IRQ_WORK_INIT_HARD(task_work_set_notify_irq); #endif /** * task_work_add - ask the @task to execute @work->func() * @task: the task which should run the callback * @work: the callback to run * @notify: how to notify the targeted task * * Queue @work for task_work_run() below and notify the @task if @notify * is @TWA_RESUME, @TWA_SIGNAL, @TWA_SIGNAL_NO_IPI or @TWA_NMI_CURRENT. * * @TWA_SIGNAL works like signals, in that the it will interrupt the targeted * task and run the task_work, regardless of whether the task is currently * running in the kernel or userspace. * @TWA_SIGNAL_NO_IPI works like @TWA_SIGNAL, except it doesn't send a * reschedule IPI to force the targeted task to reschedule and run task_work. * This can be advantageous if there's no strict requirement that the * task_work be run as soon as possible, just whenever the task enters the * kernel anyway. * @TWA_RESUME work is run only when the task exits the kernel and returns to * user mode, or before entering guest mode. * @TWA_NMI_CURRENT works like @TWA_RESUME, except it can only be used for the * current @task and if the current context is NMI. * * Fails if the @task is exiting/exited and thus it can't process this @work. * Otherwise @work->func() will be called when the @task goes through one of * the aforementioned transitions, or exits. * * If the targeted task is exiting, then an error is returned and the work item * is not queued. It's up to the caller to arrange for an alternative mechanism * in that case. * * Note: there is no ordering guarantee on works queued here. The task_work * list is LIFO. * * RETURNS: * 0 if succeeds or -ESRCH. */ int task_work_add(struct task_struct *task, struct callback_head *work, enum task_work_notify_mode notify) { struct callback_head *head; if (notify == TWA_NMI_CURRENT) { if (WARN_ON_ONCE(task != current)) return -EINVAL; if (!IS_ENABLED(CONFIG_IRQ_WORK)) return -EINVAL; } else { kasan_record_aux_stack(work); } head = READ_ONCE(task->task_works); do { if (unlikely(head == &work_exited)) return -ESRCH; work->next = head; } while (!try_cmpxchg(&task->task_works, &head, work)); switch (notify) { case TWA_NONE: break; case TWA_RESUME: set_notify_resume(task); break; case TWA_SIGNAL: set_notify_signal(task); break; case TWA_SIGNAL_NO_IPI: __set_notify_signal(task); break; #ifdef CONFIG_IRQ_WORK case TWA_NMI_CURRENT: irq_work_queue(this_cpu_ptr(&irq_work_NMI_resume)); break; #endif default: WARN_ON_ONCE(1); break; } return 0; } /** * task_work_cancel_match - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @match: match function to call * @data: data to be passed in to match function * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data) { struct callback_head **pprev = &task->task_works; struct callback_head *work; unsigned long flags; if (likely(!task_work_pending(task))) return NULL; /* * If cmpxchg() fails we continue without updating pprev. * Either we raced with task_work_add() which added the * new entry before this work, we will find it again. Or * we raced with task_work_run(), *pprev == NULL/exited. */ raw_spin_lock_irqsave(&task->pi_lock, flags); work = READ_ONCE(*pprev); while (work) { if (!match(work, data)) { pprev = &work->next; work = READ_ONCE(*pprev); } else if (try_cmpxchg(pprev, &work, work->next)) break; } raw_spin_unlock_irqrestore(&task->pi_lock, flags); return work; } static bool task_work_func_match(struct callback_head *cb, void *data) { return cb->func == data; } /** * task_work_cancel_func - cancel a pending work matching a function added by task_work_add() * @task: the task which should execute the func's work * @func: identifies the func to match with a work to remove * * Find the last queued pending work with ->func == @func and remove * it from queue. * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel_func(struct task_struct *task, task_work_func_t func) { return task_work_cancel_match(task, task_work_func_match, func); } static bool task_work_match(struct callback_head *cb, void *data) { return cb == data; } /** * task_work_cancel - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @cb: the callback to remove if queued * * Remove a callback from a task's queue if queued. * * RETURNS: * True if the callback was queued and got cancelled, false otherwise. */ bool task_work_cancel(struct task_struct *task, struct callback_head *cb) { struct callback_head *ret; ret = task_work_cancel_match(task, task_work_match, cb); return ret == cb; } /** * task_work_run - execute the works added by task_work_add() * * Flush the pending works. Should be used by the core kernel code. * Called before the task returns to the user-mode or stops, or when * it exits. In the latter case task_work_add() can no longer add the * new work after task_work_run() returns. */ void task_work_run(void) { struct task_struct *task = current; struct callback_head *work, *head, *next; for (;;) { /* * work->func() can do task_work_add(), do not set * work_exited unless the list is empty. */ work = READ_ONCE(task->task_works); do { head = NULL; if (!work) { if (task->flags & PF_EXITING) head = &work_exited; else break; } } while (!try_cmpxchg(&task->task_works, &work, head)); if (!work) break; /* * Synchronize with task_work_cancel_match(). It can not remove * the first entry == work, cmpxchg(task_works) must fail. * But it can remove another entry from the ->next list. */ raw_spin_lock_irq(&task->pi_lock); raw_spin_unlock_irq(&task->pi_lock); do { next = work->next; work->func(work); work = next; cond_resched(); } while (work); } } |
| 3 5 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILEATTR_H #define _LINUX_FILEATTR_H /* Flags shared betwen flags/xflags */ #define FS_COMMON_FL \ (FS_SYNC_FL | FS_IMMUTABLE_FL | FS_APPEND_FL | \ FS_NODUMP_FL | FS_NOATIME_FL | FS_DAX_FL | \ FS_PROJINHERIT_FL) #define FS_XFLAG_COMMON \ (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND | \ FS_XFLAG_NODUMP | FS_XFLAG_NOATIME | FS_XFLAG_DAX | \ FS_XFLAG_PROJINHERIT) /* Read-only inode flags */ #define FS_XFLAG_RDONLY_MASK \ (FS_XFLAG_PREALLOC | FS_XFLAG_HASATTR) /* Flags to indicate valid value of fsx_ fields */ #define FS_XFLAG_VALUES_MASK \ (FS_XFLAG_EXTSIZE | FS_XFLAG_COWEXTSIZE) /* Flags for directories */ #define FS_XFLAG_DIRONLY_MASK \ (FS_XFLAG_RTINHERIT | FS_XFLAG_NOSYMLINKS | FS_XFLAG_EXTSZINHERIT) /* Misc settable flags */ #define FS_XFLAG_MISC_MASK \ (FS_XFLAG_REALTIME | FS_XFLAG_NODEFRAG | FS_XFLAG_FILESTREAM) #define FS_XFLAGS_MASK \ (FS_XFLAG_COMMON | FS_XFLAG_RDONLY_MASK | FS_XFLAG_VALUES_MASK | \ FS_XFLAG_DIRONLY_MASK | FS_XFLAG_MISC_MASK) /* * Merged interface for miscellaneous file attributes. 'flags' originates from * ext* and 'fsx_flags' from xfs. There's some overlap between the two, which * is handled by the VFS helpers, so filesystems are free to implement just one * or both of these sub-interfaces. */ struct file_kattr { u32 flags; /* flags (FS_IOC_GETFLAGS/FS_IOC_SETFLAGS) */ /* struct fsxattr: */ u32 fsx_xflags; /* xflags field value (get/set) */ u32 fsx_extsize; /* extsize field value (get/set)*/ u32 fsx_nextents; /* nextents field value (get) */ u32 fsx_projid; /* project identifier (get/set) */ u32 fsx_cowextsize; /* CoW extsize field value (get/set)*/ /* selectors: */ bool flags_valid:1; bool fsx_valid:1; }; int copy_fsxattr_to_user(const struct file_kattr *fa, struct fsxattr __user *ufa); void fileattr_fill_xflags(struct file_kattr *fa, u32 xflags); void fileattr_fill_flags(struct file_kattr *fa, u32 flags); /** * fileattr_has_fsx - check for extended flags/attributes * @fa: fileattr pointer * * Return: true if any attributes are present that are not represented in * ->flags. */ static inline bool fileattr_has_fsx(const struct file_kattr *fa) { return fa->fsx_valid && ((fa->fsx_xflags & ~FS_XFLAG_COMMON) || fa->fsx_extsize != 0 || fa->fsx_projid != 0 || fa->fsx_cowextsize != 0); } int vfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa); int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct file_kattr *fa); int ioctl_getflags(struct file *file, unsigned int __user *argp); int ioctl_setflags(struct file *file, unsigned int __user *argp); int ioctl_fsgetxattr(struct file *file, void __user *argp); int ioctl_fssetxattr(struct file *file, void __user *argp); #endif /* _LINUX_FILEATTR_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #ifndef RXE_VERBS_H #define RXE_VERBS_H #include <linux/interrupt.h> #include <linux/workqueue.h> #include "rxe_pool.h" #include "rxe_task.h" #include "rxe_hw_counters.h" static inline int pkey_match(u16 key1, u16 key2) { return (((key1 & 0x7fff) != 0) && ((key1 & 0x7fff) == (key2 & 0x7fff)) && ((key1 & 0x8000) || (key2 & 0x8000))) ? 1 : 0; } /* Return >0 if psn_a > psn_b * 0 if psn_a == psn_b * <0 if psn_a < psn_b */ static inline int psn_compare(u32 psn_a, u32 psn_b) { s32 diff; diff = (psn_a - psn_b) << 8; return diff; } struct rxe_ucontext { struct ib_ucontext ibuc; struct rxe_pool_elem elem; }; struct rxe_pd { struct ib_pd ibpd; struct rxe_pool_elem elem; }; struct rxe_ah { struct ib_ah ibah; struct rxe_pool_elem elem; struct rxe_av av; bool is_user; int ah_num; }; struct rxe_cqe { union { struct ib_wc ibwc; struct ib_uverbs_wc uibwc; }; }; struct rxe_cq { struct ib_cq ibcq; struct rxe_pool_elem elem; struct rxe_queue *queue; spinlock_t cq_lock; u8 notify; bool is_user; atomic_t num_wq; }; enum wqe_state { wqe_state_posted, wqe_state_processing, wqe_state_pending, wqe_state_done, wqe_state_error, }; struct rxe_sq { int max_wr; int max_sge; int max_inline; spinlock_t sq_lock; /* guard queue */ struct rxe_queue *queue; }; struct rxe_rq { int max_wr; int max_sge; spinlock_t producer_lock; /* guard queue producer */ spinlock_t consumer_lock; /* guard queue consumer */ struct rxe_queue *queue; }; struct rxe_srq { struct ib_srq ibsrq; struct rxe_pool_elem elem; struct rxe_pd *pd; struct rxe_rq rq; u32 srq_num; int limit; int error; }; struct rxe_req_info { int wqe_index; u32 psn; int opcode; atomic_t rd_atomic; int wait_fence; int need_rd_atomic; int wait_psn; int need_retry; int wait_for_rnr_timer; int noack_pkts; int again; }; struct rxe_comp_info { u32 psn; int opcode; int timeout; int timeout_retry; int started_retry; u32 retry_cnt; u32 rnr_retry; }; /* responder states */ enum resp_states { RESPST_NONE, RESPST_GET_REQ, RESPST_CHK_PSN, RESPST_CHK_OP_SEQ, RESPST_CHK_OP_VALID, RESPST_CHK_RESOURCE, RESPST_CHK_LENGTH, RESPST_CHK_RKEY, RESPST_EXECUTE, RESPST_READ_REPLY, RESPST_ATOMIC_REPLY, RESPST_ATOMIC_WRITE_REPLY, RESPST_PROCESS_FLUSH, RESPST_COMPLETE, RESPST_ACKNOWLEDGE, RESPST_CLEANUP, RESPST_DUPLICATE_REQUEST, RESPST_ERR_MALFORMED_WQE, RESPST_ERR_UNSUPPORTED_OPCODE, RESPST_ERR_MISALIGNED_ATOMIC, RESPST_ERR_PSN_OUT_OF_SEQ, RESPST_ERR_MISSING_OPCODE_FIRST, RESPST_ERR_MISSING_OPCODE_LAST_C, RESPST_ERR_MISSING_OPCODE_LAST_D1E, RESPST_ERR_TOO_MANY_RDMA_ATM_REQ, RESPST_ERR_RNR, RESPST_ERR_RKEY_VIOLATION, RESPST_ERR_INVALIDATE_RKEY, RESPST_ERR_LENGTH, RESPST_ERR_CQ_OVERFLOW, RESPST_ERROR, RESPST_DONE, RESPST_EXIT, }; enum rdatm_res_state { rdatm_res_state_next, rdatm_res_state_new, rdatm_res_state_replay, }; struct resp_res { int type; int replay; u32 first_psn; u32 last_psn; u32 cur_psn; enum rdatm_res_state state; union { struct { u64 orig_val; } atomic; struct { u64 va_org; u32 rkey; u32 length; u64 va; u32 resid; } read; struct { u32 length; u64 va; u8 type; u8 level; } flush; }; }; struct rxe_resp_info { u32 msn; u32 psn; u32 ack_psn; int opcode; int drop_msg; int goto_error; int sent_psn_nak; enum ib_wc_status status; u8 aeth_syndrome; /* Receive only */ struct rxe_recv_wqe *wqe; /* RDMA read / atomic only */ u64 va; u64 offset; struct rxe_mr *mr; u32 resid; u32 rkey; u32 length; /* SRQ only */ struct { struct rxe_recv_wqe wqe; struct ib_sge sge[RXE_MAX_SGE]; } srq_wqe; /* Responder resources. It's a circular list where the oldest * resource is dropped first. */ struct resp_res *resources; unsigned int res_head; unsigned int res_tail; struct resp_res *res; }; struct rxe_qp { struct ib_qp ibqp; struct rxe_pool_elem elem; struct ib_qp_attr attr; unsigned int valid; unsigned int mtu; bool is_user; struct rxe_pd *pd; struct rxe_srq *srq; struct rxe_cq *scq; struct rxe_cq *rcq; enum ib_sig_type sq_sig_type; struct rxe_sq sq; struct rxe_rq rq; struct socket *sk; u32 dst_cookie; u16 src_port; struct rxe_av pri_av; struct rxe_av alt_av; atomic_t mcg_num; struct sk_buff_head req_pkts; struct sk_buff_head resp_pkts; struct rxe_task send_task; struct rxe_task recv_task; struct rxe_req_info req; struct rxe_comp_info comp; struct rxe_resp_info resp; atomic_t ssn; atomic_t skb_out; int need_req_skb; /* Timer for retranmitting packet when ACKs have been lost. RC * only. The requester sets it when it is not already * started. The responder resets it whenever an ack is * received. */ struct timer_list retrans_timer; u64 qp_timeout_jiffies; /* Timer for handling RNR NAKS. */ struct timer_list rnr_nak_timer; spinlock_t state_lock; /* guard requester and completer */ struct execute_work cleanup_work; }; enum { RXE_ACCESS_REMOTE = IB_ACCESS_REMOTE_READ | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC, RXE_ACCESS_SUPPORTED_MR = RXE_ACCESS_REMOTE | IB_ACCESS_LOCAL_WRITE | IB_ACCESS_MW_BIND | IB_ACCESS_ON_DEMAND | IB_ACCESS_FLUSH_GLOBAL | IB_ACCESS_FLUSH_PERSISTENT | IB_ACCESS_OPTIONAL, RXE_ACCESS_SUPPORTED_QP = RXE_ACCESS_SUPPORTED_MR, RXE_ACCESS_SUPPORTED_MW = RXE_ACCESS_SUPPORTED_MR | IB_ZERO_BASED, }; enum rxe_mr_state { RXE_MR_STATE_INVALID, RXE_MR_STATE_FREE, RXE_MR_STATE_VALID, }; enum rxe_mr_copy_dir { RXE_TO_MR_OBJ, RXE_FROM_MR_OBJ, }; enum rxe_mr_lookup_type { RXE_LOOKUP_LOCAL, RXE_LOOKUP_REMOTE, }; enum rxe_rereg { RXE_MR_REREG_SUPPORTED = IB_MR_REREG_PD | IB_MR_REREG_ACCESS, }; static inline int rkey_is_mw(u32 rkey) { u32 index = rkey >> 8; return (index >= RXE_MIN_MW_INDEX) && (index <= RXE_MAX_MW_INDEX); } struct rxe_mr { struct rxe_pool_elem elem; struct ib_mr ibmr; struct ib_umem *umem; u32 lkey; u32 rkey; enum rxe_mr_state state; int access; atomic_t num_mw; unsigned int page_offset; unsigned int page_shift; u64 page_mask; u32 num_buf; u32 nbuf; struct xarray page_list; }; static inline unsigned int mr_page_size(struct rxe_mr *mr) { return mr ? mr->ibmr.page_size : PAGE_SIZE; } enum rxe_mw_state { RXE_MW_STATE_INVALID = RXE_MR_STATE_INVALID, RXE_MW_STATE_FREE = RXE_MR_STATE_FREE, RXE_MW_STATE_VALID = RXE_MR_STATE_VALID, }; struct rxe_mw { struct ib_mw ibmw; struct rxe_pool_elem elem; spinlock_t lock; enum rxe_mw_state state; struct rxe_qp *qp; /* Type 2 only */ struct rxe_mr *mr; u32 rkey; int access; u64 addr; u64 length; }; struct rxe_mcg { struct rb_node node; struct kref ref_cnt; struct rxe_dev *rxe; struct list_head qp_list; union ib_gid mgid; atomic_t qp_num; u32 qkey; u16 pkey; }; struct rxe_mca { struct list_head qp_list; struct rxe_qp *qp; }; struct rxe_port { struct ib_port_attr attr; __be64 port_guid; __be64 subnet_prefix; spinlock_t port_lock; /* guard port */ unsigned int mtu_cap; /* special QPs */ u32 qp_gsi_index; }; #define RXE_PORT 1 struct rxe_dev { struct ib_device ib_dev; struct ib_device_attr attr; int max_ucontext; int max_inline_data; struct mutex usdev_lock; char raw_gid[ETH_ALEN]; struct rxe_pool uc_pool; struct rxe_pool pd_pool; struct rxe_pool ah_pool; struct rxe_pool srq_pool; struct rxe_pool qp_pool; struct rxe_pool cq_pool; struct rxe_pool mr_pool; struct rxe_pool mw_pool; /* multicast support */ spinlock_t mcg_lock; struct rb_root mcg_tree; atomic_t mcg_num; atomic_t mcg_attach; spinlock_t pending_lock; /* guard pending_mmaps */ struct list_head pending_mmaps; spinlock_t mmap_offset_lock; /* guard mmap_offset */ u64 mmap_offset; atomic64_t stats_counters[RXE_NUM_OF_COUNTERS]; struct rxe_port port; }; static inline struct net_device *rxe_ib_device_get_netdev(struct ib_device *dev) { return ib_device_get_netdev(dev, RXE_PORT); } static inline void rxe_counter_inc(struct rxe_dev *rxe, enum rxe_counters index) { atomic64_inc(&rxe->stats_counters[index]); } static inline struct rxe_dev *to_rdev(struct ib_device *dev) { return dev ? container_of(dev, struct rxe_dev, ib_dev) : NULL; } static inline struct rxe_ucontext *to_ruc(struct ib_ucontext *uc) { return uc ? container_of(uc, struct rxe_ucontext, ibuc) : NULL; } static inline struct rxe_pd *to_rpd(struct ib_pd *pd) { return pd ? container_of(pd, struct rxe_pd, ibpd) : NULL; } static inline struct rxe_ah *to_rah(struct ib_ah *ah) { return ah ? container_of(ah, struct rxe_ah, ibah) : NULL; } static inline struct rxe_srq *to_rsrq(struct ib_srq *srq) { return srq ? container_of(srq, struct rxe_srq, ibsrq) : NULL; } static inline struct rxe_qp *to_rqp(struct ib_qp *qp) { return qp ? container_of(qp, struct rxe_qp, ibqp) : NULL; } static inline struct rxe_cq *to_rcq(struct ib_cq *cq) { return cq ? container_of(cq, struct rxe_cq, ibcq) : NULL; } static inline struct rxe_mr *to_rmr(struct ib_mr *mr) { return mr ? container_of(mr, struct rxe_mr, ibmr) : NULL; } static inline struct rxe_mw *to_rmw(struct ib_mw *mw) { return mw ? container_of(mw, struct rxe_mw, ibmw) : NULL; } static inline struct rxe_pd *rxe_ah_pd(struct rxe_ah *ah) { return to_rpd(ah->ibah.pd); } static inline struct rxe_pd *mr_pd(struct rxe_mr *mr) { return to_rpd(mr->ibmr.pd); } static inline struct rxe_pd *rxe_mw_pd(struct rxe_mw *mw) { return to_rpd(mw->ibmw.pd); } int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name, struct net_device *ndev); #endif /* RXE_VERBS_H */ |
| 323 140 179 179 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 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; } |
| 72 1 71 1 71 3 1 3 68 41 41 41 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2016 - Linaro and Columbia University * Author: Jintack Lim <jintack.lim@linaro.org> */ #include <linux/kvm.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_nested.h> #include "hyp/include/hyp/adjust_pc.h" #include "trace.h" enum trap_behaviour { BEHAVE_HANDLE_LOCALLY = 0, BEHAVE_FORWARD_READ = BIT(0), BEHAVE_FORWARD_WRITE = BIT(1), BEHAVE_FORWARD_RW = BEHAVE_FORWARD_READ | BEHAVE_FORWARD_WRITE, /* Traps that take effect in Host EL0, this is rare! */ BEHAVE_FORWARD_IN_HOST_EL0 = BIT(2), }; struct trap_bits { const enum vcpu_sysreg index; const enum trap_behaviour behaviour; const u64 value; const u64 mask; }; /* Coarse Grained Trap definitions */ enum cgt_group_id { /* Indicates no coarse trap control */ __RESERVED__, /* * The first batch of IDs denote coarse trapping that are used * on their own instead of being part of a combination of * trap controls. */ CGT_HCR_TID1, CGT_HCR_TID2, CGT_HCR_TID3, CGT_HCR_IMO, CGT_HCR_FMO, CGT_HCR_TIDCP, CGT_HCR_TACR, CGT_HCR_TSW, CGT_HCR_TPC, CGT_HCR_TPU, CGT_HCR_TTLB, CGT_HCR_TVM, CGT_HCR_TDZ, CGT_HCR_TRVM, CGT_HCR_TLOR, CGT_HCR_TERR, CGT_HCR_APK, CGT_HCR_NV, CGT_HCR_NV_nNV2, CGT_HCR_NV1_nNV2, CGT_HCR_AT, CGT_HCR_nFIEN, CGT_HCR_TID4, CGT_HCR_TICAB, CGT_HCR_TOCU, CGT_HCR_ENSCXT, CGT_HCR_TTLBIS, CGT_HCR_TTLBOS, CGT_MDCR_TPMCR, CGT_MDCR_TPM, CGT_MDCR_TDE, CGT_MDCR_TDA, CGT_MDCR_TDOSA, CGT_MDCR_TDRA, CGT_MDCR_E2PB, CGT_MDCR_TPMS, CGT_MDCR_TTRF, CGT_MDCR_E2TB, CGT_MDCR_TDCC, CGT_CPTR_TAM, CGT_CPTR_TCPAC, CGT_HCRX_EnFPM, CGT_HCRX_TCR2En, CGT_HCRX_SCTLR2En, CGT_CNTHCTL_EL1TVT, CGT_CNTHCTL_EL1TVCT, CGT_ICH_HCR_TC, CGT_ICH_HCR_TALL0, CGT_ICH_HCR_TALL1, CGT_ICH_HCR_TDIR, /* * Anything after this point is a combination of coarse trap * controls, which must all be evaluated to decide what to do. */ __MULTIPLE_CONTROL_BITS__, CGT_HCR_IMO_FMO_ICH_HCR_TC = __MULTIPLE_CONTROL_BITS__, CGT_HCR_TID2_TID4, CGT_HCR_TTLB_TTLBIS, CGT_HCR_TTLB_TTLBOS, CGT_HCR_TVM_TRVM, CGT_HCR_TVM_TRVM_HCRX_TCR2En, CGT_HCR_TVM_TRVM_HCRX_SCTLR2En, CGT_HCR_TPU_TICAB, CGT_HCR_TPU_TOCU, CGT_HCR_NV1_nNV2_ENSCXT, CGT_MDCR_TPM_TPMCR, CGT_MDCR_TPM_HPMN, CGT_MDCR_TDE_TDA, CGT_MDCR_TDE_TDOSA, CGT_MDCR_TDE_TDRA, CGT_MDCR_TDCC_TDE_TDA, CGT_ICH_HCR_TC_TDIR, /* * Anything after this point requires a callback evaluating a * complex trap condition. Ugly stuff. */ __COMPLEX_CONDITIONS__, CGT_CNTHCTL_EL1PCTEN = __COMPLEX_CONDITIONS__, CGT_CNTHCTL_EL1PTEN, CGT_CNTHCTL_EL1NVPCT, CGT_CNTHCTL_EL1NVVCT, CGT_CPTR_TTA, CGT_MDCR_HPMN, /* Must be last */ __NR_CGT_GROUP_IDS__ }; static const struct trap_bits coarse_trap_bits[] = { [CGT_HCR_TID1] = { .index = HCR_EL2, .value = HCR_TID1, .mask = HCR_TID1, .behaviour = BEHAVE_FORWARD_READ, }, [CGT_HCR_TID2] = { .index = HCR_EL2, .value = HCR_TID2, .mask = HCR_TID2, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TID3] = { .index = HCR_EL2, .value = HCR_TID3, .mask = HCR_TID3, .behaviour = BEHAVE_FORWARD_READ, }, [CGT_HCR_IMO] = { .index = HCR_EL2, .value = HCR_IMO, .mask = HCR_IMO, .behaviour = BEHAVE_FORWARD_WRITE, }, [CGT_HCR_FMO] = { .index = HCR_EL2, .value = HCR_FMO, .mask = HCR_FMO, .behaviour = BEHAVE_FORWARD_WRITE, }, [CGT_HCR_TIDCP] = { .index = HCR_EL2, .value = HCR_TIDCP, .mask = HCR_TIDCP, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TACR] = { .index = HCR_EL2, .value = HCR_TACR, .mask = HCR_TACR, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TSW] = { .index = HCR_EL2, .value = HCR_TSW, .mask = HCR_TSW, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TPC] = { /* Also called TCPC when FEAT_DPB is implemented */ .index = HCR_EL2, .value = HCR_TPC, .mask = HCR_TPC, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TPU] = { .index = HCR_EL2, .value = HCR_TPU, .mask = HCR_TPU, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TTLB] = { .index = HCR_EL2, .value = HCR_TTLB, .mask = HCR_TTLB, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TVM] = { .index = HCR_EL2, .value = HCR_TVM, .mask = HCR_TVM, .behaviour = BEHAVE_FORWARD_WRITE, }, [CGT_HCR_TDZ] = { .index = HCR_EL2, .value = HCR_TDZ, .mask = HCR_TDZ, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TRVM] = { .index = HCR_EL2, .value = HCR_TRVM, .mask = HCR_TRVM, .behaviour = BEHAVE_FORWARD_READ, }, [CGT_HCR_TLOR] = { .index = HCR_EL2, .value = HCR_TLOR, .mask = HCR_TLOR, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TERR] = { .index = HCR_EL2, .value = HCR_TERR, .mask = HCR_TERR, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_APK] = { .index = HCR_EL2, .value = 0, .mask = HCR_APK, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_NV] = { .index = HCR_EL2, .value = HCR_NV, .mask = HCR_NV, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_NV_nNV2] = { .index = HCR_EL2, .value = HCR_NV, .mask = HCR_NV | HCR_NV2, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_NV1_nNV2] = { .index = HCR_EL2, .value = HCR_NV | HCR_NV1, .mask = HCR_NV | HCR_NV1 | HCR_NV2, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_AT] = { .index = HCR_EL2, .value = HCR_AT, .mask = HCR_AT, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_nFIEN] = { .index = HCR_EL2, .value = 0, .mask = HCR_FIEN, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TID4] = { .index = HCR_EL2, .value = HCR_TID4, .mask = HCR_TID4, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TICAB] = { .index = HCR_EL2, .value = HCR_TICAB, .mask = HCR_TICAB, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TOCU] = { .index = HCR_EL2, .value = HCR_TOCU, .mask = HCR_TOCU, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_ENSCXT] = { .index = HCR_EL2, .value = 0, .mask = HCR_ENSCXT, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TTLBIS] = { .index = HCR_EL2, .value = HCR_TTLBIS, .mask = HCR_TTLBIS, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCR_TTLBOS] = { .index = HCR_EL2, .value = HCR_TTLBOS, .mask = HCR_TTLBOS, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TPMCR] = { .index = MDCR_EL2, .value = MDCR_EL2_TPMCR, .mask = MDCR_EL2_TPMCR, .behaviour = BEHAVE_FORWARD_RW | BEHAVE_FORWARD_IN_HOST_EL0, }, [CGT_MDCR_TPM] = { .index = MDCR_EL2, .value = MDCR_EL2_TPM, .mask = MDCR_EL2_TPM, .behaviour = BEHAVE_FORWARD_RW | BEHAVE_FORWARD_IN_HOST_EL0, }, [CGT_MDCR_TDE] = { .index = MDCR_EL2, .value = MDCR_EL2_TDE, .mask = MDCR_EL2_TDE, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TDA] = { .index = MDCR_EL2, .value = MDCR_EL2_TDA, .mask = MDCR_EL2_TDA, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TDOSA] = { .index = MDCR_EL2, .value = MDCR_EL2_TDOSA, .mask = MDCR_EL2_TDOSA, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TDRA] = { .index = MDCR_EL2, .value = MDCR_EL2_TDRA, .mask = MDCR_EL2_TDRA, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_E2PB] = { .index = MDCR_EL2, .value = 0, .mask = BIT(MDCR_EL2_E2PB_SHIFT), .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TPMS] = { .index = MDCR_EL2, .value = MDCR_EL2_TPMS, .mask = MDCR_EL2_TPMS, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TTRF] = { .index = MDCR_EL2, .value = MDCR_EL2_TTRF, .mask = MDCR_EL2_TTRF, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_E2TB] = { .index = MDCR_EL2, .value = 0, .mask = BIT(MDCR_EL2_E2TB_SHIFT), .behaviour = BEHAVE_FORWARD_RW, }, [CGT_MDCR_TDCC] = { .index = MDCR_EL2, .value = MDCR_EL2_TDCC, .mask = MDCR_EL2_TDCC, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_CPTR_TAM] = { .index = CPTR_EL2, .value = CPTR_EL2_TAM, .mask = CPTR_EL2_TAM, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_CPTR_TCPAC] = { .index = CPTR_EL2, .value = CPTR_EL2_TCPAC, .mask = CPTR_EL2_TCPAC, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCRX_EnFPM] = { .index = HCRX_EL2, .value = 0, .mask = HCRX_EL2_EnFPM, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCRX_TCR2En] = { .index = HCRX_EL2, .value = 0, .mask = HCRX_EL2_TCR2En, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_HCRX_SCTLR2En] = { .index = HCRX_EL2, .value = 0, .mask = HCRX_EL2_SCTLR2En, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_CNTHCTL_EL1TVT] = { .index = CNTHCTL_EL2, .value = CNTHCTL_EL1TVT, .mask = CNTHCTL_EL1TVT, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_CNTHCTL_EL1TVCT] = { .index = CNTHCTL_EL2, .value = CNTHCTL_EL1TVCT, .mask = CNTHCTL_EL1TVCT, .behaviour = BEHAVE_FORWARD_READ, }, [CGT_ICH_HCR_TC] = { .index = ICH_HCR_EL2, .value = ICH_HCR_EL2_TC, .mask = ICH_HCR_EL2_TC, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_ICH_HCR_TALL0] = { .index = ICH_HCR_EL2, .value = ICH_HCR_EL2_TALL0, .mask = ICH_HCR_EL2_TALL0, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_ICH_HCR_TALL1] = { .index = ICH_HCR_EL2, .value = ICH_HCR_EL2_TALL1, .mask = ICH_HCR_EL2_TALL1, .behaviour = BEHAVE_FORWARD_RW, }, [CGT_ICH_HCR_TDIR] = { .index = ICH_HCR_EL2, .value = ICH_HCR_EL2_TDIR, .mask = ICH_HCR_EL2_TDIR, .behaviour = BEHAVE_FORWARD_RW, }, }; #define MCB(id, ...) \ [id - __MULTIPLE_CONTROL_BITS__] = \ (const enum cgt_group_id[]){ \ __VA_ARGS__, __RESERVED__ \ } static const enum cgt_group_id *coarse_control_combo[] = { MCB(CGT_HCR_TID2_TID4, CGT_HCR_TID2, CGT_HCR_TID4), MCB(CGT_HCR_TTLB_TTLBIS, CGT_HCR_TTLB, CGT_HCR_TTLBIS), MCB(CGT_HCR_TTLB_TTLBOS, CGT_HCR_TTLB, CGT_HCR_TTLBOS), MCB(CGT_HCR_TVM_TRVM, CGT_HCR_TVM, CGT_HCR_TRVM), MCB(CGT_HCR_TVM_TRVM_HCRX_TCR2En, CGT_HCR_TVM, CGT_HCR_TRVM, CGT_HCRX_TCR2En), MCB(CGT_HCR_TVM_TRVM_HCRX_SCTLR2En, CGT_HCR_TVM, CGT_HCR_TRVM, CGT_HCRX_SCTLR2En), MCB(CGT_HCR_TPU_TICAB, CGT_HCR_TPU, CGT_HCR_TICAB), MCB(CGT_HCR_TPU_TOCU, CGT_HCR_TPU, CGT_HCR_TOCU), MCB(CGT_HCR_NV1_nNV2_ENSCXT, CGT_HCR_NV1_nNV2, CGT_HCR_ENSCXT), MCB(CGT_MDCR_TPM_TPMCR, CGT_MDCR_TPM, CGT_MDCR_TPMCR), MCB(CGT_MDCR_TPM_HPMN, CGT_MDCR_TPM, CGT_MDCR_HPMN), MCB(CGT_MDCR_TDE_TDA, CGT_MDCR_TDE, CGT_MDCR_TDA), MCB(CGT_MDCR_TDE_TDOSA, CGT_MDCR_TDE, CGT_MDCR_TDOSA), MCB(CGT_MDCR_TDE_TDRA, CGT_MDCR_TDE, CGT_MDCR_TDRA), MCB(CGT_MDCR_TDCC_TDE_TDA, CGT_MDCR_TDCC, CGT_MDCR_TDE, CGT_MDCR_TDA), MCB(CGT_HCR_IMO_FMO_ICH_HCR_TC, CGT_HCR_IMO, CGT_HCR_FMO, CGT_ICH_HCR_TC), MCB(CGT_ICH_HCR_TC_TDIR, CGT_ICH_HCR_TC, CGT_ICH_HCR_TDIR), }; typedef enum trap_behaviour (*complex_condition_check)(struct kvm_vcpu *); /* * Warning, maximum confusion ahead. * * When E2H=0, CNTHCTL_EL2[1:0] are defined as EL1PCEN:EL1PCTEN * When E2H=1, CNTHCTL_EL2[11:10] are defined as EL1PTEN:EL1PCTEN * * Note the single letter difference? Yet, the bits have the same * function despite a different layout and a different name. * * We don't try to reconcile this mess. We just use the E2H=0 bits * to generate something that is in the E2H=1 format, and live with * it. You're welcome. */ static u64 get_sanitized_cnthctl(struct kvm_vcpu *vcpu) { u64 val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2); if (!vcpu_el2_e2h_is_set(vcpu)) val = (val & (CNTHCTL_EL1PCEN | CNTHCTL_EL1PCTEN)) << 10; return val & ((CNTHCTL_EL1PCEN | CNTHCTL_EL1PCTEN) << 10); } static enum trap_behaviour check_cnthctl_el1pcten(struct kvm_vcpu *vcpu) { if (get_sanitized_cnthctl(vcpu) & (CNTHCTL_EL1PCTEN << 10)) return BEHAVE_HANDLE_LOCALLY; return BEHAVE_FORWARD_RW; } static enum trap_behaviour check_cnthctl_el1pten(struct kvm_vcpu *vcpu) { if (get_sanitized_cnthctl(vcpu) & (CNTHCTL_EL1PCEN << 10)) return BEHAVE_HANDLE_LOCALLY; return BEHAVE_FORWARD_RW; } static bool is_nested_nv2_guest(struct kvm_vcpu *vcpu) { u64 val; val = __vcpu_sys_reg(vcpu, HCR_EL2); return ((val & (HCR_E2H | HCR_TGE | HCR_NV2 | HCR_NV1 | HCR_NV)) == (HCR_E2H | HCR_NV2 | HCR_NV)); } static enum trap_behaviour check_cnthctl_el1nvpct(struct kvm_vcpu *vcpu) { if (!is_nested_nv2_guest(vcpu) || !(__vcpu_sys_reg(vcpu, CNTHCTL_EL2) & CNTHCTL_EL1NVPCT)) return BEHAVE_HANDLE_LOCALLY; return BEHAVE_FORWARD_RW; } static enum trap_behaviour check_cnthctl_el1nvvct(struct kvm_vcpu *vcpu) { if (!is_nested_nv2_guest(vcpu) || !(__vcpu_sys_reg(vcpu, CNTHCTL_EL2) & CNTHCTL_EL1NVVCT)) return BEHAVE_HANDLE_LOCALLY; return BEHAVE_FORWARD_RW; } static enum trap_behaviour check_cptr_tta(struct kvm_vcpu *vcpu) { u64 val = __vcpu_sys_reg(vcpu, CPTR_EL2); if (!vcpu_el2_e2h_is_set(vcpu)) val = translate_cptr_el2_to_cpacr_el1(val); if (val & CPACR_EL1_TTA) return BEHAVE_FORWARD_RW; return BEHAVE_HANDLE_LOCALLY; } static enum trap_behaviour check_mdcr_hpmn(struct kvm_vcpu *vcpu) { u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); unsigned int idx; switch (sysreg) { case SYS_PMEVTYPERn_EL0(0) ... SYS_PMEVTYPERn_EL0(30): case SYS_PMEVCNTRn_EL0(0) ... SYS_PMEVCNTRn_EL0(30): idx = (sys_reg_CRm(sysreg) & 0x3) << 3 | sys_reg_Op2(sysreg); break; case SYS_PMXEVTYPER_EL0: case SYS_PMXEVCNTR_EL0: idx = SYS_FIELD_GET(PMSELR_EL0, SEL, __vcpu_sys_reg(vcpu, PMSELR_EL0)); break; default: /* Someone used this trap helper for something else... */ KVM_BUG_ON(1, vcpu->kvm); return BEHAVE_HANDLE_LOCALLY; } if (kvm_pmu_counter_is_hyp(vcpu, idx)) return BEHAVE_FORWARD_RW | BEHAVE_FORWARD_IN_HOST_EL0; return BEHAVE_HANDLE_LOCALLY; } #define CCC(id, fn) \ [id - __COMPLEX_CONDITIONS__] = fn static const complex_condition_check ccc[] = { CCC(CGT_CNTHCTL_EL1PCTEN, check_cnthctl_el1pcten), CCC(CGT_CNTHCTL_EL1PTEN, check_cnthctl_el1pten), CCC(CGT_CNTHCTL_EL1NVPCT, check_cnthctl_el1nvpct), CCC(CGT_CNTHCTL_EL1NVVCT, check_cnthctl_el1nvvct), CCC(CGT_CPTR_TTA, check_cptr_tta), CCC(CGT_MDCR_HPMN, check_mdcr_hpmn), }; /* * Bit assignment for the trap controls. We use a 64bit word with the * following layout for each trapped sysreg: * * [9:0] enum cgt_group_id (10 bits) * [13:10] enum fgt_group_id (4 bits) * [19:14] bit number in the FGT register (6 bits) * [20] trap polarity (1 bit) * [25:21] FG filter (5 bits) * [35:26] Main SysReg table index (10 bits) * [62:36] Unused (27 bits) * [63] RES0 - Must be zero, as lost on insertion in the xarray */ #define TC_CGT_BITS 10 #define TC_FGT_BITS 4 #define TC_FGF_BITS 5 #define TC_SRI_BITS 10 union trap_config { u64 val; struct { unsigned long cgt:TC_CGT_BITS; /* Coarse Grained Trap id */ unsigned long fgt:TC_FGT_BITS; /* Fine Grained Trap id */ unsigned long bit:6; /* Bit number */ unsigned long pol:1; /* Polarity */ unsigned long fgf:TC_FGF_BITS; /* Fine Grained Filter */ unsigned long sri:TC_SRI_BITS; /* SysReg Index */ unsigned long unused:27; /* Unused, should be zero */ unsigned long mbz:1; /* Must Be Zero */ }; }; struct encoding_to_trap_config { const u32 encoding; const u32 end; const union trap_config tc; const unsigned int line; }; /* * WARNING: using ranges is a treacherous endeavour, as sysregs that * are part of an architectural range are not necessarily contiguous * in the [Op0,Op1,CRn,CRm,Ops] space. Tread carefully. */ #define SR_RANGE_TRAP(sr_start, sr_end, trap_id) \ { \ .encoding = sr_start, \ .end = sr_end, \ .tc = { \ .cgt = trap_id, \ }, \ .line = __LINE__, \ } #define SR_TRAP(sr, trap_id) SR_RANGE_TRAP(sr, sr, trap_id) /* * Map encoding to trap bits for exception reported with EC=0x18. * These must only be evaluated when running a nested hypervisor, but * that the current context is not a hypervisor context. When the * trapped access matches one of the trap controls, the exception is * re-injected in the nested hypervisor. */ static const struct encoding_to_trap_config encoding_to_cgt[] __initconst = { SR_TRAP(SYS_REVIDR_EL1, CGT_HCR_TID1), SR_TRAP(SYS_AIDR_EL1, CGT_HCR_TID1), SR_TRAP(SYS_SMIDR_EL1, CGT_HCR_TID1), SR_TRAP(SYS_CTR_EL0, CGT_HCR_TID2), SR_TRAP(SYS_CCSIDR_EL1, CGT_HCR_TID2_TID4), SR_TRAP(SYS_CCSIDR2_EL1, CGT_HCR_TID2_TID4), SR_TRAP(SYS_CLIDR_EL1, CGT_HCR_TID2_TID4), SR_TRAP(SYS_CSSELR_EL1, CGT_HCR_TID2_TID4), SR_RANGE_TRAP(SYS_ID_PFR0_EL1, sys_reg(3, 0, 0, 7, 7), CGT_HCR_TID3), SR_TRAP(SYS_ICC_SGI0R_EL1, CGT_HCR_IMO_FMO_ICH_HCR_TC), SR_TRAP(SYS_ICC_ASGI1R_EL1, CGT_HCR_IMO_FMO_ICH_HCR_TC), SR_TRAP(SYS_ICC_SGI1R_EL1, CGT_HCR_IMO_FMO_ICH_HCR_TC), SR_RANGE_TRAP(sys_reg(3, 0, 11, 0, 0), sys_reg(3, 0, 11, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 1, 11, 0, 0), sys_reg(3, 1, 11, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 2, 11, 0, 0), sys_reg(3, 2, 11, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 3, 11, 0, 0), sys_reg(3, 3, 11, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 4, 11, 0, 0), sys_reg(3, 4, 11, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 5, 11, 0, 0), sys_reg(3, 5, 11, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 6, 11, 0, 0), sys_reg(3, 6, 11, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 7, 11, 0, 0), sys_reg(3, 7, 11, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 0, 15, 0, 0), sys_reg(3, 0, 15, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 1, 15, 0, 0), sys_reg(3, 1, 15, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 2, 15, 0, 0), sys_reg(3, 2, 15, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 3, 15, 0, 0), sys_reg(3, 3, 15, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 4, 15, 0, 0), sys_reg(3, 4, 15, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 5, 15, 0, 0), sys_reg(3, 5, 15, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 6, 15, 0, 0), sys_reg(3, 6, 15, 15, 7), CGT_HCR_TIDCP), SR_RANGE_TRAP(sys_reg(3, 7, 15, 0, 0), sys_reg(3, 7, 15, 15, 7), CGT_HCR_TIDCP), SR_TRAP(SYS_ACTLR_EL1, CGT_HCR_TACR), SR_TRAP(SYS_DC_ISW, CGT_HCR_TSW), SR_TRAP(SYS_DC_CSW, CGT_HCR_TSW), SR_TRAP(SYS_DC_CISW, CGT_HCR_TSW), SR_TRAP(SYS_DC_IGSW, CGT_HCR_TSW), SR_TRAP(SYS_DC_IGDSW, CGT_HCR_TSW), SR_TRAP(SYS_DC_CGSW, CGT_HCR_TSW), SR_TRAP(SYS_DC_CGDSW, CGT_HCR_TSW), SR_TRAP(SYS_DC_CIGSW, CGT_HCR_TSW), SR_TRAP(SYS_DC_CIGDSW, CGT_HCR_TSW), SR_TRAP(SYS_DC_CIVAC, CGT_HCR_TPC), SR_TRAP(SYS_DC_CVAC, CGT_HCR_TPC), SR_TRAP(SYS_DC_CVAP, CGT_HCR_TPC), SR_TRAP(SYS_DC_CVADP, CGT_HCR_TPC), SR_TRAP(SYS_DC_IVAC, CGT_HCR_TPC), SR_TRAP(SYS_DC_CIGVAC, CGT_HCR_TPC), SR_TRAP(SYS_DC_CIGDVAC, CGT_HCR_TPC), SR_TRAP(SYS_DC_IGVAC, CGT_HCR_TPC), SR_TRAP(SYS_DC_IGDVAC, CGT_HCR_TPC), SR_TRAP(SYS_DC_CGVAC, CGT_HCR_TPC), SR_TRAP(SYS_DC_CGDVAC, CGT_HCR_TPC), SR_TRAP(SYS_DC_CGVAP, CGT_HCR_TPC), SR_TRAP(SYS_DC_CGDVAP, CGT_HCR_TPC), SR_TRAP(SYS_DC_CGVADP, CGT_HCR_TPC), SR_TRAP(SYS_DC_CGDVADP, CGT_HCR_TPC), SR_TRAP(SYS_IC_IVAU, CGT_HCR_TPU_TOCU), SR_TRAP(SYS_IC_IALLU, CGT_HCR_TPU_TOCU), SR_TRAP(SYS_IC_IALLUIS, CGT_HCR_TPU_TICAB), SR_TRAP(SYS_DC_CVAU, CGT_HCR_TPU_TOCU), SR_TRAP(OP_TLBI_RVAE1, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_RVAAE1, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_RVALE1, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_RVAALE1, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_VMALLE1, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_VAE1, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_ASIDE1, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_VAAE1, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_VALE1, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_VAALE1, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_RVAE1NXS, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_RVAAE1NXS, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_RVALE1NXS, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_RVAALE1NXS, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_VMALLE1NXS, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_VAE1NXS, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_ASIDE1NXS, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_VAAE1NXS, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_VALE1NXS, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_VAALE1NXS, CGT_HCR_TTLB), SR_TRAP(OP_TLBI_RVAE1IS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_RVAAE1IS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_RVALE1IS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_RVAALE1IS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_VMALLE1IS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_VAE1IS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_ASIDE1IS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_VAAE1IS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_VALE1IS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_VAALE1IS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_RVAE1ISNXS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_RVAAE1ISNXS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_RVALE1ISNXS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_RVAALE1ISNXS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_VMALLE1ISNXS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_VAE1ISNXS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_ASIDE1ISNXS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_VAAE1ISNXS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_VALE1ISNXS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_VAALE1ISNXS, CGT_HCR_TTLB_TTLBIS), SR_TRAP(OP_TLBI_VMALLE1OS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_VAE1OS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_ASIDE1OS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_VAAE1OS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_VALE1OS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_VAALE1OS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_RVAE1OS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_RVAAE1OS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_RVALE1OS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_RVAALE1OS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_VMALLE1OSNXS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_VAE1OSNXS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_ASIDE1OSNXS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_VAAE1OSNXS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_VALE1OSNXS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_VAALE1OSNXS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_RVAE1OSNXS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_RVAAE1OSNXS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_RVALE1OSNXS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(OP_TLBI_RVAALE1OSNXS, CGT_HCR_TTLB_TTLBOS), SR_TRAP(SYS_SCTLR_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_SCTLR2_EL1, CGT_HCR_TVM_TRVM_HCRX_SCTLR2En), SR_TRAP(SYS_TTBR0_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_TTBR1_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_TCR_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_ESR_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_FAR_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_AFSR0_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_AFSR1_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_MAIR_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_AMAIR_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_CONTEXTIDR_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_PIR_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_PIRE0_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_POR_EL0, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_POR_EL1, CGT_HCR_TVM_TRVM), SR_TRAP(SYS_TCR2_EL1, CGT_HCR_TVM_TRVM_HCRX_TCR2En), SR_TRAP(SYS_DC_ZVA, CGT_HCR_TDZ), SR_TRAP(SYS_DC_GVA, CGT_HCR_TDZ), SR_TRAP(SYS_DC_GZVA, CGT_HCR_TDZ), SR_TRAP(SYS_LORSA_EL1, CGT_HCR_TLOR), SR_TRAP(SYS_LOREA_EL1, CGT_HCR_TLOR), SR_TRAP(SYS_LORN_EL1, CGT_HCR_TLOR), SR_TRAP(SYS_LORC_EL1, CGT_HCR_TLOR), SR_TRAP(SYS_LORID_EL1, CGT_HCR_TLOR), SR_TRAP(SYS_ERRIDR_EL1, CGT_HCR_TERR), SR_TRAP(SYS_ERRSELR_EL1, CGT_HCR_TERR), SR_TRAP(SYS_ERXADDR_EL1, CGT_HCR_TERR), SR_TRAP(SYS_ERXCTLR_EL1, CGT_HCR_TERR), SR_TRAP(SYS_ERXFR_EL1, CGT_HCR_TERR), SR_TRAP(SYS_ERXMISC0_EL1, CGT_HCR_TERR), SR_TRAP(SYS_ERXMISC1_EL1, CGT_HCR_TERR), SR_TRAP(SYS_ERXMISC2_EL1, CGT_HCR_TERR), SR_TRAP(SYS_ERXMISC3_EL1, CGT_HCR_TERR), SR_TRAP(SYS_ERXSTATUS_EL1, CGT_HCR_TERR), SR_TRAP(SYS_APIAKEYLO_EL1, CGT_HCR_APK), SR_TRAP(SYS_APIAKEYHI_EL1, CGT_HCR_APK), SR_TRAP(SYS_APIBKEYLO_EL1, CGT_HCR_APK), SR_TRAP(SYS_APIBKEYHI_EL1, CGT_HCR_APK), SR_TRAP(SYS_APDAKEYLO_EL1, CGT_HCR_APK), SR_TRAP(SYS_APDAKEYHI_EL1, CGT_HCR_APK), SR_TRAP(SYS_APDBKEYLO_EL1, CGT_HCR_APK), SR_TRAP(SYS_APDBKEYHI_EL1, CGT_HCR_APK), SR_TRAP(SYS_APGAKEYLO_EL1, CGT_HCR_APK), SR_TRAP(SYS_APGAKEYHI_EL1, CGT_HCR_APK), /* All _EL2 registers */ SR_TRAP(SYS_BRBCR_EL2, CGT_HCR_NV), SR_TRAP(SYS_VPIDR_EL2, CGT_HCR_NV), SR_TRAP(SYS_VMPIDR_EL2, CGT_HCR_NV), SR_TRAP(SYS_SCTLR_EL2, CGT_HCR_NV), SR_TRAP(SYS_ACTLR_EL2, CGT_HCR_NV), SR_TRAP(SYS_SCTLR2_EL2, CGT_HCR_NV), SR_RANGE_TRAP(SYS_HCR_EL2, SYS_HCRX_EL2, CGT_HCR_NV), SR_TRAP(SYS_SMPRIMAP_EL2, CGT_HCR_NV), SR_TRAP(SYS_SMCR_EL2, CGT_HCR_NV), SR_RANGE_TRAP(SYS_TTBR0_EL2, SYS_TCR2_EL2, CGT_HCR_NV), SR_TRAP(SYS_VTTBR_EL2, CGT_HCR_NV), SR_TRAP(SYS_VTCR_EL2, CGT_HCR_NV), SR_TRAP(SYS_VNCR_EL2, CGT_HCR_NV), SR_RANGE_TRAP(SYS_HDFGRTR_EL2, SYS_HAFGRTR_EL2, CGT_HCR_NV), /* Skip the SP_EL1 encoding... */ SR_TRAP(SYS_SPSR_EL2, CGT_HCR_NV), SR_TRAP(SYS_ELR_EL2, CGT_HCR_NV), /* Skip SPSR_irq, SPSR_abt, SPSR_und, SPSR_fiq */ SR_TRAP(SYS_AFSR0_EL2, CGT_HCR_NV), SR_TRAP(SYS_AFSR1_EL2, CGT_HCR_NV), SR_TRAP(SYS_ESR_EL2, CGT_HCR_NV), SR_TRAP(SYS_VSESR_EL2, CGT_HCR_NV), SR_TRAP(SYS_TFSR_EL2, CGT_HCR_NV), SR_TRAP(SYS_FAR_EL2, CGT_HCR_NV), SR_TRAP(SYS_HPFAR_EL2, CGT_HCR_NV), SR_TRAP(SYS_PMSCR_EL2, CGT_HCR_NV), SR_TRAP(SYS_MAIR_EL2, CGT_HCR_NV), SR_TRAP(SYS_AMAIR_EL2, CGT_HCR_NV), SR_TRAP(SYS_MPAMHCR_EL2, CGT_HCR_NV), SR_TRAP(SYS_MPAMVPMV_EL2, CGT_HCR_NV), SR_TRAP(SYS_MPAM2_EL2, CGT_HCR_NV), SR_RANGE_TRAP(SYS_MPAMVPM0_EL2, SYS_MPAMVPM7_EL2, CGT_HCR_NV), /* * Note that the spec. describes a group of MEC registers * whose access should not trap, therefore skip the following: * MECID_A0_EL2, MECID_A1_EL2, MECID_P0_EL2, * MECID_P1_EL2, MECIDR_EL2, VMECID_A_EL2, * VMECID_P_EL2. */ SR_RANGE_TRAP(SYS_VBAR_EL2, SYS_RMR_EL2, CGT_HCR_NV), SR_TRAP(SYS_VDISR_EL2, CGT_HCR_NV), /* ICH_AP0R<m>_EL2 */ SR_RANGE_TRAP(SYS_ICH_AP0R0_EL2, SYS_ICH_AP0R3_EL2, CGT_HCR_NV), /* ICH_AP1R<m>_EL2 */ SR_RANGE_TRAP(SYS_ICH_AP1R0_EL2, SYS_ICH_AP1R3_EL2, CGT_HCR_NV), SR_TRAP(SYS_ICC_SRE_EL2, CGT_HCR_NV), SR_RANGE_TRAP(SYS_ICH_HCR_EL2, SYS_ICH_EISR_EL2, CGT_HCR_NV), SR_TRAP(SYS_ICH_ELRSR_EL2, CGT_HCR_NV), SR_TRAP(SYS_ICH_VMCR_EL2, CGT_HCR_NV), /* ICH_LR<m>_EL2 */ SR_RANGE_TRAP(SYS_ICH_LR0_EL2, SYS_ICH_LR15_EL2, CGT_HCR_NV), SR_TRAP(SYS_CONTEXTIDR_EL2, CGT_HCR_NV), SR_TRAP(SYS_TPIDR_EL2, CGT_HCR_NV), SR_TRAP(SYS_SCXTNUM_EL2, CGT_HCR_NV), /* AMEVCNTVOFF0<n>_EL2, AMEVCNTVOFF1<n>_EL2 */ SR_RANGE_TRAP(SYS_AMEVCNTVOFF0n_EL2(0), SYS_AMEVCNTVOFF1n_EL2(15), CGT_HCR_NV), /* CNT*_EL2 */ SR_TRAP(SYS_CNTVOFF_EL2, CGT_HCR_NV), SR_TRAP(SYS_CNTPOFF_EL2, CGT_HCR_NV), SR_TRAP(SYS_CNTHCTL_EL2, CGT_HCR_NV), SR_RANGE_TRAP(SYS_CNTHP_TVAL_EL2, SYS_CNTHP_CVAL_EL2, CGT_HCR_NV), SR_RANGE_TRAP(SYS_CNTHV_TVAL_EL2, SYS_CNTHV_CVAL_EL2, CGT_HCR_NV), /* All _EL02, _EL12 registers up to CNTKCTL_EL12*/ SR_RANGE_TRAP(sys_reg(3, 5, 0, 0, 0), sys_reg(3, 5, 10, 15, 7), CGT_HCR_NV), SR_RANGE_TRAP(sys_reg(3, 5, 12, 0, 0), sys_reg(3, 5, 14, 1, 0), CGT_HCR_NV), SR_TRAP(SYS_CNTP_CTL_EL02, CGT_CNTHCTL_EL1NVPCT), SR_TRAP(SYS_CNTP_CVAL_EL02, CGT_CNTHCTL_EL1NVPCT), SR_TRAP(SYS_CNTV_CTL_EL02, CGT_CNTHCTL_EL1NVVCT), SR_TRAP(SYS_CNTV_CVAL_EL02, CGT_CNTHCTL_EL1NVVCT), SR_TRAP(OP_AT_S1E2R, CGT_HCR_NV), SR_TRAP(OP_AT_S1E2W, CGT_HCR_NV), SR_TRAP(OP_AT_S12E1R, CGT_HCR_NV), SR_TRAP(OP_AT_S12E1W, CGT_HCR_NV), SR_TRAP(OP_AT_S12E0R, CGT_HCR_NV), SR_TRAP(OP_AT_S12E0W, CGT_HCR_NV), SR_TRAP(OP_AT_S1E2A, CGT_HCR_NV), SR_TRAP(OP_TLBI_IPAS2E1, CGT_HCR_NV), SR_TRAP(OP_TLBI_RIPAS2E1, CGT_HCR_NV), SR_TRAP(OP_TLBI_IPAS2LE1, CGT_HCR_NV), SR_TRAP(OP_TLBI_RIPAS2LE1, CGT_HCR_NV), SR_TRAP(OP_TLBI_RVAE2, CGT_HCR_NV), SR_TRAP(OP_TLBI_RVALE2, CGT_HCR_NV), SR_TRAP(OP_TLBI_ALLE2, CGT_HCR_NV), SR_TRAP(OP_TLBI_VAE2, CGT_HCR_NV), SR_TRAP(OP_TLBI_ALLE1, CGT_HCR_NV), SR_TRAP(OP_TLBI_VALE2, CGT_HCR_NV), SR_TRAP(OP_TLBI_VMALLS12E1, CGT_HCR_NV), SR_TRAP(OP_TLBI_IPAS2E1NXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RIPAS2E1NXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_IPAS2LE1NXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RIPAS2LE1NXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RVAE2NXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RVALE2NXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_ALLE2NXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VAE2NXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_ALLE1NXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VALE2NXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VMALLS12E1NXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_IPAS2E1IS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RIPAS2E1IS, CGT_HCR_NV), SR_TRAP(OP_TLBI_IPAS2LE1IS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RIPAS2LE1IS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RVAE2IS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RVALE2IS, CGT_HCR_NV), SR_TRAP(OP_TLBI_ALLE2IS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VAE2IS, CGT_HCR_NV), SR_TRAP(OP_TLBI_ALLE1IS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VALE2IS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VMALLS12E1IS, CGT_HCR_NV), SR_TRAP(OP_TLBI_IPAS2E1ISNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RIPAS2E1ISNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_IPAS2LE1ISNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RIPAS2LE1ISNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RVAE2ISNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RVALE2ISNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_ALLE2ISNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VAE2ISNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_ALLE1ISNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VALE2ISNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VMALLS12E1ISNXS,CGT_HCR_NV), SR_TRAP(OP_TLBI_ALLE2OS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VAE2OS, CGT_HCR_NV), SR_TRAP(OP_TLBI_ALLE1OS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VALE2OS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VMALLS12E1OS, CGT_HCR_NV), SR_TRAP(OP_TLBI_IPAS2E1OS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RIPAS2E1OS, CGT_HCR_NV), SR_TRAP(OP_TLBI_IPAS2LE1OS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RIPAS2LE1OS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RVAE2OS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RVALE2OS, CGT_HCR_NV), SR_TRAP(OP_TLBI_ALLE2OSNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VAE2OSNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_ALLE1OSNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VALE2OSNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_VMALLS12E1OSNXS,CGT_HCR_NV), SR_TRAP(OP_TLBI_IPAS2E1OSNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RIPAS2E1OSNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_IPAS2LE1OSNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RIPAS2LE1OSNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RVAE2OSNXS, CGT_HCR_NV), SR_TRAP(OP_TLBI_RVALE2OSNXS, CGT_HCR_NV), SR_TRAP(OP_CPP_RCTX, CGT_HCR_NV), SR_TRAP(OP_DVP_RCTX, CGT_HCR_NV), SR_TRAP(OP_CFP_RCTX, CGT_HCR_NV), SR_TRAP(SYS_SP_EL1, CGT_HCR_NV_nNV2), SR_TRAP(SYS_VBAR_EL1, CGT_HCR_NV1_nNV2), SR_TRAP(SYS_ELR_EL1, CGT_HCR_NV1_nNV2), SR_TRAP(SYS_SPSR_EL1, CGT_HCR_NV1_nNV2), SR_TRAP(SYS_SCXTNUM_EL1, CGT_HCR_NV1_nNV2_ENSCXT), SR_TRAP(SYS_SCXTNUM_EL0, CGT_HCR_ENSCXT), SR_TRAP(OP_AT_S1E1R, CGT_HCR_AT), SR_TRAP(OP_AT_S1E1W, CGT_HCR_AT), SR_TRAP(OP_AT_S1E0R, CGT_HCR_AT), SR_TRAP(OP_AT_S1E0W, CGT_HCR_AT), SR_TRAP(OP_AT_S1E1RP, CGT_HCR_AT), SR_TRAP(OP_AT_S1E1WP, CGT_HCR_AT), SR_TRAP(OP_AT_S1E1A, CGT_HCR_AT), SR_TRAP(SYS_ERXPFGF_EL1, CGT_HCR_nFIEN), SR_TRAP(SYS_ERXPFGCTL_EL1, CGT_HCR_nFIEN), SR_TRAP(SYS_ERXPFGCDN_EL1, CGT_HCR_nFIEN), SR_TRAP(SYS_PMCR_EL0, CGT_MDCR_TPM_TPMCR), SR_TRAP(SYS_PMCNTENSET_EL0, CGT_MDCR_TPM), SR_TRAP(SYS_PMCNTENCLR_EL0, CGT_MDCR_TPM), SR_TRAP(SYS_PMOVSSET_EL0, CGT_MDCR_TPM), SR_TRAP(SYS_PMOVSCLR_EL0, CGT_MDCR_TPM), SR_TRAP(SYS_PMCEID0_EL0, CGT_MDCR_TPM), SR_TRAP(SYS_PMCEID1_EL0, CGT_MDCR_TPM), SR_TRAP(SYS_PMXEVTYPER_EL0, CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMSWINC_EL0, CGT_MDCR_TPM), SR_TRAP(SYS_PMSELR_EL0, CGT_MDCR_TPM), SR_TRAP(SYS_PMXEVCNTR_EL0, CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMCCNTR_EL0, CGT_MDCR_TPM), SR_TRAP(SYS_PMUSERENR_EL0, CGT_MDCR_TPM), SR_TRAP(SYS_PMINTENSET_EL1, CGT_MDCR_TPM), SR_TRAP(SYS_PMINTENCLR_EL1, CGT_MDCR_TPM), SR_TRAP(SYS_PMMIR_EL1, CGT_MDCR_TPM), SR_TRAP(SYS_PMEVCNTRn_EL0(0), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(1), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(2), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(3), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(4), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(5), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(6), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(7), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(8), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(9), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(10), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(11), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(12), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(13), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(14), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(15), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(16), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(17), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(18), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(19), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(20), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(21), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(22), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(23), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(24), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(25), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(26), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(27), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(28), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(29), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVCNTRn_EL0(30), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(0), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(1), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(2), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(3), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(4), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(5), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(6), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(7), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(8), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(9), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(10), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(11), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(12), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(13), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(14), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(15), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(16), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(17), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(18), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(19), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(20), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(21), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(22), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(23), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(24), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(25), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(26), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(27), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(28), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(29), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMEVTYPERn_EL0(30), CGT_MDCR_TPM_HPMN), SR_TRAP(SYS_PMCCFILTR_EL0, CGT_MDCR_TPM), SR_TRAP(SYS_MDCCSR_EL0, CGT_MDCR_TDCC_TDE_TDA), SR_TRAP(SYS_MDCCINT_EL1, CGT_MDCR_TDCC_TDE_TDA), SR_TRAP(SYS_OSDTRRX_EL1, CGT_MDCR_TDCC_TDE_TDA), SR_TRAP(SYS_OSDTRTX_EL1, CGT_MDCR_TDCC_TDE_TDA), SR_TRAP(SYS_DBGDTR_EL0, CGT_MDCR_TDCC_TDE_TDA), /* * Also covers DBGDTRRX_EL0, which has the same encoding as * SYS_DBGDTRTX_EL0... */ SR_TRAP(SYS_DBGDTRTX_EL0, CGT_MDCR_TDCC_TDE_TDA), SR_TRAP(SYS_MDSCR_EL1, CGT_MDCR_TDE_TDA), SR_TRAP(SYS_OSECCR_EL1, CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(0), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(1), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(2), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(3), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(4), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(5), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(6), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(7), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(8), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(9), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(10), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(11), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(12), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(13), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(14), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBVRn_EL1(15), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(0), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(1), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(2), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(3), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(4), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(5), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(6), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(7), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(8), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(9), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(10), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(11), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(12), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(13), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(14), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGBCRn_EL1(15), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(0), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(1), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(2), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(3), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(4), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(5), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(6), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(7), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(8), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(9), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(10), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(11), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(12), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(13), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(14), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWVRn_EL1(15), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(0), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(1), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(2), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(3), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(4), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(5), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(6), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(7), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(8), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(9), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(10), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(11), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(12), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(13), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGWCRn_EL1(14), CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGCLAIMSET_EL1, CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGCLAIMCLR_EL1, CGT_MDCR_TDE_TDA), SR_TRAP(SYS_DBGAUTHSTATUS_EL1, CGT_MDCR_TDE_TDA), SR_TRAP(SYS_OSLAR_EL1, CGT_MDCR_TDE_TDOSA), SR_TRAP(SYS_OSLSR_EL1, CGT_MDCR_TDE_TDOSA), SR_TRAP(SYS_OSDLR_EL1, CGT_MDCR_TDE_TDOSA), SR_TRAP(SYS_DBGPRCR_EL1, CGT_MDCR_TDE_TDOSA), SR_TRAP(SYS_MDRAR_EL1, CGT_MDCR_TDE_TDRA), SR_TRAP(SYS_PMBLIMITR_EL1, CGT_MDCR_E2PB), SR_TRAP(SYS_PMBPTR_EL1, CGT_MDCR_E2PB), SR_TRAP(SYS_PMBSR_EL1, CGT_MDCR_E2PB), SR_TRAP(SYS_PMSCR_EL1, CGT_MDCR_TPMS), SR_TRAP(SYS_PMSEVFR_EL1, CGT_MDCR_TPMS), SR_TRAP(SYS_PMSFCR_EL1, CGT_MDCR_TPMS), SR_TRAP(SYS_PMSICR_EL1, CGT_MDCR_TPMS), SR_TRAP(SYS_PMSIDR_EL1, CGT_MDCR_TPMS), SR_TRAP(SYS_PMSIRR_EL1, CGT_MDCR_TPMS), SR_TRAP(SYS_PMSLATFR_EL1, CGT_MDCR_TPMS), SR_TRAP(SYS_PMSNEVFR_EL1, CGT_MDCR_TPMS), SR_TRAP(SYS_PMSDSFR_EL1, CGT_MDCR_TPMS), SR_TRAP(SYS_TRFCR_EL1, CGT_MDCR_TTRF), SR_TRAP(SYS_TRBBASER_EL1, CGT_MDCR_E2TB), SR_TRAP(SYS_TRBLIMITR_EL1, CGT_MDCR_E2TB), SR_TRAP(SYS_TRBMAR_EL1, CGT_MDCR_E2TB), SR_TRAP(SYS_TRBPTR_EL1, CGT_MDCR_E2TB), SR_TRAP(SYS_TRBSR_EL1, CGT_MDCR_E2TB), SR_TRAP(SYS_TRBTRG_EL1, CGT_MDCR_E2TB), SR_TRAP(SYS_CPACR_EL1, CGT_CPTR_TCPAC), SR_TRAP(SYS_AMUSERENR_EL0, CGT_CPTR_TAM), SR_TRAP(SYS_AMCFGR_EL0, CGT_CPTR_TAM), SR_TRAP(SYS_AMCGCR_EL0, CGT_CPTR_TAM), SR_TRAP(SYS_AMCNTENCLR0_EL0, CGT_CPTR_TAM), SR_TRAP(SYS_AMCNTENCLR1_EL0, CGT_CPTR_TAM), SR_TRAP(SYS_AMCNTENSET0_EL0, CGT_CPTR_TAM), SR_TRAP(SYS_AMCNTENSET1_EL0, CGT_CPTR_TAM), SR_TRAP(SYS_AMCR_EL0, CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR0_EL0(0), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR0_EL0(1), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR0_EL0(2), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR0_EL0(3), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(0), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(1), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(2), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(3), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(4), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(5), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(6), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(7), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(8), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(9), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(10), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(11), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(12), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(13), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(14), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVCNTR1_EL0(15), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER0_EL0(0), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER0_EL0(1), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER0_EL0(2), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER0_EL0(3), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(0), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(1), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(2), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(3), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(4), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(5), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(6), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(7), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(8), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(9), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(10), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(11), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(12), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(13), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(14), CGT_CPTR_TAM), SR_TRAP(SYS_AMEVTYPER1_EL0(15), CGT_CPTR_TAM), /* op0=2, op1=1, and CRn<0b1000 */ SR_RANGE_TRAP(sys_reg(2, 1, 0, 0, 0), sys_reg(2, 1, 7, 15, 7), CGT_CPTR_TTA), SR_TRAP(SYS_CNTP_TVAL_EL0, CGT_CNTHCTL_EL1PTEN), SR_TRAP(SYS_CNTP_CVAL_EL0, CGT_CNTHCTL_EL1PTEN), SR_TRAP(SYS_CNTP_CTL_EL0, CGT_CNTHCTL_EL1PTEN), SR_TRAP(SYS_CNTPCT_EL0, CGT_CNTHCTL_EL1PCTEN), SR_TRAP(SYS_CNTPCTSS_EL0, CGT_CNTHCTL_EL1PCTEN), SR_TRAP(SYS_CNTV_TVAL_EL0, CGT_CNTHCTL_EL1TVT), SR_TRAP(SYS_CNTV_CVAL_EL0, CGT_CNTHCTL_EL1TVT), SR_TRAP(SYS_CNTV_CTL_EL0, CGT_CNTHCTL_EL1TVT), SR_TRAP(SYS_CNTVCT_EL0, CGT_CNTHCTL_EL1TVCT), SR_TRAP(SYS_CNTVCTSS_EL0, CGT_CNTHCTL_EL1TVCT), SR_TRAP(SYS_FPMR, CGT_HCRX_EnFPM), /* * IMPDEF choice: * We treat ICC_SRE_EL2.{SRE,Enable) and ICV_SRE_EL1.SRE as * RAO/WI. We therefore never consider ICC_SRE_EL2.Enable for * ICC_SRE_EL1 access, and always handle it locally. */ SR_TRAP(SYS_ICC_AP0R0_EL1, CGT_ICH_HCR_TALL0), SR_TRAP(SYS_ICC_AP0R1_EL1, CGT_ICH_HCR_TALL0), SR_TRAP(SYS_ICC_AP0R2_EL1, CGT_ICH_HCR_TALL0), SR_TRAP(SYS_ICC_AP0R3_EL1, CGT_ICH_HCR_TALL0), SR_TRAP(SYS_ICC_AP1R0_EL1, CGT_ICH_HCR_TALL1), SR_TRAP(SYS_ICC_AP1R1_EL1, CGT_ICH_HCR_TALL1), SR_TRAP(SYS_ICC_AP1R2_EL1, CGT_ICH_HCR_TALL1), SR_TRAP(SYS_ICC_AP1R3_EL1, CGT_ICH_HCR_TALL1), SR_TRAP(SYS_ICC_BPR0_EL1, CGT_ICH_HCR_TALL0), SR_TRAP(SYS_ICC_BPR1_EL1, CGT_ICH_HCR_TALL1), SR_TRAP(SYS_ICC_CTLR_EL1, CGT_ICH_HCR_TC), SR_TRAP(SYS_ICC_DIR_EL1, CGT_ICH_HCR_TC_TDIR), SR_TRAP(SYS_ICC_EOIR0_EL1, CGT_ICH_HCR_TALL0), SR_TRAP(SYS_ICC_EOIR1_EL1, CGT_ICH_HCR_TALL1), SR_TRAP(SYS_ICC_HPPIR0_EL1, CGT_ICH_HCR_TALL0), SR_TRAP(SYS_ICC_HPPIR1_EL1, CGT_ICH_HCR_TALL1), SR_TRAP(SYS_ICC_IAR0_EL1, CGT_ICH_HCR_TALL0), SR_TRAP(SYS_ICC_IAR1_EL1, CGT_ICH_HCR_TALL1), SR_TRAP(SYS_ICC_IGRPEN0_EL1, CGT_ICH_HCR_TALL0), SR_TRAP(SYS_ICC_IGRPEN1_EL1, CGT_ICH_HCR_TALL1), SR_TRAP(SYS_ICC_PMR_EL1, CGT_ICH_HCR_TC), SR_TRAP(SYS_ICC_RPR_EL1, CGT_ICH_HCR_TC), }; static DEFINE_XARRAY(sr_forward_xa); enum fg_filter_id { __NO_FGF__, HCRX_FGTnXS, /* Must be last */ __NR_FG_FILTER_IDS__ }; #define __FGT(g, b, p, f) \ { \ .fgt = g ## _GROUP, \ .bit = g ## _EL2_ ## b ## _SHIFT, \ .pol = p, \ .fgf = f, \ } #define FGT(g, b, p) __FGT(g, b, p, __NO_FGF__) /* * See the warning next to SR_RANGE_TRAP(), and apply the same * level of caution. */ #define SR_FGF_RANGE(sr, e, g, b, p, f) \ { \ .encoding = sr, \ .end = e, \ .tc = __FGT(g, b, p, f), \ .line = __LINE__, \ } #define SR_FGF(sr, g, b, p, f) SR_FGF_RANGE(sr, sr, g, b, p, f) #define SR_FGT(sr, g, b, p) SR_FGF_RANGE(sr, sr, g, b, p, __NO_FGF__) #define SR_FGT_RANGE(sr, end, g, b, p) \ SR_FGF_RANGE(sr, end, g, b, p, __NO_FGF__) static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = { /* HFGRTR_EL2, HFGWTR_EL2 */ SR_FGT(SYS_AMAIR2_EL1, HFGRTR, nAMAIR2_EL1, 0), SR_FGT(SYS_MAIR2_EL1, HFGRTR, nMAIR2_EL1, 0), SR_FGT(SYS_S2POR_EL1, HFGRTR, nS2POR_EL1, 0), SR_FGT(SYS_POR_EL1, HFGRTR, nPOR_EL1, 0), SR_FGT(SYS_POR_EL0, HFGRTR, nPOR_EL0, 0), SR_FGT(SYS_PIR_EL1, HFGRTR, nPIR_EL1, 0), SR_FGT(SYS_PIRE0_EL1, HFGRTR, nPIRE0_EL1, 0), SR_FGT(SYS_RCWMASK_EL1, HFGRTR, nRCWMASK_EL1, 0), SR_FGT(SYS_TPIDR2_EL0, HFGRTR, nTPIDR2_EL0, 0), SR_FGT(SYS_SMPRI_EL1, HFGRTR, nSMPRI_EL1, 0), SR_FGT(SYS_GCSCR_EL1, HFGRTR, nGCS_EL1, 0), SR_FGT(SYS_GCSPR_EL1, HFGRTR, nGCS_EL1, 0), SR_FGT(SYS_GCSCRE0_EL1, HFGRTR, nGCS_EL0, 0), SR_FGT(SYS_GCSPR_EL0, HFGRTR, nGCS_EL0, 0), SR_FGT(SYS_ACCDATA_EL1, HFGRTR, nACCDATA_EL1, 0), SR_FGT(SYS_ERXADDR_EL1, HFGRTR, ERXADDR_EL1, 1), SR_FGT(SYS_ERXPFGCDN_EL1, HFGRTR, ERXPFGCDN_EL1, 1), SR_FGT(SYS_ERXPFGCTL_EL1, HFGRTR, ERXPFGCTL_EL1, 1), SR_FGT(SYS_ERXPFGF_EL1, HFGRTR, ERXPFGF_EL1, 1), SR_FGT(SYS_ERXMISC0_EL1, HFGRTR, ERXMISCn_EL1, 1), SR_FGT(SYS_ERXMISC1_EL1, HFGRTR, ERXMISCn_EL1, 1), SR_FGT(SYS_ERXMISC2_EL1, HFGRTR, ERXMISCn_EL1, 1), SR_FGT(SYS_ERXMISC3_EL1, HFGRTR, ERXMISCn_EL1, 1), SR_FGT(SYS_ERXSTATUS_EL1, HFGRTR, ERXSTATUS_EL1, 1), SR_FGT(SYS_ERXCTLR_EL1, HFGRTR, ERXCTLR_EL1, 1), SR_FGT(SYS_ERXFR_EL1, HFGRTR, ERXFR_EL1, 1), SR_FGT(SYS_ERRSELR_EL1, HFGRTR, ERRSELR_EL1, 1), SR_FGT(SYS_ERRIDR_EL1, HFGRTR, ERRIDR_EL1, 1), SR_FGT(SYS_ICC_IGRPEN0_EL1, HFGRTR, ICC_IGRPENn_EL1, 1), SR_FGT(SYS_ICC_IGRPEN1_EL1, HFGRTR, ICC_IGRPENn_EL1, 1), SR_FGT(SYS_VBAR_EL1, HFGRTR, VBAR_EL1, 1), SR_FGT(SYS_TTBR1_EL1, HFGRTR, TTBR1_EL1, 1), SR_FGT(SYS_TTBR0_EL1, HFGRTR, TTBR0_EL1, 1), SR_FGT(SYS_TPIDR_EL0, HFGRTR, TPIDR_EL0, 1), SR_FGT(SYS_TPIDRRO_EL0, HFGRTR, TPIDRRO_EL0, 1), SR_FGT(SYS_TPIDR_EL1, HFGRTR, TPIDR_EL1, 1), SR_FGT(SYS_TCR_EL1, HFGRTR, TCR_EL1, 1), SR_FGT(SYS_TCR2_EL1, HFGRTR, TCR_EL1, 1), SR_FGT(SYS_SCXTNUM_EL0, HFGRTR, SCXTNUM_EL0, 1), SR_FGT(SYS_SCXTNUM_EL1, HFGRTR, SCXTNUM_EL1, 1), SR_FGT(SYS_SCTLR_EL1, HFGRTR, SCTLR_EL1, 1), SR_FGT(SYS_SCTLR2_EL1, HFGRTR, SCTLR_EL1, 1), SR_FGT(SYS_REVIDR_EL1, HFGRTR, REVIDR_EL1, 1), SR_FGT(SYS_PAR_EL1, HFGRTR, PAR_EL1, 1), SR_FGT(SYS_MPIDR_EL1, HFGRTR, MPIDR_EL1, 1), SR_FGT(SYS_MIDR_EL1, HFGRTR, MIDR_EL1, 1), SR_FGT(SYS_MAIR_EL1, HFGRTR, MAIR_EL1, 1), SR_FGT(SYS_LORSA_EL1, HFGRTR, LORSA_EL1, 1), SR_FGT(SYS_LORN_EL1, HFGRTR, LORN_EL1, 1), SR_FGT(SYS_LORID_EL1, HFGRTR, LORID_EL1, 1), SR_FGT(SYS_LOREA_EL1, HFGRTR, LOREA_EL1, 1), SR_FGT(SYS_LORC_EL1, HFGRTR, LORC_EL1, 1), SR_FGT(SYS_ISR_EL1, HFGRTR, ISR_EL1, 1), SR_FGT(SYS_FAR_EL1, HFGRTR, FAR_EL1, 1), SR_FGT(SYS_ESR_EL1, HFGRTR, ESR_EL1, 1), SR_FGT(SYS_DCZID_EL0, HFGRTR, DCZID_EL0, 1), SR_FGT(SYS_CTR_EL0, HFGRTR, CTR_EL0, 1), SR_FGT(SYS_CSSELR_EL1, HFGRTR, CSSELR_EL1, 1), SR_FGT(SYS_CPACR_EL1, HFGRTR, CPACR_EL1, 1), SR_FGT(SYS_CONTEXTIDR_EL1, HFGRTR, CONTEXTIDR_EL1, 1), SR_FGT(SYS_CLIDR_EL1, HFGRTR, CLIDR_EL1, 1), SR_FGT(SYS_CCSIDR_EL1, HFGRTR, CCSIDR_EL1, 1), SR_FGT(SYS_APIBKEYLO_EL1, HFGRTR, APIBKey, 1), SR_FGT(SYS_APIBKEYHI_EL1, HFGRTR, APIBKey, 1), SR_FGT(SYS_APIAKEYLO_EL1, HFGRTR, APIAKey, 1), SR_FGT(SYS_APIAKEYHI_EL1, HFGRTR, APIAKey, 1), SR_FGT(SYS_APGAKEYLO_EL1, HFGRTR, APGAKey, 1), SR_FGT(SYS_APGAKEYHI_EL1, HFGRTR, APGAKey, 1), SR_FGT(SYS_APDBKEYLO_EL1, HFGRTR, APDBKey, 1), SR_FGT(SYS_APDBKEYHI_EL1, HFGRTR, APDBKey, 1), SR_FGT(SYS_APDAKEYLO_EL1, HFGRTR, APDAKey, 1), SR_FGT(SYS_APDAKEYHI_EL1, HFGRTR, APDAKey, 1), SR_FGT(SYS_AMAIR_EL1, HFGRTR, AMAIR_EL1, 1), SR_FGT(SYS_AIDR_EL1, HFGRTR, AIDR_EL1, 1), SR_FGT(SYS_AFSR1_EL1, HFGRTR, AFSR1_EL1, 1), SR_FGT(SYS_AFSR0_EL1, HFGRTR, AFSR0_EL1, 1), /* HFGRTR2_EL2, HFGWTR2_EL2 */ SR_FGT(SYS_ACTLRALIAS_EL1, HFGRTR2, nACTLRALIAS_EL1, 0), SR_FGT(SYS_ACTLRMASK_EL1, HFGRTR2, nACTLRMASK_EL1, 0), SR_FGT(SYS_CPACRALIAS_EL1, HFGRTR2, nCPACRALIAS_EL1, 0), SR_FGT(SYS_CPACRMASK_EL1, HFGRTR2, nCPACRMASK_EL1, 0), SR_FGT(SYS_PFAR_EL1, HFGRTR2, nPFAR_EL1, 0), SR_FGT(SYS_RCWSMASK_EL1, HFGRTR2, nRCWSMASK_EL1, 0), SR_FGT(SYS_SCTLR2ALIAS_EL1, HFGRTR2, nSCTLRALIAS2_EL1, 0), SR_FGT(SYS_SCTLR2MASK_EL1, HFGRTR2, nSCTLR2MASK_EL1, 0), SR_FGT(SYS_SCTLRALIAS_EL1, HFGRTR2, nSCTLRALIAS_EL1, 0), SR_FGT(SYS_SCTLRMASK_EL1, HFGRTR2, nSCTLRMASK_EL1, 0), SR_FGT(SYS_TCR2ALIAS_EL1, HFGRTR2, nTCR2ALIAS_EL1, 0), SR_FGT(SYS_TCR2MASK_EL1, HFGRTR2, nTCR2MASK_EL1, 0), SR_FGT(SYS_TCRALIAS_EL1, HFGRTR2, nTCRALIAS_EL1, 0), SR_FGT(SYS_TCRMASK_EL1, HFGRTR2, nTCRMASK_EL1, 0), SR_FGT(SYS_ERXGSR_EL1, HFGRTR2, nERXGSR_EL1, 0), /* HFGITR_EL2 */ SR_FGT(OP_AT_S1E1A, HFGITR, ATS1E1A, 1), SR_FGT(OP_COSP_RCTX, HFGITR, COSPRCTX, 1), SR_FGT(OP_GCSPUSHX, HFGITR, nGCSEPP, 0), SR_FGT(OP_GCSPOPX, HFGITR, nGCSEPP, 0), SR_FGT(OP_GCSPUSHM, HFGITR, nGCSPUSHM_EL1, 0), SR_FGT(OP_BRB_IALL, HFGITR, nBRBIALL, 0), SR_FGT(OP_BRB_INJ, HFGITR, nBRBINJ, 0), SR_FGT(SYS_DC_CVAC, HFGITR, DCCVAC, 1), SR_FGT(SYS_DC_CGVAC, HFGITR, DCCVAC, 1), SR_FGT(SYS_DC_CGDVAC, HFGITR, DCCVAC, 1), SR_FGT(OP_CPP_RCTX, HFGITR, CPPRCTX, 1), SR_FGT(OP_DVP_RCTX, HFGITR, DVPRCTX, 1), SR_FGT(OP_CFP_RCTX, HFGITR, CFPRCTX, 1), SR_FGT(OP_TLBI_VAALE1, HFGITR, TLBIVAALE1, 1), SR_FGT(OP_TLBI_VALE1, HFGITR, TLBIVALE1, 1), SR_FGT(OP_TLBI_VAAE1, HFGITR, TLBIVAAE1, 1), SR_FGT(OP_TLBI_ASIDE1, HFGITR, TLBIASIDE1, 1), SR_FGT(OP_TLBI_VAE1, HFGITR, TLBIVAE1, 1), SR_FGT(OP_TLBI_VMALLE1, HFGITR, TLBIVMALLE1, 1), SR_FGT(OP_TLBI_RVAALE1, HFGITR, TLBIRVAALE1, 1), SR_FGT(OP_TLBI_RVALE1, HFGITR, TLBIRVALE1, 1), SR_FGT(OP_TLBI_RVAAE1, HFGITR, TLBIRVAAE1, 1), SR_FGT(OP_TLBI_RVAE1, HFGITR, TLBIRVAE1, 1), SR_FGT(OP_TLBI_RVAALE1IS, HFGITR, TLBIRVAALE1IS, 1), SR_FGT(OP_TLBI_RVALE1IS, HFGITR, TLBIRVALE1IS, 1), SR_FGT(OP_TLBI_RVAAE1IS, HFGITR, TLBIRVAAE1IS, 1), SR_FGT(OP_TLBI_RVAE1IS, HFGITR, TLBIRVAE1IS, 1), SR_FGT(OP_TLBI_VAALE1IS, HFGITR, TLBIVAALE1IS, 1), SR_FGT(OP_TLBI_VALE1IS, HFGITR, TLBIVALE1IS, 1), SR_FGT(OP_TLBI_VAAE1IS, HFGITR, TLBIVAAE1IS, 1), SR_FGT(OP_TLBI_ASIDE1IS, HFGITR, TLBIASIDE1IS, 1), SR_FGT(OP_TLBI_VAE1IS, HFGITR, TLBIVAE1IS, 1), SR_FGT(OP_TLBI_VMALLE1IS, HFGITR, TLBIVMALLE1IS, 1), SR_FGT(OP_TLBI_RVAALE1OS, HFGITR, TLBIRVAALE1OS, 1), SR_FGT(OP_TLBI_RVALE1OS, HFGITR, TLBIRVALE1OS, 1), SR_FGT(OP_TLBI_RVAAE1OS, HFGITR, TLBIRVAAE1OS, 1), SR_FGT(OP_TLBI_RVAE1OS, HFGITR, TLBIRVAE1OS, 1), SR_FGT(OP_TLBI_VAALE1OS, HFGITR, TLBIVAALE1OS, 1), SR_FGT(OP_TLBI_VALE1OS, HFGITR, TLBIVALE1OS, 1), SR_FGT(OP_TLBI_VAAE1OS, HFGITR, TLBIVAAE1OS, 1), SR_FGT(OP_TLBI_ASIDE1OS, HFGITR, TLBIASIDE1OS, 1), SR_FGT(OP_TLBI_VAE1OS, HFGITR, TLBIVAE1OS, 1), SR_FGT(OP_TLBI_VMALLE1OS, HFGITR, TLBIVMALLE1OS, 1), /* nXS variants must be checked against HCRX_EL2.FGTnXS */ SR_FGF(OP_TLBI_VAALE1NXS, HFGITR, TLBIVAALE1, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VALE1NXS, HFGITR, TLBIVALE1, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VAAE1NXS, HFGITR, TLBIVAAE1, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_ASIDE1NXS, HFGITR, TLBIASIDE1, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VAE1NXS, HFGITR, TLBIVAE1, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VMALLE1NXS, HFGITR, TLBIVMALLE1, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_RVAALE1NXS, HFGITR, TLBIRVAALE1, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_RVALE1NXS, HFGITR, TLBIRVALE1, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_RVAAE1NXS, HFGITR, TLBIRVAAE1, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_RVAE1NXS, HFGITR, TLBIRVAE1, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_RVAALE1ISNXS, HFGITR, TLBIRVAALE1IS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_RVALE1ISNXS, HFGITR, TLBIRVALE1IS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_RVAAE1ISNXS, HFGITR, TLBIRVAAE1IS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_RVAE1ISNXS, HFGITR, TLBIRVAE1IS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VAALE1ISNXS, HFGITR, TLBIVAALE1IS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VALE1ISNXS, HFGITR, TLBIVALE1IS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VAAE1ISNXS, HFGITR, TLBIVAAE1IS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_ASIDE1ISNXS, HFGITR, TLBIASIDE1IS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VAE1ISNXS, HFGITR, TLBIVAE1IS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VMALLE1ISNXS, HFGITR, TLBIVMALLE1IS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_RVAALE1OSNXS, HFGITR, TLBIRVAALE1OS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_RVALE1OSNXS, HFGITR, TLBIRVALE1OS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_RVAAE1OSNXS, HFGITR, TLBIRVAAE1OS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_RVAE1OSNXS, HFGITR, TLBIRVAE1OS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VAALE1OSNXS, HFGITR, TLBIVAALE1OS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VALE1OSNXS, HFGITR, TLBIVALE1OS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VAAE1OSNXS, HFGITR, TLBIVAAE1OS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_ASIDE1OSNXS, HFGITR, TLBIASIDE1OS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VAE1OSNXS, HFGITR, TLBIVAE1OS, 1, HCRX_FGTnXS), SR_FGF(OP_TLBI_VMALLE1OSNXS, HFGITR, TLBIVMALLE1OS, 1, HCRX_FGTnXS), SR_FGT(OP_AT_S1E1WP, HFGITR, ATS1E1WP, 1), SR_FGT(OP_AT_S1E1RP, HFGITR, ATS1E1RP, 1), SR_FGT(OP_AT_S1E0W, HFGITR, ATS1E0W, 1), SR_FGT(OP_AT_S1E0R, HFGITR, ATS1E0R, 1), SR_FGT(OP_AT_S1E1W, HFGITR, ATS1E1W, 1), SR_FGT(OP_AT_S1E1R, HFGITR, ATS1E1R, 1), SR_FGT(SYS_DC_ZVA, HFGITR, DCZVA, 1), SR_FGT(SYS_DC_GVA, HFGITR, DCZVA, 1), SR_FGT(SYS_DC_GZVA, HFGITR, DCZVA, 1), SR_FGT(SYS_DC_CIVAC, HFGITR, DCCIVAC, 1), SR_FGT(SYS_DC_CIGVAC, HFGITR, DCCIVAC, 1), SR_FGT(SYS_DC_CIGDVAC, HFGITR, DCCIVAC, 1), SR_FGT(SYS_DC_CVADP, HFGITR, DCCVADP, 1), SR_FGT(SYS_DC_CGVADP, HFGITR, DCCVADP, 1), SR_FGT(SYS_DC_CGDVADP, HFGITR, DCCVADP, 1), SR_FGT(SYS_DC_CVAP, HFGITR, DCCVAP, 1), SR_FGT(SYS_DC_CGVAP, HFGITR, DCCVAP, 1), SR_FGT(SYS_DC_CGDVAP, HFGITR, DCCVAP, 1), SR_FGT(SYS_DC_CVAU, HFGITR, DCCVAU, 1), SR_FGT(SYS_DC_CISW, HFGITR, DCCISW, 1), SR_FGT(SYS_DC_CIGSW, HFGITR, DCCISW, 1), SR_FGT(SYS_DC_CIGDSW, HFGITR, DCCISW, 1), SR_FGT(SYS_DC_CSW, HFGITR, DCCSW, 1), SR_FGT(SYS_DC_CGSW, HFGITR, DCCSW, 1), SR_FGT(SYS_DC_CGDSW, HFGITR, DCCSW, 1), SR_FGT(SYS_DC_ISW, HFGITR, DCISW, 1), SR_FGT(SYS_DC_IGSW, HFGITR, DCISW, 1), SR_FGT(SYS_DC_IGDSW, HFGITR, DCISW, 1), SR_FGT(SYS_DC_IVAC, HFGITR, DCIVAC, 1), SR_FGT(SYS_DC_IGVAC, HFGITR, DCIVAC, 1), SR_FGT(SYS_DC_IGDVAC, HFGITR, DCIVAC, 1), SR_FGT(SYS_IC_IVAU, HFGITR, ICIVAU, 1), SR_FGT(SYS_IC_IALLU, HFGITR, ICIALLU, 1), SR_FGT(SYS_IC_IALLUIS, HFGITR, ICIALLUIS, 1), /* HFGITR2_EL2 */ SR_FGT(SYS_DC_CIGDVAPS, HFGITR2, nDCCIVAPS, 0), SR_FGT(SYS_DC_CIVAPS, HFGITR2, nDCCIVAPS, 0), /* HDFGRTR_EL2 */ SR_FGT(SYS_PMBIDR_EL1, HDFGRTR, PMBIDR_EL1, 1), SR_FGT(SYS_PMSNEVFR_EL1, HDFGRTR, nPMSNEVFR_EL1, 0), SR_FGT(SYS_BRBINF_EL1(0), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(1), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(2), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(3), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(4), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(5), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(6), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(7), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(8), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(9), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(10), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(11), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(12), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(13), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(14), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(15), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(16), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(17), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(18), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(19), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(20), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(21), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(22), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(23), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(24), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(25), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(26), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(27), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(28), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(29), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(30), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINF_EL1(31), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBINFINJ_EL1, HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(0), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(1), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(2), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(3), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(4), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(5), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(6), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(7), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(8), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(9), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(10), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(11), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(12), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(13), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(14), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(15), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(16), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(17), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(18), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(19), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(20), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(21), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(22), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(23), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(24), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(25), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(26), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(27), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(28), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(29), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(30), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRC_EL1(31), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBSRCINJ_EL1, HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(0), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(1), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(2), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(3), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(4), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(5), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(6), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(7), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(8), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(9), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(10), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(11), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(12), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(13), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(14), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(15), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(16), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(17), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(18), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(19), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(20), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(21), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(22), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(23), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(24), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(25), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(26), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(27), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(28), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(29), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(30), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGT_EL1(31), HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTGTINJ_EL1, HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBTS_EL1, HDFGRTR, nBRBDATA, 0), SR_FGT(SYS_BRBCR_EL1, HDFGRTR, nBRBCTL, 0), SR_FGT(SYS_BRBFCR_EL1, HDFGRTR, nBRBCTL, 0), SR_FGT(SYS_BRBIDR0_EL1, HDFGRTR, nBRBIDR, 0), SR_FGT(SYS_PMCEID0_EL0, HDFGRTR, PMCEIDn_EL0, 1), SR_FGT(SYS_PMCEID1_EL0, HDFGRTR, PMCEIDn_EL0, 1), SR_FGT(SYS_PMUSERENR_EL0, HDFGRTR, PMUSERENR_EL0, 1), SR_FGT(SYS_TRBTRG_EL1, HDFGRTR, TRBTRG_EL1, 1), SR_FGT(SYS_TRBSR_EL1, HDFGRTR, TRBSR_EL1, 1), SR_FGT(SYS_TRBPTR_EL1, HDFGRTR, TRBPTR_EL1, 1), SR_FGT(SYS_TRBMAR_EL1, HDFGRTR, TRBMAR_EL1, 1), SR_FGT(SYS_TRBLIMITR_EL1, HDFGRTR, TRBLIMITR_EL1, 1), SR_FGT(SYS_TRBIDR_EL1, HDFGRTR, TRBIDR_EL1, 1), SR_FGT(SYS_TRBBASER_EL1, HDFGRTR, TRBBASER_EL1, 1), SR_FGT(SYS_TRCVICTLR, HDFGRTR, TRCVICTLR, 1), SR_FGT(SYS_TRCSTATR, HDFGRTR, TRCSTATR, 1), SR_FGT(SYS_TRCSSCSR(0), HDFGRTR, TRCSSCSRn, 1), SR_FGT(SYS_TRCSSCSR(1), HDFGRTR, TRCSSCSRn, 1), SR_FGT(SYS_TRCSSCSR(2), HDFGRTR, TRCSSCSRn, 1), SR_FGT(SYS_TRCSSCSR(3), HDFGRTR, TRCSSCSRn, 1), SR_FGT(SYS_TRCSSCSR(4), HDFGRTR, TRCSSCSRn, 1), SR_FGT(SYS_TRCSSCSR(5), HDFGRTR, TRCSSCSRn, 1), SR_FGT(SYS_TRCSSCSR(6), HDFGRTR, TRCSSCSRn, 1), SR_FGT(SYS_TRCSSCSR(7), HDFGRTR, TRCSSCSRn, 1), SR_FGT(SYS_TRCSEQSTR, HDFGRTR, TRCSEQSTR, 1), SR_FGT(SYS_TRCPRGCTLR, HDFGRTR, TRCPRGCTLR, 1), SR_FGT(SYS_TRCOSLSR, HDFGRTR, TRCOSLSR, 1), SR_FGT(SYS_TRCIMSPEC(0), HDFGRTR, TRCIMSPECn, 1), SR_FGT(SYS_TRCIMSPEC(1), HDFGRTR, TRCIMSPECn, 1), SR_FGT(SYS_TRCIMSPEC(2), HDFGRTR, TRCIMSPECn, 1), SR_FGT(SYS_TRCIMSPEC(3), HDFGRTR, TRCIMSPECn, 1), SR_FGT(SYS_TRCIMSPEC(4), HDFGRTR, TRCIMSPECn, 1), SR_FGT(SYS_TRCIMSPEC(5), HDFGRTR, TRCIMSPECn, 1), SR_FGT(SYS_TRCIMSPEC(6), HDFGRTR, TRCIMSPECn, 1), SR_FGT(SYS_TRCIMSPEC(7), HDFGRTR, TRCIMSPECn, 1), SR_FGT(SYS_TRCDEVARCH, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCDEVID, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR0, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR1, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR2, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR3, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR4, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR5, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR6, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR7, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR8, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR9, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR10, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR11, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR12, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCIDR13, HDFGRTR, TRCID, 1), SR_FGT(SYS_TRCCNTVR(0), HDFGRTR, TRCCNTVRn, 1), SR_FGT(SYS_TRCCNTVR(1), HDFGRTR, TRCCNTVRn, 1), SR_FGT(SYS_TRCCNTVR(2), HDFGRTR, TRCCNTVRn, 1), SR_FGT(SYS_TRCCNTVR(3), HDFGRTR, TRCCNTVRn, 1), SR_FGT(SYS_TRCCLAIMCLR, HDFGRTR, TRCCLAIM, 1), SR_FGT(SYS_TRCCLAIMSET, HDFGRTR, TRCCLAIM, 1), SR_FGT(SYS_TRCAUXCTLR, HDFGRTR, TRCAUXCTLR, 1), SR_FGT(SYS_TRCAUTHSTATUS, HDFGRTR, TRCAUTHSTATUS, 1), SR_FGT(SYS_TRCACATR(0), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(1), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(2), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(3), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(4), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(5), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(6), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(7), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(8), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(9), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(10), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(11), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(12), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(13), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(14), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACATR(15), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(0), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(1), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(2), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(3), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(4), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(5), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(6), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(7), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(8), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(9), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(10), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(11), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(12), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(13), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(14), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCACVR(15), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCBBCTLR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCCCTLR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCIDCCTLR0, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCIDCCTLR1, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCIDCVR(0), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCIDCVR(1), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCIDCVR(2), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCIDCVR(3), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCIDCVR(4), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCIDCVR(5), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCIDCVR(6), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCIDCVR(7), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCNTCTLR(0), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCNTCTLR(1), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCNTCTLR(2), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCNTCTLR(3), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCNTRLDVR(0), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCNTRLDVR(1), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCNTRLDVR(2), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCNTRLDVR(3), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCCONFIGR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCEVENTCTL0R, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCEVENTCTL1R, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCEXTINSELR(0), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCEXTINSELR(1), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCEXTINSELR(2), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCEXTINSELR(3), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCQCTLR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(2), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(3), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(4), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(5), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(6), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(7), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(8), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(9), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(10), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(11), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(12), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(13), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(14), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(15), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(16), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(17), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(18), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(19), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(20), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(21), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(22), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(23), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(24), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(25), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(26), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(27), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(28), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(29), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(30), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSCTLR(31), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCRSR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSEQEVR(0), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSEQEVR(1), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSEQEVR(2), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSEQRSTEVR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSCCR(0), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSCCR(1), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSCCR(2), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSCCR(3), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSCCR(4), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSCCR(5), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSCCR(6), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSCCR(7), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSPCICR(0), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSPCICR(1), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSPCICR(2), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSPCICR(3), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSPCICR(4), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSPCICR(5), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSPCICR(6), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSSPCICR(7), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSTALLCTLR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCSYNCPR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCTRACEIDR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCTSCTLR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVIIECTLR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVIPCSSCTLR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVISSCTLR, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVMIDCCTLR0, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVMIDCCTLR1, HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVMIDCVR(0), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVMIDCVR(1), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVMIDCVR(2), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVMIDCVR(3), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVMIDCVR(4), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVMIDCVR(5), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVMIDCVR(6), HDFGRTR, TRC, 1), SR_FGT(SYS_TRCVMIDCVR(7), HDFGRTR, TRC, 1), SR_FGT(SYS_PMSLATFR_EL1, HDFGRTR, PMSLATFR_EL1, 1), SR_FGT(SYS_PMSIRR_EL1, HDFGRTR, PMSIRR_EL1, 1), SR_FGT(SYS_PMSIDR_EL1, HDFGRTR, PMSIDR_EL1, 1), SR_FGT(SYS_PMSICR_EL1, HDFGRTR, PMSICR_EL1, 1), SR_FGT(SYS_PMSFCR_EL1, HDFGRTR, PMSFCR_EL1, 1), SR_FGT(SYS_PMSEVFR_EL1, HDFGRTR, PMSEVFR_EL1, 1), SR_FGT(SYS_PMSCR_EL1, HDFGRTR, PMSCR_EL1, 1), SR_FGT(SYS_PMBSR_EL1, HDFGRTR, PMBSR_EL1, 1), SR_FGT(SYS_PMBPTR_EL1, HDFGRTR, PMBPTR_EL1, 1), SR_FGT(SYS_PMBLIMITR_EL1, HDFGRTR, PMBLIMITR_EL1, 1), SR_FGT(SYS_PMMIR_EL1, HDFGRTR, PMMIR_EL1, 1), SR_FGT(SYS_PMSELR_EL0, HDFGRTR, PMSELR_EL0, 1), SR_FGT(SYS_PMOVSCLR_EL0, HDFGRTR, PMOVS, 1), SR_FGT(SYS_PMOVSSET_EL0, HDFGRTR, PMOVS, 1), SR_FGT(SYS_PMINTENCLR_EL1, HDFGRTR, PMINTEN, 1), SR_FGT(SYS_PMINTENSET_EL1, HDFGRTR, PMINTEN, 1), SR_FGT(SYS_PMCNTENCLR_EL0, HDFGRTR, PMCNTEN, 1), SR_FGT(SYS_PMCNTENSET_EL0, HDFGRTR, PMCNTEN, 1), SR_FGT(SYS_PMCCNTR_EL0, HDFGRTR, PMCCNTR_EL0, 1), SR_FGT(SYS_PMCCFILTR_EL0, HDFGRTR, PMCCFILTR_EL0, 1), SR_FGT_RANGE(SYS_PMEVTYPERn_EL0(0), SYS_PMEVTYPERn_EL0(30), HDFGRTR, PMEVTYPERn_EL0, 1), SR_FGT_RANGE(SYS_PMEVCNTRn_EL0(0), SYS_PMEVCNTRn_EL0(30), HDFGRTR, PMEVCNTRn_EL0, 1), SR_FGT(SYS_OSDLR_EL1, HDFGRTR, OSDLR_EL1, 1), SR_FGT(SYS_OSECCR_EL1, HDFGRTR, OSECCR_EL1, 1), SR_FGT(SYS_OSLSR_EL1, HDFGRTR, OSLSR_EL1, 1), SR_FGT(SYS_DBGPRCR_EL1, HDFGRTR, DBGPRCR_EL1, 1), SR_FGT(SYS_DBGAUTHSTATUS_EL1, HDFGRTR, DBGAUTHSTATUS_EL1, 1), SR_FGT(SYS_DBGCLAIMSET_EL1, HDFGRTR, DBGCLAIM, 1), SR_FGT(SYS_DBGCLAIMCLR_EL1, HDFGRTR, DBGCLAIM, 1), SR_FGT(SYS_MDSCR_EL1, HDFGRTR, MDSCR_EL1, 1), /* * The trap bits capture *64* debug registers per bit, but the * ARM ARM only describes the encoding for the first 16, and * we don't really support more than that anyway. */ SR_FGT(SYS_DBGWVRn_EL1(0), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(1), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(2), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(3), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(4), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(5), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(6), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(7), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(8), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(9), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(10), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(11), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(12), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(13), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(14), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWVRn_EL1(15), HDFGRTR, DBGWVRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(0), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(1), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(2), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(3), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(4), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(5), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(6), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(7), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(8), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(9), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(10), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(11), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(12), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(13), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(14), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGWCRn_EL1(15), HDFGRTR, DBGWCRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(0), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(1), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(2), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(3), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(4), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(5), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(6), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(7), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(8), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(9), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(10), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(11), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(12), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(13), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(14), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBVRn_EL1(15), HDFGRTR, DBGBVRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(0), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(1), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(2), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(3), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(4), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(5), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(6), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(7), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(8), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(9), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(10), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(11), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(12), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(13), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(14), HDFGRTR, DBGBCRn_EL1, 1), SR_FGT(SYS_DBGBCRn_EL1(15), HDFGRTR, DBGBCRn_EL1, 1), /* HDFGRTR2_EL2 */ SR_FGT(SYS_MDSELR_EL1, HDFGRTR2, nMDSELR_EL1, 0), SR_FGT(SYS_MDSTEPOP_EL1, HDFGRTR2, nMDSTEPOP_EL1, 0), SR_FGT(SYS_PMCCNTSVR_EL1, HDFGRTR2, nPMSSDATA, 0), SR_FGT_RANGE(SYS_PMEVCNTSVRn_EL1(0), SYS_PMEVCNTSVRn_EL1(30), HDFGRTR2, nPMSSDATA, 0), SR_FGT(SYS_PMICNTSVR_EL1, HDFGRTR2, nPMSSDATA, 0), SR_FGT(SYS_PMECR_EL1, HDFGRTR2, nPMECR_EL1, 0), SR_FGT(SYS_PMIAR_EL1, HDFGRTR2, nPMIAR_EL1, 0), SR_FGT(SYS_PMICFILTR_EL0, HDFGRTR2, nPMICFILTR_EL0, 0), SR_FGT(SYS_PMICNTR_EL0, HDFGRTR2, nPMICNTR_EL0, 0), SR_FGT(SYS_PMSSCR_EL1, HDFGRTR2, nPMSSCR_EL1, 0), SR_FGT(SYS_PMUACR_EL1, HDFGRTR2, nPMUACR_EL1, 0), SR_FGT(SYS_SPMACCESSR_EL1, HDFGRTR2, nSPMACCESSR_EL1, 0), SR_FGT(SYS_SPMCFGR_EL1, HDFGRTR2, nSPMID, 0), SR_FGT(SYS_SPMDEVARCH_EL1, HDFGRTR2, nSPMID, 0), SR_FGT(SYS_SPMCGCRn_EL1(0), HDFGRTR2, nSPMID, 0), SR_FGT(SYS_SPMCGCRn_EL1(1), HDFGRTR2, nSPMID, 0), SR_FGT(SYS_SPMIIDR_EL1, HDFGRTR2, nSPMID, 0), SR_FGT(SYS_SPMCNTENCLR_EL0, HDFGRTR2, nSPMCNTEN, 0), SR_FGT(SYS_SPMCNTENSET_EL0, HDFGRTR2, nSPMCNTEN, 0), SR_FGT(SYS_SPMCR_EL0, HDFGRTR2, nSPMCR_EL0, 0), SR_FGT(SYS_SPMDEVAFF_EL1, HDFGRTR2, nSPMDEVAFF_EL1, 0), /* * We have up to 64 of these registers in ranges of 16, banked via * SPMSELR_EL0.BANK. We're only concerned with the accessors here, * not the architectural registers. */ SR_FGT_RANGE(SYS_SPMEVCNTRn_EL0(0), SYS_SPMEVCNTRn_EL0(15), HDFGRTR2, nSPMEVCNTRn_EL0, 0), SR_FGT_RANGE(SYS_SPMEVFILT2Rn_EL0(0), SYS_SPMEVFILT2Rn_EL0(15), HDFGRTR2, nSPMEVTYPERn_EL0, 0), SR_FGT_RANGE(SYS_SPMEVFILTRn_EL0(0), SYS_SPMEVFILTRn_EL0(15), HDFGRTR2, nSPMEVTYPERn_EL0, 0), SR_FGT_RANGE(SYS_SPMEVTYPERn_EL0(0), SYS_SPMEVTYPERn_EL0(15), HDFGRTR2, nSPMEVTYPERn_EL0, 0), SR_FGT(SYS_SPMINTENCLR_EL1, HDFGRTR2, nSPMINTEN, 0), SR_FGT(SYS_SPMINTENSET_EL1, HDFGRTR2, nSPMINTEN, 0), SR_FGT(SYS_SPMOVSCLR_EL0, HDFGRTR2, nSPMOVS, 0), SR_FGT(SYS_SPMOVSSET_EL0, HDFGRTR2, nSPMOVS, 0), SR_FGT(SYS_SPMSCR_EL1, HDFGRTR2, nSPMSCR_EL1, 0), SR_FGT(SYS_SPMSELR_EL0, HDFGRTR2, nSPMSELR_EL0, 0), SR_FGT(SYS_TRCITECR_EL1, HDFGRTR2, nTRCITECR_EL1, 0), SR_FGT(SYS_PMBMAR_EL1, HDFGRTR2, nPMBMAR_EL1, 0), SR_FGT(SYS_PMSDSFR_EL1, HDFGRTR2, nPMSDSFR_EL1, 0), SR_FGT(SYS_TRBMPAM_EL1, HDFGRTR2, nTRBMPAM_EL1, 0), /* * HDFGWTR_EL2 * * Although HDFGRTR_EL2 and HDFGWTR_EL2 registers largely * overlap in their bit assignment, there are a number of bits * that are RES0 on one side, and an actual trap bit on the * other. The policy chosen here is to describe all the * read-side mappings, and only the write-side mappings that * differ from the read side, and the trap handler will pick * the correct shadow register based on the access type. * * Same model applies to the FEAT_FGT2 registers. */ SR_FGT(SYS_TRFCR_EL1, HDFGWTR, TRFCR_EL1, 1), SR_FGT(SYS_TRCOSLAR, HDFGWTR, TRCOSLAR, 1), SR_FGT(SYS_PMCR_EL0, HDFGWTR, PMCR_EL0, 1), SR_FGT(SYS_PMSWINC_EL0, HDFGWTR, PMSWINC_EL0, 1), SR_FGT(SYS_OSLAR_EL1, HDFGWTR, OSLAR_EL1, 1), /* HDFGWTR2_EL2 */ SR_FGT(SYS_PMZR_EL0, HDFGWTR2, nPMZR_EL0, 0), SR_FGT(SYS_SPMZR_EL0, HDFGWTR2, nSPMEVCNTRn_EL0, 0), /* * HAFGRTR_EL2 */ SR_FGT(SYS_AMEVTYPER1_EL0(15), HAFGRTR, AMEVTYPER115_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(14), HAFGRTR, AMEVTYPER114_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(13), HAFGRTR, AMEVTYPER113_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(12), HAFGRTR, AMEVTYPER112_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(11), HAFGRTR, AMEVTYPER111_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(10), HAFGRTR, AMEVTYPER110_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(9), HAFGRTR, AMEVTYPER19_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(8), HAFGRTR, AMEVTYPER18_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(7), HAFGRTR, AMEVTYPER17_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(6), HAFGRTR, AMEVTYPER16_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(5), HAFGRTR, AMEVTYPER15_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(4), HAFGRTR, AMEVTYPER14_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(3), HAFGRTR, AMEVTYPER13_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(2), HAFGRTR, AMEVTYPER12_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(1), HAFGRTR, AMEVTYPER11_EL0, 1), SR_FGT(SYS_AMEVTYPER1_EL0(0), HAFGRTR, AMEVTYPER10_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(15), HAFGRTR, AMEVCNTR115_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(14), HAFGRTR, AMEVCNTR114_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(13), HAFGRTR, AMEVCNTR113_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(12), HAFGRTR, AMEVCNTR112_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(11), HAFGRTR, AMEVCNTR111_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(10), HAFGRTR, AMEVCNTR110_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(9), HAFGRTR, AMEVCNTR19_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(8), HAFGRTR, AMEVCNTR18_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(7), HAFGRTR, AMEVCNTR17_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(6), HAFGRTR, AMEVCNTR16_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(5), HAFGRTR, AMEVCNTR15_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(4), HAFGRTR, AMEVCNTR14_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(3), HAFGRTR, AMEVCNTR13_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(2), HAFGRTR, AMEVCNTR12_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(1), HAFGRTR, AMEVCNTR11_EL0, 1), SR_FGT(SYS_AMEVCNTR1_EL0(0), HAFGRTR, AMEVCNTR10_EL0, 1), SR_FGT(SYS_AMCNTENCLR1_EL0, HAFGRTR, AMCNTEN1, 1), SR_FGT(SYS_AMCNTENSET1_EL0, HAFGRTR, AMCNTEN1, 1), SR_FGT(SYS_AMCNTENCLR0_EL0, HAFGRTR, AMCNTEN0, 1), SR_FGT(SYS_AMCNTENSET0_EL0, HAFGRTR, AMCNTEN0, 1), SR_FGT(SYS_AMEVCNTR0_EL0(3), HAFGRTR, AMEVCNTR03_EL0, 1), SR_FGT(SYS_AMEVCNTR0_EL0(2), HAFGRTR, AMEVCNTR02_EL0, 1), SR_FGT(SYS_AMEVCNTR0_EL0(1), HAFGRTR, AMEVCNTR01_EL0, 1), SR_FGT(SYS_AMEVCNTR0_EL0(0), HAFGRTR, AMEVCNTR00_EL0, 1), }; /* * Additional FGTs that do not fire with ESR_EL2.EC==0x18. This table * isn't used for exception routing, but only as a promise that the * trap is handled somewhere else. */ static const union trap_config non_0x18_fgt[] __initconst = { FGT(HFGITR, PSBCSYNC, 1), FGT(HFGITR, nGCSSTR_EL1, 0), FGT(HFGITR, SVC_EL1, 1), FGT(HFGITR, SVC_EL0, 1), FGT(HFGITR, ERET, 1), FGT(HFGITR2, TSBCSYNC, 1), }; static union trap_config get_trap_config(u32 sysreg) { return (union trap_config) { .val = xa_to_value(xa_load(&sr_forward_xa, sysreg)), }; } static __init void print_nv_trap_error(const struct encoding_to_trap_config *tc, const char *type, int err) { kvm_err("%s line %d encoding range " "(%d, %d, %d, %d, %d) - (%d, %d, %d, %d, %d) (err=%d)\n", type, tc->line, sys_reg_Op0(tc->encoding), sys_reg_Op1(tc->encoding), sys_reg_CRn(tc->encoding), sys_reg_CRm(tc->encoding), sys_reg_Op2(tc->encoding), sys_reg_Op0(tc->end), sys_reg_Op1(tc->end), sys_reg_CRn(tc->end), sys_reg_CRm(tc->end), sys_reg_Op2(tc->end), err); } static u32 encoding_next(u32 encoding) { u8 op0, op1, crn, crm, op2; op0 = sys_reg_Op0(encoding); op1 = sys_reg_Op1(encoding); crn = sys_reg_CRn(encoding); crm = sys_reg_CRm(encoding); op2 = sys_reg_Op2(encoding); if (op2 < Op2_mask) return sys_reg(op0, op1, crn, crm, op2 + 1); if (crm < CRm_mask) return sys_reg(op0, op1, crn, crm + 1, 0); if (crn < CRn_mask) return sys_reg(op0, op1, crn + 1, 0, 0); if (op1 < Op1_mask) return sys_reg(op0, op1 + 1, 0, 0, 0); return sys_reg(op0 + 1, 0, 0, 0, 0); } #define FGT_MASKS(__n, __m) \ struct fgt_masks __n = { .str = #__m, .res0 = __m, } FGT_MASKS(hfgrtr_masks, HFGRTR_EL2_RES0); FGT_MASKS(hfgwtr_masks, HFGWTR_EL2_RES0); FGT_MASKS(hfgitr_masks, HFGITR_EL2_RES0); FGT_MASKS(hdfgrtr_masks, HDFGRTR_EL2_RES0); FGT_MASKS(hdfgwtr_masks, HDFGWTR_EL2_RES0); FGT_MASKS(hafgrtr_masks, HAFGRTR_EL2_RES0); FGT_MASKS(hfgrtr2_masks, HFGRTR2_EL2_RES0); FGT_MASKS(hfgwtr2_masks, HFGWTR2_EL2_RES0); FGT_MASKS(hfgitr2_masks, HFGITR2_EL2_RES0); FGT_MASKS(hdfgrtr2_masks, HDFGRTR2_EL2_RES0); FGT_MASKS(hdfgwtr2_masks, HDFGWTR2_EL2_RES0); static __init bool aggregate_fgt(union trap_config tc) { struct fgt_masks *rmasks, *wmasks; switch (tc.fgt) { case HFGRTR_GROUP: rmasks = &hfgrtr_masks; wmasks = &hfgwtr_masks; break; case HDFGRTR_GROUP: rmasks = &hdfgrtr_masks; wmasks = &hdfgwtr_masks; break; case HAFGRTR_GROUP: rmasks = &hafgrtr_masks; wmasks = NULL; break; case HFGITR_GROUP: rmasks = &hfgitr_masks; wmasks = NULL; break; case HFGRTR2_GROUP: rmasks = &hfgrtr2_masks; wmasks = &hfgwtr2_masks; break; case HDFGRTR2_GROUP: rmasks = &hdfgrtr2_masks; wmasks = &hdfgwtr2_masks; break; case HFGITR2_GROUP: rmasks = &hfgitr2_masks; wmasks = NULL; break; } /* * A bit can be reserved in either the R or W register, but * not both. */ if ((BIT(tc.bit) & rmasks->res0) && (!wmasks || (BIT(tc.bit) & wmasks->res0))) return false; if (tc.pol) rmasks->mask |= BIT(tc.bit) & ~rmasks->res0; else rmasks->nmask |= BIT(tc.bit) & ~rmasks->res0; if (wmasks) { if (tc.pol) wmasks->mask |= BIT(tc.bit) & ~wmasks->res0; else wmasks->nmask |= BIT(tc.bit) & ~wmasks->res0; } return true; } static __init int check_fgt_masks(struct fgt_masks *masks) { unsigned long duplicate = masks->mask & masks->nmask; u64 res0 = masks->res0; int ret = 0; if (duplicate) { int i; for_each_set_bit(i, &duplicate, 64) { kvm_err("%s[%d] bit has both polarities\n", masks->str, i); } ret = -EINVAL; } masks->res0 = ~(masks->mask | masks->nmask); if (masks->res0 != res0) kvm_info("Implicit %s = %016llx, expecting %016llx\n", masks->str, masks->res0, res0); return ret; } static __init int check_all_fgt_masks(int ret) { static struct fgt_masks * const masks[] __initconst = { &hfgrtr_masks, &hfgwtr_masks, &hfgitr_masks, &hdfgrtr_masks, &hdfgwtr_masks, &hafgrtr_masks, &hfgrtr2_masks, &hfgwtr2_masks, &hfgitr2_masks, &hdfgrtr2_masks, &hdfgwtr2_masks, }; int err = 0; for (int i = 0; i < ARRAY_SIZE(masks); i++) err |= check_fgt_masks(masks[i]); return ret ?: err; } #define for_each_encoding_in(__x, __s, __e) \ for (u32 __x = __s; __x <= __e; __x = encoding_next(__x)) int __init populate_nv_trap_config(void) { int ret = 0; BUILD_BUG_ON(sizeof(union trap_config) != sizeof(void *)); BUILD_BUG_ON(__NR_CGT_GROUP_IDS__ > BIT(TC_CGT_BITS)); BUILD_BUG_ON(__NR_FGT_GROUP_IDS__ > BIT(TC_FGT_BITS)); BUILD_BUG_ON(__NR_FG_FILTER_IDS__ > BIT(TC_FGF_BITS)); BUILD_BUG_ON(__HCRX_EL2_MASK & __HCRX_EL2_nMASK); for (int i = 0; i < ARRAY_SIZE(encoding_to_cgt); i++) { const struct encoding_to_trap_config *cgt = &encoding_to_cgt[i]; void *prev; if (cgt->tc.val & BIT(63)) { kvm_err("CGT[%d] has MBZ bit set\n", i); ret = -EINVAL; } for_each_encoding_in(enc, cgt->encoding, cgt->end) { prev = xa_store(&sr_forward_xa, enc, xa_mk_value(cgt->tc.val), GFP_KERNEL); if (prev && !xa_is_err(prev)) { ret = -EINVAL; print_nv_trap_error(cgt, "Duplicate CGT", ret); } if (xa_is_err(prev)) { ret = xa_err(prev); print_nv_trap_error(cgt, "Failed CGT insertion", ret); } } } if (__HCRX_EL2_RES0 != HCRX_EL2_RES0) kvm_info("Sanitised HCR_EL2_RES0 = %016llx, expecting %016llx\n", __HCRX_EL2_RES0, HCRX_EL2_RES0); kvm_info("nv: %ld coarse grained trap handlers\n", ARRAY_SIZE(encoding_to_cgt)); if (!cpus_have_final_cap(ARM64_HAS_FGT)) goto check_mcb; for (int i = 0; i < ARRAY_SIZE(encoding_to_fgt); i++) { const struct encoding_to_trap_config *fgt = &encoding_to_fgt[i]; union trap_config tc; void *prev; if (fgt->tc.fgt >= __NR_FGT_GROUP_IDS__) { ret = -EINVAL; print_nv_trap_error(fgt, "Invalid FGT", ret); } for_each_encoding_in(enc, fgt->encoding, fgt->end) { tc = get_trap_config(enc); if (tc.fgt) { ret = -EINVAL; print_nv_trap_error(fgt, "Duplicate FGT", ret); } tc.val |= fgt->tc.val; prev = xa_store(&sr_forward_xa, enc, xa_mk_value(tc.val), GFP_KERNEL); if (xa_is_err(prev)) { ret = xa_err(prev); print_nv_trap_error(fgt, "Failed FGT insertion", ret); } if (!aggregate_fgt(tc)) { ret = -EINVAL; print_nv_trap_error(fgt, "FGT bit is reserved", ret); } } } for (int i = 0; i < ARRAY_SIZE(non_0x18_fgt); i++) { if (!aggregate_fgt(non_0x18_fgt[i])) { ret = -EINVAL; kvm_err("non_0x18_fgt[%d] is reserved\n", i); } } ret = check_all_fgt_masks(ret); kvm_info("nv: %ld fine grained trap handlers\n", ARRAY_SIZE(encoding_to_fgt)); check_mcb: for (int id = __MULTIPLE_CONTROL_BITS__; id < __COMPLEX_CONDITIONS__; id++) { const enum cgt_group_id *cgids; cgids = coarse_control_combo[id - __MULTIPLE_CONTROL_BITS__]; for (int i = 0; cgids[i] != __RESERVED__; i++) { if (cgids[i] >= __MULTIPLE_CONTROL_BITS__ && cgids[i] < __COMPLEX_CONDITIONS__) { kvm_err("Recursive MCB %d/%d\n", id, cgids[i]); ret = -EINVAL; } } } if (ret) xa_destroy(&sr_forward_xa); return ret; } int __init populate_sysreg_config(const struct sys_reg_desc *sr, unsigned int idx) { union trap_config tc; u32 encoding; void *ret; /* * 0 is a valid value for the index, but not for the storage. * We'll store (idx+1), so check against an offset'd limit. */ if (idx >= (BIT(TC_SRI_BITS) - 1)) { kvm_err("sysreg %s (%d) out of range\n", sr->name, idx); return -EINVAL; } encoding = sys_reg(sr->Op0, sr->Op1, sr->CRn, sr->CRm, sr->Op2); tc = get_trap_config(encoding); if (tc.sri) { kvm_err("sysreg %s (%d) duplicate entry (%d)\n", sr->name, idx - 1, tc.sri); return -EINVAL; } tc.sri = idx + 1; ret = xa_store(&sr_forward_xa, encoding, xa_mk_value(tc.val), GFP_KERNEL); return xa_err(ret); } static enum trap_behaviour get_behaviour(struct kvm_vcpu *vcpu, const struct trap_bits *tb) { enum trap_behaviour b = BEHAVE_HANDLE_LOCALLY; u64 val; val = __vcpu_sys_reg(vcpu, tb->index); if ((val & tb->mask) == tb->value) b |= tb->behaviour; return b; } static enum trap_behaviour __compute_trap_behaviour(struct kvm_vcpu *vcpu, const enum cgt_group_id id, enum trap_behaviour b) { switch (id) { const enum cgt_group_id *cgids; case __RESERVED__ ... __MULTIPLE_CONTROL_BITS__ - 1: if (likely(id != __RESERVED__)) b |= get_behaviour(vcpu, &coarse_trap_bits[id]); break; case __MULTIPLE_CONTROL_BITS__ ... __COMPLEX_CONDITIONS__ - 1: /* Yes, this is recursive. Don't do anything stupid. */ cgids = coarse_control_combo[id - __MULTIPLE_CONTROL_BITS__]; for (int i = 0; cgids[i] != __RESERVED__; i++) b |= __compute_trap_behaviour(vcpu, cgids[i], b); break; default: if (ARRAY_SIZE(ccc)) b |= ccc[id - __COMPLEX_CONDITIONS__](vcpu); break; } return b; } static enum trap_behaviour compute_trap_behaviour(struct kvm_vcpu *vcpu, const union trap_config tc) { enum trap_behaviour b = BEHAVE_HANDLE_LOCALLY; return __compute_trap_behaviour(vcpu, tc.cgt, b); } static u64 kvm_get_sysreg_res0(struct kvm *kvm, enum vcpu_sysreg sr) { struct kvm_sysreg_masks *masks; /* Only handle the VNCR-backed regs for now */ if (sr < __VNCR_START__) return 0; masks = kvm->arch.sysreg_masks; return masks->mask[sr - __VNCR_START__].res0; } static bool check_fgt_bit(struct kvm_vcpu *vcpu, enum vcpu_sysreg sr, const union trap_config tc) { struct kvm *kvm = vcpu->kvm; u64 val; /* * KVM doesn't know about any FGTs that apply to the host, and hopefully * that'll remain the case. */ if (is_hyp_ctxt(vcpu)) return false; val = __vcpu_sys_reg(vcpu, sr); if (tc.pol) return (val & BIT(tc.bit)); /* * FGTs with negative polarities are an absolute nightmare, as * we need to evaluate the bit in the light of the feature * that defines it. WTF were they thinking? * * So let's check if the bit has been earmarked as RES0, as * this indicates an unimplemented feature. */ if (val & BIT(tc.bit)) return false; return !(kvm_get_sysreg_res0(kvm, sr) & BIT(tc.bit)); } bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index) { enum vcpu_sysreg fgtreg; union trap_config tc; enum trap_behaviour b; bool is_read; u32 sysreg; u64 esr; esr = kvm_vcpu_get_esr(vcpu); sysreg = esr_sys64_to_sysreg(esr); is_read = (esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ; tc = get_trap_config(sysreg); /* * A value of 0 for the whole entry means that we know nothing * for this sysreg, and that it cannot be re-injected into the * nested hypervisor. In this situation, let's cut it short. */ if (!tc.val) goto local; /* * If a sysreg can be trapped using a FGT, first check whether we * trap for the purpose of forbidding the feature. In that case, * inject an UNDEF. */ if (tc.fgt != __NO_FGT_GROUP__ && (vcpu->kvm->arch.fgu[tc.fgt] & BIT(tc.bit))) { kvm_inject_undefined(vcpu); return true; } /* * If we're not nesting, immediately return to the caller, with the * sysreg index, should we have it. */ if (!vcpu_has_nv(vcpu)) goto local; /* * There are a few traps that take effect InHost, but are constrained * to EL0. Don't bother with computing the trap behaviour if the vCPU * isn't in EL0. */ if (is_hyp_ctxt(vcpu) && !vcpu_is_host_el0(vcpu)) goto local; switch ((enum fgt_group_id)tc.fgt) { case __NO_FGT_GROUP__: break; case HFGRTR_GROUP: fgtreg = is_read ? HFGRTR_EL2 : HFGWTR_EL2; break; case HDFGRTR_GROUP: fgtreg = is_read ? HDFGRTR_EL2 : HDFGWTR_EL2; break; case HAFGRTR_GROUP: fgtreg = HAFGRTR_EL2; break; case HFGITR_GROUP: fgtreg = HFGITR_EL2; switch (tc.fgf) { u64 tmp; case __NO_FGF__: break; case HCRX_FGTnXS: tmp = __vcpu_sys_reg(vcpu, HCRX_EL2); if (tmp & HCRX_EL2_FGTnXS) tc.fgt = __NO_FGT_GROUP__; } break; case HFGRTR2_GROUP: fgtreg = is_read ? HFGRTR2_EL2 : HFGWTR2_EL2; break; case HDFGRTR2_GROUP: fgtreg = is_read ? HDFGRTR2_EL2 : HDFGWTR2_EL2; break; case HFGITR2_GROUP: fgtreg = HFGITR2_EL2; break; default: /* Something is really wrong, bail out */ WARN_ONCE(1, "Bad FGT group (encoding %08x, config %016llx)\n", sysreg, tc.val); goto local; } if (tc.fgt != __NO_FGT_GROUP__ && check_fgt_bit(vcpu, fgtreg, tc)) goto inject; b = compute_trap_behaviour(vcpu, tc); if (!(b & BEHAVE_FORWARD_IN_HOST_EL0) && vcpu_is_host_el0(vcpu)) goto local; if (((b & BEHAVE_FORWARD_READ) && is_read) || ((b & BEHAVE_FORWARD_WRITE) && !is_read)) goto inject; local: if (!tc.sri) { struct sys_reg_params params; params = esr_sys64_to_params(esr); /* * Check for the IMPDEF range, as per DDI0487 J.a, * D18.3.2 Reserved encodings for IMPLEMENTATION * DEFINED registers. */ if (!(params.Op0 == 3 && (params.CRn & 0b1011) == 0b1011)) print_sys_reg_msg(¶ms, "Unsupported guest access at: %lx\n", *vcpu_pc(vcpu)); kvm_inject_undefined(vcpu); return true; } *sr_index = tc.sri - 1; return false; inject: trace_kvm_forward_sysreg_trap(vcpu, sysreg, is_read); kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu)); return true; } static bool __forward_traps(struct kvm_vcpu *vcpu, unsigned int reg, u64 control_bit) { if (is_nested_ctxt(vcpu) && (__vcpu_sys_reg(vcpu, reg) & control_bit)) { kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu)); return true; } return false; } static bool forward_hcr_traps(struct kvm_vcpu *vcpu, u64 control_bit) { return __forward_traps(vcpu, HCR_EL2, control_bit); } bool forward_smc_trap(struct kvm_vcpu *vcpu) { return forward_hcr_traps(vcpu, HCR_TSC); } static bool forward_mdcr_traps(struct kvm_vcpu *vcpu, u64 control_bit) { return __forward_traps(vcpu, MDCR_EL2, control_bit); } bool forward_debug_exception(struct kvm_vcpu *vcpu) { return forward_mdcr_traps(vcpu, MDCR_EL2_TDE); } static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr) { u64 mode = spsr & PSR_MODE_MASK; /* * Possible causes for an Illegal Exception Return from EL2: * - trying to return to EL3 * - trying to return to an illegal M value * - trying to return to a 32bit EL * - trying to return to EL1 with HCR_EL2.TGE set */ if (mode == PSR_MODE_EL3t || mode == PSR_MODE_EL3h || mode == 0b00001 || (mode & BIT(1)) || (spsr & PSR_MODE32_BIT) || (vcpu_el2_tge_is_set(vcpu) && (mode == PSR_MODE_EL1t || mode == PSR_MODE_EL1h))) { /* * The guest is playing with our nerves. Preserve EL, SP, * masks, flags from the existing PSTATE, and set IL. * The HW will then generate an Illegal State Exception * immediately after ERET. */ spsr = *vcpu_cpsr(vcpu); spsr &= (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT | PSR_MODE_MASK | PSR_MODE32_BIT); spsr |= PSR_IL_BIT; } return spsr; } void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) { u64 spsr, elr, esr; spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2); spsr = kvm_check_illegal_exception_return(vcpu, spsr); /* Check for an ERETAx */ esr = kvm_vcpu_get_esr(vcpu); if (esr_iss_is_eretax(esr) && !kvm_auth_eretax(vcpu, &elr)) { /* * Oh no, ERETAx failed to authenticate. * * If we have FPACCOMBINE and we don't have a pending * Illegal Execution State exception (which has priority * over FPAC), deliver an exception right away. * * Otherwise, let the mangled ELR value trickle down the * ERET handling, and the guest will have a little surprise. */ if (kvm_has_pauth(vcpu->kvm, FPACCOMBINE) && !(spsr & PSR_IL_BIT)) { esr &= ESR_ELx_ERET_ISS_ERETA; esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_FPAC); kvm_inject_nested_sync(vcpu, esr); return; } } preempt_disable(); vcpu_set_flag(vcpu, IN_NESTED_ERET); kvm_arch_vcpu_put(vcpu); if (!esr_iss_is_eretax(esr)) elr = __vcpu_sys_reg(vcpu, ELR_EL2); trace_kvm_nested_eret(vcpu, elr, spsr); *vcpu_pc(vcpu) = elr; *vcpu_cpsr(vcpu) = spsr; kvm_arch_vcpu_load(vcpu, smp_processor_id()); vcpu_clear_flag(vcpu, IN_NESTED_ERET); preempt_enable(); if (kvm_vcpu_has_pmu(vcpu)) kvm_pmu_nested_transition(vcpu); } static void kvm_inject_el2_exception(struct kvm_vcpu *vcpu, u64 esr_el2, enum exception_type type) { trace_kvm_inject_nested_exception(vcpu, esr_el2, type); switch (type) { case except_type_sync: kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SYNC); vcpu_write_sys_reg(vcpu, esr_el2, ESR_EL2); break; case except_type_irq: kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_IRQ); break; case except_type_serror: kvm_pend_exception(vcpu, EXCEPT_AA64_EL2_SERR); break; default: WARN_ONCE(1, "Unsupported EL2 exception injection %d\n", type); } } /* * Emulate taking an exception to EL2. * See ARM ARM J8.1.2 AArch64.TakeException() */ static int kvm_inject_nested(struct kvm_vcpu *vcpu, u64 esr_el2, enum exception_type type) { u64 pstate, mode; bool direct_inject; if (!vcpu_has_nv(vcpu)) { kvm_err("Unexpected call to %s for the non-nesting configuration\n", __func__); return -EINVAL; } /* * As for ERET, we can avoid doing too much on the injection path by * checking that we either took the exception from a VHE host * userspace or from vEL2. In these cases, there is no change in * translation regime (or anything else), so let's do as little as * possible. */ pstate = *vcpu_cpsr(vcpu); mode = pstate & (PSR_MODE_MASK | PSR_MODE32_BIT); direct_inject = (mode == PSR_MODE_EL0t && vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)); direct_inject |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t); if (direct_inject) { kvm_inject_el2_exception(vcpu, esr_el2, type); return 1; } preempt_disable(); /* * We may have an exception or PC update in the EL0/EL1 context. * Commit it before entering EL2. */ __kvm_adjust_pc(vcpu); kvm_arch_vcpu_put(vcpu); kvm_inject_el2_exception(vcpu, esr_el2, type); /* * A hard requirement is that a switch between EL1 and EL2 * contexts has to happen between a put/load, so that we can * pick the correct timer and interrupt configuration, among * other things. * * Make sure the exception actually took place before we load * the new context. */ __kvm_adjust_pc(vcpu); kvm_arch_vcpu_load(vcpu, smp_processor_id()); preempt_enable(); if (kvm_vcpu_has_pmu(vcpu)) kvm_pmu_nested_transition(vcpu); return 1; } int kvm_inject_nested_sync(struct kvm_vcpu *vcpu, u64 esr_el2) { return kvm_inject_nested(vcpu, esr_el2, except_type_sync); } int kvm_inject_nested_irq(struct kvm_vcpu *vcpu) { /* * Do not inject an irq if the: * - Current exception level is EL2, and * - virtual HCR_EL2.TGE == 0 * - virtual HCR_EL2.IMO == 0 * * See Table D1-17 "Physical interrupt target and masking when EL3 is * not implemented and EL2 is implemented" in ARM DDI 0487C.a. */ if (vcpu_is_el2(vcpu) && !vcpu_el2_tge_is_set(vcpu) && !(__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_IMO)) return 1; /* esr_el2 value doesn't matter for exits due to irqs. */ return kvm_inject_nested(vcpu, 0, except_type_irq); } int kvm_inject_nested_sea(struct kvm_vcpu *vcpu, bool iabt, u64 addr) { u64 esr = FIELD_PREP(ESR_ELx_EC_MASK, iabt ? ESR_ELx_EC_IABT_LOW : ESR_ELx_EC_DABT_LOW); esr |= ESR_ELx_FSC_EXTABT | ESR_ELx_IL; vcpu_write_sys_reg(vcpu, addr, FAR_EL2); if (__vcpu_sys_reg(vcpu, SCTLR2_EL2) & SCTLR2_EL1_EASE) return kvm_inject_nested(vcpu, esr, except_type_serror); return kvm_inject_nested_sync(vcpu, esr); } int kvm_inject_nested_serror(struct kvm_vcpu *vcpu, u64 esr) { /* * Hardware sets up the EC field when propagating ESR as a result of * vSError injection. Manually populate EC for an emulated SError * exception. */ esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SERROR); return kvm_inject_nested(vcpu, esr, except_type_serror); } |
| 86 927 501 501 501 499 177 177 922 923 42 42 922 921 921 524 524 478 479 479 201 856 831 832 834 3 3 390 391 391 262 262 72 72 97 97 37 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * * Support six policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * * interleave Allocate memory interleaved over a set of nodes, * with normal fallback if it fails. * For VMA based allocations this interleaves based on the * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. * * weighted interleave * Allocate memory interleaved over a set of nodes based on * a set of weights (per-node), with normal fallback if it * fails. Otherwise operates the same as interleave. * Example: nodeset(0,1) & weights (2,1) - 2 pages allocated * on node 0 for every 1 page allocated on node 1. * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. * * preferred many Try a set of nodes first before normal fallback. This is * similar to preferred without the special case. * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. * * The process policy is applied for most non interrupt memory allocations * in that process' context. Interrupts ignore the policies and always * try to allocate on the local CPU. The VMA policy is only applied for memory * allocations for a VMA in the VM. * * Currently there are a few corner cases in swapping where the policy * is not applied, but the majority should be handled. When process policy * is used it is not remembered over swap outs/swap ins. * * Only the highest zone in the zone hierarchy gets policied. Allocations * requesting a lower zone just use default policy. This implies that * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * * For shmem/tmpfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ /* Notebook: fix mmap readahead to honour policy and enable policy for any page cache object statistics for bigpages global policy for page cache? currently it uses process policy. Requires first item above. handle mremap for shared memory (currently ignored for the policy) grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/ptrace.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/migrate.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/printk.h> #include <linux/swapops.h> #include <linux/gcd.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <linux/uaccess.h> #include <linux/memory.h> #include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ #define MPOL_MF_WRLOCK (MPOL_MF_INTERNAL << 2) /* Write-lock walked vmas */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; /* * weightiness balances the tradeoff between small weights (cycles through nodes * faster, more fair/even distribution) and large weights (smaller errors * between actual bandwidth ratios and weight ratios). 32 is a number that has * been found to perform at a reasonable compromise between the two goals. */ static const int weightiness = 32; /* * A null weighted_interleave_state is interpreted as having .mode="auto", * and .iw_table is interpreted as an array of 1s with length nr_node_ids. */ struct weighted_interleave_state { bool mode_auto; u8 iw_table[]; }; static struct weighted_interleave_state __rcu *wi_state; static unsigned int *node_bw_table; /* * wi_state_lock protects both wi_state and node_bw_table. * node_bw_table is only used by writers to update wi_state. */ static DEFINE_MUTEX(wi_state_lock); static u8 get_il_weight(int node) { struct weighted_interleave_state *state; u8 weight = 1; rcu_read_lock(); state = rcu_dereference(wi_state); if (state) weight = state->iw_table[node]; rcu_read_unlock(); return weight; } /* * Convert bandwidth values into weighted interleave weights. * Call with wi_state_lock. */ static void reduce_interleave_weights(unsigned int *bw, u8 *new_iw) { u64 sum_bw = 0; unsigned int cast_sum_bw, scaling_factor = 1, iw_gcd = 0; int nid; for_each_node_state(nid, N_MEMORY) sum_bw += bw[nid]; /* Scale bandwidths to whole numbers in the range [1, weightiness] */ for_each_node_state(nid, N_MEMORY) { /* * Try not to perform 64-bit division. * If sum_bw < scaling_factor, then sum_bw < U32_MAX. * If sum_bw > scaling_factor, then round the weight up to 1. */ scaling_factor = weightiness * bw[nid]; if (bw[nid] && sum_bw < scaling_factor) { cast_sum_bw = (unsigned int)sum_bw; new_iw[nid] = scaling_factor / cast_sum_bw; } else { new_iw[nid] = 1; } if (!iw_gcd) iw_gcd = new_iw[nid]; iw_gcd = gcd(iw_gcd, new_iw[nid]); } /* 1:2 is strictly better than 16:32. Reduce by the weights' GCD. */ for_each_node_state(nid, N_MEMORY) new_iw[nid] /= iw_gcd; } int mempolicy_set_node_perf(unsigned int node, struct access_coordinate *coords) { struct weighted_interleave_state *new_wi_state, *old_wi_state = NULL; unsigned int *old_bw, *new_bw; unsigned int bw_val; int i; bw_val = min(coords->read_bandwidth, coords->write_bandwidth); new_bw = kcalloc(nr_node_ids, sizeof(unsigned int), GFP_KERNEL); if (!new_bw) return -ENOMEM; new_wi_state = kmalloc(struct_size(new_wi_state, iw_table, nr_node_ids), GFP_KERNEL); if (!new_wi_state) { kfree(new_bw); return -ENOMEM; } new_wi_state->mode_auto = true; for (i = 0; i < nr_node_ids; i++) new_wi_state->iw_table[i] = 1; /* * Update bandwidth info, even in manual mode. That way, when switching * to auto mode in the future, iw_table can be overwritten using * accurate bw data. */ mutex_lock(&wi_state_lock); old_bw = node_bw_table; if (old_bw) memcpy(new_bw, old_bw, nr_node_ids * sizeof(*old_bw)); new_bw[node] = bw_val; node_bw_table = new_bw; old_wi_state = rcu_dereference_protected(wi_state, lockdep_is_held(&wi_state_lock)); if (old_wi_state && !old_wi_state->mode_auto) { /* Manual mode; skip reducing weights and updating wi_state */ mutex_unlock(&wi_state_lock); kfree(new_wi_state); goto out; } /* NULL wi_state assumes auto=true; reduce weights and update wi_state*/ reduce_interleave_weights(new_bw, new_wi_state->iw_table); rcu_assign_pointer(wi_state, new_wi_state); mutex_unlock(&wi_state_lock); if (old_wi_state) { synchronize_rcu(); kfree(old_wi_state); } out: kfree(old_bw); return 0; } /** * numa_nearest_node - Find nearest node by state * @node: Node id to start the search * @state: State to filter the search * * Lookup the closest node by distance if @nid is not in state. * * Return: this @node if it is in state, otherwise the closest node by distance */ int numa_nearest_node(int node, unsigned int state) { int min_dist = INT_MAX, dist, n, min_node; if (state >= NR_NODE_STATES) return -EINVAL; if (node == NUMA_NO_NODE || node_state(node, state)) return node; min_node = node; for_each_node_state(n, state) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(numa_nearest_node); /** * nearest_node_nodemask - Find the node in @mask at the nearest distance * from @node. * * @node: a valid node ID to start the search from. * @mask: a pointer to a nodemask representing the allowed nodes. * * This function iterates over all nodes in @mask and calculates the * distance from the starting @node, then it returns the node ID that is * the closest to @node, or MAX_NUMNODES if no node is found. * * Note that @node must be a valid node ID usable with node_distance(), * providing an invalid node ID (e.g., NUMA_NO_NODE) may result in crashes * or unexpected behavior. */ int nearest_node_nodemask(int node, nodemask_t *mask) { int dist, n, min_dist = INT_MAX, min_node = MAX_NUMNODES; for_each_node_mask(n, *mask) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(nearest_node_nodemask); struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; int node; if (pol) return pol; node = numa_node_id(); if (node != NUMA_NO_NODE) { pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ if (pol->mode) return pol; } return &default_policy; } static const struct mempolicy_operations { int (*create)(struct mempolicy *pol, const nodemask_t *nodes); void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); } mpol_ops[MPOL_MAX]; static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_MODE_FLAGS; } static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, const nodemask_t *rel) { nodemask_t tmp; nodes_fold(tmp, *orig, nodes_weight(*rel)); nodes_onto(*ret, tmp, *rel); } static int mpol_new_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; nodes_clear(pol->nodes); node_set(first_node(*nodes), pol->nodes); return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. */ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes, struct nodemask_scratch *nsc) { int ret; /* * Default (pol==NULL) resp. local memory policies are not a * subject of any remapping. They also do not need any special * constructor. */ if (!pol || pol->mode == MPOL_LOCAL) return 0; /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } /* * This function just creates a new policy, does some check and simple * initialization. You must invoke mpol_set_nodemask() to set nodes. */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); return NULL; } VM_BUG_ON(!nodes); /* * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). * All other modes require a valid pointer to a non-empty nodemask. */ if (mode == MPOL_PREFERRED) { if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; policy->home_node = NUMA_NO_NODE; return policy; } /* Slow path of a mpol destructor. */ void __mpol_put(struct mempolicy *pol) { if (!atomic_dec_and_test(&pol->refcnt)) return; kmem_cache_free(policy_cache, pol); } static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) { } static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) nodes_and(tmp, pol->w.user_nodemask, *nodes); else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) tmp = *nodes; pol->nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { pol->w.cpuset_mems_allowed = *nodes; } /* * mpol_rebind_policy - Migrate a policy to a different set of nodes * * Per-vma policies are protected by mmap_lock. Allocations using per-task * policies are protected by task->mems_allowed_seq to prevent a premature * OOM/allocation failure due to parallel nodemask modification. */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; mpol_ops[pol->mode].rebind(pol, newmask); } /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. * * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); } /* * Rebind each vma in mm to new nodemask. * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mmap_write_lock(mm); for_each_vma(vmi, vma) { vma_start_write(vma); mpol_rebind_policy(vma->vm_policy, new); } mmap_write_unlock(mm); } static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { [MPOL_DEFAULT] = { .rebind = mpol_rebind_default, }, [MPOL_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_PREFERRED] = { .create = mpol_new_preferred, .rebind = mpol_rebind_preferred, }, [MPOL_BIND] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_LOCAL] = { .rebind = mpol_rebind_default, }, [MPOL_PREFERRED_MANY] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_preferred, }, [MPOL_WEIGHTED_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, }; static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags); static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid); static bool strictly_unmovable(unsigned long flags) { /* * STRICT without MOVE flags lets do_mbind() fail immediately with -EIO * if any misplaced page is found. */ return (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) == MPOL_MF_STRICT; } struct migration_mpol { /* for alloc_migration_target_by_mpol() */ struct mempolicy *pol; pgoff_t ilx; }; struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; unsigned long start; unsigned long end; struct vm_area_struct *first; struct folio *large; /* note last large folio encountered */ long nr_failed; /* could not be isolated at this time */ }; /* * Check if the folio's nid is in qp->nmask. * * If MPOL_MF_INVERT is set in qp->flags, check if the nid is * in the invert of qp->nmask. */ static inline bool queue_folio_required(struct folio *folio, struct queue_pages *qp) { int nid = folio_nid(folio); unsigned long flags = qp->flags; return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) { struct folio *folio; struct queue_pages *qp = walk->private; if (unlikely(is_pmd_migration_entry(*pmd))) { qp->nr_failed++; return; } folio = pmd_folio(*pmd); if (is_huge_zero_folio(folio)) { walk->action = ACTION_CONTINUE; return; } if (!queue_folio_required(folio, qp)) return; if (!(qp->flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma) || !migrate_folio_add(folio, qp->pagelist, qp->flags)) qp->nr_failed++; } /* * Scan through folios, checking if they satisfy the required conditions, * moving them from LRU to local pagelist for migration if they do (or not). * * queue_folios_pte_range() has two possible return values: * 0 - continue walking to scan for more, even if an existing folio on the * wrong node could not be isolated and queued for migration. * -EIO - only MPOL_MF_STRICT was specified, without MPOL_MF_MOVE or ..._ALL, * and an existing folio was on a node that does not follow the policy. */ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; int max_nr, nr; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { queue_folios_pmd(pmd, walk); spin_unlock(ptl); goto out; } mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); if (!pte) { walk->action = ACTION_AGAIN; return 0; } for (; addr != end; pte += nr, addr += nr * PAGE_SIZE) { max_nr = (end - addr) >> PAGE_SHIFT; nr = 1; ptent = ptep_get(pte); if (pte_none(ptent)) continue; if (!pte_present(ptent)) { if (is_migration_entry(pte_to_swp_entry(ptent))) qp->nr_failed++; continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; if (folio_test_large(folio) && max_nr != 1) nr = folio_pte_batch(folio, pte, ptent, max_nr); /* * vm_normal_folio() filters out zero pages, but there might * still be reserved folios to skip, perhaps in a VDSO. */ if (folio_test_reserved(folio)) continue; if (!queue_folio_required(folio, qp)) continue; if (folio_test_large(folio)) { /* * A large folio can only be isolated from LRU once, * but may be mapped by many PTEs (and Copy-On-Write may * intersperse PTEs of other, order 0, folios). This is * a common case, so don't mistake it for failure (but * there can be other cases of multi-mapped pages which * this quick check does not help to filter out - and a * search of the pagelist might grow to be prohibitive). * * migrate_pages(&pagelist) returns nr_failed folios, so * check "large" now so that queue_pages_range() returns * a comparable nr_failed folios. This does imply that * if folio could not be isolated for some racy reason * at its first PTE, later PTEs will not give it another * chance of isolation; but keeps the accounting simple. */ if (folio == qp->large) continue; qp->large = folio; } if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(vma) || !migrate_folio_add(folio, qp->pagelist, flags)) { qp->nr_failed += nr; if (strictly_unmovable(flags)) break; } } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); out: if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; return 0; } static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; struct folio *folio; spinlock_t *ptl; pte_t entry; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); entry = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(entry)) { if (unlikely(is_hugetlb_entry_migration(entry))) qp->nr_failed++; goto unlock; } folio = pfn_folio(pte_pfn(entry)); if (!queue_folio_required(folio, qp)) goto unlock; if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma)) { qp->nr_failed++; goto unlock; } /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_maybe_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || (!folio_maybe_mapped_shared(folio) && !hugetlb_pmd_shared(pte))) if (!folio_isolate_hugetlb(folio, qp->pagelist)) qp->nr_failed++; unlock: spin_unlock(ptl); if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; #endif return 0; } #ifdef CONFIG_NUMA_BALANCING /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these * faults, pages may be migrated for better NUMA placement. * * This is assuming that NUMA faults are handled using PROT_NONE. If * an architecture makes a different choice, it will need further * changes to the core. */ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct mmu_gather tlb; long nr_updated; tlb_gather_mmu(&tlb, vma->vm_mm); nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); if (nr_updated > 0) { count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); count_memcg_events_mm(vma->vm_mm, NUMA_PTE_UPDATES, nr_updated); } tlb_finish_mmu(&tlb); return nr_updated; } #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *next, *vma = walk->vma; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; /* range check first */ VM_BUG_ON_VMA(!range_in_vma(vma, start, end), vma); if (!qp->first) { qp->first = vma; if (!(flags & MPOL_MF_DISCONTIG_OK) && (qp->start < vma->vm_start)) /* hole at head side of range */ return -EFAULT; } next = find_vma(vma->vm_mm, vma->vm_end); if (!(flags & MPOL_MF_DISCONTIG_OK) && ((vma->vm_end < qp->end) && (!next || vma->vm_end < next->vm_start))) /* hole at middle or tail of range */ return -EFAULT; /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable */ if (!vma_migratable(vma) && !(flags & MPOL_MF_STRICT)) return 1; /* * Check page nodes, and queue pages to move, in the current vma. * But if no moving, and no strict checking, the scan can be skipped. */ if (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) return 0; return 1; } static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_RDLOCK, }; static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_WRLOCK, }; /* * Walk through page tables and collect pages to be migrated. * * If pages found in a given range are not on the required set of @nodes, * and migration is allowed, they are isolated and queued to @pagelist. * * queue_pages_range() may return: * 0 - all pages already on the right node, or successfully queued for moving * (or neither strict checking nor moving requested: only range checking). * >0 - this number of misplaced folios could not be queued for moving * (a hugetlbfs page or a transparent huge page being counted as 1). * -EIO - a misplaced page found, when MPOL_MF_STRICT specified without MOVEs. * -EFAULT - a hole in the memory range, when MPOL_MF_DISCONTIG_OK unspecified. */ static long queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, .start = start, .end = end, .first = NULL, }; const struct mm_walk_ops *ops = (flags & MPOL_MF_WRLOCK) ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); if (!qp.first) /* whole range in hole */ err = -EFAULT; return err ? : qp.nr_failed; } /* * Apply policy to a single VMA * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct mempolicy *old; struct mempolicy *new; vma_assert_write_locked(vma); new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) goto err_out; } old = vma->vm_policy; vma->vm_policy = new; /* protected by mmap_lock */ mpol_put(old); return 0; err_out: mpol_put(new); return err; } /* Split or merge the VMA (if required) and apply the new policy */ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, struct mempolicy *new_pol) { unsigned long vmstart, vmend; vmend = min(end, vma->vm_end); if (start > vma->vm_start) { *prev = vma; vmstart = start; } else { vmstart = vma->vm_start; } if (mpol_equal(vma->vm_policy, new_pol)) { *prev = vma; return 0; } vma = vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol); if (IS_ERR(vma)) return PTR_ERR(vma); *prev = vma; return vma_replace_policy(vma, new_pol); } /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new, *old; NODEMASK_SCRATCH(scratch); int ret; if (!scratch) return -ENOMEM; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out; } task_lock(current); ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { task_unlock(current); mpol_put(new); goto out; } old = current->mempolicy; current->mempolicy = new; if (new && (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE)) { current->il_prev = MAX_NUMNODES-1; current->il_weight = 0; } task_unlock(current); mpol_put(old); ret = 0; out: NODEMASK_SCRATCH_FREE(scratch); return ret; } /* * Return nodemask for policy for get_mempolicy() query * * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes) { nodes_clear(*nodes); if (pol == &default_policy) return; switch (pol->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: *nodes = pol->nodes; break; case MPOL_LOCAL: /* return empty node mask for local allocation */ break; default: BUG(); } } static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p = NULL; int ret; ret = get_user_pages_fast(addr & PAGE_MASK, 1, 0, &p); if (ret > 0) { ret = page_to_nid(p); put_page(p); } return ret; } /* Retrieve NUMA policy */ static long do_get_mempolicy(int *policy, nodemask_t *nmask, unsigned long addr, unsigned long flags) { int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; if (flags & MPOL_F_MEMS_ALLOWED) { if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ task_lock(current); *nmask = cpuset_current_mems_allowed; task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { pgoff_t ilx; /* ignored here */ /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); vma = vma_lookup(mm, addr); if (!vma) { mmap_read_unlock(mm); return -EFAULT; } pol = __get_vma_policy(vma, addr, &ilx); } else if (addr) return -EINVAL; if (!pol) pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, because we are about to * drop the mmap_lock, after which only "pol" remains * valid, "vma" is stale. */ pol_refcount = pol; vma = NULL; mpol_get(pol); mmap_read_unlock(mm); err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->nodes); } else if (pol == current->mempolicy && pol->mode == MPOL_WEIGHTED_INTERLEAVE) { if (current->il_weight) *policy = current->il_prev; else *policy = next_node_in(current->il_prev, pol->nodes); } else { err = -EINVAL; goto out; } } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; /* * Internal mempolicy flags must be masked off before exposing * the policy to userspace. */ *policy |= (pol->flags & MPOL_MODE_FLAGS); } err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { *nmask = pol->w.user_nodemask; } else { task_lock(current); get_policy_nodemask(pol, nmask); task_unlock(current); } } out: mpol_cond_put(pol); if (vma) mmap_read_unlock(mm); if (pol_refcount) mpol_put(pol_refcount); return err; } #ifdef CONFIG_MIGRATION static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_maybe_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || !folio_maybe_mapped_shared(folio)) { if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, foliolist); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } else { /* * Non-movable folio may reach here. And, there may be * temporary off LRU folios or non-LRU movable folios. * Treat them as unmovable folios since they can't be * isolated, so they can't be moved at the moment. */ return false; } } return true; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ static long migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) { nodemask_t nmask; struct vm_area_struct *vma; LIST_HEAD(pagelist); long nr_failed; long err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, .reason = MR_SYSCALL, }; nodes_clear(nmask); node_set(source, nmask); VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); mmap_read_lock(mm); vma = find_vma(mm, 0); if (unlikely(!vma)) { mmap_read_unlock(mm); return 0; } /* * This does not migrate the range, but isolates all pages that * need migration. Between passing in the full user address * space range and MPOL_MF_DISCONTIG_OK, this call cannot fail, * but passes back the count of pages which could not be isolated. */ nr_failed = queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); mmap_read_unlock(mm); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(&pagelist); } if (err >= 0) err += nr_failed; return err; } /* * Move pages between the two nodesets so as to preserve the physical * layout as much as possible. * * Returns the number of page that could not be moved. */ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { long nr_failed = 0; long err = 0; nodemask_t tmp; lru_cache_disable(); /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' * bit in 'tmp', and return that <source, dest> pair for migration. * The pair of nodemasks 'to' and 'from' define the map. * * If no pair of bits is found that way, fallback to picking some * pair of 'source' and 'dest' bits that are not the same. If the * 'source' and 'dest' bits are the same, this represents a node * that will be migrating to itself, so no pages need move. * * If no bits are left in 'tmp', or if all remaining bits left * in 'tmp' correspond to the same bit in 'to', return false * (nothing left to migrate). * * This lets us pick a pair of nodes to migrate between, such that * if possible the dest node is not already occupied by some other * source node, minimizing the risk of overloading the memory on a * node that would happen if we migrated incoming memory to a node * before migrating outgoing memory source that same node. * * A single scan of tmp is sufficient. As we go, we remember the * most recent <s, d> pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. * Otherwise when we finish scanning from_tmp, we at least have the * most recent <s, d> pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. */ tmp = *from; while (!nodes_empty(tmp)) { int s, d; int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { /* * do_migrate_pages() tries to maintain the relative * node relationship of the pages established between * threads and memory areas. * * However if the number of source nodes is not equal to * the number of destination nodes we can not preserve * this node relative relationship. In that case, skip * copying memory from a node that is in the destination * mask. * * Example: [2,3,4] -> [3,4,5] moves everything. * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ if ((nodes_weight(*from) != nodes_weight(*to)) && (node_isset(s, *to))) continue; d = node_remap(s, *from, *to); if (s == d) continue; source = s; /* Node moved. Memorize */ dest = d; /* dest not in remaining from nodes? */ if (!node_isset(dest, tmp)) break; } if (source == NUMA_NO_NODE) break; node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) nr_failed += err; if (err < 0) break; } lru_cache_enable(); if (err < 0) return err; return (nr_failed < INT_MAX) ? nr_failed : INT_MAX; } /* * Allocate a new folio for page migration, according to NUMA mempolicy. */ static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { struct migration_mpol *mmpol = (struct migration_mpol *)private; struct mempolicy *pol = mmpol->pol; pgoff_t ilx = mmpol->ilx; unsigned int order; int nid = numa_node_id(); gfp_t gfp; order = folio_order(src); ilx += src->index >> order; if (folio_test_hugetlb(src)) { nodemask_t *nodemask; struct hstate *h; h = folio_hstate(src); gfp = htlb_alloc_mask(h); nodemask = policy_nodemask(gfp, pol, ilx, &nid); return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp, htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND)); } if (folio_test_large(src)) gfp = GFP_TRANSHUGE; else gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL | __GFP_COMP; return folio_alloc_mpol(gfp, order, pol, ilx, nid); } #else static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { return false; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return -ENOSYS; } static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vma_iterator vmi; struct migration_mpol mmpol; struct mempolicy *new; unsigned long end; long err; long nr_failed; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; if (start & ~PAGE_MASK) return -EINVAL; if (mode == MPOL_DEFAULT) flags &= ~MPOL_MF_STRICT; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all */ if (!new) flags |= MPOL_MF_DISCONTIG_OK; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_disable(); { NODEMASK_SCRATCH(scratch); if (scratch) { mmap_write_lock(mm); err = mpol_set_nodemask(new, nmask, scratch); if (err) mmap_write_unlock(mm); } else err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } if (err) goto mpol_out; /* * Lock the VMAs before scanning for pages to migrate, * to ensure we don't miss a concurrently inserted page. */ nr_failed = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist); if (nr_failed < 0) { err = nr_failed; nr_failed = 0; } else { vma_iter_init(&vmi, mm, start); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { err = mbind_range(&vmi, vma, &prev, start, end, new); if (err) break; } } if (!err && !list_empty(&pagelist)) { /* Convert MPOL_DEFAULT's NULL to task or default policy */ if (!new) { new = get_task_policy(current); mpol_get(new); } mmpol.pol = new; mmpol.ilx = 0; /* * In the interleaved case, attempt to allocate on exactly the * targeted nodes, for the first VMA to be migrated; for later * VMAs, the nodes will still be interleaved from the targeted * nodemask, but one by one may be selected differently. */ if (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE) { struct folio *folio; unsigned int order; unsigned long addr = -EFAULT; list_for_each_entry(folio, &pagelist, lru) { if (!folio_test_ksm(folio)) break; } if (!list_entry_is_head(folio, &pagelist, lru)) { vma_iter_init(&vmi, mm, start); for_each_vma_range(vmi, vma, end) { addr = page_address_in_vma(folio, folio_page(folio, 0), vma); if (addr != -EFAULT) break; } } if (addr != -EFAULT) { order = folio_order(folio); /* We already know the pol, but not the ilx */ mpol_cond_put(get_vma_policy(vma, addr, order, &mmpol.ilx)); /* Set base from which to increment by index */ mmpol.ilx -= folio->index >> order; } } } mmap_write_unlock(mm); if (!err && !list_empty(&pagelist)) { nr_failed |= migrate_pages(&pagelist, alloc_migration_target_by_mpol, NULL, (unsigned long)&mmpol, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL); } if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); mpol_out: mpol_put(new); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_enable(); return err; } /* * User space interface with variable sized bitmaps for nodelists. */ static int get_bitmap(unsigned long *mask, const unsigned long __user *nmask, unsigned long maxnode) { unsigned long nlongs = BITS_TO_LONGS(maxnode); int ret; if (in_compat_syscall()) ret = compat_get_bitmap(mask, (const compat_ulong_t __user *)nmask, maxnode); else ret = copy_from_user(mask, nmask, nlongs * sizeof(unsigned long)); if (ret) return -EFAULT; if (maxnode % BITS_PER_LONG) mask[nlongs - 1] &= (1UL << (maxnode % BITS_PER_LONG)) - 1; return 0; } /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) return 0; if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; /* * When the user specified more nodes than supported just check * if the non supported part is all zero, one word at a time, * starting at the end. */ while (maxnode > MAX_NUMNODES) { unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG); unsigned long t; if (get_bitmap(&t, &nmask[(maxnode - 1) / BITS_PER_LONG], bits)) return -EFAULT; if (maxnode - bits >= MAX_NUMNODES) { maxnode -= bits; } else { maxnode = MAX_NUMNODES; t &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); } if (t) return -EINVAL; } return get_bitmap(nodes_addr(*nodes), nmask, maxnode); } /* Copy a kernel node mask to user space */ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); bool compat = in_compat_syscall(); if (compat) nbytes = BITS_TO_COMPAT_LONGS(nr_node_ids) * sizeof(compat_long_t); if (copy > nbytes) { if (copy > PAGE_SIZE) return -EINVAL; if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; maxnode = nr_node_ids; } if (compat) return compat_put_bitmap((compat_ulong_t __user *)mask, nodes_addr(*nodes), maxnode); return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } /* Basic parameter sanity check used by both mbind() and set_mempolicy() */ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) { *flags = *mode & MPOL_MODE_FLAGS; *mode &= ~MPOL_MODE_FLAGS; if ((unsigned int)(*mode) >= MPOL_MAX) return -EINVAL; if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; if (*flags & MPOL_F_NUMA_BALANCING) { if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY) *flags |= (MPOL_F_MOF | MPOL_F_MORON); else return -EINVAL; } return 0; } static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; start = untagged_addr(start); err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len, unsigned long, home_node, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct mempolicy *new, *old; unsigned long end; int err = -ENOENT; VMA_ITERATOR(vmi, mm, start); start = untagged_addr(start); if (start & ~PAGE_MASK) return -EINVAL; /* * flags is used for future extension if any. */ if (flags != 0) return -EINVAL; /* * Check home_node is online to avoid accessing uninitialized * NODE_DATA. */ if (home_node >= MAX_NUMNODES || !node_online(home_node)) return -EINVAL; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; mmap_write_lock(mm); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { /* * If any vma in the range got policy other than MPOL_BIND * or MPOL_PREFERRED_MANY we return error. We don't reset * the home node for vmas we already updated before. */ old = vma_policy(vma); if (!old) { prev = vma; continue; } if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) { err = -EOPNOTSUPP; break; } new = mpol_dup(old); if (IS_ERR(new)) { err = PTR_ERR(new); break; } vma_start_write(vma); new->home_node = home_node; err = mbind_range(&vmi, vma, &prev, start, end, new); mpol_put(new); if (err) break; } mmap_write_unlock(mm); return err; } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { return kernel_mbind(start, len, mode, nmask, maxnode, flags); } /* Set the process memory policy */ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_set_mempolicy(lmode, mode_flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { return kernel_set_mempolicy(mode, nmask, maxnode); } static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { struct mm_struct *mm = NULL; struct task_struct *task; nodemask_t task_nodes; int err; nodemask_t *old; nodemask_t *new; NODEMASK_SCRATCH(scratch); if (!scratch) return -ENOMEM; old = &scratch->mask1; new = &scratch->mask2; err = get_nodes(old, old_nodes, maxnode); if (err) goto out; err = get_nodes(new, new_nodes, maxnode); if (err) goto out; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); err = -ESRCH; goto out; } get_task_struct(task); err = -EINVAL; /* * Check if this process has the right to modify the specified process. * Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out_put; } rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out_put; } task_nodes = cpuset_mems_allowed(current); nodes_and(*new, *new, task_nodes); if (nodes_empty(*new)) goto out_put; err = security_task_movememory(task); if (err) goto out_put; mm = get_task_mm(task); put_task_struct(task); if (!mm) { err = -EINVAL; goto out; } err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); mmput(mm); out: NODEMASK_SCRATCH_FREE(scratch); return err; out_put: put_task_struct(task); goto out; } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, const unsigned long __user *, old_nodes, const unsigned long __user *, new_nodes) { return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; addr = untagged_addr(addr); err = do_get_mempolicy(&pval, &nodes, addr, flags); if (err) return err; if (policy && put_user(pval, policy)) return -EFAULT; if (nmask) err = copy_nodes_to_user(nmask, maxnode, &nodes); return err; } SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; /* * DAX device mappings require predictable access latency, so avoid * incurring periodic faults. */ if (vma_is_dax(vma)) return false; if (is_vm_hugetlb_page(vma) && !hugepage_migration_supported(hstate_vma(vma))) return false; /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not * possible. */ if (vma->vm_file && gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) < policy_zone) return false; return true; } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx) { *ilx = 0; return (vma->vm_ops && vma->vm_ops->get_policy) ? vma->vm_ops->get_policy(vma, addr, ilx) : vma->vm_policy; } /* * get_vma_policy(@vma, @addr, @order, @ilx) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * @order: 0, or appropriate huge_page_order for interleaving * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or * MPOL_WEIGHTED_INTERLEAVE * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { struct mempolicy *pol; pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) { *ilx += vma->vm_pgoff >> order; *ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order); } return pol; } bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; if (vma->vm_ops && vma->vm_ops->get_policy) { bool ret = false; pgoff_t ilx; /* ignored here */ pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); return ret; } pol = vma->vm_policy; if (!pol) pol = get_task_policy(current); return pol->flags & MPOL_F_MOF; } bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* * if policy->nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->nodes is intersect with node_states[N_MEMORY]. * so if the following test fails, it implies * policy->nodes has movable memory only. */ if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; } static unsigned int weighted_interleave_nodes(struct mempolicy *policy) { unsigned int node; unsigned int cpuset_mems_cookie; retry: /* to prevent miscount use tsk->mems_allowed_seq to detect rebind */ cpuset_mems_cookie = read_mems_allowed_begin(); node = current->il_prev; if (!current->il_weight || !node_isset(node, policy->nodes)) { node = next_node_in(node, policy->nodes); if (read_mems_allowed_retry(cpuset_mems_cookie)) goto retry; if (node == MAX_NUMNODES) return node; current->il_prev = node; current->il_weight = get_il_weight(node); } current->il_weight--; return node; } /* Do dynamic interleaving for a process */ static unsigned int interleave_nodes(struct mempolicy *policy) { unsigned int nid; unsigned int cpuset_mems_cookie; /* to prevent miscount, use tsk->mems_allowed_seq to detect rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nid = next_node_in(current->il_prev, policy->nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); if (nid < MAX_NUMNODES) current->il_prev = nid; return nid; } /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; int node = numa_mem_id(); if (!in_task()) return node; policy = current->mempolicy; if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: return first_node(policy->nodes); case MPOL_INTERLEAVE: return interleave_nodes(policy); case MPOL_WEIGHTED_INTERLEAVE: return weighted_interleave_nodes(policy); case MPOL_BIND: case MPOL_PREFERRED_MANY: { struct zoneref *z; /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->nodes); return zonelist_zone(z) ? zonelist_node_idx(z) : node; } case MPOL_LOCAL: return node; default: BUG(); } } static unsigned int read_once_policy_nodemask(struct mempolicy *pol, nodemask_t *mask) { /* * barrier stabilizes the nodemask locally so that it can be iterated * over safely without concern for changes. Allocators validate node * selection does not violate mems_allowed, so this is safe. */ barrier(); memcpy(mask, &pol->nodes, sizeof(nodemask_t)); barrier(); return nodes_weight(*mask); } static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx) { struct weighted_interleave_state *state; nodemask_t nodemask; unsigned int target, nr_nodes; u8 *table = NULL; unsigned int weight_total = 0; u8 weight; int nid = 0; nr_nodes = read_once_policy_nodemask(pol, &nodemask); if (!nr_nodes) return numa_node_id(); rcu_read_lock(); state = rcu_dereference(wi_state); /* Uninitialized wi_state means we should assume all weights are 1 */ if (state) table = state->iw_table; /* calculate the total weight */ for_each_node_mask(nid, nodemask) weight_total += table ? table[nid] : 1; /* Calculate the node offset based on totals */ target = ilx % weight_total; nid = first_node(nodemask); while (target) { /* detect system default usage */ weight = table ? table[nid] : 1; if (target < weight) break; target -= weight; nid = next_node_in(nid, nodemask); } rcu_read_unlock(); return nid; } /* * Do static interleaving for interleave index @ilx. Returns the ilx'th * node in pol->nodes (starting from ilx=0), wrapping around if ilx * exceeds the number of present nodes. */ static unsigned int interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nnodes; int i; int nid; nnodes = read_once_policy_nodemask(pol, &nodemask); if (!nnodes) return numa_node_id(); target = ilx % nnodes; nid = first_node(nodemask); for (i = 0; i < target; i++) nid = next_node(nid, nodemask); return nid; } /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation, together with preferred node id (or the input node id). */ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid) { nodemask_t *nodemask = NULL; switch (pol->mode) { case MPOL_PREFERRED: /* Override input node id */ *nid = first_node(pol->nodes); break; case MPOL_PREFERRED_MANY: nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; break; case MPOL_BIND: /* Restrict to nodemask (but not on lower zones) */ if (apply_policy_zone(pol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&pol->nodes)) nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the * requested node and not break the policy. */ WARN_ON_ONCE(gfp & __GFP_THISNODE); break; case MPOL_INTERLEAVE: /* Override input node id */ *nid = (ilx == NO_INTERLEAVE_INDEX) ? interleave_nodes(pol) : interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: *nid = (ilx == NO_INTERLEAVE_INDEX) ? weighted_interleave_nodes(pol) : weighted_interleave_nid(pol, ilx); break; } return nodemask; } #ifdef CONFIG_HUGETLBFS /* * huge_node(@vma, @addr, @gfp_flags, @mpol) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup and interleave policy * @gfp_flags: for requested zone * @mpol: pointer to mempolicy pointer for reference counted mempolicy * @nodemask: pointer to nodemask pointer for 'bind' and 'prefer-many' policy * * Returns a nid suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'bind' or 'prefer-many', returns a pointer * to the mempolicy's @nodemask for filtering the zonelist. */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { pgoff_t ilx; int nid; nid = numa_node_id(); *mpol = get_vma_policy(vma, addr, hstate_vma(vma)->order, &ilx); *nodemask = policy_nodemask(gfp_flags, *mpol, ilx, &nid); return nid; } /* * init_nodemask_of_mempolicy * * If the current task's mempolicy is "default" [NULL], return 'false' * to indicate default policy. Otherwise, extract the policy nodemask * for 'bind' or 'interleave' policy into the argument nodemask, or * initialize the argument nodemask to contain the single node for * 'preferred' or 'local' policy and return 'true' to indicate presence * of non-default mempolicy. * * We don't bother with reference counting the mempolicy [mpol_get/put] * because the current task is examining it's own mempolicy and a task's * mempolicy is only ever changed by the task itself. * * N.B., it is the caller's responsibility to free a returned nodemask. */ bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; if (!(mask && current->mempolicy)) return false; task_lock(current); mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: *mask = mempolicy->nodes; break; case MPOL_LOCAL: init_nodemask_of_node(mask, numa_node_id()); break; default: BUG(); } task_unlock(current); return true; } #endif /* * mempolicy_in_oom_domain * * If tsk's mempolicy is "bind", check for intersection between mask and * the policy nodemask. Otherwise, return true for all other policies * including "interleave", as a tsk with "interleave" policy may have * memory allocated from all nodes in system. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; bool ret = true; if (!mask) return ret; task_lock(tsk); mempolicy = tsk->mempolicy; if (mempolicy && mempolicy->mode == MPOL_BIND) ret = nodes_intersects(mempolicy->nodes, *mask); task_unlock(tsk); return ret; } static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, int nid, nodemask_t *nodemask) { struct page *page; gfp_t preferred_gfp; /* * This is a two pass approach. The first pass will only try the * preferred nodes but skip the direct reclaim and allow the * allocation to fail, while the second pass will try all the * nodes in system. */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); page = __alloc_frozen_pages_noprof(preferred_gfp, order, nid, nodemask); if (!page) page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL); return page; } /** * alloc_pages_mpol - Allocate pages according to NUMA mempolicy. * @gfp: GFP flags. * @order: Order of the page allocation. * @pol: Pointer to the NUMA mempolicy. * @ilx: Index for interleave mempolicy (also distinguishes alloc_pages()). * @nid: Preferred node (usually numa_node_id() but @mpol may override it). * * Return: The page on success or NULL if allocation fails. */ static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { nodemask_t *nodemask; struct page *page; nodemask = policy_nodemask(gfp, pol, ilx, &nid); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_preferred_many(gfp, order, nid, nodemask); if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && /* filter "hugepage" allocation, unless from alloc_pages() */ order == HPAGE_PMD_ORDER && ilx != NO_INTERLEAVE_INDEX) { /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred * node) we only try to allocate from the current/preferred * node and don't fall back to other nodes, as the cost of * remote accesses would likely offset THP benefits. * * If the policy is interleave or does not allow the current * node in its nodemask, we allocate the standard way. */ if (pol->mode != MPOL_INTERLEAVE && pol->mode != MPOL_WEIGHTED_INTERLEAVE && (!nodemask || node_isset(nid, *nodemask))) { /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ page = __alloc_frozen_pages_noprof( gfp | __GFP_THISNODE | __GFP_NORETRY, order, nid, NULL); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ } } page = __alloc_frozen_pages_noprof(gfp, order, nid, nodemask); if (unlikely(pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { preempt_disable(); __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } } return page; } struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { struct page *page = alloc_pages_mpol(gfp | __GFP_COMP, order, pol, ilx, nid); if (!page) return NULL; set_page_refcounted(page); return page_rmappable_folio(page); } /** * vma_alloc_folio - Allocate a folio for a VMA. * @gfp: GFP flags. * @order: Order of the folio. * @vma: Pointer to VMA. * @addr: Virtual address of the allocation. Must be inside @vma. * * Allocate a folio for a specific address in @vma, using the appropriate * NUMA policy. The caller must hold the mmap_lock of the mm_struct of the * VMA to prevent it from going away. Should be used for all allocations * for folios that will be mapped into user space, excepting hugetlbfs, and * excepting where direct use of folio_alloc_mpol() is more appropriate. * * Return: The folio on success or NULL if allocation fails. */ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct folio *folio; if (vma->vm_flags & VM_DROPPABLE) gfp |= __GFP_NOWARN; pol = get_vma_policy(vma, addr, order, &ilx); folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id()); mpol_cond_put(pol); return folio; } EXPORT_SYMBOL(vma_alloc_folio_noprof); struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned order) { struct mempolicy *pol = &default_policy; /* * No reference counting needed for current->mempolicy * nor system default_policy */ if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); return alloc_pages_mpol(gfp, order, pol, NO_INTERLEAVE_INDEX, numa_node_id()); } /** * alloc_pages - Allocate pages. * @gfp: GFP flags. * @order: Power of two of number of pages to allocate. * * Allocate 1 << @order contiguous pages. The physical address of the * first page is naturally aligned (eg an order-3 allocation will be aligned * to a multiple of 8 * PAGE_SIZE bytes). The NUMA policy of the current * process is honoured when in process context. * * Context: Can be called from any context, providing the appropriate GFP * flags are used. * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order) { struct page *page = alloc_frozen_pages_noprof(gfp, order); if (page) set_page_refcounted(page); return page; } EXPORT_SYMBOL(alloc_pages_noprof); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order)); } EXPORT_SYMBOL(folio_alloc_noprof); static unsigned long alloc_pages_bulk_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { int nodes; unsigned long nr_pages_per_node; int delta; int i; unsigned long nr_allocated; unsigned long total_allocated = 0; nodes = nodes_weight(pol->nodes); nr_pages_per_node = nr_pages / nodes; delta = nr_pages - nodes * nr_pages_per_node; for (i = 0; i < nodes; i++) { if (delta) { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node + 1, page_array); delta--; } else { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node, page_array); } page_array += nr_allocated; total_allocated += nr_allocated; } return total_allocated; } static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { struct weighted_interleave_state *state; struct task_struct *me = current; unsigned int cpuset_mems_cookie; unsigned long total_allocated = 0; unsigned long nr_allocated = 0; unsigned long rounds; unsigned long node_pages, delta; u8 *weights, weight; unsigned int weight_total = 0; unsigned long rem_pages = nr_pages; nodemask_t nodes; int nnodes, node; int resume_node = MAX_NUMNODES - 1; u8 resume_weight = 0; int prev_node; int i; if (!nr_pages) return 0; /* read the nodes onto the stack, retry if done during rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nnodes = read_once_policy_nodemask(pol, &nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); /* if the nodemask has become invalid, we cannot do anything */ if (!nnodes) return 0; /* Continue allocating from most recent node and adjust the nr_pages */ node = me->il_prev; weight = me->il_weight; if (weight && node_isset(node, nodes)) { node_pages = min(rem_pages, weight); nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, page_array); page_array += nr_allocated; total_allocated += nr_allocated; /* if that's all the pages, no need to interleave */ if (rem_pages <= weight) { me->il_weight -= rem_pages; return total_allocated; } /* Otherwise we adjust remaining pages, continue from there */ rem_pages -= weight; } /* clear active weight in case of an allocation failure */ me->il_weight = 0; prev_node = node; /* create a local copy of node weights to operate on outside rcu */ weights = kzalloc(nr_node_ids, GFP_KERNEL); if (!weights) return total_allocated; rcu_read_lock(); state = rcu_dereference(wi_state); if (state) { memcpy(weights, state->iw_table, nr_node_ids * sizeof(u8)); rcu_read_unlock(); } else { rcu_read_unlock(); for (i = 0; i < nr_node_ids; i++) weights[i] = 1; } /* calculate total, detect system default usage */ for_each_node_mask(node, nodes) weight_total += weights[node]; /* * Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls. * Track which node weighted interleave should resume from. * * if (rounds > 0) and (delta == 0), resume_node will always be * the node following prev_node and its weight. */ rounds = rem_pages / weight_total; delta = rem_pages % weight_total; resume_node = next_node_in(prev_node, nodes); resume_weight = weights[resume_node]; for (i = 0; i < nnodes; i++) { node = next_node_in(prev_node, nodes); weight = weights[node]; node_pages = weight * rounds; /* If a delta exists, add this node's portion of the delta */ if (delta > weight) { node_pages += weight; delta -= weight; } else if (delta) { /* when delta is depleted, resume from that node */ node_pages += delta; resume_node = node; resume_weight = weight - delta; delta = 0; } /* node_pages can be 0 if an allocation fails and rounds == 0 */ if (!node_pages) break; nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, page_array); page_array += nr_allocated; total_allocated += nr_allocated; if (total_allocated == nr_pages) break; prev_node = node; } me->il_prev = resume_node; me->il_weight = resume_weight; kfree(weights); return total_allocated; } static unsigned long alloc_pages_bulk_preferred_many(gfp_t gfp, int nid, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { gfp_t preferred_gfp; unsigned long nr_allocated = 0; preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes, nr_pages, page_array); if (nr_allocated < nr_pages) nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL, nr_pages - nr_allocated, page_array + nr_allocated); return nr_allocated; } /* alloc pages bulk and mempolicy should be considered at the * same time in some situation such as vmalloc. * * It can accelerate memory allocation especially interleaving * allocate memory. */ unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; nodemask_t *nodemask; int nid; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE) return alloc_pages_bulk_interleave(gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_WEIGHTED_INTERLEAVE) return alloc_pages_bulk_weighted_interleave( gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_bulk_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); nid = numa_node_id(); nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid); return alloc_pages_bulk_noprof(gfp, nid, nodemask, nr_pages, page_array); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(src->vm_policy); if (IS_ERR(pol)) return PTR_ERR(pol); dst->vm_policy = pol; return 0; } /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). * * current's mempolicy may be rebinded by the other task(the task that changes * cpuset's mems), so we needn't do rebind work for current task. */ /* Slow path of a mempolicy duplicate */ struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* task's mempolicy is protected by alloc_lock */ if (old == current->mempolicy) { task_lock(current); *new = *old; task_unlock(current); } else *new = *old; if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); mpol_rebind_policy(new, &mems); } atomic_set(&new->refcnt, 1); return new; } /* Slow path of a mempolicy comparison */ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) return false; if (a->mode != b->mode) return false; if (a->flags != b->flags) return false; if (a->home_node != b->home_node) return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: return !!nodes_equal(a->nodes, b->nodes); case MPOL_LOCAL: return true; default: BUG(); return false; } } /* * Shared memory backing store policy support. * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ /* * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ static struct sp_node *sp_lookup(struct shared_policy *sp, pgoff_t start, pgoff_t end) { struct rb_node *n = sp->root.rb_node; while (n) { struct sp_node *p = rb_entry(n, struct sp_node, nd); if (start >= p->end) n = n->rb_right; else if (end <= p->start) n = n->rb_left; else break; } if (!n) return NULL; for (;;) { struct sp_node *w = NULL; struct rb_node *prev = rb_prev(n); if (!prev) break; w = rb_entry(prev, struct sp_node, nd); if (w->end <= start) break; n = prev; } return rb_entry(n, struct sp_node, nd); } /* * Insert a new shared policy into the list. Caller holds sp->lock for * writing. */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; struct rb_node *parent = NULL; struct sp_node *nd; while (*p) { parent = *p; nd = rb_entry(parent, struct sp_node, nd); if (new->start < nd->start) p = &(*p)->rb_left; else if (new->end > nd->end) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); } /* Find shared policy intersecting idx */ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { struct mempolicy *pol = NULL; struct sp_node *sn; if (!sp->root.rb_node) return NULL; read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } read_unlock(&sp->lock); return pol; } static void sp_free(struct sp_node *n) { mpol_put(n->policy); kmem_cache_free(sn_cache, n); } /** * mpol_misplaced - check whether current folio node is valid in policy * * @folio: folio to be checked * @vmf: structure describing the fault * @addr: virtual address in @vma for shared policy lookup and interleave policy * * Lookup current policy node id for vma,addr and "compare to" folio's * node id. Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. * * Return: NUMA_NO_NODE if the page is in a node that is valid for this * policy, or a suitable node ID to allocate a replacement folio from. */ int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct zoneref *z; int curnid = folio_nid(folio); struct vm_area_struct *vma = vmf->vma; int thiscpu = raw_smp_processor_id(); int thisnid = numa_node_id(); int polnid = NUMA_NO_NODE; int ret = NUMA_NO_NODE; /* * Make sure ptl is held so that we don't preempt and we * have a stable smp processor id */ lockdep_assert_held(vmf->ptl); pol = get_vma_policy(vma, addr, folio_order(folio), &ilx); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: polnid = interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: polnid = weighted_interleave_nid(pol, ilx); break; case MPOL_PREFERRED: if (node_isset(curnid, pol->nodes)) goto out; polnid = first_node(pol->nodes); break; case MPOL_LOCAL: polnid = numa_node_id(); break; case MPOL_BIND: case MPOL_PREFERRED_MANY: /* * Even though MPOL_PREFERRED_MANY can allocate pages outside * policy nodemask we don't allow numa migration to nodes * outside policy nodemask for now. This is done so that if we * want demotion to slow memory to happen, before allocating * from some DRAM node say 'x', we will end up using a * MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario * we should not promote to node 'x' from slow memory node. */ if (pol->flags & MPOL_F_MORON) { /* * Optimize placement among multiple nodes * via NUMA balancing */ if (node_isset(thisnid, pol->nodes)) break; goto out; } /* * use current page if in policy nodemask, * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( node_zonelist(thisnid, GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->nodes); polnid = zonelist_node_idx(z); break; default: BUG(); } /* Migrate the folio towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; if (!should_numa_migrate_memory(current, folio, curnid, thiscpu)) goto out; } if (curnid != polnid) ret = polnid; out: mpol_cond_put(pol); return ret; } /* * Drop the (possibly final) reference to task->mempolicy. It needs to be * dropped after task->mempolicy is set to NULL so that any allocation done as * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed * policy. */ void mpol_put_task_policy(struct task_struct *task) { struct mempolicy *pol; task_lock(task); pol = task->mempolicy; task->mempolicy = NULL; task_unlock(task); mpol_put(pol); } static void sp_delete(struct shared_policy *sp, struct sp_node *n) { rb_erase(&n->nd, &sp->root); sp_free(n); } static void sp_node_init(struct sp_node *node, unsigned long start, unsigned long end, struct mempolicy *pol) { node->start = start; node->end = end; node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { struct sp_node *n; struct mempolicy *newpol; n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n); return NULL; } newpol->flags |= MPOL_F_SHARED; sp_node_init(n, start, end, newpol); return n; } /* Replace a policy range. */ static int shared_policy_replace(struct shared_policy *sp, pgoff_t start, pgoff_t end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; struct mempolicy *mpol_new = NULL; int ret = 0; restart: write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { struct rb_node *next = rb_next(&n->nd); if (n->start >= start) { if (n->end <= end) sp_delete(sp, n); else n->start = end; } else { /* Old policy spanning whole new range. */ if (n->end > end) { if (!n_new) goto alloc_new; *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); sp_node_init(n_new, end, n->end, mpol_new); n->end = start; sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; } else n->end = start; } if (!next) break; n = rb_entry(next, struct sp_node, nd); } if (new) sp_insert(sp, new); write_unlock(&sp->lock); ret = 0; err_out: if (mpol_new) mpol_put(mpol_new); if (n_new) kmem_cache_free(sn_cache, n_new); return ret; alloc_new: write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) goto err_out; mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; atomic_set(&mpol_new->refcnt, 1); goto restart; } /** * mpol_shared_policy_init - initialize shared policy for inode * @sp: pointer to inode shared policy * @mpol: struct mempolicy to install * * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ rwlock_init(&sp->lock); if (mpol) { struct sp_node *sn; struct mempolicy *npol; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; /* contextualize the tmpfs mount point mempolicy to this file */ npol = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(npol)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); ret = mpol_set_nodemask(npol, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) goto put_npol; /* alloc node covering entire file; adds ref to file's npol */ sn = sp_alloc(0, MAX_LFS_FILESIZE >> PAGE_SHIFT, npol); if (sn) sp_insert(sp, sn); put_npol: mpol_put(npol); /* drop initial ref on file's npol */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); if (pol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, pol); if (!new) return -ENOMEM; } err = shared_policy_replace(sp, vma->vm_pgoff, vma->vm_pgoff + sz, new); if (err && new) sp_free(new); return err; } /* Free a backing policy store on inode delete. */ void mpol_free_shared_policy(struct shared_policy *sp) { struct sp_node *n; struct rb_node *next; if (!sp->root.rb_node) return; write_lock(&sp->lock); next = rb_first(&sp->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(sp, n); } write_unlock(&sp->lock); } #ifdef CONFIG_NUMA_BALANCING static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { bool numabalancing_default = false; if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } static int __init setup_numabalancing(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "enable")) { numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { numabalancing_override = -1; ret = 1; } out: if (!ret) pr_warn("Unable to parse numa_balancing=\n"); return ret; } __setup("numa_balancing=", setup_numabalancing); #else static inline void __init check_numabalancing_enable(void) { } #endif /* CONFIG_NUMA_BALANCING */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; unsigned long largest = 0; int nid, prefer = 0; policy_cache = kmem_cache_create("numa_policy", sizeof(struct mempolicy), 0, SLAB_PANIC, NULL); sn_cache = kmem_cache_create("shared_policy_node", sizeof(struct sp_node), 0, SLAB_PANIC, NULL); for_each_node(nid) { preferred_node_policy[nid] = (struct mempolicy) { .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, .nodes = nodemask_of_node(nid), }; } /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ if (largest < total_pages) { largest = total_pages; prefer = nid; } /* Interleave this node? */ if ((total_pages << PAGE_SHIFT) >= (16 << 20)) node_set(nid, interleave_nodes); } /* All too small, use the largest */ if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } /* * Parse and format mempolicy from/to strings */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", [MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave", [MPOL_LOCAL] = "local", [MPOL_PREFERRED_MANY] = "prefer (many)", }; #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. * @str: string containing mempolicy to parse * @mpol: pointer to struct mempolicy pointer, returned on success. * * Format of input: * <mode>[=<flags>][:<nodelist>] * * Return: %0 on success, else %1 */ int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); int err = 1, mode; if (flags) *flags++ = '\0'; /* terminate mode string */ if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; switch (mode) { case MPOL_PREFERRED: /* * Insist on a nodelist of one node only, although later * we use first_node(nodes) to grab a single node, so here * nodelist (or nodes) cannot be empty. */ if (nodelist) { char *rest = nodelist; while (isdigit(*rest)) rest++; if (*rest) goto out; if (nodes_empty(nodes)) goto out; } break; case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ if (!nodelist) nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* * Don't allow a nodelist; mpol_new() checks flags */ if (nodelist) goto out; break; case MPOL_DEFAULT: /* * Insist on a empty nodelist */ if (!nodelist) err = 0; goto out; case MPOL_PREFERRED_MANY: case MPOL_BIND: /* * Insist on a nodelist */ if (!nodelist) goto out; } mode_flags = 0; if (flags) { /* * Currently, we only support two mutually exclusive * mode flags. */ if (!strcmp(flags, "static")) mode_flags |= MPOL_F_STATIC_NODES; else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) goto out; /* * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ if (mode != MPOL_PREFERRED) { new->nodes = nodes; } else if (nodelist) { nodes_clear(new->nodes); node_set(first_node(nodes), new->nodes); } else { new->mode = MPOL_LOCAL; } /* * Save nodes for contextualization: this will be used to "clone" * the mempolicy in a specific context [cpuset] at a later time. */ new->w.user_nodemask = nodes; err = 0; out: /* Restore string for error message */ if (nodelist) *--nodelist = ':'; if (flags) *--flags = '='; if (!err) *mpol = new; return err; } #endif /* CONFIG_TMPFS */ /** * mpol_to_str - format a mempolicy structure for printing * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. * Recommend a @maxlen of at least 51 for the longest mode, "weighted * interleave", plus the longest flag flags, "relative|balancing", and to * display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; nodemask_t nodes = NODE_MASK_NONE; unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; if (pol && pol != &default_policy && !(pol >= &preferred_node_policy[0] && pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) { mode = pol->mode; flags = pol->flags; } switch (mode) { case MPOL_DEFAULT: case MPOL_LOCAL: break; case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: nodes = pol->nodes; break; default: WARN_ON_ONCE(1); snprintf(p, maxlen, "unknown"); return; } p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { p += snprintf(p, buffer + maxlen - p, "="); /* * Static and relative are mutually exclusive. */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); if (flags & MPOL_F_NUMA_BALANCING) { if (!is_power_of_2(flags & MPOL_MODE_FLAGS)) p += snprintf(p, buffer + maxlen - p, "|"); p += snprintf(p, buffer + maxlen - p, "balancing"); } } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } #ifdef CONFIG_SYSFS struct iw_node_attr { struct kobj_attribute kobj_attr; int nid; }; struct sysfs_wi_group { struct kobject wi_kobj; struct mutex kobj_lock; struct iw_node_attr *nattrs[]; }; static struct sysfs_wi_group *wi_group; static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct iw_node_attr *node_attr; u8 weight; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); weight = get_il_weight(node_attr->nid); return sysfs_emit(buf, "%d\n", weight); } static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct weighted_interleave_state *new_wi_state, *old_wi_state = NULL; struct iw_node_attr *node_attr; u8 weight = 0; int i; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); if (count == 0 || sysfs_streq(buf, "") || kstrtou8(buf, 0, &weight) || weight == 0) return -EINVAL; new_wi_state = kzalloc(struct_size(new_wi_state, iw_table, nr_node_ids), GFP_KERNEL); if (!new_wi_state) return -ENOMEM; mutex_lock(&wi_state_lock); old_wi_state = rcu_dereference_protected(wi_state, lockdep_is_held(&wi_state_lock)); if (old_wi_state) { memcpy(new_wi_state->iw_table, old_wi_state->iw_table, nr_node_ids * sizeof(u8)); } else { for (i = 0; i < nr_node_ids; i++) new_wi_state->iw_table[i] = 1; } new_wi_state->iw_table[node_attr->nid] = weight; new_wi_state->mode_auto = false; rcu_assign_pointer(wi_state, new_wi_state); mutex_unlock(&wi_state_lock); if (old_wi_state) { synchronize_rcu(); kfree(old_wi_state); } return count; } static ssize_t weighted_interleave_auto_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct weighted_interleave_state *state; bool wi_auto = true; rcu_read_lock(); state = rcu_dereference(wi_state); if (state) wi_auto = state->mode_auto; rcu_read_unlock(); return sysfs_emit(buf, "%s\n", str_true_false(wi_auto)); } static ssize_t weighted_interleave_auto_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct weighted_interleave_state *new_wi_state, *old_wi_state = NULL; unsigned int *bw; bool input; int i; if (kstrtobool(buf, &input)) return -EINVAL; new_wi_state = kzalloc(struct_size(new_wi_state, iw_table, nr_node_ids), GFP_KERNEL); if (!new_wi_state) return -ENOMEM; for (i = 0; i < nr_node_ids; i++) new_wi_state->iw_table[i] = 1; mutex_lock(&wi_state_lock); if (!input) { old_wi_state = rcu_dereference_protected(wi_state, lockdep_is_held(&wi_state_lock)); if (!old_wi_state) goto update_wi_state; if (input == old_wi_state->mode_auto) { mutex_unlock(&wi_state_lock); return count; } memcpy(new_wi_state->iw_table, old_wi_state->iw_table, nr_node_ids * sizeof(u8)); goto update_wi_state; } bw = node_bw_table; if (!bw) { mutex_unlock(&wi_state_lock); kfree(new_wi_state); return -ENODEV; } new_wi_state->mode_auto = true; reduce_interleave_weights(bw, new_wi_state->iw_table); update_wi_state: rcu_assign_pointer(wi_state, new_wi_state); mutex_unlock(&wi_state_lock); if (old_wi_state) { synchronize_rcu(); kfree(old_wi_state); } return count; } static void sysfs_wi_node_delete(int nid) { struct iw_node_attr *attr; if (nid < 0 || nid >= nr_node_ids) return; mutex_lock(&wi_group->kobj_lock); attr = wi_group->nattrs[nid]; if (!attr) { mutex_unlock(&wi_group->kobj_lock); return; } wi_group->nattrs[nid] = NULL; mutex_unlock(&wi_group->kobj_lock); sysfs_remove_file(&wi_group->wi_kobj, &attr->kobj_attr.attr); kfree(attr->kobj_attr.attr.name); kfree(attr); } static void sysfs_wi_node_delete_all(void) { int nid; for (nid = 0; nid < nr_node_ids; nid++) sysfs_wi_node_delete(nid); } static void wi_state_free(void) { struct weighted_interleave_state *old_wi_state; mutex_lock(&wi_state_lock); old_wi_state = rcu_dereference_protected(wi_state, lockdep_is_held(&wi_state_lock)); rcu_assign_pointer(wi_state, NULL); mutex_unlock(&wi_state_lock); if (old_wi_state) { synchronize_rcu(); kfree(old_wi_state); } } static struct kobj_attribute wi_auto_attr = __ATTR(auto, 0664, weighted_interleave_auto_show, weighted_interleave_auto_store); static void wi_cleanup(void) { sysfs_remove_file(&wi_group->wi_kobj, &wi_auto_attr.attr); sysfs_wi_node_delete_all(); wi_state_free(); } static void wi_kobj_release(struct kobject *wi_kobj) { kfree(wi_group); } static const struct kobj_type wi_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = wi_kobj_release, }; static int sysfs_wi_node_add(int nid) { int ret; char *name; struct iw_node_attr *new_attr; if (nid < 0 || nid >= nr_node_ids) { pr_err("invalid node id: %d\n", nid); return -EINVAL; } new_attr = kzalloc(sizeof(*new_attr), GFP_KERNEL); if (!new_attr) return -ENOMEM; name = kasprintf(GFP_KERNEL, "node%d", nid); if (!name) { kfree(new_attr); return -ENOMEM; } sysfs_attr_init(&new_attr->kobj_attr.attr); new_attr->kobj_attr.attr.name = name; new_attr->kobj_attr.attr.mode = 0644; new_attr->kobj_attr.show = node_show; new_attr->kobj_attr.store = node_store; new_attr->nid = nid; mutex_lock(&wi_group->kobj_lock); if (wi_group->nattrs[nid]) { mutex_unlock(&wi_group->kobj_lock); ret = -EEXIST; goto out; } ret = sysfs_create_file(&wi_group->wi_kobj, &new_attr->kobj_attr.attr); if (ret) { mutex_unlock(&wi_group->kobj_lock); goto out; } wi_group->nattrs[nid] = new_attr; mutex_unlock(&wi_group->kobj_lock); return 0; out: kfree(new_attr->kobj_attr.attr.name); kfree(new_attr); return ret; } static int wi_node_notifier(struct notifier_block *nb, unsigned long action, void *data) { int err; struct node_notify *nn = data; int nid = nn->nid; switch (action) { case NODE_ADDED_FIRST_MEMORY: err = sysfs_wi_node_add(nid); if (err) pr_err("failed to add sysfs for node%d during hotplug: %d\n", nid, err); break; case NODE_REMOVED_LAST_MEMORY: sysfs_wi_node_delete(nid); break; } return NOTIFY_OK; } static int __init add_weighted_interleave_group(struct kobject *mempolicy_kobj) { int nid, err; wi_group = kzalloc(struct_size(wi_group, nattrs, nr_node_ids), GFP_KERNEL); if (!wi_group) return -ENOMEM; mutex_init(&wi_group->kobj_lock); err = kobject_init_and_add(&wi_group->wi_kobj, &wi_ktype, mempolicy_kobj, "weighted_interleave"); if (err) goto err_put_kobj; err = sysfs_create_file(&wi_group->wi_kobj, &wi_auto_attr.attr); if (err) goto err_put_kobj; for_each_online_node(nid) { if (!node_state(nid, N_MEMORY)) continue; err = sysfs_wi_node_add(nid); if (err) { pr_err("failed to add sysfs for node%d during init: %d\n", nid, err); goto err_cleanup_kobj; } } hotplug_node_notifier(wi_node_notifier, DEFAULT_CALLBACK_PRI); return 0; err_cleanup_kobj: wi_cleanup(); kobject_del(&wi_group->wi_kobj); err_put_kobj: kobject_put(&wi_group->wi_kobj); return err; } static int __init mempolicy_sysfs_init(void) { int err; static struct kobject *mempolicy_kobj; mempolicy_kobj = kobject_create_and_add("mempolicy", mm_kobj); if (!mempolicy_kobj) return -ENOMEM; err = add_weighted_interleave_group(mempolicy_kobj); if (err) goto err_kobj; return 0; err_kobj: kobject_del(mempolicy_kobj); kobject_put(mempolicy_kobj); return err; } late_initcall(mempolicy_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 6 6 4 3 4 3 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | // SPDX-License-Identifier: GPL-2.0-only /* * ratelimit.c - Do something with rate limit. * * Isolated from kernel/printk.c by Dave Young <hidave.darkstar@gmail.com> * * 2008-05-01 rewrite the function and use a ratelimit_state data struct as * parameter. Now every user can use their own standalone ratelimit_state. */ #include <linux/ratelimit.h> #include <linux/jiffies.h> #include <linux/export.h> /* * __ratelimit - rate limiting * @rs: ratelimit_state data * @func: name of calling function * * This enforces a rate limit: not more than @rs->burst callbacks * in every @rs->interval * * RETURNS: * 0 means callbacks will be suppressed. * 1 means go ahead and do it. */ int ___ratelimit(struct ratelimit_state *rs, const char *func) { /* Paired with WRITE_ONCE() in .proc_handler(). * Changing two values seperately could be inconsistent * and some message could be lost. (See: net_ratelimit_state). */ int interval = READ_ONCE(rs->interval); int burst = READ_ONCE(rs->burst); unsigned long flags; int ret = 0; /* * Zero interval says never limit, otherwise, non-positive burst * says always limit. */ if (interval <= 0 || burst <= 0) { WARN_ONCE(interval < 0 || burst < 0, "Negative interval (%d) or burst (%d): Uninitialized ratelimit_state structure?\n", interval, burst); ret = interval == 0 || burst > 0; if (!(READ_ONCE(rs->flags) & RATELIMIT_INITIALIZED) || (!interval && !burst) || !raw_spin_trylock_irqsave(&rs->lock, flags)) goto nolock_ret; /* Force re-initialization once re-enabled. */ rs->flags &= ~RATELIMIT_INITIALIZED; goto unlock_ret; } /* * If we contend on this state's lock then just check if * the current burst is used or not. It might cause * false positive when we are past the interval and * the current lock owner is just about to reset it. */ if (!raw_spin_trylock_irqsave(&rs->lock, flags)) { if (READ_ONCE(rs->flags) & RATELIMIT_INITIALIZED && atomic_read(&rs->rs_n_left) > 0 && atomic_dec_return(&rs->rs_n_left) >= 0) ret = 1; goto nolock_ret; } if (!(rs->flags & RATELIMIT_INITIALIZED)) { rs->begin = jiffies; rs->flags |= RATELIMIT_INITIALIZED; atomic_set(&rs->rs_n_left, rs->burst); } if (time_is_before_jiffies(rs->begin + interval)) { int m; /* * Reset rs_n_left ASAP to reduce false positives * in parallel calls, see above. */ atomic_set(&rs->rs_n_left, rs->burst); rs->begin = jiffies; if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { m = ratelimit_state_reset_miss(rs); if (m) { printk_deferred(KERN_WARNING "%s: %d callbacks suppressed\n", func, m); } } } /* Note that the burst might be taken by a parallel call. */ if (atomic_read(&rs->rs_n_left) > 0 && atomic_dec_return(&rs->rs_n_left) >= 0) ret = 1; unlock_ret: raw_spin_unlock_irqrestore(&rs->lock, flags); nolock_ret: if (!ret) ratelimit_state_inc_miss(rs); return ret; } EXPORT_SYMBOL(___ratelimit); |
| 302 302 302 302 302 302 195 195 6 6 6 302 302 302 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * kobject.c - library routines for handling generic kernel objects * * Copyright (c) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2006-2007 Greg Kroah-Hartman <greg@kroah.com> * Copyright (c) 2006-2007 Novell Inc. * * Please see the file Documentation/core-api/kobject.rst for critical information * about using the kobject interface. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kobject.h> #include <linux/string.h> #include <linux/export.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/random.h> /** * kobject_namespace() - Return @kobj's namespace tag. * @kobj: kobject in question * * Returns namespace tag of @kobj if its parent has namespace ops enabled * and thus @kobj should have a namespace tag associated with it. Returns * %NULL otherwise. */ const void *kobject_namespace(const struct kobject *kobj) { const struct kobj_ns_type_operations *ns_ops = kobj_ns_ops(kobj); if (!ns_ops || ns_ops->type == KOBJ_NS_TYPE_NONE) return NULL; return kobj->ktype->namespace(kobj); } /** * kobject_get_ownership() - Get sysfs ownership data for @kobj. * @kobj: kobject in question * @uid: kernel user ID for sysfs objects * @gid: kernel group ID for sysfs objects * * Returns initial uid/gid pair that should be used when creating sysfs * representation of given kobject. Normally used to adjust ownership of * objects in a container. */ void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; if (kobj->ktype->get_ownership) kobj->ktype->get_ownership(kobj, uid, gid); } static bool kobj_ns_type_is_valid(enum kobj_ns_type type) { if ((type <= KOBJ_NS_TYPE_NONE) || (type >= KOBJ_NS_TYPES)) return false; return true; } static int create_dir(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); const struct kobj_ns_type_operations *ops; int error; error = sysfs_create_dir_ns(kobj, kobject_namespace(kobj)); if (error) return error; if (ktype) { error = sysfs_create_groups(kobj, ktype->default_groups); if (error) { sysfs_remove_dir(kobj); return error; } } /* * @kobj->sd may be deleted by an ancestor going away. Hold an * extra reference so that it stays until @kobj is gone. */ sysfs_get(kobj->sd); /* * If @kobj has ns_ops, its children need to be filtered based on * their namespace tags. Enable namespace support on @kobj->sd. */ ops = kobj_child_ns_ops(kobj); if (ops) { BUG_ON(!kobj_ns_type_is_valid(ops->type)); BUG_ON(!kobj_ns_type_registered(ops->type)); sysfs_enable_ns(kobj->sd); } return 0; } static int get_kobj_path_length(const struct kobject *kobj) { int length = 1; const struct kobject *parent = kobj; /* walk up the ancestors until we hit the one pointing to the * root. * Add 1 to strlen for leading '/' of each level. */ do { if (kobject_name(parent) == NULL) return 0; length += strlen(kobject_name(parent)) + 1; parent = parent->parent; } while (parent); return length; } static int fill_kobj_path(const struct kobject *kobj, char *path, int length) { const struct kobject *parent; --length; for (parent = kobj; parent; parent = parent->parent) { int cur = strlen(kobject_name(parent)); /* back up enough to print this name with '/' */ length -= cur; if (length <= 0) return -EINVAL; memcpy(path + length, kobject_name(parent), cur); *(path + --length) = '/'; } pr_debug("'%s' (%p): %s: path = '%s'\n", kobject_name(kobj), kobj, __func__, path); return 0; } /** * kobject_get_path() - Allocate memory and fill in the path for @kobj. * @kobj: kobject in question, with which to build the path * @gfp_mask: the allocation type used to allocate the path * * Return: The newly allocated memory, caller must free with kfree(). */ char *kobject_get_path(const struct kobject *kobj, gfp_t gfp_mask) { char *path; int len; retry: len = get_kobj_path_length(kobj); if (len == 0) return NULL; path = kzalloc(len, gfp_mask); if (!path) return NULL; if (fill_kobj_path(kobj, path, len)) { kfree(path); goto retry; } return path; } EXPORT_SYMBOL_GPL(kobject_get_path); /* add the kobject to its kset's list */ static void kobj_kset_join(struct kobject *kobj) { if (!kobj->kset) return; kset_get(kobj->kset); spin_lock(&kobj->kset->list_lock); list_add_tail(&kobj->entry, &kobj->kset->list); spin_unlock(&kobj->kset->list_lock); } /* remove the kobject from its kset's list */ static void kobj_kset_leave(struct kobject *kobj) { if (!kobj->kset) return; spin_lock(&kobj->kset->list_lock); list_del_init(&kobj->entry); spin_unlock(&kobj->kset->list_lock); kset_put(kobj->kset); } static void kobject_init_internal(struct kobject *kobj) { if (!kobj) return; kref_init(&kobj->kref); INIT_LIST_HEAD(&kobj->entry); kobj->state_in_sysfs = 0; kobj->state_add_uevent_sent = 0; kobj->state_remove_uevent_sent = 0; kobj->state_initialized = 1; } static int kobject_add_internal(struct kobject *kobj) { int error = 0; struct kobject *parent; if (!kobj) return -ENOENT; if (!kobj->name || !kobj->name[0]) { WARN(1, "kobject: (%p): attempted to be registered with empty name!\n", kobj); return -EINVAL; } parent = kobject_get(kobj->parent); /* join kset if set, use it as parent if we do not already have one */ if (kobj->kset) { if (!parent) parent = kobject_get(&kobj->kset->kobj); kobj_kset_join(kobj); kobj->parent = parent; } pr_debug("'%s' (%p): %s: parent: '%s', set: '%s'\n", kobject_name(kobj), kobj, __func__, parent ? kobject_name(parent) : "<NULL>", kobj->kset ? kobject_name(&kobj->kset->kobj) : "<NULL>"); error = create_dir(kobj); if (error) { kobj_kset_leave(kobj); kobject_put(parent); kobj->parent = NULL; /* be noisy on error issues */ if (error == -EEXIST) pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n", __func__, kobject_name(kobj)); else pr_err("%s failed for %s (error: %d parent: %s)\n", __func__, kobject_name(kobj), error, parent ? kobject_name(parent) : "'none'"); } else kobj->state_in_sysfs = 1; return error; } /** * kobject_set_name_vargs() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * @vargs: vargs to format the string. */ int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs) { const char *s; if (kobj->name && !fmt) return 0; s = kvasprintf_const(GFP_KERNEL, fmt, vargs); if (!s) return -ENOMEM; /* * ewww... some of these buggers have '/' in the name ... If * that's the case, we need to make sure we have an actual * allocated copy to modify, since kvasprintf_const may have * returned something from .rodata. */ if (strchr(s, '/')) { char *t; t = kstrdup(s, GFP_KERNEL); kfree_const(s); if (!t) return -ENOMEM; s = strreplace(t, '/', '!'); } kfree_const(kobj->name); kobj->name = s; return 0; } /** * kobject_set_name() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * * This sets the name of the kobject. If you have already added the * kobject to the system, you must call kobject_rename() in order to * change the name of the kobject. */ int kobject_set_name(struct kobject *kobj, const char *fmt, ...) { va_list vargs; int retval; va_start(vargs, fmt); retval = kobject_set_name_vargs(kobj, fmt, vargs); va_end(vargs); return retval; } EXPORT_SYMBOL(kobject_set_name); /** * kobject_init() - Initialize a kobject structure. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * * This function will properly initialize a kobject such that it can then * be passed to the kobject_add() call. * * After this function is called, the kobject MUST be cleaned up by a call * to kobject_put(), not by a call to kfree directly to ensure that all of * the memory is cleaned up properly. */ void kobject_init(struct kobject *kobj, const struct kobj_type *ktype) { char *err_str; if (!kobj) { err_str = "invalid kobject pointer!"; goto error; } if (!ktype) { err_str = "must have a ktype to be initialized properly!\n"; goto error; } if (kobj->state_initialized) { /* do not error out as sometimes we can recover */ pr_err("kobject (%p): tried to init an initialized object, something is seriously wrong.\n", kobj); dump_stack_lvl(KERN_ERR); } kobject_init_internal(kobj); kobj->ktype = ktype; return; error: pr_err("kobject (%p): %s\n", kobj, err_str); dump_stack_lvl(KERN_ERR); } EXPORT_SYMBOL(kobject_init); static __printf(3, 0) int kobject_add_varg(struct kobject *kobj, struct kobject *parent, const char *fmt, va_list vargs) { int retval; retval = kobject_set_name_vargs(kobj, fmt, vargs); if (retval) { pr_err("can not set name properly!\n"); return retval; } kobj->parent = parent; return kobject_add_internal(kobj); } /** * kobject_add() - The main kobject add function. * @kobj: the kobject to add * @parent: pointer to the parent of the kobject. * @fmt: format to name the kobject with. * * The kobject name is set and added to the kobject hierarchy in this * function. * * If @parent is set, then the parent of the @kobj will be set to it. * If @parent is NULL, then the parent of the @kobj will be set to the * kobject associated with the kset assigned to this kobject. If no kset * is assigned to the kobject, then the kobject will be located in the * root of the sysfs tree. * * Note, no "add" uevent will be created with this call, the caller should set * up all of the necessary sysfs files for the object and then call * kobject_uevent() with the UEVENT_ADD parameter to ensure that * userspace is properly notified of this kobject's creation. * * Return: If this function returns an error, kobject_put() must be * called to properly clean up the memory associated with the * object. Under no instance should the kobject that is passed * to this function be directly freed with a call to kfree(), * that can leak memory. * * If this function returns success, kobject_put() must also be called * in order to properly clean up the memory associated with the object. * * In short, once this function is called, kobject_put() MUST be called * when the use of the object is finished in order to properly free * everything. */ int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; if (!kobj) return -EINVAL; if (!kobj->state_initialized) { pr_err("kobject '%s' (%p): tried to add an uninitialized object, something is seriously wrong.\n", kobject_name(kobj), kobj); dump_stack_lvl(KERN_ERR); return -EINVAL; } va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL(kobject_add); /** * kobject_init_and_add() - Initialize a kobject structure and add it to * the kobject hierarchy. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * @parent: pointer to the parent of this kobject. * @fmt: the name of the kobject. * * This function combines the call to kobject_init() and kobject_add(). * * If this function returns an error, kobject_put() must be called to * properly clean up the memory associated with the object. This is the * same type of error handling after a call to kobject_add() and kobject * lifetime rules are the same here. */ int kobject_init_and_add(struct kobject *kobj, const struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; kobject_init(kobj, ktype); va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL_GPL(kobject_init_and_add); /** * kobject_rename() - Change the name of an object. * @kobj: object in question. * @new_name: object's new name * * It is the responsibility of the caller to provide mutual * exclusion between two different calls of kobject_rename * on the same kobject and to ensure that new_name is valid and * won't conflict with other kobjects. */ int kobject_rename(struct kobject *kobj, const char *new_name) { int error = 0; const char *devpath = NULL; const char *dup_name = NULL, *name; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; if (!kobj->parent) { kobject_put(kobj); return -EINVAL; } devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; name = dup_name = kstrdup_const(new_name, GFP_KERNEL); if (!name) { error = -ENOMEM; goto out; } error = sysfs_rename_dir_ns(kobj, new_name, kobject_namespace(kobj)); if (error) goto out; /* Install the new kobject name */ dup_name = kobj->name; kobj->name = name; /* This function is mostly/only used for network interface. * Some hotplug package track interfaces by their name and * therefore want to know when the name is changed by the user. */ kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kfree_const(dup_name); kfree(devpath_string); kfree(devpath); kobject_put(kobj); return error; } EXPORT_SYMBOL_GPL(kobject_rename); /** * kobject_move() - Move object to another parent. * @kobj: object in question. * @new_parent: object's new parent (can be NULL) */ int kobject_move(struct kobject *kobj, struct kobject *new_parent) { int error; struct kobject *old_parent; const char *devpath = NULL; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; new_parent = kobject_get(new_parent); if (!new_parent) { if (kobj->kset) new_parent = kobject_get(&kobj->kset->kobj); } /* old object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; error = sysfs_move_dir_ns(kobj, new_parent, kobject_namespace(kobj)); if (error) goto out; old_parent = kobj->parent; kobj->parent = new_parent; new_parent = NULL; kobject_put(old_parent); kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kobject_put(new_parent); kobject_put(kobj); kfree(devpath_string); kfree(devpath); return error; } EXPORT_SYMBOL_GPL(kobject_move); static void __kobject_del(struct kobject *kobj) { struct kernfs_node *sd; const struct kobj_type *ktype; sd = kobj->sd; ktype = get_ktype(kobj); if (ktype) sysfs_remove_groups(kobj, ktype->default_groups); /* send "remove" if the caller did not do it but sent "add" */ if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) { pr_debug("'%s' (%p): auto cleanup 'remove' event\n", kobject_name(kobj), kobj); kobject_uevent(kobj, KOBJ_REMOVE); } sysfs_remove_dir(kobj); sysfs_put(sd); kobj->state_in_sysfs = 0; kobj_kset_leave(kobj); kobj->parent = NULL; } /** * kobject_del() - Unlink kobject from hierarchy. * @kobj: object. * * This is the function that should be called to delete an object * successfully added via kobject_add(). */ void kobject_del(struct kobject *kobj) { struct kobject *parent; if (!kobj) return; parent = kobj->parent; __kobject_del(kobj); kobject_put(parent); } EXPORT_SYMBOL(kobject_del); /** * kobject_get() - Increment refcount for object. * @kobj: object. */ struct kobject *kobject_get(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_get() is being called.\n", kobject_name(kobj), kobj); kref_get(&kobj->kref); } return kobj; } EXPORT_SYMBOL(kobject_get); struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj) { if (!kobj) return NULL; if (!kref_get_unless_zero(&kobj->kref)) kobj = NULL; return kobj; } EXPORT_SYMBOL(kobject_get_unless_zero); /* * kobject_cleanup - free kobject resources. * @kobj: object to cleanup */ static void kobject_cleanup(struct kobject *kobj) { struct kobject *parent = kobj->parent; const struct kobj_type *t = get_ktype(kobj); const char *name = kobj->name; pr_debug("'%s' (%p): %s, parent %p\n", kobject_name(kobj), kobj, __func__, kobj->parent); if (t && !t->release) pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", kobject_name(kobj), kobj); /* remove from sysfs if the caller did not do it */ if (kobj->state_in_sysfs) { pr_debug("'%s' (%p): auto cleanup kobject_del\n", kobject_name(kobj), kobj); __kobject_del(kobj); } else { /* avoid dropping the parent reference unnecessarily */ parent = NULL; } if (t && t->release) { pr_debug("'%s' (%p): calling ktype release\n", kobject_name(kobj), kobj); t->release(kobj); } /* free name if we allocated it */ if (name) { pr_debug("'%s': free name\n", name); kfree_const(name); } kobject_put(parent); } #ifdef CONFIG_DEBUG_KOBJECT_RELEASE static void kobject_delayed_cleanup(struct work_struct *work) { kobject_cleanup(container_of(to_delayed_work(work), struct kobject, release)); } #endif static void kobject_release(struct kref *kref) { struct kobject *kobj = container_of(kref, struct kobject, kref); #ifdef CONFIG_DEBUG_KOBJECT_RELEASE unsigned long delay = HZ + HZ * get_random_u32_below(4); pr_info("'%s' (%p): %s, parent %p (delayed %ld)\n", kobject_name(kobj), kobj, __func__, kobj->parent, delay); INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup); schedule_delayed_work(&kobj->release, delay); #else kobject_cleanup(kobj); #endif } /** * kobject_put() - Decrement refcount for object. * @kobj: object. * * Decrement the refcount, and if 0, call kobject_cleanup(). */ void kobject_put(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_put() is being called.\n", kobject_name(kobj), kobj); kref_put(&kobj->kref, kobject_release); } } EXPORT_SYMBOL(kobject_put); static void dynamic_kobj_release(struct kobject *kobj) { pr_debug("(%p): %s\n", kobj, __func__); kfree(kobj); } static const struct kobj_type dynamic_kobj_ktype = { .release = dynamic_kobj_release, .sysfs_ops = &kobj_sysfs_ops, }; /** * kobject_create() - Create a struct kobject dynamically. * * This function creates a kobject structure dynamically and sets it up * to be a "dynamic" kobject with a default release function set up. * * If the kobject was not able to be created, NULL will be returned. * The kobject structure returned from here must be cleaned up with a * call to kobject_put() and not kfree(), as kobject_init() has * already been called on this structure. */ static struct kobject *kobject_create(void) { struct kobject *kobj; kobj = kzalloc(sizeof(*kobj), GFP_KERNEL); if (!kobj) return NULL; kobject_init(kobj, &dynamic_kobj_ktype); return kobj; } /** * kobject_create_and_add() - Create a struct kobject dynamically and * register it with sysfs. * @name: the name for the kobject * @parent: the parent kobject of this kobject, if any. * * This function creates a kobject structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kobject_put() and the structure will be dynamically freed when * it is no longer being used. * * If the kobject was not able to be created, NULL will be returned. */ struct kobject *kobject_create_and_add(const char *name, struct kobject *parent) { struct kobject *kobj; int retval; kobj = kobject_create(); if (!kobj) return NULL; retval = kobject_add(kobj, parent, "%s", name); if (retval) { pr_warn("%s: kobject_add error: %d\n", __func__, retval); kobject_put(kobj); kobj = NULL; } return kobj; } EXPORT_SYMBOL_GPL(kobject_create_and_add); /** * kset_init() - Initialize a kset for use. * @k: kset */ void kset_init(struct kset *k) { kobject_init_internal(&k->kobj); INIT_LIST_HEAD(&k->list); spin_lock_init(&k->list_lock); } /* default kobject attribute operations */ static ssize_t kobj_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->show) ret = kattr->show(kobj, kattr, buf); return ret; } static ssize_t kobj_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->store) ret = kattr->store(kobj, kattr, buf, count); return ret; } const struct sysfs_ops kobj_sysfs_ops = { .show = kobj_attr_show, .store = kobj_attr_store, }; EXPORT_SYMBOL_GPL(kobj_sysfs_ops); /** * kset_register() - Initialize and add a kset. * @k: kset. * * NOTE: On error, the kset.kobj.name allocated by() kobj_set_name() * is freed, it can not be used any more. */ int kset_register(struct kset *k) { int err; if (!k) return -EINVAL; if (!k->kobj.ktype) { pr_err("must have a ktype to be initialized properly!\n"); return -EINVAL; } kset_init(k); err = kobject_add_internal(&k->kobj); if (err) { kfree_const(k->kobj.name); /* Set it to NULL to avoid accessing bad pointer in callers. */ k->kobj.name = NULL; return err; } kobject_uevent(&k->kobj, KOBJ_ADD); return 0; } EXPORT_SYMBOL(kset_register); /** * kset_unregister() - Remove a kset. * @k: kset. */ void kset_unregister(struct kset *k) { if (!k) return; kobject_del(&k->kobj); kobject_put(&k->kobj); } EXPORT_SYMBOL(kset_unregister); /** * kset_find_obj() - Search for object in kset. * @kset: kset we're looking in. * @name: object's name. * * Lock kset via @kset->subsys, and iterate over @kset->list, * looking for a matching kobject. If matching object is found * take a reference and return the object. */ struct kobject *kset_find_obj(struct kset *kset, const char *name) { struct kobject *k; struct kobject *ret = NULL; spin_lock(&kset->list_lock); list_for_each_entry(k, &kset->list, entry) { if (kobject_name(k) && !strcmp(kobject_name(k), name)) { ret = kobject_get_unless_zero(k); break; } } spin_unlock(&kset->list_lock); return ret; } EXPORT_SYMBOL_GPL(kset_find_obj); static void kset_release(struct kobject *kobj) { struct kset *kset = container_of(kobj, struct kset, kobj); pr_debug("'%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); kfree(kset); } static void kset_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { if (kobj->parent) kobject_get_ownership(kobj->parent, uid, gid); } static const struct kobj_type kset_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = kset_release, .get_ownership = kset_get_ownership, }; /** * kset_create() - Create a struct kset dynamically. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically. This structure can * then be registered with the system and show up in sysfs with a call to * kset_register(). When you are finished with this structure, if * kset_register() has been called, call kset_unregister() and the * structure will be dynamically freed when it is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ static struct kset *kset_create(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int retval; kset = kzalloc(sizeof(*kset), GFP_KERNEL); if (!kset) return NULL; retval = kobject_set_name(&kset->kobj, "%s", name); if (retval) { kfree(kset); return NULL; } kset->uevent_ops = uevent_ops; kset->kobj.parent = parent_kobj; /* * The kobject of this kset will have a type of kset_ktype and belong to * no kset itself. That way we can properly free it when it is * finished being used. */ kset->kobj.ktype = &kset_ktype; kset->kobj.kset = NULL; return kset; } /** * kset_create_and_add() - Create a struct kset dynamically and add it to sysfs. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kset_unregister() and the structure will be dynamically freed when it * is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ struct kset *kset_create_and_add(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int error; kset = kset_create(name, uevent_ops, parent_kobj); if (!kset) return NULL; error = kset_register(kset); if (error) { kfree(kset); return NULL; } return kset; } EXPORT_SYMBOL_GPL(kset_create_and_add); static DEFINE_SPINLOCK(kobj_ns_type_lock); static const struct kobj_ns_type_operations *kobj_ns_ops_tbl[KOBJ_NS_TYPES]; int kobj_ns_type_register(const struct kobj_ns_type_operations *ops) { enum kobj_ns_type type = ops->type; int error; spin_lock(&kobj_ns_type_lock); error = -EINVAL; if (!kobj_ns_type_is_valid(type)) goto out; error = -EBUSY; if (kobj_ns_ops_tbl[type]) goto out; error = 0; kobj_ns_ops_tbl[type] = ops; out: spin_unlock(&kobj_ns_type_lock); return error; } int kobj_ns_type_registered(enum kobj_ns_type type) { int registered = 0; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type)) registered = kobj_ns_ops_tbl[type] != NULL; spin_unlock(&kobj_ns_type_lock); return registered; } const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *parent) { const struct kobj_ns_type_operations *ops = NULL; if (parent && parent->ktype && parent->ktype->child_ns_type) ops = parent->ktype->child_ns_type(parent); return ops; } const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj) { return kobj_child_ns_ops(kobj->parent); } bool kobj_ns_current_may_mount(enum kobj_ns_type type) { bool may_mount = true; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) may_mount = kobj_ns_ops_tbl[type]->current_may_mount(); spin_unlock(&kobj_ns_type_lock); return may_mount; } void *kobj_ns_grab_current(enum kobj_ns_type type) { void *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->grab_current_ns(); spin_unlock(&kobj_ns_type_lock); return ns; } EXPORT_SYMBOL_GPL(kobj_ns_grab_current); void kobj_ns_drop(enum kobj_ns_type type, void *ns) { spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type] && kobj_ns_ops_tbl[type]->drop_ns) kobj_ns_ops_tbl[type]->drop_ns(ns); spin_unlock(&kobj_ns_type_lock); } EXPORT_SYMBOL_GPL(kobj_ns_drop); |
| 355 355 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BIT_SPINLOCK_H #define __LINUX_BIT_SPINLOCK_H #include <linux/kernel.h> #include <linux/preempt.h> #include <linux/atomic.h> #include <linux/bug.h> /* * bit-based spin_lock() * * Don't use this unless you really need to: spin_lock() and spin_unlock() * are significantly faster. */ static __always_inline void bit_spin_lock(int bitnum, unsigned long *addr) { /* * Assuming the lock is uncontended, this never enters * the body of the outer loop. If it is contended, then * within the inner loop a non-atomic test is used to * busywait with less bus contention for a good time to * attempt to acquire the lock bit. */ preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) while (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); do { cpu_relax(); } while (test_bit(bitnum, addr)); preempt_disable(); } #endif __acquire(bitlock); } /* * Return true if it was acquired */ static __always_inline int bit_spin_trylock(int bitnum, unsigned long *addr) { preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) if (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); return 0; } #endif __acquire(bitlock); return 1; } /* * bit-based spin_unlock() */ static __always_inline void bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); } /* * bit-based spin_unlock() * non-atomic version, which can be used eg. if the bit lock itself is * protecting the rest of the flags in the word. */ static __always_inline void __bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) __clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); } /* * Return true if the lock is held. */ static inline int bit_spin_is_locked(int bitnum, unsigned long *addr) { #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) return test_bit(bitnum, addr); #elif defined CONFIG_PREEMPT_COUNT return preempt_count(); #else return 1; #endif } #endif /* __LINUX_BIT_SPINLOCK_H */ |
| 1 224 | 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-only /* * Guest PC manipulation helpers * * Copyright (C) 2012,2013 - ARM Ltd * Copyright (C) 2020 - Google LLC * Author: Marc Zyngier <maz@kernel.org> */ #ifndef __ARM64_KVM_HYP_ADJUST_PC_H__ #define __ARM64_KVM_HYP_ADJUST_PC_H__ #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { kvm_skip_instr32(vcpu); } else { *vcpu_pc(vcpu) += 4; *vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK; } /* advance the singlestep state machine */ *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } /* * Skip an instruction which has been emulated at hyp while most guest sysregs * are live. */ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR); kvm_skip_instr(vcpu); write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR); write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); } /* * Skip an instruction while host sysregs are live. * Assumes host is always 64-bit. */ static inline void kvm_skip_host_instr(void) { write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR); } #endif |
| 297 297 243 243 248 247 209 199 20 243 243 158 242 243 243 243 242 243 242 242 3 3 3 3 242 243 243 243 243 243 241 243 243 243 243 243 243 157 243 243 14 14 14 14 14 367 364 367 368 367 235 177 176 365 365 364 365 365 3 3 3 3 3 3 3 3 28 28 28 28 27 3 28 28 28 27 28 28 28 28 28 28 3 27 3 3 3 3 3 3 35 35 20 20 35 35 35 35 35 35 | 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 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 | // SPDX-License-Identifier: GPL-2.0-only /* * kernel/workqueue.c - generic async execution with shared worker pool * * Copyright (C) 2002 Ingo Molnar * * Derived from the taskqueue/keventd code by: * David Woodhouse <dwmw2@infradead.org> * Andrew Morton * Kai Petzke <wpp@marie.physik.tu-berlin.de> * Theodore Ts'o <tytso@mit.edu> * * Made to use alloc_percpu by Christoph Lameter. * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * This is the generic async execution mechanism. Work items as are * executed in process context. The worker pool is shared and * automatically managed. There are two worker pools for each CPU (one for * normal work items and the other for high priority ones) and some extra * pools for workqueues which are not bound to any specific CPU - the * number of these backing pools is dynamic. * * Please read Documentation/core-api/workqueue.rst for details. */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/signal.h> #include <linux/completion.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/kthread.h> #include <linux/hardirq.h> #include <linux/mempolicy.h> #include <linux/freezer.h> #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> #include <linux/jhash.h> #include <linux/hashtable.h> #include <linux/rculist.h> #include <linux/nodemask.h> #include <linux/moduleparam.h> #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/sched/debug.h> #include <linux/nmi.h> #include <linux/kvm_para.h> #include <linux/delay.h> #include <linux/irq_work.h> #include "workqueue_internal.h" enum worker_pool_flags { /* * worker_pool flags * * A bound pool is either associated or disassociated with its CPU. * While associated (!DISASSOCIATED), all workers are bound to the * CPU and none has %WORKER_UNBOUND set and concurrency management * is in effect. * * While DISASSOCIATED, the cpu may be offline and all workers have * %WORKER_UNBOUND set and concurrency management disabled, and may * be executing on any CPU. The pool behaves as an unbound one. * * Note that DISASSOCIATED should be flipped only while holding * wq_pool_attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. * * As there can only be one concurrent BH execution context per CPU, a * BH pool is per-CPU and always DISASSOCIATED. */ POOL_BH = 1 << 0, /* is a BH pool */ POOL_MANAGER_ACTIVE = 1 << 1, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ POOL_BH_DRAINING = 1 << 3, /* draining after CPU offline */ }; enum worker_flags { /* worker flags */ WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ WORKER_UNBOUND = 1 << 7, /* worker is unbound */ WORKER_REBOUND = 1 << 8, /* worker was rebound */ WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND | WORKER_REBOUND, }; enum work_cancel_flags { WORK_CANCEL_DELAYED = 1 << 0, /* canceling a delayed_work */ WORK_CANCEL_DISABLE = 1 << 1, /* canceling to disable */ }; enum wq_internal_consts { NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ UNBOUND_POOL_HASH_ORDER = 6, /* hashed by pool->attrs */ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2, /* call for help after 10ms (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ /* * Rescue workers are used only on emergencies and shared by * all cpus. Give MIN_NICE. */ RESCUER_NICE_LEVEL = MIN_NICE, HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 32, WORKER_ID_LEN = 10 + WQ_NAME_LEN, /* "kworker/R-" + WQ_NAME_LEN */ }; /* * We don't want to trap softirq for too long. See MAX_SOFTIRQ_TIME and * MAX_SOFTIRQ_RESTART in kernel/softirq.c. These are macros because * msecs_to_jiffies() can't be an initializer. */ #define BH_WORKER_JIFFIES msecs_to_jiffies(2) #define BH_WORKER_RESTARTS 10 /* * Structure fields follow one of the following exclusion rules. * * I: Modifiable by initialization/destruction paths and read-only for * everyone else. * * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. * * L: pool->lock protected. Access with pool->lock held. * * LN: pool->lock and wq_node_nr_active->lock protected for writes. Either for * reads. * * K: Only modified by worker while holding pool->lock. Can be safely read by * self, while holding pool->lock or from IRQ context if %current is the * kworker. * * S: Only modified by worker self. * * A: wq_pool_attach_mutex protected. * * PL: wq_pool_mutex protected. * * PR: wq_pool_mutex protected for writes. RCU protected for reads. * * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. * * PWR: wq_pool_mutex and wq->mutex protected for writes. Either or * RCU for reads. * * WQ: wq->mutex protected. * * WR: wq->mutex protected for writes. RCU protected for reads. * * WO: wq->mutex protected for writes. Updated with WRITE_ONCE() and can be read * with READ_ONCE() without locking. * * MD: wq_mayday_lock protected. * * WD: Used internally by the watchdog. */ /* struct worker is defined in workqueue_internal.h */ struct worker_pool { raw_spinlock_t lock; /* the pool lock */ int cpu; /* I: the associated cpu */ int node; /* I: the associated node ID */ int id; /* I: pool ID */ unsigned int flags; /* L: flags */ unsigned long watchdog_ts; /* L: watchdog timestamp */ bool cpu_stall; /* WD: stalled cpu bound pool */ /* * The counter is incremented in a process context on the associated CPU * w/ preemption disabled, and decremented or reset in the same context * but w/ pool->lock held. The readers grab pool->lock and are * guaranteed to see if the counter reached zero. */ int nr_running; struct list_head worklist; /* L: list of pending works */ int nr_workers; /* L: total number of workers */ int nr_idle; /* L: currently idle workers */ struct list_head idle_list; /* L: list of idle workers */ struct timer_list idle_timer; /* L: worker idle timeout */ struct work_struct idle_cull_work; /* L: worker idle cleanup */ struct timer_list mayday_timer; /* L: SOS timer for workers */ /* a workers is either on busy_hash or idle_list, or the manager */ DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); /* L: hash of busy workers */ struct worker *manager; /* L: purely informational */ struct list_head workers; /* A: attached workers */ struct ida worker_ida; /* worker IDs for task name */ struct workqueue_attrs *attrs; /* I: worker attributes */ struct hlist_node hash_node; /* PL: unbound_pool_hash node */ int refcnt; /* PL: refcnt for unbound pools */ #ifdef CONFIG_PREEMPT_RT spinlock_t cb_lock; /* BH worker cancel lock */ #endif /* * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; }; /* * Per-pool_workqueue statistics. These can be monitored using * tools/workqueue/wq_monitor.py. */ enum pool_workqueue_stats { PWQ_STAT_STARTED, /* work items started execution */ PWQ_STAT_COMPLETED, /* work items completed execution */ PWQ_STAT_CPU_TIME, /* total CPU time consumed */ PWQ_STAT_CPU_INTENSIVE, /* wq_cpu_intensive_thresh_us violations */ PWQ_STAT_CM_WAKEUP, /* concurrency-management worker wakeups */ PWQ_STAT_REPATRIATED, /* unbound workers brought back into scope */ PWQ_STAT_MAYDAY, /* maydays to rescuer */ PWQ_STAT_RESCUED, /* linked work items executed by rescuer */ PWQ_NR_STATS, }; /* * The per-pool workqueue. While queued, bits below WORK_PWQ_SHIFT * of work_struct->data are used for flags and the remaining high bits * point to the pwq; thus, pwqs need to be aligned at two's power of the * number of flag bits. */ struct pool_workqueue { struct worker_pool *pool; /* I: the associated pool */ struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ int refcnt; /* L: reference count */ int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ bool plugged; /* L: execution suspended */ /* * nr_active management and WORK_STRUCT_INACTIVE: * * When pwq->nr_active >= max_active, new work item is queued to * pwq->inactive_works instead of pool->worklist and marked with * WORK_STRUCT_INACTIVE. * * All work items marked with WORK_STRUCT_INACTIVE do not participate in * nr_active and all work items in pwq->inactive_works are marked with * WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE work items are * in pwq->inactive_works. Some of them are ready to run in * pool->worklist or worker->scheduled. Those work itmes are only struct * wq_barrier which is used for flush_work() and should not participate * in nr_active. For non-barrier work item, it is marked with * WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works. */ int nr_active; /* L: nr of active works */ struct list_head inactive_works; /* L: inactive works */ struct list_head pending_node; /* LN: node on wq_node_nr_active->pending_pwqs */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ u64 stats[PWQ_NR_STATS]; /* * Release of unbound pwq is punted to a kthread_worker. See put_pwq() * and pwq_release_workfn() for details. pool_workqueue itself is also * RCU protected so that the first pwq can be determined without * grabbing wq->mutex. */ struct kthread_work release_work; struct rcu_head rcu; } __aligned(1 << WORK_STRUCT_PWQ_SHIFT); /* * Structure used to wait for workqueue flush. */ struct wq_flusher { struct list_head list; /* WQ: list of flushers */ int flush_color; /* WQ: flush color waiting for */ struct completion done; /* flush completion */ }; struct wq_device; /* * Unlike in a per-cpu workqueue where max_active limits its concurrency level * on each CPU, in an unbound workqueue, max_active applies to the whole system. * As sharing a single nr_active across multiple sockets can be very expensive, * the counting and enforcement is per NUMA node. * * The following struct is used to enforce per-node max_active. When a pwq wants * to start executing a work item, it should increment ->nr using * tryinc_node_nr_active(). If acquisition fails due to ->nr already being over * ->max, the pwq is queued on ->pending_pwqs. As in-flight work items finish * and decrement ->nr, node_activate_pending_pwq() activates the pending pwqs in * round-robin order. */ struct wq_node_nr_active { int max; /* per-node max_active */ atomic_t nr; /* per-node nr_active */ raw_spinlock_t lock; /* nests inside pool locks */ struct list_head pending_pwqs; /* LN: pwqs with inactive works */ }; /* * The externally visible workqueue. It relays the issued work items to * the appropriate worker_pool through its pool_workqueues. */ struct workqueue_struct { struct list_head pwqs; /* WR: all pwqs of this wq */ struct list_head list; /* PR: list of all workqueues */ struct mutex mutex; /* protects this wq */ int work_color; /* WQ: current work color */ int flush_color; /* WQ: current flush color */ atomic_t nr_pwqs_to_flush; /* flush in progress */ struct wq_flusher *first_flusher; /* WQ: first flusher */ struct list_head flusher_queue; /* WQ: flush waiters */ struct list_head flusher_overflow; /* WQ: flush overflow list */ struct list_head maydays; /* MD: pwqs requesting rescue */ struct worker *rescuer; /* MD: rescue worker */ int nr_drainers; /* WQ: drain in progress */ /* See alloc_workqueue() function comment for info on min/max_active */ int max_active; /* WO: max active works */ int min_active; /* WO: min active works */ int saved_max_active; /* WQ: saved max_active */ int saved_min_active; /* WQ: saved min_active */ struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ struct pool_workqueue __rcu *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ #endif #ifdef CONFIG_LOCKDEP char *lock_name; struct lock_class_key key; struct lockdep_map __lockdep_map; struct lockdep_map *lockdep_map; #endif char name[WQ_NAME_LEN]; /* I: workqueue name */ /* * Destruction of workqueue_struct is RCU protected to allow walking * the workqueues list without grabbing wq_pool_mutex. * This is used to dump all workqueues from sysrq. */ struct rcu_head rcu; /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __rcu * __percpu *cpu_pwq; /* I: per-cpu pwqs */ struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */ }; /* * Each pod type describes how CPUs should be grouped for unbound workqueues. * See the comment above workqueue_attrs->affn_scope. */ struct wq_pod_type { int nr_pods; /* number of pods */ cpumask_var_t *pod_cpus; /* pod -> cpus */ int *pod_node; /* pod -> node */ int *cpu_pod; /* cpu -> pod */ }; struct work_offq_data { u32 pool_id; u32 disable; u32 flags; }; static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = { [WQ_AFFN_DFL] = "default", [WQ_AFFN_CPU] = "cpu", [WQ_AFFN_SMT] = "smt", [WQ_AFFN_CACHE] = "cache", [WQ_AFFN_NUMA] = "numa", [WQ_AFFN_SYSTEM] = "system", }; /* * Per-cpu work items which run for longer than the following threshold are * automatically considered CPU intensive and excluded from concurrency * management to prevent them from noticeably delaying other per-cpu work items. * ULONG_MAX indicates that the user hasn't overridden it with a boot parameter. * The actual value is initialized in wq_cpu_intensive_thresh_init(). */ static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX; module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644); #ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT static unsigned int wq_cpu_intensive_warning_thresh = 4; module_param_named(cpu_intensive_warning_thresh, wq_cpu_intensive_warning_thresh, uint, 0644); #endif /* see the comment above the definition of WQ_POWER_EFFICIENT */ static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); module_param_named(power_efficient, wq_power_efficient, bool, 0444); static bool wq_online; /* can kworkers be created yet? */ static bool wq_topo_initialized __read_mostly = false; static struct kmem_cache *pwq_cache; static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES]; static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE; /* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */ static struct workqueue_attrs *unbound_wq_update_pwq_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */ static DEFINE_RAW_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ /* wait for manager to go away */ static struct rcuwait manager_wait = __RCUWAIT_INITIALIZER(manager_wait); static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* PL: mirror the cpu_online_mask excluding the CPU in the midst of hotplugging */ static cpumask_var_t wq_online_cpumask; /* PL&A: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; /* PL: user requested unbound cpumask via sysfs */ static cpumask_var_t wq_requested_unbound_cpumask; /* PL: isolated cpumask to be excluded from unbound cpumask */ static cpumask_var_t wq_isolated_cpumask; /* for further constrain wq_unbound_cpumask by cmdline parameter*/ static struct cpumask wq_cmdline_cpumask __initdata; /* CPU where unbound work was last round robin scheduled from this CPU */ static DEFINE_PER_CPU(int, wq_rr_cpu_last); /* * Local execution of unbound work items is no longer guaranteed. The * following always forces round-robin CPU selection on unbound work items * to uncover usages which depend on it. */ #ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU static bool wq_debug_force_rr_cpu = true; #else static bool wq_debug_force_rr_cpu = false; #endif module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); /* to raise softirq for the BH worker pools on other CPUs */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_work [NR_STD_WORKER_POOLS], bh_pool_irq_works); /* the BH worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], bh_worker_pools); /* the per-cpu worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ /* PL: hash of all unbound pools keyed by pool->attrs */ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); /* I: attributes used when instantiating standard unbound pools on demand */ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; /* I: attributes used when instantiating ordered pools on demand */ static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; /* * I: kthread_worker to release pwq's. pwq release needs to be bounced to a * process context while holding a pool lock. Bounce to a dedicated kthread * worker to avoid A-A deadlocks. */ static struct kthread_worker *pwq_release_worker __ro_after_init; struct workqueue_struct *system_wq __ro_after_init; EXPORT_SYMBOL(system_wq); struct workqueue_struct *system_percpu_wq __ro_after_init; EXPORT_SYMBOL(system_percpu_wq); struct workqueue_struct *system_highpri_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_highpri_wq); struct workqueue_struct *system_long_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_long_wq); struct workqueue_struct *system_unbound_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_unbound_wq); struct workqueue_struct *system_dfl_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_dfl_wq); struct workqueue_struct *system_freezable_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_wq); struct workqueue_struct *system_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); struct workqueue_struct *system_bh_wq; EXPORT_SYMBOL_GPL(system_bh_wq); struct workqueue_struct *system_bh_highpri_wq; EXPORT_SYMBOL_GPL(system_bh_highpri_wq); static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); static void show_pwq(struct pool_workqueue *pwq); static void show_one_worker_pool(struct worker_pool *pool); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> #define assert_rcu_or_pool_mutex() \ RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \ !lockdep_is_held(&wq->mutex) && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU, wq->mutex or wq_pool_mutex should be held") #define for_each_bh_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(bh_worker_pools, cpu)[0]; \ (pool) < &per_cpu(bh_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) /** * for_each_pool - iterate through all worker_pools in the system * @pool: iteration cursor * @pi: integer used for iteration * * This must be called either with wq_pool_mutex held or RCU read * locked. If the pool needs to be used beyond the locking in effect, the * caller is responsible for guaranteeing that the pool stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool(pool, pi) \ idr_for_each_entry(&worker_pool_idr, pool, pi) \ if (({ assert_rcu_or_pool_mutex(); false; })) { } \ else /** * for_each_pool_worker - iterate through all workers of a worker_pool * @worker: iteration cursor * @pool: worker_pool to iterate workers of * * This must be called with wq_pool_attach_mutex. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool_worker(worker, pool) \ list_for_each_entry((worker), &(pool)->workers, node) \ if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \ else /** * for_each_pwq - iterate through all pool_workqueues of the specified workqueue * @pwq: iteration cursor * @wq: the target workqueue * * This must be called either with wq->mutex held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pwq(pwq, wq) \ list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node, \ lockdep_is_held(&(wq->mutex))) #ifdef CONFIG_DEBUG_OBJECTS_WORK static const struct debug_obj_descr work_debug_descr; static void *work_debug_hint(void *addr) { return ((struct work_struct *) addr)->func; } static bool work_is_static_object(void *addr) { struct work_struct *work = addr; return test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work)); } /* * fixup_init is called when: * - an active object is initialized */ static bool work_fixup_init(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_init(work, &work_debug_descr); return true; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool work_fixup_free(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_free(work, &work_debug_descr); return true; default: return false; } } static const struct debug_obj_descr work_debug_descr = { .name = "work_struct", .debug_hint = work_debug_hint, .is_static_object = work_is_static_object, .fixup_init = work_fixup_init, .fixup_free = work_fixup_free, }; static inline void debug_work_activate(struct work_struct *work) { debug_object_activate(work, &work_debug_descr); } static inline void debug_work_deactivate(struct work_struct *work) { debug_object_deactivate(work, &work_debug_descr); } void __init_work(struct work_struct *work, int onstack) { if (onstack) debug_object_init_on_stack(work, &work_debug_descr); else debug_object_init(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(__init_work); void destroy_work_on_stack(struct work_struct *work) { debug_object_free(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_work_on_stack); void destroy_delayed_work_on_stack(struct delayed_work *work) { timer_destroy_on_stack(&work->timer); debug_object_free(&work->work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); #else static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } #endif /** * worker_pool_assign_id - allocate ID and assign it to @pool * @pool: the pool pointer of interest * * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned * successfully, -errno on failure. */ static int worker_pool_assign_id(struct worker_pool *pool) { int ret; lockdep_assert_held(&wq_pool_mutex); ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE, GFP_KERNEL); if (ret >= 0) { pool->id = ret; return 0; } return ret; } static struct pool_workqueue __rcu ** unbound_pwq_slot(struct workqueue_struct *wq, int cpu) { if (cpu >= 0) return per_cpu_ptr(wq->cpu_pwq, cpu); else return &wq->dfl_pwq; } /* @cpu < 0 for dfl_pwq */ static struct pool_workqueue *unbound_pwq(struct workqueue_struct *wq, int cpu) { return rcu_dereference_check(*unbound_pwq_slot(wq, cpu), lockdep_is_held(&wq_pool_mutex) || lockdep_is_held(&wq->mutex)); } /** * unbound_effective_cpumask - effective cpumask of an unbound workqueue * @wq: workqueue of interest * * @wq->unbound_attrs->cpumask contains the cpumask requested by the user which * is masked with wq_unbound_cpumask to determine the effective cpumask. The * default pwq is always mapped to the pool with the current effective cpumask. */ static struct cpumask *unbound_effective_cpumask(struct workqueue_struct *wq) { return unbound_pwq(wq, -1)->pool->attrs->__pod_cpumask; } static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; } static int get_work_color(unsigned long work_data) { return (work_data >> WORK_STRUCT_COLOR_SHIFT) & ((1 << WORK_STRUCT_COLOR_BITS) - 1); } static int work_next_color(int color) { return (color + 1) % WORK_NR_COLORS; } static unsigned long pool_offq_flags(struct worker_pool *pool) { return (pool->flags & POOL_BH) ? WORK_OFFQ_BH : 0; } /* * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data * contain the pointer to the queued pwq. Once execution starts, the flag * is cleared and the high bits contain OFFQ flags and pool ID. * * set_work_pwq(), set_work_pool_and_clear_pending() and mark_work_canceling() * can be used to set the pwq, pool or clear work->data. These functions should * only be called while the work is owned - ie. while the PENDING bit is set. * * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq * corresponding to a work. Pool is available once the work has been * queued anywhere after initialization until it is sync canceled. pwq is * available only while the work item is queued. */ static inline void set_work_data(struct work_struct *work, unsigned long data) { WARN_ON_ONCE(!work_pending(work)); atomic_long_set(&work->data, data | work_static(work)); } static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, unsigned long flags) { set_work_data(work, (unsigned long)pwq | WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | flags); } static void set_work_pool_and_keep_pending(struct work_struct *work, int pool_id, unsigned long flags) { set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | WORK_STRUCT_PENDING | flags); } static void set_work_pool_and_clear_pending(struct work_struct *work, int pool_id, unsigned long flags) { /* * The following wmb is paired with the implied mb in * test_and_set_bit(PENDING) and ensures all updates to @work made * here are visible to and precede any updates by the next PENDING * owner. */ smp_wmb(); set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | flags); /* * The following mb guarantees that previous clear of a PENDING bit * will not be reordered with any speculative LOADS or STORES from * work->current_func, which is executed afterwards. This possible * reordering can lead to a missed execution on attempt to queue * the same @work. E.g. consider this case: * * CPU#0 CPU#1 * ---------------------------- -------------------------------- * * 1 STORE event_indicated * 2 queue_work_on() { * 3 test_and_set_bit(PENDING) * 4 } set_..._and_clear_pending() { * 5 set_work_data() # clear bit * 6 smp_mb() * 7 work->current_func() { * 8 LOAD event_indicated * } * * Without an explicit full barrier speculative LOAD on line 8 can * be executed before CPU#0 does STORE on line 1. If that happens, * CPU#0 observes the PENDING bit is still set and new execution of * a @work is not queued in a hope, that CPU#1 will eventually * finish the queued @work. Meanwhile CPU#1 does not see * event_indicated is set, because speculative LOAD was executed * before actual STORE. */ smp_mb(); } static inline struct pool_workqueue *work_struct_pwq(unsigned long data) { return (struct pool_workqueue *)(data & WORK_STRUCT_PWQ_MASK); } static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data); else return NULL; } /** * get_work_pool - return the worker_pool a given work was associated with * @work: the work item of interest * * Pools are created and destroyed under wq_pool_mutex, and allows read * access under RCU read lock. As such, this function should be * called under wq_pool_mutex or inside of a rcu_read_lock() region. * * All fields of the returned pool are accessible as long as the above * mentioned locking is in effect. If the returned pool needs to be used * beyond the critical section, the caller is responsible for ensuring the * returned pool is and stays online. * * Return: The worker_pool @work was last associated with. %NULL if none. */ static struct worker_pool *get_work_pool(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); int pool_id; assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) return NULL; return idr_find(&worker_pool_idr, pool_id); } static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits) { return (v >> shift) & ((1U << bits) - 1); } static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data) { WARN_ON_ONCE(data & WORK_STRUCT_PWQ); offqd->pool_id = shift_and_mask(data, WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS); offqd->disable = shift_and_mask(data, WORK_OFFQ_DISABLE_SHIFT, WORK_OFFQ_DISABLE_BITS); offqd->flags = data & WORK_OFFQ_FLAG_MASK; } static unsigned long work_offqd_pack_flags(struct work_offq_data *offqd) { return ((unsigned long)offqd->disable << WORK_OFFQ_DISABLE_SHIFT) | ((unsigned long)offqd->flags); } /* * Policy functions. These define the policies on how the global worker * pools are managed. Unless noted otherwise, these functions assume that * they're being called with pool->lock held. */ /* * Need to wake up a worker? Called from anything but currently * running workers. * * Note that, because unbound workers never contribute to nr_running, this * function will always return %true for unbound pools as long as the * worklist isn't empty. */ static bool need_more_worker(struct worker_pool *pool) { return !list_empty(&pool->worklist) && !pool->nr_running; } /* Can I start working? Called from busy but !running workers. */ static bool may_start_working(struct worker_pool *pool) { return pool->nr_idle; } /* Do I need to keep working? Called from currently running workers. */ static bool keep_working(struct worker_pool *pool) { return !list_empty(&pool->worklist) && (pool->nr_running <= 1); } /* Do we need a new worker? Called from manager. */ static bool need_to_create_worker(struct worker_pool *pool) { return need_more_worker(pool) && !may_start_working(pool); } /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; } /** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set * * Set @flags in @worker->flags and adjust nr_running accordingly. */ static inline void worker_set_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); /* If transitioning into NOT_RUNNING, adjust nr_running. */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { pool->nr_running--; } worker->flags |= flags; } /** * worker_clr_flags - clear worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to clear * * Clear @flags in @worker->flags and adjust nr_running accordingly. */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; unsigned int oflags = worker->flags; lockdep_assert_held(&pool->lock); worker->flags &= ~flags; /* * If transitioning out of NOT_RUNNING, increment nr_running. Note * that the nested NOT_RUNNING is not a noop. NOT_RUNNING is mask * of multiple flags, not a single flag. */ if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) if (!(worker->flags & WORKER_NOT_RUNNING)) pool->nr_running++; } /* Return the first idle worker. Called with pool->lock held. */ static struct worker *first_idle_worker(struct worker_pool *pool) { if (unlikely(list_empty(&pool->idle_list))) return NULL; return list_first_entry(&pool->idle_list, struct worker, entry); } /** * worker_enter_idle - enter idle state * @worker: worker which is entering idle state * * @worker is entering idle state. Update stats and idle timer if * necessary. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_enter_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) || WARN_ON_ONCE(!list_empty(&worker->entry) && (worker->hentry.next || worker->hentry.pprev))) return; /* can't use worker_set_flags(), also called from create_worker() */ worker->flags |= WORKER_IDLE; pool->nr_idle++; worker->last_active = jiffies; /* idle_list is LIFO */ list_add(&worker->entry, &pool->idle_list); if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* Sanity check nr_running. */ WARN_ON_ONCE(pool->nr_workers == pool->nr_idle && pool->nr_running); } /** * worker_leave_idle - leave idle state * @worker: worker which is leaving idle state * * @worker is leaving idle state. Update stats. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_leave_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE))) return; worker_clr_flags(worker, WORKER_IDLE); pool->nr_idle--; list_del_init(&worker->entry); } /** * find_worker_executing_work - find worker which is executing a work * @pool: pool of interest * @work: work to find worker for * * Find a worker which is executing @work on @pool by searching * @pool->busy_hash which is keyed by the address of @work. For a worker * to match, its current execution should match the address of @work and * its work function. This is to avoid unwanted dependency between * unrelated work executions through a work item being recycled while still * being executed. * * This is a bit tricky. A work item may be freed once its execution * starts and nothing prevents the freed area from being recycled for * another work item. If the same work item address ends up being reused * before the original execution finishes, workqueue will identify the * recycled work item as currently executing and make it wait until the * current execution finishes, introducing an unwanted dependency. * * This function checks the work item address and work function to avoid * false positives. Note that this isn't complete as one may construct a * work function which can introduce dependency onto itself through a * recycled work item. Well, if somebody wants to shoot oneself in the * foot that badly, there's only so much we can do, and if such deadlock * actually occurs, it should be easy to locate the culprit work function. * * CONTEXT: * raw_spin_lock_irq(pool->lock). * * Return: * Pointer to worker which is executing @work if found, %NULL * otherwise. */ static struct worker *find_worker_executing_work(struct worker_pool *pool, struct work_struct *work) { struct worker *worker; hash_for_each_possible(pool->busy_hash, worker, hentry, (unsigned long)work) if (worker->current_work == work && worker->current_func == work->func) return worker; return NULL; } /** * move_linked_works - move linked works to a list * @work: start of series of works to be scheduled * @head: target list to append @work to * @nextp: out parameter for nested worklist walking * * Schedule linked works starting from @work to @head. Work series to be * scheduled starts at @work and includes any consecutive work with * WORK_STRUCT_LINKED set in its predecessor. See assign_work() for details on * @nextp. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void move_linked_works(struct work_struct *work, struct list_head *head, struct work_struct **nextp) { struct work_struct *n; /* * Linked worklist will always end before the end of the list, * use NULL for list head. */ list_for_each_entry_safe_from(work, n, NULL, entry) { list_move_tail(&work->entry, head); if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) break; } /* * If we're already inside safe list traversal and have moved * multiple works to the scheduled queue, the next position * needs to be updated. */ if (nextp) *nextp = n; } /** * assign_work - assign a work item and its linked work items to a worker * @work: work to assign * @worker: worker to assign to * @nextp: out parameter for nested worklist walking * * Assign @work and its linked work items to @worker. If @work is already being * executed by another worker in the same pool, it'll be punted there. * * If @nextp is not NULL, it's updated to point to the next work of the last * scheduled work. This allows assign_work() to be nested inside * list_for_each_entry_safe(). * * Returns %true if @work was successfully assigned to @worker. %false if @work * was punted to another worker already executing it. */ static bool assign_work(struct work_struct *work, struct worker *worker, struct work_struct **nextp) { struct worker_pool *pool = worker->pool; struct worker *collision; lockdep_assert_held(&pool->lock); /* * A single work shouldn't be executed concurrently by multiple workers. * __queue_work() ensures that @work doesn't jump to a different pool * while still running in the previous pool. Here, we should ensure that * @work is not executed concurrently by multiple workers from the same * pool. Check whether anyone is already processing the work. If so, * defer the work to the currently executing one. */ collision = find_worker_executing_work(pool, work); if (unlikely(collision)) { move_linked_works(work, &collision->scheduled, nextp); return false; } move_linked_works(work, &worker->scheduled, nextp); return true; } static struct irq_work *bh_pool_irq_work(struct worker_pool *pool) { int high = pool->attrs->nice == HIGHPRI_NICE_LEVEL ? 1 : 0; return &per_cpu(bh_pool_irq_works, pool->cpu)[high]; } static void kick_bh_pool(struct worker_pool *pool) { #ifdef CONFIG_SMP /* see drain_dead_softirq_workfn() for BH_DRAINING */ if (unlikely(pool->cpu != smp_processor_id() && !(pool->flags & POOL_BH_DRAINING))) { irq_work_queue_on(bh_pool_irq_work(pool), pool->cpu); return; } #endif if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) raise_softirq_irqoff(HI_SOFTIRQ); else raise_softirq_irqoff(TASKLET_SOFTIRQ); } /** * kick_pool - wake up an idle worker if necessary * @pool: pool to kick * * @pool may have pending work items. Wake up worker if necessary. Returns * whether a worker was woken up. */ static bool kick_pool(struct worker_pool *pool) { struct worker *worker = first_idle_worker(pool); struct task_struct *p; lockdep_assert_held(&pool->lock); if (!need_more_worker(pool) || !worker) return false; if (pool->flags & POOL_BH) { kick_bh_pool(pool); return true; } p = worker->task; #ifdef CONFIG_SMP /* * Idle @worker is about to execute @work and waking up provides an * opportunity to migrate @worker at a lower cost by setting the task's * wake_cpu field. Let's see if we want to move @worker to improve * execution locality. * * We're waking the worker that went idle the latest and there's some * chance that @worker is marked idle but hasn't gone off CPU yet. If * so, setting the wake_cpu won't do anything. As this is a best-effort * optimization and the race window is narrow, let's leave as-is for * now. If this becomes pronounced, we can skip over workers which are * still on cpu when picking an idle worker. * * If @pool has non-strict affinity, @worker might have ended up outside * its affinity scope. Repatriate. */ if (!pool->attrs->affn_strict && !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask, cpu_online_mask); if (wake_cpu < nr_cpu_ids) { p->wake_cpu = wake_cpu; get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; } } #endif wake_up_process(p); return true; } #ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT /* * Concurrency-managed per-cpu work items that hog CPU for longer than * wq_cpu_intensive_thresh_us trigger the automatic CPU_INTENSIVE mechanism, * which prevents them from stalling other concurrency-managed work items. If a * work function keeps triggering this mechanism, it's likely that the work item * should be using an unbound workqueue instead. * * wq_cpu_intensive_report() tracks work functions which trigger such conditions * and report them so that they can be examined and converted to use unbound * workqueues as appropriate. To avoid flooding the console, each violating work * function is tracked and reported with exponential backoff. */ #define WCI_MAX_ENTS 128 struct wci_ent { work_func_t func; atomic64_t cnt; struct hlist_node hash_node; }; static struct wci_ent wci_ents[WCI_MAX_ENTS]; static int wci_nr_ents; static DEFINE_RAW_SPINLOCK(wci_lock); static DEFINE_HASHTABLE(wci_hash, ilog2(WCI_MAX_ENTS)); static struct wci_ent *wci_find_ent(work_func_t func) { struct wci_ent *ent; hash_for_each_possible_rcu(wci_hash, ent, hash_node, (unsigned long)func) { if (ent->func == func) return ent; } return NULL; } static void wq_cpu_intensive_report(work_func_t func) { struct wci_ent *ent; restart: ent = wci_find_ent(func); if (ent) { u64 cnt; /* * Start reporting from the warning_thresh and back off * exponentially. */ cnt = atomic64_inc_return_relaxed(&ent->cnt); if (wq_cpu_intensive_warning_thresh && cnt >= wq_cpu_intensive_warning_thresh && is_power_of_2(cnt + 1 - wq_cpu_intensive_warning_thresh)) printk_deferred(KERN_WARNING "workqueue: %ps hogged CPU for >%luus %llu times, consider switching to WQ_UNBOUND\n", ent->func, wq_cpu_intensive_thresh_us, atomic64_read(&ent->cnt)); return; } /* * @func is a new violation. Allocate a new entry for it. If wcn_ents[] * is exhausted, something went really wrong and we probably made enough * noise already. */ if (wci_nr_ents >= WCI_MAX_ENTS) return; raw_spin_lock(&wci_lock); if (wci_nr_ents >= WCI_MAX_ENTS) { raw_spin_unlock(&wci_lock); return; } if (wci_find_ent(func)) { raw_spin_unlock(&wci_lock); goto restart; } ent = &wci_ents[wci_nr_ents++]; ent->func = func; atomic64_set(&ent->cnt, 0); hash_add_rcu(wci_hash, &ent->hash_node, (unsigned long)func); raw_spin_unlock(&wci_lock); goto restart; } #else /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ static void wq_cpu_intensive_report(work_func_t func) {} #endif /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ /** * wq_worker_running - a worker is running again * @task: task waking up * * This function is called when a worker returns from schedule() */ void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); if (!READ_ONCE(worker->sleeping)) return; /* * If preempted by unbind_workers() between the WORKER_NOT_RUNNING check * and the nr_running increment below, we may ruin the nr_running reset * and leave with an unexpected pool->nr_running == 1 on the newly unbound * pool. Protect against such race. */ preempt_disable(); if (!(worker->flags & WORKER_NOT_RUNNING)) worker->pool->nr_running++; preempt_enable(); /* * CPU intensive auto-detection cares about how long a work item hogged * CPU without sleeping. Reset the starting timestamp on wakeup. */ worker->current_at = worker->task->se.sum_exec_runtime; WRITE_ONCE(worker->sleeping, 0); } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep * * This function is called from schedule() when a busy worker is * going to sleep. */ void wq_worker_sleeping(struct task_struct *task) { struct worker *worker = kthread_data(task); struct worker_pool *pool; /* * Rescuers, which may not have all the fields set up like normal * workers, also reach here, let's not access anything before * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) return; pool = worker->pool; /* Return if preempted before wq_worker_running() was reached */ if (READ_ONCE(worker->sleeping)) return; WRITE_ONCE(worker->sleeping, 1); raw_spin_lock_irq(&pool->lock); /* * Recheck in case unbind_workers() preempted us. We don't * want to decrement nr_running after the worker is unbound * and nr_running has been reset. */ if (worker->flags & WORKER_NOT_RUNNING) { raw_spin_unlock_irq(&pool->lock); return; } pool->nr_running--; if (kick_pool(pool)) worker->current_pwq->stats[PWQ_STAT_CM_WAKEUP]++; raw_spin_unlock_irq(&pool->lock); } /** * wq_worker_tick - a scheduler tick occurred while a kworker is running * @task: task currently running * * Called from sched_tick(). We're in the IRQ context and the current * worker's fields which follow the 'K' locking rule can be accessed safely. */ void wq_worker_tick(struct task_struct *task) { struct worker *worker = kthread_data(task); struct pool_workqueue *pwq = worker->current_pwq; struct worker_pool *pool = worker->pool; if (!pwq) return; pwq->stats[PWQ_STAT_CPU_TIME] += TICK_USEC; if (!wq_cpu_intensive_thresh_us) return; /* * If the current worker is concurrency managed and hogged the CPU for * longer than wq_cpu_intensive_thresh_us, it's automatically marked * CPU_INTENSIVE to avoid stalling other concurrency-managed work items. * * Set @worker->sleeping means that @worker is in the process of * switching out voluntarily and won't be contributing to * @pool->nr_running until it wakes up. As wq_worker_sleeping() also * decrements ->nr_running, setting CPU_INTENSIVE here can lead to * double decrements. The task is releasing the CPU anyway. Let's skip. * We probably want to make this prettier in the future. */ if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) || worker->task->se.sum_exec_runtime - worker->current_at < wq_cpu_intensive_thresh_us * NSEC_PER_USEC) return; raw_spin_lock(&pool->lock); worker_set_flags(worker, WORKER_CPU_INTENSIVE); wq_cpu_intensive_report(worker->current_func); pwq->stats[PWQ_STAT_CPU_INTENSIVE]++; if (kick_pool(pool)) pwq->stats[PWQ_STAT_CM_WAKEUP]++; raw_spin_unlock(&pool->lock); } /** * wq_worker_last_func - retrieve worker's last work function * @task: Task to retrieve last work function of. * * Determine the last function a worker executed. This is called from * the scheduler to get a worker's last known identity. * * CONTEXT: * raw_spin_lock_irq(rq->lock) * * This function is called during schedule() when a kworker is going * to sleep. It's used by psi to identify aggregation workers during * dequeuing, to allow periodic aggregation to shut-off when that * worker is the last task in the system or cgroup to go to sleep. * * As this function doesn't involve any workqueue-related locking, it * only returns stable values when called from inside the scheduler's * queuing and dequeuing paths, when @task, which must be a kworker, * is guaranteed to not be processing any works. * * Return: * The last work function %current executed as a worker, NULL if it * hasn't executed any work yet. */ work_func_t wq_worker_last_func(struct task_struct *task) { struct worker *worker = kthread_data(task); return worker->last_func; } /** * wq_node_nr_active - Determine wq_node_nr_active to use * @wq: workqueue of interest * @node: NUMA node, can be %NUMA_NO_NODE * * Determine wq_node_nr_active to use for @wq on @node. Returns: * * - %NULL for per-cpu workqueues as they don't need to use shared nr_active. * * - node_nr_active[nr_node_ids] if @node is %NUMA_NO_NODE. * * - Otherwise, node_nr_active[@node]. */ static struct wq_node_nr_active *wq_node_nr_active(struct workqueue_struct *wq, int node) { if (!(wq->flags & WQ_UNBOUND)) return NULL; if (node == NUMA_NO_NODE) node = nr_node_ids; return wq->node_nr_active[node]; } /** * wq_update_node_max_active - Update per-node max_actives to use * @wq: workqueue to update * @off_cpu: CPU that's going down, -1 if a CPU is not going down * * Update @wq->node_nr_active[]->max. @wq must be unbound. max_active is * distributed among nodes according to the proportions of numbers of online * cpus. The result is always between @wq->min_active and max_active. */ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) { struct cpumask *effective = unbound_effective_cpumask(wq); int min_active = READ_ONCE(wq->min_active); int max_active = READ_ONCE(wq->max_active); int total_cpus, node; lockdep_assert_held(&wq->mutex); if (!wq_topo_initialized) return; if (off_cpu >= 0 && !cpumask_test_cpu(off_cpu, effective)) off_cpu = -1; total_cpus = cpumask_weight_and(effective, cpu_online_mask); if (off_cpu >= 0) total_cpus--; /* If all CPUs of the wq get offline, use the default values */ if (unlikely(!total_cpus)) { for_each_node(node) wq_node_nr_active(wq, node)->max = min_active; wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; return; } for_each_node(node) { int node_cpus; node_cpus = cpumask_weight_and(effective, cpumask_of_node(node)); if (off_cpu >= 0 && cpu_to_node(off_cpu) == node) node_cpus--; wq_node_nr_active(wq, node)->max = clamp(DIV_ROUND_UP(max_active * node_cpus, total_cpus), min_active, max_active); } wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; } /** * get_pwq - get an extra reference on the specified pool_workqueue * @pwq: pool_workqueue to get * * Obtain an extra reference on @pwq. The caller should guarantee that * @pwq has positive refcnt and be holding the matching pool->lock. */ static void get_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); WARN_ON_ONCE(pwq->refcnt <= 0); pwq->refcnt++; } /** * put_pwq - put a pool_workqueue reference * @pwq: pool_workqueue to put * * Drop a reference of @pwq. If its refcnt reaches zero, schedule its * destruction. The caller should be holding the matching pool->lock. */ static void put_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); if (likely(--pwq->refcnt)) return; /* * @pwq can't be released under pool->lock, bounce to a dedicated * kthread_worker to avoid A-A deadlocks. */ kthread_queue_work(pwq_release_worker, &pwq->release_work); } /** * put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock * @pwq: pool_workqueue to put (can be %NULL) * * put_pwq() with locking. This function also allows %NULL @pwq. */ static void put_pwq_unlocked(struct pool_workqueue *pwq) { if (pwq) { /* * As both pwqs and pools are RCU protected, the * following lock operations are safe. */ raw_spin_lock_irq(&pwq->pool->lock); put_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); } } static bool pwq_is_empty(struct pool_workqueue *pwq) { return !pwq->nr_active && list_empty(&pwq->inactive_works); } static void __pwq_activate_work(struct pool_workqueue *pwq, struct work_struct *work) { unsigned long *wdb = work_data_bits(work); WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE)); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) pwq->pool->watchdog_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb); } static bool tryinc_node_nr_active(struct wq_node_nr_active *nna) { int max = READ_ONCE(nna->max); int old = atomic_read(&nna->nr); do { if (old >= max) return false; } while (!atomic_try_cmpxchg_relaxed(&nna->nr, &old, old + 1)); return true; } /** * pwq_tryinc_nr_active - Try to increment nr_active for a pwq * @pwq: pool_workqueue of interest * @fill: max_active may have increased, try to increase concurrency level * * Try to increment nr_active for @pwq. Returns %true if an nr_active count is * successfully obtained. %false otherwise. */ static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill) { struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna = wq_node_nr_active(wq, pool->node); bool obtained = false; lockdep_assert_held(&pool->lock); if (!nna) { /* BH or per-cpu workqueue, pwq->nr_active is sufficient */ obtained = pwq->nr_active < READ_ONCE(wq->max_active); goto out; } if (unlikely(pwq->plugged)) return false; /* * Unbound workqueue uses per-node shared nr_active $nna. If @pwq is * already waiting on $nna, pwq_dec_nr_active() will maintain the * concurrency level. Don't jump the line. * * We need to ignore the pending test after max_active has increased as * pwq_dec_nr_active() can only maintain the concurrency level but not * increase it. This is indicated by @fill. */ if (!list_empty(&pwq->pending_node) && likely(!fill)) goto out; obtained = tryinc_node_nr_active(nna); if (obtained) goto out; /* * Lockless acquisition failed. Lock, add ourself to $nna->pending_pwqs * and try again. The smp_mb() is paired with the implied memory barrier * of atomic_dec_return() in pwq_dec_nr_active() to ensure that either * we see the decremented $nna->nr or they see non-empty * $nna->pending_pwqs. */ raw_spin_lock(&nna->lock); if (list_empty(&pwq->pending_node)) list_add_tail(&pwq->pending_node, &nna->pending_pwqs); else if (likely(!fill)) goto out_unlock; smp_mb(); obtained = tryinc_node_nr_active(nna); /* * If @fill, @pwq might have already been pending. Being spuriously * pending in cold paths doesn't affect anything. Let's leave it be. */ if (obtained && likely(!fill)) list_del_init(&pwq->pending_node); out_unlock: raw_spin_unlock(&nna->lock); out: if (obtained) pwq->nr_active++; return obtained; } /** * pwq_activate_first_inactive - Activate the first inactive work item on a pwq * @pwq: pool_workqueue of interest * @fill: max_active may have increased, try to increase concurrency level * * Activate the first inactive work item of @pwq if available and allowed by * max_active limit. * * Returns %true if an inactive work item has been activated. %false if no * inactive work item is found or max_active limit is reached. */ static bool pwq_activate_first_inactive(struct pool_workqueue *pwq, bool fill) { struct work_struct *work = list_first_entry_or_null(&pwq->inactive_works, struct work_struct, entry); if (work && pwq_tryinc_nr_active(pwq, fill)) { __pwq_activate_work(pwq, work); return true; } else { return false; } } /** * unplug_oldest_pwq - unplug the oldest pool_workqueue * @wq: workqueue_struct where its oldest pwq is to be unplugged * * This function should only be called for ordered workqueues where only the * oldest pwq is unplugged, the others are plugged to suspend execution to * ensure proper work item ordering:: * * dfl_pwq --------------+ [P] - plugged * | * v * pwqs -> A -> B [P] -> C [P] (newest) * | | | * 1 3 5 * | | | * 2 4 6 * * When the oldest pwq is drained and removed, this function should be called * to unplug the next oldest one to start its work item execution. Note that * pwq's are linked into wq->pwqs with the oldest first, so the first one in * the list is the oldest. */ static void unplug_oldest_pwq(struct workqueue_struct *wq) { struct pool_workqueue *pwq; lockdep_assert_held(&wq->mutex); /* Caller should make sure that pwqs isn't empty before calling */ pwq = list_first_entry_or_null(&wq->pwqs, struct pool_workqueue, pwqs_node); raw_spin_lock_irq(&pwq->pool->lock); if (pwq->plugged) { pwq->plugged = false; if (pwq_activate_first_inactive(pwq, true)) kick_pool(pwq->pool); } raw_spin_unlock_irq(&pwq->pool->lock); } /** * node_activate_pending_pwq - Activate a pending pwq on a wq_node_nr_active * @nna: wq_node_nr_active to activate a pending pwq for * @caller_pool: worker_pool the caller is locking * * Activate a pwq in @nna->pending_pwqs. Called with @caller_pool locked. * @caller_pool may be unlocked and relocked to lock other worker_pools. */ static void node_activate_pending_pwq(struct wq_node_nr_active *nna, struct worker_pool *caller_pool) { struct worker_pool *locked_pool = caller_pool; struct pool_workqueue *pwq; struct work_struct *work; lockdep_assert_held(&caller_pool->lock); raw_spin_lock(&nna->lock); retry: pwq = list_first_entry_or_null(&nna->pending_pwqs, struct pool_workqueue, pending_node); if (!pwq) goto out_unlock; /* * If @pwq is for a different pool than @locked_pool, we need to lock * @pwq->pool->lock. Let's trylock first. If unsuccessful, do the unlock * / lock dance. For that, we also need to release @nna->lock as it's * nested inside pool locks. */ if (pwq->pool != locked_pool) { raw_spin_unlock(&locked_pool->lock); locked_pool = pwq->pool; if (!raw_spin_trylock(&locked_pool->lock)) { raw_spin_unlock(&nna->lock); raw_spin_lock(&locked_pool->lock); raw_spin_lock(&nna->lock); goto retry; } } /* * $pwq may not have any inactive work items due to e.g. cancellations. * Drop it from pending_pwqs and see if there's another one. */ work = list_first_entry_or_null(&pwq->inactive_works, struct work_struct, entry); if (!work) { list_del_init(&pwq->pending_node); goto retry; } /* * Acquire an nr_active count and activate the inactive work item. If * $pwq still has inactive work items, rotate it to the end of the * pending_pwqs so that we round-robin through them. This means that * inactive work items are not activated in queueing order which is fine * given that there has never been any ordering across different pwqs. */ if (likely(tryinc_node_nr_active(nna))) { pwq->nr_active++; __pwq_activate_work(pwq, work); if (list_empty(&pwq->inactive_works)) list_del_init(&pwq->pending_node); else list_move_tail(&pwq->pending_node, &nna->pending_pwqs); /* if activating a foreign pool, make sure it's running */ if (pwq->pool != caller_pool) kick_pool(pwq->pool); } out_unlock: raw_spin_unlock(&nna->lock); if (locked_pool != caller_pool) { raw_spin_unlock(&locked_pool->lock); raw_spin_lock(&caller_pool->lock); } } /** * pwq_dec_nr_active - Retire an active count * @pwq: pool_workqueue of interest * * Decrement @pwq's nr_active and try to activate the first inactive work item. * For unbound workqueues, this function may temporarily drop @pwq->pool->lock. */ static void pwq_dec_nr_active(struct pool_workqueue *pwq) { struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pool->node); lockdep_assert_held(&pool->lock); /* * @pwq->nr_active should be decremented for both percpu and unbound * workqueues. */ pwq->nr_active--; /* * For a percpu workqueue, it's simple. Just need to kick the first * inactive work item on @pwq itself. */ if (!nna) { pwq_activate_first_inactive(pwq, false); return; } /* * If @pwq is for an unbound workqueue, it's more complicated because * multiple pwqs and pools may be sharing the nr_active count. When a * pwq needs to wait for an nr_active count, it puts itself on * $nna->pending_pwqs. The following atomic_dec_return()'s implied * memory barrier is paired with smp_mb() in pwq_tryinc_nr_active() to * guarantee that either we see non-empty pending_pwqs or they see * decremented $nna->nr. * * $nna->max may change as CPUs come online/offline and @pwq->wq's * max_active gets updated. However, it is guaranteed to be equal to or * larger than @pwq->wq->min_active which is above zero unless freezing. * This maintains the forward progress guarantee. */ if (atomic_dec_return(&nna->nr) >= READ_ONCE(nna->max)) return; if (!list_empty(&nna->pending_pwqs)) node_activate_pending_pwq(nna, pool); } /** * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight * @pwq: pwq of interest * @work_data: work_data of work which left the queue * * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its pwq and handle workqueue flushing. * * NOTE: * For unbound workqueues, this function may temporarily drop @pwq->pool->lock * and thus should be called after all other state updates for the in-flight * work item is complete. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_data) { int color = get_work_color(work_data); if (!(work_data & WORK_STRUCT_INACTIVE)) pwq_dec_nr_active(pwq); pwq->nr_in_flight[color]--; /* is flush in progress and are we at the flushing tip? */ if (likely(pwq->flush_color != color)) goto out_put; /* are there still in-flight works? */ if (pwq->nr_in_flight[color]) goto out_put; /* this pwq is done, clear flush_color */ pwq->flush_color = -1; /* * If this was the last pwq, wake up the first flusher. It * will handle the rest. */ if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush)) complete(&pwq->wq->first_flusher->done); out_put: put_pwq(pwq); } /** * try_to_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @cflags: %WORK_CANCEL_ flags * @irq_flags: place to store irq state * * Try to grab PENDING bit of @work. This function can handle @work in any * stable state - idle, on timer or on worklist. * * Return: * * ======== ================================================================ * 1 if @work was pending and we successfully stole PENDING * 0 if @work was idle and we claimed PENDING * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry * ======== ================================================================ * * Note: * On >= 0 return, the caller owns @work's PENDING bit. To avoid getting * interrupted while holding PENDING and @work off queue, irq must be * disabled on entry. This, combined with delayed_work->timer being * irqsafe, ensures that we return -EAGAIN for finite short period of time. * * On successful return, >= 0, irq is disabled and the caller is * responsible for releasing it using local_irq_restore(*@irq_flags). * * This function is safe to call from any context including IRQ handler. */ static int try_to_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { struct worker_pool *pool; struct pool_workqueue *pwq; local_irq_save(*irq_flags); /* try to steal the timer if it exists */ if (cflags & WORK_CANCEL_DELAYED) { struct delayed_work *dwork = to_delayed_work(work); /* * dwork->timer is irqsafe. If timer_delete() fails, it's * guaranteed that the timer is not queued anywhere and not * running on the local CPU. */ if (likely(timer_delete(&dwork->timer))) return 1; } /* try to claim PENDING the normal way */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; rcu_read_lock(); /* * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. */ pool = get_work_pool(work); if (!pool) goto fail; raw_spin_lock(&pool->lock); /* * work->data is guaranteed to point to pwq only while the work * item is queued on pwq->wq, and both updating work->data to point * to pwq on queueing and to pool on dequeueing are done under * pwq->pool->lock. This in turn guarantees that, if work->data * points to pwq which is associated with a locked pool, the work * item is currently queued on that pool. */ pwq = get_work_pwq(work); if (pwq && pwq->pool == pool) { unsigned long work_data = *work_data_bits(work); debug_work_deactivate(work); /* * A cancelable inactive work item must be in the * pwq->inactive_works since a queued barrier can't be * canceled (see the comments in insert_wq_barrier()). * * An inactive work item cannot be deleted directly because * it might have linked barrier work items which, if left * on the inactive_works list, will confuse pwq->nr_active * management later on and cause stall. Move the linked * barrier work items to the worklist when deleting the grabbed * item. Also keep WORK_STRUCT_INACTIVE in work_data, so that * it doesn't participate in nr_active management in later * pwq_dec_nr_in_flight(). */ if (work_data & WORK_STRUCT_INACTIVE) move_linked_works(work, &pwq->pool->worklist, NULL); list_del_init(&work->entry); /* * work->data points to pwq iff queued. Let's point to pool. As * this destroys work->data needed by the next step, stash it. */ set_work_pool_and_keep_pending(work, pool->id, pool_offq_flags(pool)); /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); raw_spin_unlock(&pool->lock); rcu_read_unlock(); return 1; } raw_spin_unlock(&pool->lock); fail: rcu_read_unlock(); local_irq_restore(*irq_flags); return -EAGAIN; } /** * work_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @cflags: %WORK_CANCEL_ flags * @irq_flags: place to store IRQ state * * Grab PENDING bit of @work. @work can be in any stable state - idle, on timer * or on worklist. * * Can be called from any context. IRQ is disabled on return with IRQ state * stored in *@irq_flags. The caller is responsible for re-enabling it using * local_irq_restore(). * * Returns %true if @work was pending. %false if idle. */ static bool work_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { int ret; while (true) { ret = try_to_grab_pending(work, cflags, irq_flags); if (ret >= 0) return ret; cpu_relax(); } } /** * insert_work - insert a work into a pool * @pwq: pwq @work belongs to * @work: work to insert * @head: insertion point * @extra_flags: extra WORK_STRUCT_* flags to set * * Insert @work which belongs to @pwq after @head. @extra_flags is or'd to * work_struct flags. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, struct list_head *head, unsigned int extra_flags) { debug_work_activate(work); /* record the work call stack in order to print it in KASAN reports */ kasan_record_aux_stack(work); /* we own @work, set data and link */ set_work_pwq(work, pwq, extra_flags); list_add_tail(&work->entry, head); get_pwq(pwq); } /* * Test whether @work is being queued from another work executing on the * same workqueue. */ static bool is_chained_work(struct workqueue_struct *wq) { struct worker *worker; worker = current_wq_worker(); /* * Return %true iff I'm a worker executing a work item on @wq. If * I'm @worker, it's safe to dereference it without locking. */ return worker && worker->current_pwq->wq == wq; } /* * When queueing an unbound work item to a wq, prefer local CPU if allowed * by wq_unbound_cpumask. Otherwise, round robin among the allowed ones to * avoid perturbing sensitive tasks. */ static int wq_select_unbound_cpu(int cpu) { int new_cpu; if (likely(!wq_debug_force_rr_cpu)) { if (cpumask_test_cpu(cpu, wq_unbound_cpumask)) return cpu; } else { pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n"); } new_cpu = __this_cpu_read(wq_rr_cpu_last); new_cpu = cpumask_next_and_wrap(new_cpu, wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) return cpu; __this_cpu_write(wq_rr_cpu_last, new_cpu); return new_cpu; } static void __queue_work(int cpu, struct workqueue_struct *wq, struct work_struct *work) { struct pool_workqueue *pwq; struct worker_pool *last_pool, *pool; unsigned int work_flags; unsigned int req_cpu = cpu; /* * While a work item is PENDING && off queue, a task trying to * steal the PENDING will busy-loop waiting for it to either get * queued or lose PENDING. Grabbing PENDING and queueing should * happen with IRQ disabled. */ lockdep_assert_irqs_disabled(); /* * For a draining wq, only works from the same workqueue are * allowed. The __WQ_DESTROYING helps to spot the issue that * queues a new work item to a wq after destroy_workqueue(wq). */ if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) && WARN_ONCE(!is_chained_work(wq), "workqueue: cannot queue %ps on wq %s\n", work->func, wq->name))) { return; } rcu_read_lock(); retry: /* pwq which will be used unless @work is executing elsewhere */ if (req_cpu == WORK_CPU_UNBOUND) { if (wq->flags & WQ_UNBOUND) cpu = wq_select_unbound_cpu(raw_smp_processor_id()); else cpu = raw_smp_processor_id(); } pwq = rcu_dereference(*per_cpu_ptr(wq->cpu_pwq, cpu)); pool = pwq->pool; /* * If @work was previously on a different pool, it might still be * running there, in which case the work needs to be queued on that * pool to guarantee non-reentrancy. * * For ordered workqueue, work items must be queued on the newest pwq * for accurate order management. Guaranteed order also guarantees * non-reentrancy. See the comments above unplug_oldest_pwq(). */ last_pool = get_work_pool(work); if (last_pool && last_pool != pool && !(wq->flags & __WQ_ORDERED)) { struct worker *worker; raw_spin_lock(&last_pool->lock); worker = find_worker_executing_work(last_pool, work); if (worker && worker->current_pwq->wq == wq) { pwq = worker->current_pwq; pool = pwq->pool; WARN_ON_ONCE(pool != last_pool); } else { /* meh... not running there, queue here */ raw_spin_unlock(&last_pool->lock); raw_spin_lock(&pool->lock); } } else { raw_spin_lock(&pool->lock); } /* * pwq is determined and locked. For unbound pools, we could have raced * with pwq release and it could already be dead. If its refcnt is zero, * repeat pwq selection. Note that unbound pwqs never die without * another pwq replacing it in cpu_pwq or while work items are executing * on it, so the retrying is guaranteed to make forward-progress. */ if (unlikely(!pwq->refcnt)) { if (wq->flags & WQ_UNBOUND) { raw_spin_unlock(&pool->lock); cpu_relax(); goto retry; } /* oops */ WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt", wq->name, cpu); } /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); if (WARN_ON(!list_empty(&work->entry))) goto out; pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); /* * Limit the number of concurrently active work items to max_active. * @work must also queue behind existing inactive work items to maintain * ordering when max_active changes. See wq_adjust_max_active(). */ if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) { if (list_empty(&pool->worklist)) pool->watchdog_ts = jiffies; trace_workqueue_activate_work(work); insert_work(pwq, work, &pool->worklist, work_flags); kick_pool(pool); } else { work_flags |= WORK_STRUCT_INACTIVE; insert_work(pwq, work, &pwq->inactive_works, work_flags); } out: raw_spin_unlock(&pool->lock); rcu_read_unlock(); } static bool clear_pending_if_disabled(struct work_struct *work) { unsigned long data = *work_data_bits(work); struct work_offq_data offqd; if (likely((data & WORK_STRUCT_PWQ) || !(data & WORK_OFFQ_DISABLE_MASK))) return false; work_offqd_unpack(&offqd, data); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); return true; } /** * queue_work_on - queue work on specific cpu * @cpu: CPU number to execute work on * @wq: workqueue to use * @work: work to queue * * We queue the work to a specific CPU, the caller must ensure it * can't go away. Callers that fail to ensure that the specified * CPU cannot go away will execute on a randomly chosen CPU. * But note well that callers specifying a CPU that never has been * online will get a splat. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { bool ret = false; unsigned long irq_flags; local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { __queue_work(cpu, wq, work); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_work_on); /** * select_numa_node_cpu - Select a CPU based on NUMA node * @node: NUMA node ID that we want to select a CPU from * * This function will attempt to find a "random" cpu available on a given * node. If there are no CPUs available on the given node it will return * WORK_CPU_UNBOUND indicating that we should just schedule to any * available CPU if we need to schedule this work. */ static int select_numa_node_cpu(int node) { int cpu; /* Delay binding to CPU if node is not valid or online */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node)) return WORK_CPU_UNBOUND; /* Use local node/cpu if we are already there */ cpu = raw_smp_processor_id(); if (node == cpu_to_node(cpu)) return cpu; /* Use "random" otherwise know as "first" online CPU of node */ cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask); /* If CPU is valid return that, otherwise just defer */ return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND; } /** * queue_work_node - queue work on a "random" cpu for a given NUMA node * @node: NUMA node that we are targeting the work for * @wq: workqueue to use * @work: work to queue * * We queue the work to a "random" CPU within a given NUMA node. The basic * idea here is to provide a way to somehow associate work with a given * NUMA node. * * This function will only make a best effort attempt at getting this onto * the right NUMA node. If no node is requested or the requested node is * offline then we just fall back to standard queue_work behavior. * * Currently the "random" CPU ends up being the first available CPU in the * intersection of cpu_online_mask and the cpumask of the node, unless we * are running on the node. In that case we just use the current CPU. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work) { unsigned long irq_flags; bool ret = false; /* * This current implementation is specific to unbound workqueues. * Specifically we only return the first available CPU for a given * node instead of cycling through individual CPUs within the node. * * If this is used with a per-cpu workqueue then the logic in * workqueue_select_cpu_near would need to be updated to allow for * some round robin type logic. */ WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)); local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { int cpu = select_numa_node_cpu(node); __queue_work(cpu, wq, work); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(queue_work_node); void delayed_work_timer_fn(struct timer_list *t) { struct delayed_work *dwork = timer_container_of(dwork, t, timer); /* should have been called from irqsafe timer with irq already off */ __queue_work(dwork->cpu, dwork->wq, &dwork->work); } EXPORT_SYMBOL(delayed_work_timer_fn); static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; WARN_ON_ONCE(!wq); WARN_ON_ONCE(timer->function != delayed_work_timer_fn); WARN_ON_ONCE(timer_pending(timer)); WARN_ON_ONCE(!list_empty(&work->entry)); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { __queue_work(cpu, wq, &dwork->work); return; } WARN_ON_ONCE(cpu != WORK_CPU_UNBOUND && !cpu_online(cpu)); dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; if (housekeeping_enabled(HK_TYPE_TIMER)) { /* If the current cpu is a housekeeping cpu, use it. */ cpu = smp_processor_id(); if (!housekeeping_test_cpu(cpu, HK_TYPE_TIMER)) cpu = housekeeping_any_cpu(HK_TYPE_TIMER); add_timer_on(timer, cpu); } else { if (likely(cpu == WORK_CPU_UNBOUND)) add_timer_global(timer); else add_timer_on(timer, cpu); } } /** * queue_delayed_work_on - queue work on specific CPU after delay * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * We queue the delayed_work to a specific CPU, for non-zero delays the * caller must ensure it is online and can't go away. Callers that fail * to ensure this, may get @dwork->timer queued to an offlined CPU and * this will prevent queueing of @dwork->work unless the offlined CPU * becomes online again. * * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. */ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct work_struct *work = &dwork->work; bool ret = false; unsigned long irq_flags; /* read the comment in __queue_work() */ local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); /** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is * zero, @work is guaranteed to be scheduled immediately regardless of its * current state. * * Return: %false if @dwork was idle and queued, %true if @dwork was * pending and its timer was modified. * * This function is safe to call from any context including IRQ handler. * See try_to_grab_pending() for details. */ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { unsigned long irq_flags; bool ret; ret = work_grab_pending(&dwork->work, WORK_CANCEL_DELAYED, &irq_flags); if (!clear_pending_if_disabled(&dwork->work)) __queue_delayed_work(cpu, wq, dwork, delay); local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(mod_delayed_work_on); static void rcu_work_rcufn(struct rcu_head *rcu) { struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); /* read the comment in __queue_work() */ local_irq_disable(); __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); local_irq_enable(); } /** * queue_rcu_work - queue work after a RCU grace period * @wq: workqueue to use * @rwork: work to queue * * Return: %false if @rwork was already pending, %true otherwise. Note * that a full RCU grace period is guaranteed only after a %true return. * While @rwork is guaranteed to be executed after a %false return, the * execution may happen before a full RCU grace period has passed. */ bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork) { struct work_struct *work = &rwork->work; /* * rcu_work can't be canceled or disabled. Warn if the user reached * inside @rwork and disabled the inner work. */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !WARN_ON_ONCE(clear_pending_if_disabled(work))) { rwork->wq = wq; call_rcu_hurry(&rwork->rcu, rcu_work_rcufn); return true; } return false; } EXPORT_SYMBOL(queue_rcu_work); static struct worker *alloc_worker(int node) { struct worker *worker; worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node); if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); INIT_LIST_HEAD(&worker->node); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } return worker; } static cpumask_t *pool_allowed_cpus(struct worker_pool *pool) { if (pool->cpu < 0 && pool->attrs->affn_strict) return pool->attrs->__pod_cpumask; else return pool->attrs->cpumask; } /** * worker_attach_to_pool() - attach a worker to a pool * @worker: worker to be attached * @pool: the target pool * * Attach @worker to @pool. Once attached, the %WORKER_UNBOUND flag and * cpu-binding of @worker are kept coordinated with the pool across * cpu-[un]hotplugs. */ static void worker_attach_to_pool(struct worker *worker, struct worker_pool *pool) { mutex_lock(&wq_pool_attach_mutex); /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains stable * across this function. See the comments above the flag definition for * details. BH workers are, while per-CPU, always DISASSOCIATED. */ if (pool->flags & POOL_DISASSOCIATED) { worker->flags |= WORKER_UNBOUND; } else { WARN_ON_ONCE(pool->flags & POOL_BH); kthread_set_per_cpu(worker->task, pool->cpu); } if (worker->rescue_wq) set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; mutex_unlock(&wq_pool_attach_mutex); } static void unbind_worker(struct worker *worker) { lockdep_assert_held(&wq_pool_attach_mutex); kthread_set_per_cpu(worker->task, -1); if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask)) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0); else WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); } static void detach_worker(struct worker *worker) { lockdep_assert_held(&wq_pool_attach_mutex); unbind_worker(worker); list_del(&worker->node); } /** * worker_detach_from_pool() - detach a worker from its pool * @worker: worker which is attached to its pool * * Undo the attaching which had been done in worker_attach_to_pool(). The * caller worker shouldn't access to the pool after detached except it has * other reference to the pool. */ static void worker_detach_from_pool(struct worker *worker) { struct worker_pool *pool = worker->pool; /* there is one permanent BH worker per CPU which should never detach */ WARN_ON_ONCE(pool->flags & POOL_BH); mutex_lock(&wq_pool_attach_mutex); detach_worker(worker); worker->pool = NULL; mutex_unlock(&wq_pool_attach_mutex); /* clear leftover flags without pool->lock after it is detached */ worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND); } static int format_worker_id(char *buf, size_t size, struct worker *worker, struct worker_pool *pool) { if (worker->rescue_wq) return scnprintf(buf, size, "kworker/R-%s", worker->rescue_wq->name); if (pool) { if (pool->cpu >= 0) return scnprintf(buf, size, "kworker/%d:%d%s", pool->cpu, worker->id, pool->attrs->nice < 0 ? "H" : ""); else return scnprintf(buf, size, "kworker/u%d:%d", pool->id, worker->id); } else { return scnprintf(buf, size, "kworker/dying"); } } /** * create_worker - create a new workqueue worker * @pool: pool the new worker will belong to * * Create and start a new worker which is attached to @pool. * * CONTEXT: * Might sleep. Does GFP_KERNEL allocations. * * Return: * Pointer to the newly created worker. */ static struct worker *create_worker(struct worker_pool *pool) { struct worker *worker; int id; /* ID is needed to determine kthread name */ id = ida_alloc(&pool->worker_ida, GFP_KERNEL); if (id < 0) { pr_err_once("workqueue: Failed to allocate a worker ID: %pe\n", ERR_PTR(id)); return NULL; } worker = alloc_worker(pool->node); if (!worker) { pr_err_once("workqueue: Failed to allocate a worker\n"); goto fail; } worker->id = id; if (!(pool->flags & POOL_BH)) { char id_buf[WORKER_ID_LEN]; format_worker_id(id_buf, sizeof(id_buf), worker, pool); worker->task = kthread_create_on_node(worker_thread, worker, pool->node, "%s", id_buf); if (IS_ERR(worker->task)) { if (PTR_ERR(worker->task) == -EINTR) { pr_err("workqueue: Interrupted when creating a worker thread \"%s\"\n", id_buf); } else { pr_err_once("workqueue: Failed to create a worker thread: %pe", worker->task); } goto fail; } set_user_nice(worker->task, pool->attrs->nice); kthread_bind_mask(worker->task, pool_allowed_cpus(pool)); } /* successful, attach the worker to the pool */ worker_attach_to_pool(worker, pool); /* start the newly created worker */ raw_spin_lock_irq(&pool->lock); worker->pool->nr_workers++; worker_enter_idle(worker); /* * @worker is waiting on a completion in kthread() and will trigger hung * check if not woken up soon. As kick_pool() is noop if @pool is empty, * wake it up explicitly. */ if (worker->task) wake_up_process(worker->task); raw_spin_unlock_irq(&pool->lock); return worker; fail: ida_free(&pool->worker_ida, id); kfree(worker); return NULL; } static void detach_dying_workers(struct list_head *cull_list) { struct worker *worker; list_for_each_entry(worker, cull_list, entry) detach_worker(worker); } static void reap_dying_workers(struct list_head *cull_list) { struct worker *worker, *tmp; list_for_each_entry_safe(worker, tmp, cull_list, entry) { list_del_init(&worker->entry); kthread_stop_put(worker->task); kfree(worker); } } /** * set_worker_dying - Tag a worker for destruction * @worker: worker to be destroyed * @list: transfer worker away from its pool->idle_list and into list * * Tag @worker for destruction and adjust @pool stats accordingly. The worker * should be idle. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void set_worker_dying(struct worker *worker, struct list_head *list) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); lockdep_assert_held(&wq_pool_attach_mutex); /* sanity check frenzy */ if (WARN_ON(worker->current_work) || WARN_ON(!list_empty(&worker->scheduled)) || WARN_ON(!(worker->flags & WORKER_IDLE))) return; pool->nr_workers--; pool->nr_idle--; worker->flags |= WORKER_DIE; list_move(&worker->entry, list); /* get an extra task struct reference for later kthread_stop_put() */ get_task_struct(worker->task); } /** * idle_worker_timeout - check if some idle workers can now be deleted. * @t: The pool's idle_timer that just expired * * The timer is armed in worker_enter_idle(). Note that it isn't disarmed in * worker_leave_idle(), as a worker flicking between idle and active while its * pool is at the too_many_workers() tipping point would cause too much timer * housekeeping overhead. Since IDLE_WORKER_TIMEOUT is long enough, we just let * it expire and re-evaluate things from there. */ static void idle_worker_timeout(struct timer_list *t) { struct worker_pool *pool = timer_container_of(pool, t, idle_timer); bool do_cull = false; if (work_pending(&pool->idle_cull_work)) return; raw_spin_lock_irq(&pool->lock); if (too_many_workers(pool)) { struct worker *worker; unsigned long expires; /* idle_list is kept in LIFO order, check the last one */ worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; do_cull = !time_before(jiffies, expires); if (!do_cull) mod_timer(&pool->idle_timer, expires); } raw_spin_unlock_irq(&pool->lock); if (do_cull) queue_work(system_dfl_wq, &pool->idle_cull_work); } /** * idle_cull_fn - cull workers that have been idle for too long. * @work: the pool's work for handling these idle workers * * This goes through a pool's idle workers and gets rid of those that have been * idle for at least IDLE_WORKER_TIMEOUT seconds. * * We don't want to disturb isolated CPUs because of a pcpu kworker being * culled, so this also resets worker affinity. This requires a sleepable * context, hence the split between timer callback and work item. */ static void idle_cull_fn(struct work_struct *work) { struct worker_pool *pool = container_of(work, struct worker_pool, idle_cull_work); LIST_HEAD(cull_list); /* * Grabbing wq_pool_attach_mutex here ensures an already-running worker * cannot proceed beyong set_pf_worker() in its self-destruct path. * This is required as a previously-preempted worker could run after * set_worker_dying() has happened but before detach_dying_workers() did. */ mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) { mod_timer(&pool->idle_timer, expires); break; } set_worker_dying(worker, &cull_list); } raw_spin_unlock_irq(&pool->lock); detach_dying_workers(&cull_list); mutex_unlock(&wq_pool_attach_mutex); reap_dying_workers(&cull_list); } static void send_mayday(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq_mayday_lock); if (!wq->rescuer) return; /* mayday mayday mayday */ if (list_empty(&pwq->mayday_node)) { /* * If @pwq is for an unbound wq, its base ref may be put at * any time due to an attribute change. Pin @pwq until the * rescuer is done with it. */ get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); wake_up_process(wq->rescuer->task); pwq->stats[PWQ_STAT_MAYDAY]++; } } static void pool_mayday_timeout(struct timer_list *t) { struct worker_pool *pool = timer_container_of(pool, t, mayday_timer); struct work_struct *work; raw_spin_lock_irq(&pool->lock); raw_spin_lock(&wq_mayday_lock); /* for wq->maydays */ if (need_to_create_worker(pool)) { /* * We've been trying to create a new worker but * haven't been successful. We might be hitting an * allocation deadlock. Send distress signals to * rescuers. */ list_for_each_entry(work, &pool->worklist, entry) send_mayday(work); } raw_spin_unlock(&wq_mayday_lock); raw_spin_unlock_irq(&pool->lock); mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } /** * maybe_create_worker - create a new worker if necessary * @pool: pool to create a new worker for * * Create a new worker for @pool if necessary. @pool is guaranteed to * have at least one idle worker on return from this function. If * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is * sent to all rescuers with works scheduled on @pool to resolve * possible allocation deadlock. * * On return, need_to_create_worker() is guaranteed to be %false and * may_start_working() %true. * * LOCKING: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. */ static void maybe_create_worker(struct worker_pool *pool) __releases(&pool->lock) __acquires(&pool->lock) { restart: raw_spin_unlock_irq(&pool->lock); /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); while (true) { if (create_worker(pool) || !need_to_create_worker(pool)) break; schedule_timeout_interruptible(CREATE_COOLDOWN); if (!need_to_create_worker(pool)) break; } timer_delete_sync(&pool->mayday_timer); raw_spin_lock_irq(&pool->lock); /* * This is necessary even after a new worker was just successfully * created as @pool->lock was dropped and the new worker might have * already become busy. */ if (need_to_create_worker(pool)) goto restart; } #ifdef CONFIG_PREEMPT_RT static void worker_lock_callback(struct worker_pool *pool) { spin_lock(&pool->cb_lock); } static void worker_unlock_callback(struct worker_pool *pool) { spin_unlock(&pool->cb_lock); } static void workqueue_callback_cancel_wait_running(struct worker_pool *pool) { spin_lock(&pool->cb_lock); spin_unlock(&pool->cb_lock); } #else static void worker_lock_callback(struct worker_pool *pool) { } static void worker_unlock_callback(struct worker_pool *pool) { } static void workqueue_callback_cancel_wait_running(struct worker_pool *pool) { } #endif /** * manage_workers - manage worker pool * @worker: self * * Assume the manager role and manage the worker pool @worker belongs * to. At any given time, there can be only zero or one manager per * pool. The exclusion is handled automatically by this function. * * The caller can safely start processing works on false return. On * true return, it's guaranteed that need_to_create_worker() is false * and may_start_working() is true. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. * * Return: * %false if the pool doesn't need management and the caller can safely * start processing works, %true if management function was performed and * the conditions that the caller verified before calling the function may * no longer be true. */ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & POOL_MANAGER_ACTIVE) return false; pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; pool->flags &= ~POOL_MANAGER_ACTIVE; rcuwait_wake_up(&manager_wait); return true; } /** * process_one_work - process single work * @worker: self * @work: work to process * * Process @work. This function contains all the logics necessary to * process a single work including synchronization against and * interaction with other workers on the same cpu, queueing and * flushing. As long as context requirement is met, any worker can * call this function to process a work. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which is released and regrabbed. */ static void process_one_work(struct worker *worker, struct work_struct *work) __releases(&pool->lock) __acquires(&pool->lock) { struct pool_workqueue *pwq = get_work_pwq(work); struct worker_pool *pool = worker->pool; unsigned long work_data; int lockdep_start_depth, rcu_start_depth; bool bh_draining = pool->flags & POOL_BH_DRAINING; #ifdef CONFIG_LOCKDEP /* * It is permissible to free the struct work_struct from * inside the function that is called from it, this we need to * take into account for lockdep too. To avoid bogus "held * lock freed" warnings as well as problems when looking into * work->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &work->lockdep_map); #endif /* ensure we're on the correct CPU */ WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && raw_smp_processor_id() != pool->cpu); /* claim and dequeue */ debug_work_deactivate(work); hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work); worker->current_work = work; worker->current_func = work->func; worker->current_pwq = pwq; if (worker->task) worker->current_at = worker->task->se.sum_exec_runtime; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); /* * Record wq name for cmdline and debug reporting, may get * overridden through set_worker_desc(). */ strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN); list_del_init(&work->entry); /* * CPU intensive works don't participate in concurrency management. * They're the scheduler's responsibility. This takes @worker out * of concurrency management and the next code block will chain * execution of the pending work items. */ if (unlikely(pwq->wq->flags & WQ_CPU_INTENSIVE)) worker_set_flags(worker, WORKER_CPU_INTENSIVE); /* * Kick @pool if necessary. It's always noop for per-cpu worker pools * since nr_running would always be >= 1 at this point. This is used to * chain execution of the pending work items for WORKER_NOT_RUNNING * workers such as the UNBOUND and CPU_INTENSIVE ones. */ kick_pool(pool); /* * Record the last pool and clear PENDING which should be the last * update to @work. Also, do this inside @pool->lock so that * PENDING and queued state changes happen together while IRQ is * disabled. */ set_work_pool_and_clear_pending(work, pool->id, pool_offq_flags(pool)); pwq->stats[PWQ_STAT_STARTED]++; raw_spin_unlock_irq(&pool->lock); rcu_start_depth = rcu_preempt_depth(); lockdep_start_depth = lockdep_depth(current); /* see drain_dead_softirq_workfn() */ if (!bh_draining) lock_map_acquire(pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); /* * Strictly speaking we should mark the invariant state without holding * any locks, that is, before these two lock_map_acquire()'s. * * However, that would result in: * * A(W1) * WFC(C) * A(W1) * C(C) * * Which would create W1->C->W1 dependencies, even though there is no * actual deadlock possible. There are two solutions, using a * read-recursive acquire on the work(queue) 'locks', but this will then * hit the lockdep limitation on recursive locks, or simply discard * these locks. * * AFAICT there is no possible deadlock scenario between the * flush_work() and complete() primitives (except for single-threaded * workqueues), so hiding them isn't a problem. */ lockdep_invariant_state(true); trace_workqueue_execute_start(work); worker->current_func(work); /* * While we must be careful to not use "work" after this, the trace * point will only record its address. */ trace_workqueue_execute_end(work, worker->current_func); lock_map_release(&lockdep_map); if (!bh_draining) lock_map_release(pwq->wq->lockdep_map); if (unlikely((worker->task && in_atomic()) || lockdep_depth(current) != lockdep_start_depth || rcu_preempt_depth() != rcu_start_depth)) { pr_err("BUG: workqueue leaked atomic, lock or RCU: %s[%d]\n" " preempt=0x%08x lock=%d->%d RCU=%d->%d workfn=%ps\n", current->comm, task_pid_nr(current), preempt_count(), lockdep_start_depth, lockdep_depth(current), rcu_start_depth, rcu_preempt_depth(), worker->current_func); debug_show_held_locks(current); dump_stack(); } /* * The following prevents a kworker from hogging CPU on !PREEMPTION * kernels, where a requeueing work item waiting for something to * happen could deadlock with stop_machine as such work item could * indefinitely requeue itself while all other CPUs are trapped in * stop_machine. At the same time, report a quiescent RCU state so * the same condition doesn't freeze RCU. */ if (worker->task) cond_resched(); raw_spin_lock_irq(&pool->lock); pwq->stats[PWQ_STAT_COMPLETED]++; /* * In addition to %WQ_CPU_INTENSIVE, @worker may also have been marked * CPU intensive by wq_worker_tick() if @work hogged CPU longer than * wq_cpu_intensive_thresh_us. Clear it. */ worker_clr_flags(worker, WORKER_CPU_INTENSIVE); /* tag the worker for identification in schedule() */ worker->last_func = worker->current_func; /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; worker->current_func = NULL; worker->current_pwq = NULL; worker->current_color = INT_MAX; /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); } /** * process_scheduled_works - process scheduled works * @worker: self * * Process all scheduled works. Please note that the scheduled list * may change while processing a work, so this function repeatedly * fetches a work from the top and executes it. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. */ static void process_scheduled_works(struct worker *worker) { struct work_struct *work; bool first = true; while ((work = list_first_entry_or_null(&worker->scheduled, struct work_struct, entry))) { if (first) { worker->pool->watchdog_ts = jiffies; first = false; } process_one_work(worker, work); } } static void set_pf_worker(bool val) { mutex_lock(&wq_pool_attach_mutex); if (val) current->flags |= PF_WQ_WORKER; else current->flags &= ~PF_WQ_WORKER; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_thread - the worker thread function * @__worker: self * * The worker thread function. All workers belong to a worker_pool - * either a per-cpu one or dynamic unbound one. These workers process all * work items regardless of their specific target workqueue. The only * exception is work items which belong to workqueues with a rescuer which * will be explained in rescuer_thread(). * * Return: 0 */ static int worker_thread(void *__worker) { struct worker *worker = __worker; struct worker_pool *pool = worker->pool; /* tell the scheduler that this is a workqueue worker */ set_pf_worker(true); woke_up: raw_spin_lock_irq(&pool->lock); /* am I supposed to die? */ if (unlikely(worker->flags & WORKER_DIE)) { raw_spin_unlock_irq(&pool->lock); set_pf_worker(false); /* * The worker is dead and PF_WQ_WORKER is cleared, worker->pool * shouldn't be accessed, reset it to NULL in case otherwise. */ worker->pool = NULL; ida_free(&pool->worker_ida, worker->id); return 0; } worker_leave_idle(worker); recheck: /* no more worker necessary? */ if (!need_more_worker(pool)) goto sleep; /* do we need to manage? */ if (unlikely(!may_start_working(pool)) && manage_workers(worker)) goto recheck; /* * ->scheduled list can only be filled while a worker is * preparing to process a work or actually processing it. * Make sure nobody diddled with it while I was sleeping. */ WARN_ON_ONCE(!list_empty(&worker->scheduled)); /* * Finish PREP stage. We're guaranteed to have at least one idle * worker or that someone else has already assumed the manager * role. This is where @worker starts participating in concurrency * management if applicable and concurrency management is restored * after being rebound. See rebind_workers() for details. */ worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); if (assign_work(work, worker, NULL)) process_scheduled_works(worker); } while (keep_working(pool)); worker_set_flags(worker, WORKER_PREP); sleep: /* * pool->lock is held and there's no work to process and no need to * manage, sleep. Workers are woken up only while holding * pool->lock or from local cpu, so setting the current state * before releasing pool->lock is enough to prevent losing any * event. */ worker_enter_idle(worker); __set_current_state(TASK_IDLE); raw_spin_unlock_irq(&pool->lock); schedule(); goto woke_up; } /** * rescuer_thread - the rescuer thread function * @__rescuer: self * * Workqueue rescuer thread function. There's one rescuer for each * workqueue which has WQ_MEM_RECLAIM set. * * Regular work processing on a pool may block trying to create a new * worker which uses GFP_KERNEL allocation which has slight chance of * developing into deadlock if some works currently on the same queue * need to be processed to satisfy the GFP_KERNEL allocation. This is * the problem rescuer solves. * * When such condition is possible, the pool summons rescuers of all * workqueues which have works queued on the pool and let them process * those works so that forward progress can be guaranteed. * * This should happen rarely. * * Return: 0 */ static int rescuer_thread(void *__rescuer) { struct worker *rescuer = __rescuer; struct workqueue_struct *wq = rescuer->rescue_wq; bool should_stop; set_user_nice(current, RESCUER_NICE_LEVEL); /* * Mark rescuer as worker too. As WORKER_PREP is never cleared, it * doesn't participate in concurrency management. */ set_pf_worker(true); repeat: set_current_state(TASK_IDLE); /* * By the time the rescuer is requested to stop, the workqueue * shouldn't have any work pending, but @wq->maydays may still have * pwq(s) queued. This can happen by non-rescuer workers consuming * all the work items before the rescuer got to them. Go through * @wq->maydays processing before acting on should_stop so that the * list is always empty on exit. */ should_stop = kthread_should_stop(); /* see whether any pwq is asking for help */ raw_spin_lock_irq(&wq_mayday_lock); while (!list_empty(&wq->maydays)) { struct pool_workqueue *pwq = list_first_entry(&wq->maydays, struct pool_workqueue, mayday_node); struct worker_pool *pool = pwq->pool; struct work_struct *work, *n; __set_current_state(TASK_RUNNING); list_del_init(&pwq->mayday_node); raw_spin_unlock_irq(&wq_mayday_lock); worker_attach_to_pool(rescuer, pool); raw_spin_lock_irq(&pool->lock); /* * Slurp in all works issued via this workqueue and * process'em. */ WARN_ON_ONCE(!list_empty(&rescuer->scheduled)); list_for_each_entry_safe(work, n, &pool->worklist, entry) { if (get_work_pwq(work) == pwq && assign_work(work, rescuer, &n)) pwq->stats[PWQ_STAT_RESCUED]++; } if (!list_empty(&rescuer->scheduled)) { process_scheduled_works(rescuer); /* * The above execution of rescued work items could * have created more to rescue through * pwq_activate_first_inactive() or chained * queueing. Let's put @pwq back on mayday list so * that such back-to-back work items, which may be * being used to relieve memory pressure, don't * incur MAYDAY_INTERVAL delay inbetween. */ if (pwq->nr_active && need_to_create_worker(pool)) { raw_spin_lock(&wq_mayday_lock); /* * Queue iff we aren't racing destruction * and somebody else hasn't queued it already. */ if (wq->rescuer && list_empty(&pwq->mayday_node)) { get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); } raw_spin_unlock(&wq_mayday_lock); } } /* * Leave this pool. Notify regular workers; otherwise, we end up * with 0 concurrency and stalling the execution. */ kick_pool(pool); raw_spin_unlock_irq(&pool->lock); worker_detach_from_pool(rescuer); /* * Put the reference grabbed by send_mayday(). @pool might * go away any time after it. */ put_pwq_unlocked(pwq); raw_spin_lock_irq(&wq_mayday_lock); } raw_spin_unlock_irq(&wq_mayday_lock); if (should_stop) { __set_current_state(TASK_RUNNING); set_pf_worker(false); return 0; } /* rescuers should never participate in concurrency management */ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); goto repeat; } static void bh_worker(struct worker *worker) { struct worker_pool *pool = worker->pool; int nr_restarts = BH_WORKER_RESTARTS; unsigned long end = jiffies + BH_WORKER_JIFFIES; worker_lock_callback(pool); raw_spin_lock_irq(&pool->lock); worker_leave_idle(worker); /* * This function follows the structure of worker_thread(). See there for * explanations on each step. */ if (!need_more_worker(pool)) goto done; WARN_ON_ONCE(!list_empty(&worker->scheduled)); worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); if (assign_work(work, worker, NULL)) process_scheduled_works(worker); } while (keep_working(pool) && --nr_restarts && time_before(jiffies, end)); worker_set_flags(worker, WORKER_PREP); done: worker_enter_idle(worker); kick_pool(pool); raw_spin_unlock_irq(&pool->lock); worker_unlock_callback(pool); } /* * TODO: Convert all tasklet users to workqueue and use softirq directly. * * This is currently called from tasklet[_hi]action() and thus is also called * whenever there are tasklets to run. Let's do an early exit if there's nothing * queued. Once conversion from tasklet is complete, the need_more_worker() test * can be dropped. * * After full conversion, we'll add worker->softirq_action, directly use the * softirq action and obtain the worker pointer from the softirq_action pointer. */ void workqueue_softirq_action(bool highpri) { struct worker_pool *pool = &per_cpu(bh_worker_pools, smp_processor_id())[highpri]; if (need_more_worker(pool)) bh_worker(list_first_entry(&pool->workers, struct worker, node)); } struct wq_drain_dead_softirq_work { struct work_struct work; struct worker_pool *pool; struct completion done; }; static void drain_dead_softirq_workfn(struct work_struct *work) { struct wq_drain_dead_softirq_work *dead_work = container_of(work, struct wq_drain_dead_softirq_work, work); struct worker_pool *pool = dead_work->pool; bool repeat; /* * @pool's CPU is dead and we want to execute its still pending work * items from this BH work item which is running on a different CPU. As * its CPU is dead, @pool can't be kicked and, as work execution path * will be nested, a lockdep annotation needs to be suppressed. Mark * @pool with %POOL_BH_DRAINING for the special treatments. */ raw_spin_lock_irq(&pool->lock); pool->flags |= POOL_BH_DRAINING; raw_spin_unlock_irq(&pool->lock); bh_worker(list_first_entry(&pool->workers, struct worker, node)); raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_BH_DRAINING; repeat = need_more_worker(pool); raw_spin_unlock_irq(&pool->lock); /* * bh_worker() might hit consecutive execution limit and bail. If there * still are pending work items, reschedule self and return so that we * don't hog this CPU's BH. */ if (repeat) { if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) queue_work(system_bh_highpri_wq, work); else queue_work(system_bh_wq, work); } else { complete(&dead_work->done); } } /* * @cpu is dead. Drain the remaining BH work items on the current CPU. It's * possible to allocate dead_work per CPU and avoid flushing. However, then we * have to worry about draining overlapping with CPU coming back online or * nesting (one CPU's dead_work queued on another CPU which is also dead and so * on). Let's keep it simple and drain them synchronously. These are BH work * items which shouldn't be requeued on the same pool. Shouldn't take long. */ void workqueue_softirq_dead(unsigned int cpu) { int i; for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct worker_pool *pool = &per_cpu(bh_worker_pools, cpu)[i]; struct wq_drain_dead_softirq_work dead_work; if (!need_more_worker(pool)) continue; INIT_WORK_ONSTACK(&dead_work.work, drain_dead_softirq_workfn); dead_work.pool = pool; init_completion(&dead_work.done); if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) queue_work(system_bh_highpri_wq, &dead_work.work); else queue_work(system_bh_wq, &dead_work.work); wait_for_completion(&dead_work.done); destroy_work_on_stack(&dead_work.work); } } /** * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) * @from_cancel: are we called from the work cancel path * * %current is trying to flush the whole @target_wq or @target_work on it. * If this is not the cancel path (which implies work being flushed is either * already running, or will not be at all), check if @target_wq doesn't have * %WQ_MEM_RECLAIM and verify that %current is not reclaiming memory or running * on a workqueue which doesn't have %WQ_MEM_RECLAIM as that can break forward- * progress guarantee leading to a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, struct work_struct *target_work, bool from_cancel) { work_func_t target_func; struct worker *worker; if (from_cancel || target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); target_func = target_work ? target_work->func : NULL; WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", current->pid, current->comm, target_wq->name, target_func); WARN_ONCE(worker && ((worker->current_pwq->wq->flags & (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func); } struct wq_barrier { struct work_struct work; struct completion done; struct task_struct *task; /* purely informational */ }; static void wq_barrier_func(struct work_struct *work) { struct wq_barrier *barr = container_of(work, struct wq_barrier, work); complete(&barr->done); } /** * insert_wq_barrier - insert a barrier work * @pwq: pwq to insert barrier into * @barr: wq_barrier to insert * @target: target work to attach @barr to * @worker: worker currently executing @target, NULL if @target is not executing * * @barr is linked to @target such that @barr is completed only after * @target finishes execution. Please note that the ordering * guarantee is observed only with respect to @target and on the local * cpu. * * Currently, a queued barrier can't be canceled. This is because * try_to_grab_pending() can't determine whether the work to be * grabbed is at the head of the queue and thus can't clear LINKED * flag of the previous work while there must be a valid next work * after a work with LINKED flag set. * * Note that when @worker is non-NULL, @target may be modified * underneath us, so we can't reliably determine pwq from @target. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { static __maybe_unused struct lock_class_key bh_key, thr_key; unsigned int work_flags = 0; unsigned int work_color; struct list_head *head; /* * debugobject calls are safe here even with pool->lock locked * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. * * BH and threaded workqueues need separate lockdep keys to avoid * spuriously triggering "inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} * usage". */ INIT_WORK_ONSTACK_KEY(&barr->work, wq_barrier_func, (pwq->wq->flags & WQ_BH) ? &bh_key : &thr_key); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion_map(&barr->done, &target->lockdep_map); barr->task = current; /* The barrier work item does not participate in nr_active. */ work_flags |= WORK_STRUCT_INACTIVE; /* * If @target is currently being executed, schedule the * barrier to the worker; otherwise, put it after @target. */ if (worker) { head = worker->scheduled.next; work_color = worker->current_color; } else { unsigned long *bits = work_data_bits(target); head = target->entry.next; /* there can already be other linked works, inherit and set */ work_flags |= *bits & WORK_STRUCT_LINKED; work_color = get_work_color(*bits); __set_bit(WORK_STRUCT_LINKED_BIT, bits); } pwq->nr_in_flight[work_color]++; work_flags |= work_color_to_flags(work_color); insert_work(pwq, &barr->work, head, work_flags); } /** * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing * @wq: workqueue being flushed * @flush_color: new flush color, < 0 for no-op * @work_color: new work color, < 0 for no-op * * Prepare pwqs for workqueue flushing. * * If @flush_color is non-negative, flush_color on all pwqs should be * -1. If no pwq has in-flight commands at the specified color, all * pwq->flush_color's stay at -1 and %false is returned. If any pwq * has in flight commands, its pwq->flush_color is set to * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq * wakeup logic is armed and %true is returned. * * The caller should have initialized @wq->first_flusher prior to * calling this function with non-negative @flush_color. If * @flush_color is negative, no flush color update is done and %false * is returned. * * If @work_color is non-negative, all pwqs should have the same * work_color which is previous to @work_color and all will be * advanced to @work_color. * * CONTEXT: * mutex_lock(wq->mutex). * * Return: * %true if @flush_color >= 0 and there's something to flush. %false * otherwise. */ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, int flush_color, int work_color) { bool wait = false; struct pool_workqueue *pwq; struct worker_pool *current_pool = NULL; if (flush_color >= 0) { WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush)); atomic_set(&wq->nr_pwqs_to_flush, 1); } /* * For unbound workqueue, pwqs will map to only a few pools. * Most of the time, pwqs within the same pool will be linked * sequentially to wq->pwqs by cpu index. So in the majority * of pwq iters, the pool is the same, only doing lock/unlock * if the pool has changed. This can largely reduce expensive * lock operations. */ for_each_pwq(pwq, wq) { if (current_pool != pwq->pool) { if (likely(current_pool)) raw_spin_unlock_irq(¤t_pool->lock); current_pool = pwq->pool; raw_spin_lock_irq(¤t_pool->lock); } if (flush_color >= 0) { WARN_ON_ONCE(pwq->flush_color != -1); if (pwq->nr_in_flight[flush_color]) { pwq->flush_color = flush_color; atomic_inc(&wq->nr_pwqs_to_flush); wait = true; } } if (work_color >= 0) { WARN_ON_ONCE(work_color != work_next_color(pwq->work_color)); pwq->work_color = work_color; } } if (current_pool) raw_spin_unlock_irq(¤t_pool->lock); if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) complete(&wq->first_flusher->done); return wait; } static void touch_wq_lockdep_map(struct workqueue_struct *wq) { #ifdef CONFIG_LOCKDEP if (unlikely(!wq->lockdep_map)) return; if (wq->flags & WQ_BH) local_bh_disable(); lock_map_acquire(wq->lockdep_map); lock_map_release(wq->lockdep_map); if (wq->flags & WQ_BH) local_bh_enable(); #endif } static void touch_work_lockdep_map(struct work_struct *work, struct workqueue_struct *wq) { #ifdef CONFIG_LOCKDEP if (wq->flags & WQ_BH) local_bh_disable(); lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); if (wq->flags & WQ_BH) local_bh_enable(); #endif } /** * __flush_workqueue - ensure that any scheduled work has run to completion. * @wq: workqueue to flush * * This function sleeps until all work items which were queued on entry * have finished execution, but it is not livelocked by new incoming ones. */ void __flush_workqueue(struct workqueue_struct *wq) { struct wq_flusher this_flusher = { .list = LIST_HEAD_INIT(this_flusher.list), .flush_color = -1, .done = COMPLETION_INITIALIZER_ONSTACK_MAP(this_flusher.done, (*wq->lockdep_map)), }; int next_color; if (WARN_ON(!wq_online)) return; touch_wq_lockdep_map(wq); mutex_lock(&wq->mutex); /* * Start-to-wait phase */ next_color = work_next_color(wq->work_color); if (next_color != wq->flush_color) { /* * Color space is not full. The current work_color * becomes our flush_color and work_color is advanced * by one. */ WARN_ON_ONCE(!list_empty(&wq->flusher_overflow)); this_flusher.flush_color = wq->work_color; wq->work_color = next_color; if (!wq->first_flusher) { /* no flush in progress, become the first flusher */ WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); wq->first_flusher = &this_flusher; if (!flush_workqueue_prep_pwqs(wq, wq->flush_color, wq->work_color)) { /* nothing to flush, done */ wq->flush_color = next_color; wq->first_flusher = NULL; goto out_unlock; } } else { /* wait in queue */ WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color); list_add_tail(&this_flusher.list, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } } else { /* * Oops, color space is full, wait on overflow queue. * The next flush completion will assign us * flush_color and transfer to flusher_queue. */ list_add_tail(&this_flusher.list, &wq->flusher_overflow); } check_flush_dependency(wq, NULL, false); mutex_unlock(&wq->mutex); wait_for_completion(&this_flusher.done); /* * Wake-up-and-cascade phase * * First flushers are responsible for cascading flushes and * handling overflow. Non-first flushers can simply return. */ if (READ_ONCE(wq->first_flusher) != &this_flusher) return; mutex_lock(&wq->mutex); /* we might have raced, check again with mutex held */ if (wq->first_flusher != &this_flusher) goto out_unlock; WRITE_ONCE(wq->first_flusher, NULL); WARN_ON_ONCE(!list_empty(&this_flusher.list)); WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); while (true) { struct wq_flusher *next, *tmp; /* complete all the flushers sharing the current flush color */ list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) { if (next->flush_color != wq->flush_color) break; list_del_init(&next->list); complete(&next->done); } WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) && wq->flush_color != work_next_color(wq->work_color)); /* this flush_color is finished, advance by one */ wq->flush_color = work_next_color(wq->flush_color); /* one color has been freed, handle overflow queue */ if (!list_empty(&wq->flusher_overflow)) { /* * Assign the same color to all overflowed * flushers, advance work_color and append to * flusher_queue. This is the start-to-wait * phase for these overflowed flushers. */ list_for_each_entry(tmp, &wq->flusher_overflow, list) tmp->flush_color = wq->work_color; wq->work_color = work_next_color(wq->work_color); list_splice_tail_init(&wq->flusher_overflow, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } if (list_empty(&wq->flusher_queue)) { WARN_ON_ONCE(wq->flush_color != wq->work_color); break; } /* * Need to flush more colors. Make the next flusher * the new first flusher and arm pwqs. */ WARN_ON_ONCE(wq->flush_color == wq->work_color); WARN_ON_ONCE(wq->flush_color != next->flush_color); list_del_init(&next->list); wq->first_flusher = next; if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1)) break; /* * Meh... this color is already done, clear first * flusher and repeat cascading. */ wq->first_flusher = NULL; } out_unlock: mutex_unlock(&wq->mutex); } EXPORT_SYMBOL(__flush_workqueue); /** * drain_workqueue - drain a workqueue * @wq: workqueue to drain * * Wait until the workqueue becomes empty. While draining is in progress, * only chain queueing is allowed. IOW, only currently pending or running * work items on @wq can queue further work items on it. @wq is flushed * repeatedly until it becomes empty. The number of flushing is determined * by the depth of chaining and should be relatively short. Whine if it * takes too long. */ void drain_workqueue(struct workqueue_struct *wq) { unsigned int flush_cnt = 0; struct pool_workqueue *pwq; /* * __queue_work() needs to test whether there are drainers, is much * hotter than drain_workqueue() and already looks at @wq->flags. * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers. */ mutex_lock(&wq->mutex); if (!wq->nr_drainers++) wq->flags |= __WQ_DRAINING; mutex_unlock(&wq->mutex); reflush: __flush_workqueue(wq); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { bool drained; raw_spin_lock_irq(&pwq->pool->lock); drained = pwq_is_empty(pwq); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) continue; if (++flush_cnt == 10 || (flush_cnt % 100 == 0 && flush_cnt <= 1000)) pr_warn("workqueue %s: %s() isn't complete after %u tries\n", wq->name, __func__, flush_cnt); mutex_unlock(&wq->mutex); goto reflush; } if (!--wq->nr_drainers) wq->flags &= ~__WQ_DRAINING; mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(drain_workqueue); static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, bool from_cancel) { struct worker *worker = NULL; struct worker_pool *pool; struct pool_workqueue *pwq; struct workqueue_struct *wq; rcu_read_lock(); pool = get_work_pool(work); if (!pool) { rcu_read_unlock(); return false; } raw_spin_lock_irq(&pool->lock); /* see the comment in try_to_grab_pending() with the same code */ pwq = get_work_pwq(work); if (pwq) { if (unlikely(pwq->pool != pool)) goto already_gone; } else { worker = find_worker_executing_work(pool, work); if (!worker) goto already_gone; pwq = worker->current_pwq; } wq = pwq->wq; check_flush_dependency(wq, work, from_cancel); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); touch_work_lockdep_map(work, wq); /* * Force a lock recursion deadlock when using flush_work() inside a * single-threaded or rescuer equipped workqueue. * * For single threaded workqueues the deadlock happens when the work * is after the work issuing the flush_work(). For rescuer equipped * workqueues the deadlock happens when the rescuer stalls, blocking * forward progress. */ if (!from_cancel && (wq->saved_max_active == 1 || wq->rescuer)) touch_wq_lockdep_map(wq); rcu_read_unlock(); return true; already_gone: raw_spin_unlock_irq(&pool->lock); rcu_read_unlock(); return false; } static bool __flush_work(struct work_struct *work, bool from_cancel) { struct wq_barrier barr; if (WARN_ON(!wq_online)) return false; if (WARN_ON(!work->func)) return false; if (!start_flush_work(work, &barr, from_cancel)) return false; /* * start_flush_work() returned %true. If @from_cancel is set, we know * that @work must have been executing during start_flush_work() and * can't currently be queued. Its data must contain OFFQ bits. If @work * was queued on a BH workqueue, we also know that it was running in the * BH context and thus can be busy-waited. */ if (from_cancel) { unsigned long data = *work_data_bits(work); if (!WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) { /* * On RT, prevent a live lock when %current preempted * soft interrupt processing by blocking on lock which * is owned by the thread invoking the callback. */ while (!try_wait_for_completion(&barr.done)) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) { struct worker_pool *pool; guard(rcu)(); pool = get_work_pool(work); if (pool) workqueue_callback_cancel_wait_running(pool); } else { cpu_relax(); } } goto out_destroy; } } wait_for_completion(&barr.done); out_destroy: destroy_work_on_stack(&barr.work); return true; } /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush * * Wait until @work has finished execution. @work is guaranteed to be idle * on return if it hasn't been requeued since flush started. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_work(struct work_struct *work) { might_sleep(); return __flush_work(work, false); } EXPORT_SYMBOL_GPL(flush_work); /** * flush_delayed_work - wait for a dwork to finish executing the last queueing * @dwork: the delayed work to flush * * Delayed timer is cancelled and the pending work is queued for * immediate execution. Like flush_work(), this function only * considers the last queueing instance of @dwork. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_delayed_work(struct delayed_work *dwork) { local_irq_disable(); if (timer_delete_sync(&dwork->timer)) __queue_work(dwork->cpu, dwork->wq, &dwork->work); local_irq_enable(); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); /** * flush_rcu_work - wait for a rwork to finish executing the last queueing * @rwork: the rcu work to flush * * Return: * %true if flush_rcu_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_rcu_work(struct rcu_work *rwork) { if (test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&rwork->work))) { rcu_barrier(); flush_work(&rwork->work); return true; } else { return flush_work(&rwork->work); } } EXPORT_SYMBOL(flush_rcu_work); static void work_offqd_disable(struct work_offq_data *offqd) { const unsigned long max = (1lu << WORK_OFFQ_DISABLE_BITS) - 1; if (likely(offqd->disable < max)) offqd->disable++; else WARN_ONCE(true, "workqueue: work disable count overflowed\n"); } static void work_offqd_enable(struct work_offq_data *offqd) { if (likely(offqd->disable > 0)) offqd->disable--; else WARN_ONCE(true, "workqueue: work disable count underflowed\n"); } static bool __cancel_work(struct work_struct *work, u32 cflags) { struct work_offq_data offqd; unsigned long irq_flags; int ret; ret = work_grab_pending(work, cflags, &irq_flags); work_offqd_unpack(&offqd, *work_data_bits(work)); if (cflags & WORK_CANCEL_DISABLE) work_offqd_disable(&offqd); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return ret; } static bool __cancel_work_sync(struct work_struct *work, u32 cflags) { bool ret; ret = __cancel_work(work, cflags | WORK_CANCEL_DISABLE); if (*work_data_bits(work) & WORK_OFFQ_BH) WARN_ON_ONCE(in_hardirq()); else might_sleep(); /* * Skip __flush_work() during early boot when we know that @work isn't * executing. This allows canceling during early boot. */ if (wq_online) __flush_work(work, true); if (!(cflags & WORK_CANCEL_DISABLE)) enable_work(work); return ret; } /* * See cancel_delayed_work() */ bool cancel_work(struct work_struct *work) { return __cancel_work(work, 0); } EXPORT_SYMBOL(cancel_work); /** * cancel_work_sync - cancel a work and wait for it to finish * @work: the work to cancel * * Cancel @work and wait for its execution to finish. This function can be used * even if the work re-queues itself or migrates to another workqueue. On return * from this function, @work is guaranteed to be not pending or executing on any * CPU as long as there aren't racing enqueues. * * cancel_work_sync(&delayed_work->work) must not be used for delayed_work's. * Use cancel_delayed_work_sync() instead. * * Must be called from a sleepable context if @work was last queued on a non-BH * workqueue. Can also be called from non-hardirq atomic contexts including BH * if @work was last queued on a BH workqueue. * * Returns %true if @work was pending, %false otherwise. */ bool cancel_work_sync(struct work_struct *work) { return __cancel_work_sync(work, 0); } EXPORT_SYMBOL_GPL(cancel_work_sync); /** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel * * Kill off a pending delayed_work. * * Return: %true if @dwork was pending and canceled; %false if it wasn't * pending. * * Note: * The work callback function may still be running on return, unless * it returns %true and the work doesn't re-arm itself. Explicitly flush or * use cancel_delayed_work_sync() to wait on it. * * This function is safe to call from any context including IRQ handler. */ bool cancel_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work); /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish * @dwork: the delayed work cancel * * This is cancel_work_sync() for delayed works. * * Return: * %true if @dwork was pending, %false otherwise. */ bool cancel_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work_sync); /** * disable_work - Disable and cancel a work item * @work: work item to disable * * Disable @work by incrementing its disable count and cancel it if currently * pending. As long as the disable count is non-zero, any attempt to queue @work * will fail and return %false. The maximum supported disable depth is 2 to the * power of %WORK_OFFQ_DISABLE_BITS, currently 65536. * * Can be called from any context. Returns %true if @work was pending, %false * otherwise. */ bool disable_work(struct work_struct *work) { return __cancel_work(work, WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_work); /** * disable_work_sync - Disable, cancel and drain a work item * @work: work item to disable * * Similar to disable_work() but also wait for @work to finish if currently * executing. * * Must be called from a sleepable context if @work was last queued on a non-BH * workqueue. Can also be called from non-hardirq atomic contexts including BH * if @work was last queued on a BH workqueue. * * Returns %true if @work was pending, %false otherwise. */ bool disable_work_sync(struct work_struct *work) { return __cancel_work_sync(work, WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_work_sync); /** * enable_work - Enable a work item * @work: work item to enable * * Undo disable_work[_sync]() by decrementing @work's disable count. @work can * only be queued if its disable count is 0. * * Can be called from any context. Returns %true if the disable count reached 0. * Otherwise, %false. */ bool enable_work(struct work_struct *work) { struct work_offq_data offqd; unsigned long irq_flags; work_grab_pending(work, 0, &irq_flags); work_offqd_unpack(&offqd, *work_data_bits(work)); work_offqd_enable(&offqd); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return !offqd.disable; } EXPORT_SYMBOL_GPL(enable_work); /** * disable_delayed_work - Disable and cancel a delayed work item * @dwork: delayed work item to disable * * disable_work() for delayed work items. */ bool disable_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_delayed_work); /** * disable_delayed_work_sync - Disable, cancel and drain a delayed work item * @dwork: delayed work item to disable * * disable_work_sync() for delayed work items. */ bool disable_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_delayed_work_sync); /** * enable_delayed_work - Enable a delayed work item * @dwork: delayed work item to enable * * enable_work() for delayed work items. */ bool enable_delayed_work(struct delayed_work *dwork) { return enable_work(&dwork->work); } EXPORT_SYMBOL_GPL(enable_delayed_work); /** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * * schedule_on_each_cpu() executes @func on each online CPU using the * system workqueue and blocks until all CPUs have completed. * schedule_on_each_cpu() is very slow. * * Return: * 0 on success, -errno on failure. */ int schedule_on_each_cpu(work_func_t func) { int cpu; struct work_struct __percpu *works; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; cpus_read_lock(); for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, func); schedule_work_on(cpu, work); } for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); cpus_read_unlock(); free_percpu(works); return 0; } /** * execute_in_process_context - reliably execute the routine with user context * @fn: the function to execute * @ew: guaranteed storage for the execute work structure (must * be available when the work executes) * * Executes the function immediately if process context is available, * otherwise schedules the function for delayed execution. * * Return: 0 - function was executed * 1 - function was scheduled for execution */ int execute_in_process_context(work_func_t fn, struct execute_work *ew) { if (!in_interrupt()) { fn(&ew->work); return 0; } INIT_WORK(&ew->work, fn); schedule_work(&ew->work); return 1; } EXPORT_SYMBOL_GPL(execute_in_process_context); /** * free_workqueue_attrs - free a workqueue_attrs * @attrs: workqueue_attrs to free * * Undo alloc_workqueue_attrs(). */ void free_workqueue_attrs(struct workqueue_attrs *attrs) { if (attrs) { free_cpumask_var(attrs->cpumask); free_cpumask_var(attrs->__pod_cpumask); kfree(attrs); } } /** * alloc_workqueue_attrs - allocate a workqueue_attrs * * Allocate a new workqueue_attrs, initialize with default settings and * return it. * * Return: The allocated new workqueue_attr on success. %NULL on failure. */ struct workqueue_attrs *alloc_workqueue_attrs_noprof(void) { struct workqueue_attrs *attrs; attrs = kzalloc(sizeof(*attrs), GFP_KERNEL); if (!attrs) goto fail; if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL)) goto fail; if (!alloc_cpumask_var(&attrs->__pod_cpumask, GFP_KERNEL)) goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); attrs->affn_scope = WQ_AFFN_DFL; return attrs; fail: free_workqueue_attrs(attrs); return NULL; } static void copy_workqueue_attrs(struct workqueue_attrs *to, const struct workqueue_attrs *from) { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); cpumask_copy(to->__pod_cpumask, from->__pod_cpumask); to->affn_strict = from->affn_strict; /* * Unlike hash and equality test, copying shouldn't ignore wq-only * fields as copying is used for both pool and wq attrs. Instead, * get_unbound_pool() explicitly clears the fields. */ to->affn_scope = from->affn_scope; to->ordered = from->ordered; } /* * Some attrs fields are workqueue-only. Clear them for worker_pool's. See the * comments in 'struct workqueue_attrs' definition. */ static void wqattrs_clear_for_pool(struct workqueue_attrs *attrs) { attrs->affn_scope = WQ_AFFN_NR_TYPES; attrs->ordered = false; if (attrs->affn_strict) cpumask_copy(attrs->cpumask, cpu_possible_mask); } /* hash value of the content of @attr */ static u32 wqattrs_hash(const struct workqueue_attrs *attrs) { u32 hash = 0; hash = jhash_1word(attrs->nice, hash); hash = jhash_1word(attrs->affn_strict, hash); hash = jhash(cpumask_bits(attrs->__pod_cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); if (!attrs->affn_strict) hash = jhash(cpumask_bits(attrs->cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); return hash; } /* content equality test */ static bool wqattrs_equal(const struct workqueue_attrs *a, const struct workqueue_attrs *b) { if (a->nice != b->nice) return false; if (a->affn_strict != b->affn_strict) return false; if (!cpumask_equal(a->__pod_cpumask, b->__pod_cpumask)) return false; if (!a->affn_strict && !cpumask_equal(a->cpumask, b->cpumask)) return false; return true; } /* Update @attrs with actually available CPUs */ static void wqattrs_actualize_cpumask(struct workqueue_attrs *attrs, const cpumask_t *unbound_cpumask) { /* * Calculate the effective CPU mask of @attrs given @unbound_cpumask. If * @attrs->cpumask doesn't overlap with @unbound_cpumask, we fallback to * @unbound_cpumask. */ cpumask_and(attrs->cpumask, attrs->cpumask, unbound_cpumask); if (unlikely(cpumask_empty(attrs->cpumask))) cpumask_copy(attrs->cpumask, unbound_cpumask); } /* find wq_pod_type to use for @attrs */ static const struct wq_pod_type * wqattrs_pod_type(const struct workqueue_attrs *attrs) { enum wq_affn_scope scope; struct wq_pod_type *pt; /* to synchronize access to wq_affn_dfl */ lockdep_assert_held(&wq_pool_mutex); if (attrs->affn_scope == WQ_AFFN_DFL) scope = wq_affn_dfl; else scope = attrs->affn_scope; pt = &wq_pod_types[scope]; if (!WARN_ON_ONCE(attrs->affn_scope == WQ_AFFN_NR_TYPES) && likely(pt->nr_pods)) return pt; /* * Before workqueue_init_topology(), only SYSTEM is available which is * initialized in workqueue_init_early(). */ pt = &wq_pod_types[WQ_AFFN_SYSTEM]; BUG_ON(!pt->nr_pods); return pt; } /** * init_worker_pool - initialize a newly zalloc'd worker_pool * @pool: worker_pool to initialize * * Initialize a newly zalloc'd @pool. It also allocates @pool->attrs. * * Return: 0 on success, -errno on failure. Even on failure, all fields * inside @pool proper are initialized and put_unbound_pool() can be called * on @pool safely to release it. */ static int init_worker_pool(struct worker_pool *pool) { raw_spin_lock_init(&pool->lock); pool->id = -1; pool->cpu = -1; pool->node = NUMA_NO_NODE; pool->flags |= POOL_DISASSOCIATED; pool->watchdog_ts = jiffies; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); hash_init(pool->busy_hash); timer_setup(&pool->idle_timer, idle_worker_timeout, TIMER_DEFERRABLE); INIT_WORK(&pool->idle_cull_work, idle_cull_fn); timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0); INIT_LIST_HEAD(&pool->workers); ida_init(&pool->worker_ida); INIT_HLIST_NODE(&pool->hash_node); pool->refcnt = 1; #ifdef CONFIG_PREEMPT_RT spin_lock_init(&pool->cb_lock); #endif /* shouldn't fail above this point */ pool->attrs = alloc_workqueue_attrs(); if (!pool->attrs) return -ENOMEM; wqattrs_clear_for_pool(pool->attrs); return 0; } #ifdef CONFIG_LOCKDEP static void wq_init_lockdep(struct workqueue_struct *wq) { char *lock_name; lockdep_register_key(&wq->key); lock_name = kasprintf(GFP_KERNEL, "%s%s", "(wq_completion)", wq->name); if (!lock_name) lock_name = wq->name; wq->lock_name = lock_name; wq->lockdep_map = &wq->__lockdep_map; lockdep_init_map(wq->lockdep_map, lock_name, &wq->key, 0); } static void wq_unregister_lockdep(struct workqueue_struct *wq) { if (wq->lockdep_map != &wq->__lockdep_map) return; lockdep_unregister_key(&wq->key); } static void wq_free_lockdep(struct workqueue_struct *wq) { if (wq->lockdep_map != &wq->__lockdep_map) return; if (wq->lock_name != wq->name) kfree(wq->lock_name); } #else static void wq_init_lockdep(struct workqueue_struct *wq) { } static void wq_unregister_lockdep(struct workqueue_struct *wq) { } static void wq_free_lockdep(struct workqueue_struct *wq) { } #endif static void free_node_nr_active(struct wq_node_nr_active **nna_ar) { int node; for_each_node(node) { kfree(nna_ar[node]); nna_ar[node] = NULL; } kfree(nna_ar[nr_node_ids]); nna_ar[nr_node_ids] = NULL; } static void init_node_nr_active(struct wq_node_nr_active *nna) { nna->max = WQ_DFL_MIN_ACTIVE; atomic_set(&nna->nr, 0); raw_spin_lock_init(&nna->lock); INIT_LIST_HEAD(&nna->pending_pwqs); } /* * Each node's nr_active counter will be accessed mostly from its own node and * should be allocated in the node. */ static int alloc_node_nr_active(struct wq_node_nr_active **nna_ar) { struct wq_node_nr_active *nna; int node; for_each_node(node) { nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, node); if (!nna) goto err_free; init_node_nr_active(nna); nna_ar[node] = nna; } /* [nr_node_ids] is used as the fallback */ nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, NUMA_NO_NODE); if (!nna) goto err_free; init_node_nr_active(nna); nna_ar[nr_node_ids] = nna; return 0; err_free: free_node_nr_active(nna_ar); return -ENOMEM; } static void rcu_free_wq(struct rcu_head *rcu) { struct workqueue_struct *wq = container_of(rcu, struct workqueue_struct, rcu); if (wq->flags & WQ_UNBOUND) free_node_nr_active(wq->node_nr_active); wq_free_lockdep(wq); free_percpu(wq->cpu_pwq); free_workqueue_attrs(wq->unbound_attrs); kfree(wq); } static void rcu_free_pool(struct rcu_head *rcu) { struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu); ida_destroy(&pool->worker_ida); free_workqueue_attrs(pool->attrs); kfree(pool); } /** * put_unbound_pool - put a worker_pool * @pool: worker_pool to put * * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU * safe manner. get_unbound_pool() calls this function on its failure path * and this function should be able to release pools which went through, * successfully or not, init_worker_pool(). * * Should be called with wq_pool_mutex held. */ static void put_unbound_pool(struct worker_pool *pool) { struct worker *worker; LIST_HEAD(cull_list); lockdep_assert_held(&wq_pool_mutex); if (--pool->refcnt) return; /* sanity checks */ if (WARN_ON(!(pool->cpu < 0)) || WARN_ON(!list_empty(&pool->worklist))) return; /* release id and unhash */ if (pool->id >= 0) idr_remove(&worker_pool_idr, pool->id); hash_del(&pool->hash_node); /* * Become the manager and destroy all workers. This prevents * @pool's workers from blocking on attach_mutex. We're the last * manager and @pool gets freed with the flag set. * * Having a concurrent manager is quite unlikely to happen as we can * only get here with * pwq->refcnt == pool->refcnt == 0 * which implies no work queued to the pool, which implies no worker can * become the manager. However a worker could have taken the role of * manager before the refcnts dropped to 0, since maybe_create_worker() * drops pool->lock */ while (true) { rcuwait_wait_event(&manager_wait, !(pool->flags & POOL_MANAGER_ACTIVE), TASK_UNINTERRUPTIBLE); mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); if (!(pool->flags & POOL_MANAGER_ACTIVE)) { pool->flags |= POOL_MANAGER_ACTIVE; break; } raw_spin_unlock_irq(&pool->lock); mutex_unlock(&wq_pool_attach_mutex); } while ((worker = first_idle_worker(pool))) set_worker_dying(worker, &cull_list); WARN_ON(pool->nr_workers || pool->nr_idle); raw_spin_unlock_irq(&pool->lock); detach_dying_workers(&cull_list); mutex_unlock(&wq_pool_attach_mutex); reap_dying_workers(&cull_list); /* shut down the timers */ timer_delete_sync(&pool->idle_timer); cancel_work_sync(&pool->idle_cull_work); timer_delete_sync(&pool->mayday_timer); /* RCU protected to allow dereferences from get_work_pool() */ call_rcu(&pool->rcu, rcu_free_pool); } /** * get_unbound_pool - get a worker_pool with the specified attributes * @attrs: the attributes of the worker_pool to get * * Obtain a worker_pool which has the same attributes as @attrs, bump the * reference count and return it. If there already is a matching * worker_pool, it will be used; otherwise, this function attempts to * create a new one. * * Should be called with wq_pool_mutex held. * * Return: On success, a worker_pool with the same attributes as @attrs. * On failure, %NULL. */ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_NUMA]; u32 hash = wqattrs_hash(attrs); struct worker_pool *pool; int pod, node = NUMA_NO_NODE; lockdep_assert_held(&wq_pool_mutex); /* do we already have a matching pool? */ hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) { if (wqattrs_equal(pool->attrs, attrs)) { pool->refcnt++; return pool; } } /* If __pod_cpumask is contained inside a NUMA pod, that's our node */ for (pod = 0; pod < pt->nr_pods; pod++) { if (cpumask_subset(attrs->__pod_cpumask, pt->pod_cpus[pod])) { node = pt->pod_node[pod]; break; } } /* nope, create a new one */ pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, node); if (!pool || init_worker_pool(pool) < 0) goto fail; pool->node = node; copy_workqueue_attrs(pool->attrs, attrs); wqattrs_clear_for_pool(pool->attrs); if (worker_pool_assign_id(pool) < 0) goto fail; /* create and start the initial worker */ if (wq_online && !create_worker(pool)) goto fail; /* install */ hash_add(unbound_pool_hash, &pool->hash_node, hash); return pool; fail: if (pool) put_unbound_pool(pool); return NULL; } /* * Scheduled on pwq_release_worker by put_pwq() when an unbound pwq hits zero * refcnt and needs to be destroyed. */ static void pwq_release_workfn(struct kthread_work *work) { struct pool_workqueue *pwq = container_of(work, struct pool_workqueue, release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; bool is_last = false; /* * When @pwq is not linked, it doesn't hold any reference to the * @wq, and @wq is invalid to access. */ if (!list_empty(&pwq->pwqs_node)) { mutex_lock(&wq->mutex); list_del_rcu(&pwq->pwqs_node); is_last = list_empty(&wq->pwqs); /* * For ordered workqueue with a plugged dfl_pwq, restart it now. */ if (!is_last && (wq->flags & __WQ_ORDERED)) unplug_oldest_pwq(wq); mutex_unlock(&wq->mutex); } if (wq->flags & WQ_UNBOUND) { mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); mutex_unlock(&wq_pool_mutex); } if (!list_empty(&pwq->pending_node)) { struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pwq->pool->node); raw_spin_lock_irq(&nna->lock); list_del_init(&pwq->pending_node); raw_spin_unlock_irq(&nna->lock); } kfree_rcu(pwq, rcu); /* * If we're the last pwq going away, @wq is already dead and no one * is gonna access it anymore. Schedule RCU free. */ if (is_last) { wq_unregister_lockdep(wq); call_rcu(&wq->rcu, rcu_free_wq); } } /* initialize newly allocated @pwq which is associated with @wq and @pool */ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, struct worker_pool *pool) { BUG_ON((unsigned long)pwq & ~WORK_STRUCT_PWQ_MASK); memset(pwq, 0, sizeof(*pwq)); pwq->pool = pool; pwq->wq = wq; pwq->flush_color = -1; pwq->refcnt = 1; INIT_LIST_HEAD(&pwq->inactive_works); INIT_LIST_HEAD(&pwq->pending_node); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); kthread_init_work(&pwq->release_work, pwq_release_workfn); } /* sync @pwq with the current state of its associated wq and link it */ static void link_pwq(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq->mutex); /* may be called multiple times, ignore if already linked */ if (!list_empty(&pwq->pwqs_node)) return; /* set the matching work_color */ pwq->work_color = wq->work_color; /* link in @pwq */ list_add_tail_rcu(&pwq->pwqs_node, &wq->pwqs); } /* obtain a pool matching @attr and create a pwq associating the pool and @wq */ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct worker_pool *pool; struct pool_workqueue *pwq; lockdep_assert_held(&wq_pool_mutex); pool = get_unbound_pool(attrs); if (!pool) return NULL; pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!pwq) { put_unbound_pool(pool); return NULL; } init_pwq(pwq, wq, pool); return pwq; } static void apply_wqattrs_lock(void) { mutex_lock(&wq_pool_mutex); } static void apply_wqattrs_unlock(void) { mutex_unlock(&wq_pool_mutex); } /** * wq_calc_pod_cpumask - calculate a wq_attrs' cpumask for a pod * @attrs: the wq_attrs of the default pwq of the target workqueue * @cpu: the target CPU * * Calculate the cpumask a workqueue with @attrs should use on @pod. * The result is stored in @attrs->__pod_cpumask. * * If pod affinity is not enabled, @attrs->cpumask is always used. If enabled * and @pod has online CPUs requested by @attrs, the returned cpumask is the * intersection of the possible CPUs of @pod and @attrs->cpumask. * * The caller is responsible for ensuring that the cpumask of @pod stays stable. */ static void wq_calc_pod_cpumask(struct workqueue_attrs *attrs, int cpu) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int pod = pt->cpu_pod[cpu]; /* calculate possible CPUs in @pod that @attrs wants */ cpumask_and(attrs->__pod_cpumask, pt->pod_cpus[pod], attrs->cpumask); /* does @pod have any online CPUs @attrs wants? */ if (!cpumask_intersects(attrs->__pod_cpumask, wq_online_cpumask)) { cpumask_copy(attrs->__pod_cpumask, attrs->cpumask); return; } } /* install @pwq into @wq and return the old pwq, @cpu < 0 for dfl_pwq */ static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq, int cpu, struct pool_workqueue *pwq) { struct pool_workqueue __rcu **slot = unbound_pwq_slot(wq, cpu); struct pool_workqueue *old_pwq; lockdep_assert_held(&wq_pool_mutex); lockdep_assert_held(&wq->mutex); /* link_pwq() can handle duplicate calls */ link_pwq(pwq); old_pwq = rcu_access_pointer(*slot); rcu_assign_pointer(*slot, pwq); return old_pwq; } /* context to store the prepared attrs & pwqs before applying */ struct apply_wqattrs_ctx { struct workqueue_struct *wq; /* target workqueue */ struct workqueue_attrs *attrs; /* attrs to apply */ struct list_head list; /* queued for batching commit */ struct pool_workqueue *dfl_pwq; struct pool_workqueue *pwq_tbl[]; }; /* free the resources after success or abort */ static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) { if (ctx) { int cpu; for_each_possible_cpu(cpu) put_pwq_unlocked(ctx->pwq_tbl[cpu]); put_pwq_unlocked(ctx->dfl_pwq); free_workqueue_attrs(ctx->attrs); kfree(ctx); } } /* allocate the attrs and pwqs for later installation */ static struct apply_wqattrs_ctx * apply_wqattrs_prepare(struct workqueue_struct *wq, const struct workqueue_attrs *attrs, const cpumask_var_t unbound_cpumask) { struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs; int cpu; lockdep_assert_held(&wq_pool_mutex); if (WARN_ON(attrs->affn_scope < 0 || attrs->affn_scope >= WQ_AFFN_NR_TYPES)) return ERR_PTR(-EINVAL); ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_cpu_ids), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(); if (!ctx || !new_attrs) goto out_free; /* * If something goes wrong during CPU up/down, we'll fall back to * the default pwq covering whole @attrs->cpumask. Always create * it even if we don't use it immediately. */ copy_workqueue_attrs(new_attrs, attrs); wqattrs_actualize_cpumask(new_attrs, unbound_cpumask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); if (!ctx->dfl_pwq) goto out_free; for_each_possible_cpu(cpu) { if (new_attrs->ordered) { ctx->dfl_pwq->refcnt++; ctx->pwq_tbl[cpu] = ctx->dfl_pwq; } else { wq_calc_pod_cpumask(new_attrs, cpu); ctx->pwq_tbl[cpu] = alloc_unbound_pwq(wq, new_attrs); if (!ctx->pwq_tbl[cpu]) goto out_free; } } /* save the user configured attrs and sanitize it. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->attrs = new_attrs; /* * For initialized ordered workqueues, there should only be one pwq * (dfl_pwq). Set the plugged flag of ctx->dfl_pwq to suspend execution * of newly queued work items until execution of older work items in * the old pwq's have completed. */ if ((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)) ctx->dfl_pwq->plugged = true; ctx->wq = wq; return ctx; out_free: free_workqueue_attrs(new_attrs); apply_wqattrs_cleanup(ctx); return ERR_PTR(-ENOMEM); } /* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) { int cpu; /* all pwqs have been created successfully, let's install'em */ mutex_lock(&ctx->wq->mutex); copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); /* save the previous pwqs and install the new ones */ for_each_possible_cpu(cpu) ctx->pwq_tbl[cpu] = install_unbound_pwq(ctx->wq, cpu, ctx->pwq_tbl[cpu]); ctx->dfl_pwq = install_unbound_pwq(ctx->wq, -1, ctx->dfl_pwq); /* update node_nr_active->max */ wq_update_node_max_active(ctx->wq, -1); /* rescuer needs to respect wq cpumask changes */ if (ctx->wq->rescuer) set_cpus_allowed_ptr(ctx->wq->rescuer->task, unbound_effective_cpumask(ctx->wq)); mutex_unlock(&ctx->wq->mutex); } static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct apply_wqattrs_ctx *ctx; /* only unbound workqueues can change attributes */ if (WARN_ON(!(wq->flags & WQ_UNBOUND))) return -EINVAL; ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask); if (IS_ERR(ctx)) return PTR_ERR(ctx); /* the ctx has been prepared successfully, let's commit it */ apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); return 0; } /** * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue * @wq: the target workqueue * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() * * Apply @attrs to an unbound workqueue @wq. Unless disabled, this function maps * a separate pwq to each CPU pod with possibles CPUs in @attrs->cpumask so that * work items are affine to the pod it was issued on. Older pwqs are released as * in-flight work items finish. Note that a work item which repeatedly requeues * itself back-to-back will stay on its current pwq. * * Performs GFP_KERNEL allocations. * * Return: 0 on success and -errno on failure. */ int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { int ret; mutex_lock(&wq_pool_mutex); ret = apply_workqueue_attrs_locked(wq, attrs); mutex_unlock(&wq_pool_mutex); return ret; } /** * unbound_wq_update_pwq - update a pwq slot for CPU hot[un]plug * @wq: the target workqueue * @cpu: the CPU to update the pwq slot for * * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and * %CPU_DOWN_FAILED. @cpu is in the same pod of the CPU being hot[un]plugged. * * * If pod affinity can't be adjusted due to memory allocation failure, it falls * back to @wq->dfl_pwq which may not be optimal but is always correct. * * Note that when the last allowed CPU of a pod goes offline for a workqueue * with a cpumask spanning multiple pods, the workers which were already * executing the work items for the workqueue will lose their CPU affinity and * may execute on any CPU. This is similar to how per-cpu workqueues behave on * CPU_DOWN. If a workqueue user wants strict affinity, it's the user's * responsibility to flush the work item from CPU_DOWN_PREPARE. */ static void unbound_wq_update_pwq(struct workqueue_struct *wq, int cpu) { struct pool_workqueue *old_pwq = NULL, *pwq; struct workqueue_attrs *target_attrs; lockdep_assert_held(&wq_pool_mutex); if (!(wq->flags & WQ_UNBOUND) || wq->unbound_attrs->ordered) return; /* * We don't wanna alloc/free wq_attrs for each wq for each CPU. * Let's use a preallocated one. The following buf is protected by * CPU hotplug exclusion. */ target_attrs = unbound_wq_update_pwq_attrs_buf; copy_workqueue_attrs(target_attrs, wq->unbound_attrs); wqattrs_actualize_cpumask(target_attrs, wq_unbound_cpumask); /* nothing to do if the target cpumask matches the current pwq */ wq_calc_pod_cpumask(target_attrs, cpu); if (wqattrs_equal(target_attrs, unbound_pwq(wq, cpu)->pool->attrs)) return; /* create a new pwq */ pwq = alloc_unbound_pwq(wq, target_attrs); if (!pwq) { pr_warn("workqueue: allocation failed while updating CPU pod affinity of \"%s\"\n", wq->name); goto use_dfl_pwq; } /* Install the new pwq. */ mutex_lock(&wq->mutex); old_pwq = install_unbound_pwq(wq, cpu, pwq); goto out_unlock; use_dfl_pwq: mutex_lock(&wq->mutex); pwq = unbound_pwq(wq, -1); raw_spin_lock_irq(&pwq->pool->lock); get_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); old_pwq = install_unbound_pwq(wq, cpu, pwq); out_unlock: mutex_unlock(&wq->mutex); put_pwq_unlocked(old_pwq); } static int alloc_and_link_pwqs(struct workqueue_struct *wq) { bool highpri = wq->flags & WQ_HIGHPRI; int cpu, ret; lockdep_assert_held(&wq_pool_mutex); wq->cpu_pwq = alloc_percpu(struct pool_workqueue *); if (!wq->cpu_pwq) goto enomem; if (!(wq->flags & WQ_UNBOUND)) { struct worker_pool __percpu *pools; if (wq->flags & WQ_BH) pools = bh_worker_pools; else pools = cpu_worker_pools; for_each_possible_cpu(cpu) { struct pool_workqueue **pwq_p; struct worker_pool *pool; pool = &(per_cpu_ptr(pools, cpu)[highpri]); pwq_p = per_cpu_ptr(wq->cpu_pwq, cpu); *pwq_p = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!*pwq_p) goto enomem; init_pwq(*pwq_p, wq, pool); mutex_lock(&wq->mutex); link_pwq(*pwq_p); mutex_unlock(&wq->mutex); } return 0; } if (wq->flags & __WQ_ORDERED) { struct pool_workqueue *dfl_pwq; ret = apply_workqueue_attrs_locked(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ dfl_pwq = rcu_access_pointer(wq->dfl_pwq); WARN(!ret && (wq->pwqs.next != &dfl_pwq->pwqs_node || wq->pwqs.prev != &dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); } else { ret = apply_workqueue_attrs_locked(wq, unbound_std_wq_attrs[highpri]); } return ret; enomem: if (wq->cpu_pwq) { for_each_possible_cpu(cpu) { struct pool_workqueue *pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); if (pwq) kmem_cache_free(pwq_cache, pwq); } free_percpu(wq->cpu_pwq); wq->cpu_pwq = NULL; } return -ENOMEM; } static int wq_clamp_max_active(int max_active, unsigned int flags, const char *name) { if (max_active < 1 || max_active > WQ_MAX_ACTIVE) pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n", max_active, name, 1, WQ_MAX_ACTIVE); return clamp_val(max_active, 1, WQ_MAX_ACTIVE); } /* * Workqueues which may be used during memory reclaim should have a rescuer * to guarantee forward progress. */ static int init_rescuer(struct workqueue_struct *wq) { struct worker *rescuer; char id_buf[WORKER_ID_LEN]; int ret; lockdep_assert_held(&wq_pool_mutex); if (!(wq->flags & WQ_MEM_RECLAIM)) return 0; rescuer = alloc_worker(NUMA_NO_NODE); if (!rescuer) { pr_err("workqueue: Failed to allocate a rescuer for wq \"%s\"\n", wq->name); return -ENOMEM; } rescuer->rescue_wq = wq; format_worker_id(id_buf, sizeof(id_buf), rescuer, NULL); rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", id_buf); if (IS_ERR(rescuer->task)) { ret = PTR_ERR(rescuer->task); pr_err("workqueue: Failed to create a rescuer kthread for wq \"%s\": %pe", wq->name, ERR_PTR(ret)); kfree(rescuer); return ret; } wq->rescuer = rescuer; if (wq->flags & WQ_UNBOUND) kthread_bind_mask(rescuer->task, unbound_effective_cpumask(wq)); else kthread_bind_mask(rescuer->task, cpu_possible_mask); wake_up_process(rescuer->task); return 0; } /** * wq_adjust_max_active - update a wq's max_active to the current setting * @wq: target workqueue * * If @wq isn't freezing, set @wq->max_active to the saved_max_active and * activate inactive work items accordingly. If @wq is freezing, clear * @wq->max_active to zero. */ static void wq_adjust_max_active(struct workqueue_struct *wq) { bool activated; int new_max, new_min; lockdep_assert_held(&wq->mutex); if ((wq->flags & WQ_FREEZABLE) && workqueue_freezing) { new_max = 0; new_min = 0; } else { new_max = wq->saved_max_active; new_min = wq->saved_min_active; } if (wq->max_active == new_max && wq->min_active == new_min) return; /* * Update @wq->max/min_active and then kick inactive work items if more * active work items are allowed. This doesn't break work item ordering * because new work items are always queued behind existing inactive * work items if there are any. */ WRITE_ONCE(wq->max_active, new_max); WRITE_ONCE(wq->min_active, new_min); if (wq->flags & WQ_UNBOUND) wq_update_node_max_active(wq, -1); if (new_max == 0) return; /* * Round-robin through pwq's activating the first inactive work item * until max_active is filled. */ do { struct pool_workqueue *pwq; activated = false; for_each_pwq(pwq, wq) { unsigned long irq_flags; /* can be called during early boot w/ irq disabled */ raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); if (pwq_activate_first_inactive(pwq, true)) { activated = true; kick_pool(pwq->pool); } raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); } } while (activated); } __printf(1, 0) static struct workqueue_struct *__alloc_workqueue(const char *fmt, unsigned int flags, int max_active, va_list args) { struct workqueue_struct *wq; size_t wq_size; int name_len; if (flags & WQ_BH) { if (WARN_ON_ONCE(flags & ~__WQ_BH_ALLOWS)) return NULL; if (WARN_ON_ONCE(max_active)) return NULL; } /* see the comment above the definition of WQ_POWER_EFFICIENT */ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) flags |= WQ_UNBOUND; /* allocate wq and format name */ if (flags & WQ_UNBOUND) wq_size = struct_size(wq, node_nr_active, nr_node_ids + 1); else wq_size = sizeof(*wq); wq = kzalloc_noprof(wq_size, GFP_KERNEL); if (!wq) return NULL; if (flags & WQ_UNBOUND) { wq->unbound_attrs = alloc_workqueue_attrs_noprof(); if (!wq->unbound_attrs) goto err_free_wq; } name_len = vsnprintf(wq->name, sizeof(wq->name), fmt, args); if (name_len >= WQ_NAME_LEN) pr_warn_once("workqueue: name exceeds WQ_NAME_LEN. Truncating to: %s\n", wq->name); if (flags & WQ_BH) { /* * BH workqueues always share a single execution context per CPU * and don't impose any max_active limit. */ max_active = INT_MAX; } else { max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); } /* init wq */ wq->flags = flags; wq->max_active = max_active; wq->min_active = min(max_active, WQ_DFL_MIN_ACTIVE); wq->saved_max_active = wq->max_active; wq->saved_min_active = wq->min_active; mutex_init(&wq->mutex); atomic_set(&wq->nr_pwqs_to_flush, 0); INIT_LIST_HEAD(&wq->pwqs); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); INIT_LIST_HEAD(&wq->maydays); INIT_LIST_HEAD(&wq->list); if (flags & WQ_UNBOUND) { if (alloc_node_nr_active(wq->node_nr_active) < 0) goto err_free_wq; } /* * wq_pool_mutex protects the workqueues list, allocations of PWQs, * and the global freeze state. */ apply_wqattrs_lock(); if (alloc_and_link_pwqs(wq) < 0) goto err_unlock_free_node_nr_active; mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); list_add_tail_rcu(&wq->list, &workqueues); if (wq_online && init_rescuer(wq) < 0) goto err_unlock_destroy; apply_wqattrs_unlock(); if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq)) goto err_destroy; return wq; err_unlock_free_node_nr_active: apply_wqattrs_unlock(); /* * Failed alloc_and_link_pwqs() may leave pending pwq->release_work, * flushing the pwq_release_worker ensures that the pwq_release_workfn() * completes before calling kfree(wq). */ if (wq->flags & WQ_UNBOUND) { kthread_flush_worker(pwq_release_worker); free_node_nr_active(wq->node_nr_active); } err_free_wq: free_workqueue_attrs(wq->unbound_attrs); kfree(wq); return NULL; err_unlock_destroy: apply_wqattrs_unlock(); err_destroy: destroy_workqueue(wq); return NULL; } __printf(1, 4) struct workqueue_struct *alloc_workqueue_noprof(const char *fmt, unsigned int flags, int max_active, ...) { struct workqueue_struct *wq; va_list args; va_start(args, max_active); wq = __alloc_workqueue(fmt, flags, max_active, args); va_end(args); if (!wq) return NULL; wq_init_lockdep(wq); return wq; } EXPORT_SYMBOL_GPL(alloc_workqueue_noprof); #ifdef CONFIG_LOCKDEP __printf(1, 5) struct workqueue_struct * alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active, struct lockdep_map *lockdep_map, ...) { struct workqueue_struct *wq; va_list args; va_start(args, lockdep_map); wq = __alloc_workqueue(fmt, flags, max_active, args); va_end(args); if (!wq) return NULL; wq->lockdep_map = lockdep_map; return wq; } EXPORT_SYMBOL_GPL(alloc_workqueue_lockdep_map); #endif static bool pwq_busy(struct pool_workqueue *pwq) { int i; for (i = 0; i < WORK_NR_COLORS; i++) if (pwq->nr_in_flight[i]) return true; if ((pwq != rcu_access_pointer(pwq->wq->dfl_pwq)) && (pwq->refcnt > 1)) return true; if (!pwq_is_empty(pwq)) return true; return false; } /** * destroy_workqueue - safely terminate a workqueue * @wq: target workqueue * * Safely destroy a workqueue. All work currently pending will be done first. * * This function does NOT guarantee that non-pending work that has been * submitted with queue_delayed_work() and similar functions will be done * before destroying the workqueue. The fundamental problem is that, currently, * the workqueue has no way of accessing non-pending delayed_work. delayed_work * is only linked on the timer-side. All delayed_work must, therefore, be * canceled before calling this function. * * TODO: It would be better if the problem described above wouldn't exist and * destroy_workqueue() would cleanly cancel all pending and non-pending * delayed_work. */ void destroy_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; int cpu; /* * Remove it from sysfs first so that sanity check failure doesn't * lead to sysfs name conflicts. */ workqueue_sysfs_unregister(wq); /* mark the workqueue destruction is in progress */ mutex_lock(&wq->mutex); wq->flags |= __WQ_DESTROYING; mutex_unlock(&wq->mutex); /* drain it before proceeding with destruction */ drain_workqueue(wq); /* kill rescuer, if sanity checks fail, leave it w/o rescuer */ if (wq->rescuer) { struct worker *rescuer = wq->rescuer; /* this prevents new queueing */ raw_spin_lock_irq(&wq_mayday_lock); wq->rescuer = NULL; raw_spin_unlock_irq(&wq_mayday_lock); /* rescuer will empty maydays list before exiting */ kthread_stop(rescuer->task); kfree(rescuer); } /* * Sanity checks - grab all the locks so that we wait for all * in-flight operations which may do put_pwq(). */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { raw_spin_lock_irq(&pwq->pool->lock); if (WARN_ON(pwq_busy(pwq))) { pr_warn("%s: %s has the following busy pwq\n", __func__, wq->name); show_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); mutex_unlock(&wq->mutex); mutex_unlock(&wq_pool_mutex); show_one_workqueue(wq); return; } raw_spin_unlock_irq(&pwq->pool->lock); } mutex_unlock(&wq->mutex); /* * wq list is used to freeze wq, remove from list after * flushing is complete in case freeze races us. */ list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); /* * We're the sole accessor of @wq. Directly access cpu_pwq and dfl_pwq * to put the base refs. @wq will be auto-destroyed from the last * pwq_put. RCU read lock prevents @wq from going away from under us. */ rcu_read_lock(); for_each_possible_cpu(cpu) { put_pwq_unlocked(unbound_pwq(wq, cpu)); RCU_INIT_POINTER(*unbound_pwq_slot(wq, cpu), NULL); } put_pwq_unlocked(unbound_pwq(wq, -1)); RCU_INIT_POINTER(*unbound_pwq_slot(wq, -1), NULL); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(destroy_workqueue); /** * workqueue_set_max_active - adjust max_active of a workqueue * @wq: target workqueue * @max_active: new max_active value. * * Set max_active of @wq to @max_active. See the alloc_workqueue() function * comment. * * CONTEXT: * Don't call from IRQ context. */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { /* max_active doesn't mean anything for BH workqueues */ if (WARN_ON(wq->flags & WQ_BH)) return; /* disallow meddling with max_active for ordered workqueues */ if (WARN_ON(wq->flags & __WQ_ORDERED)) return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); mutex_lock(&wq->mutex); wq->saved_max_active = max_active; if (wq->flags & WQ_UNBOUND) wq->saved_min_active = min(wq->saved_min_active, max_active); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** * workqueue_set_min_active - adjust min_active of an unbound workqueue * @wq: target unbound workqueue * @min_active: new min_active value * * Set min_active of an unbound workqueue. Unlike other types of workqueues, an * unbound workqueue is not guaranteed to be able to process max_active * interdependent work items. Instead, an unbound workqueue is guaranteed to be * able to process min_active number of interdependent work items which is * %WQ_DFL_MIN_ACTIVE by default. * * Use this function to adjust the min_active value between 0 and the current * max_active. */ void workqueue_set_min_active(struct workqueue_struct *wq, int min_active) { /* min_active is only meaningful for non-ordered unbound workqueues */ if (WARN_ON((wq->flags & (WQ_BH | WQ_UNBOUND | __WQ_ORDERED)) != WQ_UNBOUND)) return; mutex_lock(&wq->mutex); wq->saved_min_active = clamp(min_active, 0, wq->saved_max_active); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } /** * current_work - retrieve %current task's work struct * * Determine if %current task is a workqueue worker and what it's working on. * Useful to find out the context that the %current task is running in. * * Return: work struct if %current task is a workqueue worker, %NULL otherwise. */ struct work_struct *current_work(void) { struct worker *worker = current_wq_worker(); return worker ? worker->current_work : NULL; } EXPORT_SYMBOL(current_work); /** * current_is_workqueue_rescuer - is %current workqueue rescuer? * * Determine whether %current is a workqueue rescuer. Can be used from * work functions to determine whether it's being run off the rescuer task. * * Return: %true if %current is a workqueue rescuer. %false otherwise. */ bool current_is_workqueue_rescuer(void) { struct worker *worker = current_wq_worker(); return worker && worker->rescue_wq; } /** * workqueue_congested - test whether a workqueue is congested * @cpu: CPU in question * @wq: target workqueue * * Test whether @wq's cpu workqueue for @cpu is congested. There is * no synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. * * With the exception of ordered workqueues, all workqueues have per-cpu * pool_workqueues, each with its own congested state. A workqueue being * congested on one CPU doesn't mean that the workqueue is contested on any * other CPUs. * * Return: * %true if congested, %false otherwise. */ bool workqueue_congested(int cpu, struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool ret; preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); ret = !list_empty(&pwq->inactive_works); preempt_enable(); return ret; } EXPORT_SYMBOL_GPL(workqueue_congested); /** * work_busy - test whether a work is currently pending or running * @work: the work to be tested * * Test whether @work is currently pending or running. There is no * synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * Return: * OR'd bitmask of WORK_BUSY_* bits. */ unsigned int work_busy(struct work_struct *work) { struct worker_pool *pool; unsigned long irq_flags; unsigned int ret = 0; if (work_pending(work)) ret |= WORK_BUSY_PENDING; rcu_read_lock(); pool = get_work_pool(work); if (pool) { raw_spin_lock_irqsave(&pool->lock, irq_flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_busy); /** * set_worker_desc - set description for the current work item * @fmt: printf-style format string * @...: arguments for the format string * * This function can be called by a running work function to describe what * the work item is about. If the worker task gets dumped, this * information will be printed out together to help debugging. The * description can be at most WORKER_DESC_LEN including the trailing '\0'. */ void set_worker_desc(const char *fmt, ...) { struct worker *worker = current_wq_worker(); va_list args; if (worker) { va_start(args, fmt); vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); va_end(args); } } EXPORT_SYMBOL_GPL(set_worker_desc); /** * print_worker_info - print out worker information and description * @log_lvl: the log level to use when printing * @task: target task * * If @task is a worker and currently executing a work item, print out the * name of the workqueue being serviced and worker description set with * set_worker_desc() by the currently executing work item. * * This function can be safely called on any task as long as the * task_struct itself is accessible. While safe, this function isn't * synchronized and may print out mixups or garbages of limited length. */ void print_worker_info(const char *log_lvl, struct task_struct *task) { work_func_t *fn = NULL; char name[WQ_NAME_LEN] = { }; char desc[WORKER_DESC_LEN] = { }; struct pool_workqueue *pwq = NULL; struct workqueue_struct *wq = NULL; struct worker *worker; if (!(task->flags & PF_WQ_WORKER)) return; /* * This function is called without any synchronization and @task * could be in any state. Be careful with dereferences. */ worker = kthread_probe_data(task); /* * Carefully copy the associated workqueue's workfn, name and desc. * Keep the original last '\0' in case the original is garbage. */ copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn)); copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq)); copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq)); copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1); copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1); if (fn || name[0] || desc[0]) { printk("%sWorkqueue: %s %ps", log_lvl, name, fn); if (strcmp(name, desc)) pr_cont(" (%s)", desc); pr_cont("\n"); } } static void pr_cont_pool_info(struct worker_pool *pool) { pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); if (pool->node != NUMA_NO_NODE) pr_cont(" node=%d", pool->node); pr_cont(" flags=0x%x", pool->flags); if (pool->flags & POOL_BH) pr_cont(" bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else pr_cont(" nice=%d", pool->attrs->nice); } static void pr_cont_worker_id(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & WQ_BH) pr_cont("bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else pr_cont("%d%s", task_pid_nr(worker->task), worker->rescue_wq ? "(RESCUER)" : ""); } struct pr_cont_work_struct { bool comma; work_func_t func; long ctr; }; static void pr_cont_work_flush(bool comma, work_func_t func, struct pr_cont_work_struct *pcwsp) { if (!pcwsp->ctr) goto out_record; if (func == pcwsp->func) { pcwsp->ctr++; return; } if (pcwsp->ctr == 1) pr_cont("%s %ps", pcwsp->comma ? "," : "", pcwsp->func); else pr_cont("%s %ld*%ps", pcwsp->comma ? "," : "", pcwsp->ctr, pcwsp->func); pcwsp->ctr = 0; out_record: if ((long)func == -1L) return; pcwsp->comma = comma; pcwsp->func = func; pcwsp->ctr = 1; } static void pr_cont_work(bool comma, struct work_struct *work, struct pr_cont_work_struct *pcwsp) { if (work->func == wq_barrier_func) { struct wq_barrier *barr; barr = container_of(work, struct wq_barrier, work); pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont("%s BAR(%d)", comma ? "," : "", task_pid_nr(barr->task)); } else { if (!comma) pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont_work_flush(comma, work->func, pcwsp); } } static void show_pwq(struct pool_workqueue *pwq) { struct pr_cont_work_struct pcws = { .ctr = 0, }; struct worker_pool *pool = pwq->pool; struct work_struct *work; struct worker *worker; bool has_in_flight = false, has_pending = false; int bkt; pr_info(" pwq %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" active=%d refcnt=%d%s\n", pwq->nr_active, pwq->refcnt, !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq == pwq) { has_in_flight = true; break; } } if (has_in_flight) { bool comma = false; pr_info(" in-flight:"); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq != pwq) continue; pr_cont(" %s", comma ? "," : ""); pr_cont_worker_id(worker); pr_cont(":%ps", worker->current_func); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work, &pcws); pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); comma = true; } pr_cont("\n"); } list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) == pwq) { has_pending = true; break; } } if (has_pending) { bool comma = false; pr_info(" pending:"); list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) != pwq) continue; pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } if (!list_empty(&pwq->inactive_works)) { bool comma = false; pr_info(" inactive:"); list_for_each_entry(work, &pwq->inactive_works, entry) { pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } } /** * show_one_workqueue - dump state of specified workqueue * @wq: workqueue whose state will be printed */ void show_one_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool idle = true; unsigned long irq_flags; for_each_pwq(pwq, wq) { if (!pwq_is_empty(pwq)) { idle = false; break; } } if (idle) /* Nothing to print for idle workqueue */ return; pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); if (!pwq_is_empty(pwq)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); show_pwq(pwq); printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } } /** * show_one_worker_pool - dump state of specified worker pool * @pool: worker pool whose state will be printed */ static void show_one_worker_pool(struct worker_pool *pool) { struct worker *worker; bool first = true; unsigned long irq_flags; unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, irq_flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; /* How long the first pending work is waiting for a worker. */ if (!list_empty(&pool->worklist)) hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; /* * Defer printing to avoid deadlocks in console drivers that * queue work while holding locks also taken in their write * paths. */ printk_deferred_enter(); pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); list_for_each_entry(worker, &pool->idle_list, entry) { pr_cont(" %s", first ? "idle: " : ""); pr_cont_worker_id(worker); first = false; } pr_cont("\n"); printk_deferred_exit(); next_pool: raw_spin_unlock_irqrestore(&pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } /** * show_all_workqueues - dump workqueue state * * Called from a sysrq handler and prints out all busy workqueues and pools. */ void show_all_workqueues(void) { struct workqueue_struct *wq; struct worker_pool *pool; int pi; rcu_read_lock(); pr_info("Showing busy workqueues and worker pools:\n"); list_for_each_entry_rcu(wq, &workqueues, list) show_one_workqueue(wq); for_each_pool(pool, pi) show_one_worker_pool(pool); rcu_read_unlock(); } /** * show_freezable_workqueues - dump freezable workqueue state * * Called from try_to_freeze_tasks() and prints out all freezable workqueues * still busy. */ void show_freezable_workqueues(void) { struct workqueue_struct *wq; rcu_read_lock(); pr_info("Showing freezable workqueues that are still busy:\n"); list_for_each_entry_rcu(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; show_one_workqueue(wq); } rcu_read_unlock(); } /* used to show worker information through /proc/PID/{comm,stat,status} */ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) { /* stabilize PF_WQ_WORKER and worker pool association */ mutex_lock(&wq_pool_attach_mutex); if (task->flags & PF_WQ_WORKER) { struct worker *worker = kthread_data(task); struct worker_pool *pool = worker->pool; int off; off = format_worker_id(buf, size, worker, pool); if (pool) { raw_spin_lock_irq(&pool->lock); /* * ->desc tracks information (wq name or * set_worker_desc()) for the latest execution. If * current, prepend '+', otherwise '-'. */ if (worker->desc[0] != '\0') { if (worker->current_work) scnprintf(buf + off, size - off, "+%s", worker->desc); else scnprintf(buf + off, size - off, "-%s", worker->desc); } raw_spin_unlock_irq(&pool->lock); } } else { strscpy(buf, task->comm, size); } mutex_unlock(&wq_pool_attach_mutex); } #ifdef CONFIG_SMP /* * CPU hotplug. * * There are two challenges in supporting CPU hotplug. Firstly, there * are a lot of assumptions on strong associations among work, pwq and * pool which make migrating pending and scheduled works very * difficult to implement without impacting hot paths. Secondly, * worker pools serve mix of short, long and very long running works making * blocked draining impractical. * * This is solved by allowing the pools to be disassociated from the CPU * running as an unbound one and allowing it to be reattached later if the * cpu comes back online. */ static void unbind_workers(int cpu) { struct worker_pool *pool; struct worker *worker; for_each_cpu_worker_pool(pool, cpu) { mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); /* * We've blocked all attach/detach operations. Make all workers * unbound and set DISASSOCIATED. Before this, all workers * must be on the cpu. After this, they may become diasporas. * And the preemption disabled section in their sched callbacks * are guaranteed to see WORKER_UNBOUND since the code here * is on the same cpu. */ for_each_pool_worker(worker, pool) worker->flags |= WORKER_UNBOUND; pool->flags |= POOL_DISASSOCIATED; /* * The handling of nr_running in sched callbacks are disabled * now. Zap nr_running. After this, nr_running stays zero and * need_more_worker() and keep_working() are always true as * long as the worklist is not empty. This pool now behaves as * an unbound (in terms of concurrency management) pool which * are served by workers tied to the pool. */ pool->nr_running = 0; /* * With concurrency management just turned off, a busy * worker blocking could lead to lengthy stalls. Kick off * unbound chain execution of currently pending work items. */ kick_pool(pool); raw_spin_unlock_irq(&pool->lock); for_each_pool_worker(worker, pool) unbind_worker(worker); mutex_unlock(&wq_pool_attach_mutex); } } /** * rebind_workers - rebind all workers of a pool to the associated CPU * @pool: pool of interest * * @pool->cpu is coming online. Rebind all workers to the CPU. */ static void rebind_workers(struct worker_pool *pool) { struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* * Restore CPU affinity of all workers. As all idle workers should * be on the run-queue of the associated CPU before any local * wake-ups for concurrency management happen, restore CPU affinity * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ for_each_pool_worker(worker, pool) { kthread_set_per_cpu(worker->task, pool->cpu); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)) < 0); } raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_DISASSOCIATED; for_each_pool_worker(worker, pool) { unsigned int worker_flags = worker->flags; /* * We want to clear UNBOUND but can't directly call * worker_clr_flags() or adjust nr_running. Atomically * replace UNBOUND with another NOT_RUNNING flag REBOUND. * @worker will clear REBOUND using worker_clr_flags() when * it initiates the next execution cycle thus restoring * concurrency management. Note that when or whether * @worker clears REBOUND doesn't affect correctness. * * WRITE_ONCE() is necessary because @worker->flags may be * tested without holding any lock in * wq_worker_running(). Without it, NOT_RUNNING test may * fail incorrectly leading to premature concurrency * management operations. */ WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND)); worker_flags |= WORKER_REBOUND; worker_flags &= ~WORKER_UNBOUND; WRITE_ONCE(worker->flags, worker_flags); } raw_spin_unlock_irq(&pool->lock); } /** * restore_unbound_workers_cpumask - restore cpumask of unbound workers * @pool: unbound pool of interest * @cpu: the CPU which is coming up * * An unbound pool may end up with a cpumask which doesn't have any online * CPUs. When a worker of such pool get scheduled, the scheduler resets * its cpus_allowed. If @cpu is in @pool's cpumask which didn't have any * online CPU before, cpus_allowed of all its workers should be restored. */ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) { static cpumask_t cpumask; struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* is @cpu allowed for @pool? */ if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) return; cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); /* as we're called from CPU_ONLINE, the following shouldn't fail */ for_each_pool_worker(worker, pool) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } int workqueue_prepare_cpu(unsigned int cpu) { struct worker_pool *pool; for_each_cpu_worker_pool(pool, cpu) { if (pool->nr_workers) continue; if (!create_worker(pool)) return -ENOMEM; } return 0; } int workqueue_online_cpu(unsigned int cpu) { struct worker_pool *pool; struct workqueue_struct *wq; int pi; mutex_lock(&wq_pool_mutex); cpumask_set_cpu(cpu, wq_online_cpumask); for_each_pool(pool, pi) { /* BH pools aren't affected by hotplug */ if (pool->flags & POOL_BH) continue; mutex_lock(&wq_pool_attach_mutex); if (pool->cpu == cpu) rebind_workers(pool); else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); mutex_unlock(&wq_pool_attach_mutex); } /* update pod affinity of unbound workqueues */ list_for_each_entry(wq, &workqueues, list) { struct workqueue_attrs *attrs = wq->unbound_attrs; if (attrs) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int tcpu; for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) unbound_wq_update_pwq(wq, tcpu); mutex_lock(&wq->mutex); wq_update_node_max_active(wq, -1); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); return 0; } int workqueue_offline_cpu(unsigned int cpu) { struct workqueue_struct *wq; /* unbinding per-cpu workers should happen on the local CPU */ if (WARN_ON(cpu != smp_processor_id())) return -1; unbind_workers(cpu); /* update pod affinity of unbound workqueues */ mutex_lock(&wq_pool_mutex); cpumask_clear_cpu(cpu, wq_online_cpumask); list_for_each_entry(wq, &workqueues, list) { struct workqueue_attrs *attrs = wq->unbound_attrs; if (attrs) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int tcpu; for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) unbound_wq_update_pwq(wq, tcpu); mutex_lock(&wq->mutex); wq_update_node_max_active(wq, cpu); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); return 0; } struct work_for_cpu { struct work_struct work; long (*fn)(void *); void *arg; long ret; }; static void work_for_cpu_fn(struct work_struct *work) { struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work); wfc->ret = wfc->fn(wfc->arg); } /** * work_on_cpu_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function arg * @key: The lock class key for lock debugging purposes * * It is up to the caller to ensure that the cpu doesn't go offline. * The caller must not hold any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key) { struct work_for_cpu wfc = { .fn = fn, .arg = arg }; INIT_WORK_ONSTACK_KEY(&wfc.work, work_for_cpu_fn, key); schedule_work_on(cpu, &wfc.work); flush_work(&wfc.work); destroy_work_on_stack(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu_key); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER /** * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable * workqueues will queue new works to their inactive_works list instead of * pool->worklist. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void freeze_workqueues_begin(void) { struct workqueue_struct *wq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(workqueue_freezing); workqueue_freezing = true; list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } mutex_unlock(&wq_pool_mutex); } /** * freeze_workqueues_busy - are freezable workqueues still busy? * * Check whether freezing is complete. This function must be called * between freeze_workqueues_begin() and thaw_workqueues(). * * CONTEXT: * Grabs and releases wq_pool_mutex. * * Return: * %true if some freezable workqueues are still busy. %false if freezing * is complete. */ bool freeze_workqueues_busy(void) { bool busy = false; struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(!workqueue_freezing); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; /* * nr_active is monotonically decreasing. It's safe * to peek without lock. */ rcu_read_lock(); for_each_pwq(pwq, wq) { WARN_ON_ONCE(pwq->nr_active < 0); if (pwq->nr_active) { busy = true; rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); } out_unlock: mutex_unlock(&wq_pool_mutex); return busy; } /** * thaw_workqueues - thaw workqueues * * Thaw workqueues. Normal queueing is restored and all collected * frozen works are transferred to their respective pool worklists. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void thaw_workqueues(void) { struct workqueue_struct *wq; mutex_lock(&wq_pool_mutex); if (!workqueue_freezing) goto out_unlock; workqueue_freezing = false; /* restore max_active and repopulate worklist */ list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } out_unlock: mutex_unlock(&wq_pool_mutex); } #endif /* CONFIG_FREEZER */ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) { LIST_HEAD(ctxs); int ret = 0; struct workqueue_struct *wq; struct apply_wqattrs_ctx *ctx, *n; lockdep_assert_held(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_UNBOUND) || (wq->flags & __WQ_DESTROYING)) continue; ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask); if (IS_ERR(ctx)) { ret = PTR_ERR(ctx); break; } list_add_tail(&ctx->list, &ctxs); } list_for_each_entry_safe(ctx, n, &ctxs, list) { if (!ret) apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); } if (!ret) { mutex_lock(&wq_pool_attach_mutex); cpumask_copy(wq_unbound_cpumask, unbound_cpumask); mutex_unlock(&wq_pool_attach_mutex); } return ret; } /** * workqueue_unbound_exclude_cpumask - Exclude given CPUs from unbound cpumask * @exclude_cpumask: the cpumask to be excluded from wq_unbound_cpumask * * This function can be called from cpuset code to provide a set of isolated * CPUs that should be excluded from wq_unbound_cpumask. */ int workqueue_unbound_exclude_cpumask(cpumask_var_t exclude_cpumask) { cpumask_var_t cpumask; int ret = 0; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; mutex_lock(&wq_pool_mutex); /* * If the operation fails, it will fall back to * wq_requested_unbound_cpumask which is initially set to * (HK_TYPE_WQ ∩ HK_TYPE_DOMAIN) house keeping mask and rewritten * by any subsequent write to workqueue/cpumask sysfs file. */ if (!cpumask_andnot(cpumask, wq_requested_unbound_cpumask, exclude_cpumask)) cpumask_copy(cpumask, wq_requested_unbound_cpumask); if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); /* Save the current isolated cpumask & export it via sysfs */ if (!ret) cpumask_copy(wq_isolated_cpumask, exclude_cpumask); mutex_unlock(&wq_pool_mutex); free_cpumask_var(cpumask); return ret; } static int parse_affn_scope(const char *val) { int i; for (i = 0; i < ARRAY_SIZE(wq_affn_names); i++) { if (!strncasecmp(val, wq_affn_names[i], strlen(wq_affn_names[i]))) return i; } return -EINVAL; } static int wq_affn_dfl_set(const char *val, const struct kernel_param *kp) { struct workqueue_struct *wq; int affn, cpu; affn = parse_affn_scope(val); if (affn < 0) return affn; if (affn == WQ_AFFN_DFL) return -EINVAL; cpus_read_lock(); mutex_lock(&wq_pool_mutex); wq_affn_dfl = affn; list_for_each_entry(wq, &workqueues, list) { for_each_online_cpu(cpu) unbound_wq_update_pwq(wq, cpu); } mutex_unlock(&wq_pool_mutex); cpus_read_unlock(); return 0; } static int wq_affn_dfl_get(char *buffer, const struct kernel_param *kp) { return scnprintf(buffer, PAGE_SIZE, "%s\n", wq_affn_names[wq_affn_dfl]); } static const struct kernel_param_ops wq_affn_dfl_ops = { .set = wq_affn_dfl_set, .get = wq_affn_dfl_get, }; module_param_cb(default_affinity_scope, &wq_affn_dfl_ops, NULL, 0644); #ifdef CONFIG_SYSFS /* * Workqueues with WQ_SYSFS flag set is visible to userland via * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the * following attributes. * * per_cpu RO bool : whether the workqueue is per-cpu or unbound * max_active RW int : maximum number of in-flight work items * * Unbound workqueues have the following extra attributes. * * nice RW int : nice value of the workers * cpumask RW mask : bitmask of allowed CPUs for the workers * affinity_scope RW str : worker CPU affinity scope (cache, numa, none) * affinity_strict RW bool : worker CPU affinity is strict */ struct wq_device { struct workqueue_struct *wq; struct device dev; }; static struct workqueue_struct *dev_to_wq(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); return wq_dev->wq; } static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); } static DEVICE_ATTR_RO(per_cpu); static ssize_t max_active_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); } static ssize_t max_active_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); int val; if (sscanf(buf, "%d", &val) != 1 || val <= 0) return -EINVAL; workqueue_set_max_active(wq, val); return count; } static DEVICE_ATTR_RW(max_active); static struct attribute *wq_sysfs_attrs[] = { &dev_attr_per_cpu.attr, &dev_attr_max_active.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs); static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); mutex_unlock(&wq->mutex); return written; } /* prepare workqueue_attrs for sysfs store operations */ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) { struct workqueue_attrs *attrs; lockdep_assert_held(&wq_pool_mutex); attrs = alloc_workqueue_attrs(); if (!attrs) return NULL; copy_workqueue_attrs(attrs, wq->unbound_attrs); return attrs; } static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; if (sscanf(buf, "%d", &attrs->nice) == 1 && attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) ret = apply_workqueue_attrs_locked(wq, attrs); else ret = -EINVAL; out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(wq->unbound_attrs->cpumask)); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; ret = cpumask_parse(buf, attrs->cpumask); if (!ret) ret = apply_workqueue_attrs_locked(wq, attrs); out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_affn_scope_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); if (wq->unbound_attrs->affn_scope == WQ_AFFN_DFL) written = scnprintf(buf, PAGE_SIZE, "%s (%s)\n", wq_affn_names[WQ_AFFN_DFL], wq_affn_names[wq_affn_dfl]); else written = scnprintf(buf, PAGE_SIZE, "%s\n", wq_affn_names[wq->unbound_attrs->affn_scope]); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_affn_scope_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int affn, ret = -ENOMEM; affn = parse_affn_scope(buf); if (affn < 0) return affn; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (attrs) { attrs->affn_scope = affn; ret = apply_workqueue_attrs_locked(wq, attrs); } apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_affinity_strict_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->affn_strict); } static ssize_t wq_affinity_strict_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int v, ret = -ENOMEM; if (sscanf(buf, "%d", &v) != 1) return -EINVAL; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (attrs) { attrs->affn_strict = (bool)v; ret = apply_workqueue_attrs_locked(wq, attrs); } apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static struct device_attribute wq_sysfs_unbound_attrs[] = { __ATTR(nice, 0644, wq_nice_show, wq_nice_store), __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), __ATTR(affinity_scope, 0644, wq_affn_scope_show, wq_affn_scope_store), __ATTR(affinity_strict, 0644, wq_affinity_strict_show, wq_affinity_strict_store), __ATTR_NULL, }; static const struct bus_type wq_subsys = { .name = "workqueue", .dev_groups = wq_sysfs_groups, }; /** * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask * @cpumask: the cpumask to set * * The low-level workqueues cpumask is a global cpumask that limits * the affinity of all unbound workqueues. This function check the @cpumask * and apply it to all unbound workqueues and updates all pwqs of them. * * Return: 0 - Success * -EINVAL - Invalid @cpumask * -ENOMEM - Failed to allocate memory for attrs or pwqs. */ static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) { int ret = -EINVAL; /* * Not excluding isolated cpus on purpose. * If the user wishes to include them, we allow that. */ cpumask_and(cpumask, cpumask, cpu_possible_mask); if (!cpumask_empty(cpumask)) { ret = 0; apply_wqattrs_lock(); if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); if (!ret) cpumask_copy(wq_requested_unbound_cpumask, cpumask); apply_wqattrs_unlock(); } return ret; } static ssize_t __wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf, cpumask_var_t mask) { int written; mutex_lock(&wq_pool_mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); mutex_unlock(&wq_pool_mutex); return written; } static ssize_t cpumask_requested_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask); } static DEVICE_ATTR_RO(cpumask_requested); static ssize_t cpumask_isolated_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask); } static DEVICE_ATTR_RO(cpumask_isolated); static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask); } static ssize_t cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { cpumask_var_t cpumask; int ret; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; ret = cpumask_parse(buf, cpumask); if (!ret) ret = workqueue_set_unbound_cpumask(cpumask); free_cpumask_var(cpumask); return ret ? ret : count; } static DEVICE_ATTR_RW(cpumask); static struct attribute *wq_sysfs_cpumask_attrs[] = { &dev_attr_cpumask.attr, &dev_attr_cpumask_requested.attr, &dev_attr_cpumask_isolated.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs_cpumask); static int __init wq_sysfs_init(void) { return subsys_virtual_register(&wq_subsys, wq_sysfs_cpumask_groups); } core_initcall(wq_sysfs_init); static void wq_device_release(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); kfree(wq_dev); } /** * workqueue_sysfs_register - make a workqueue visible in sysfs * @wq: the workqueue to register * * Expose @wq in sysfs under /sys/bus/workqueue/devices. * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set * which is the preferred method. * * Workqueue user should use this function directly iff it wants to apply * workqueue_attrs before making the workqueue visible in sysfs; otherwise, * apply_workqueue_attrs() may race against userland updating the * attributes. * * Return: 0 on success, -errno on failure. */ int workqueue_sysfs_register(struct workqueue_struct *wq) { struct wq_device *wq_dev; int ret; /* * Adjusting max_active breaks ordering guarantee. Disallow exposing * ordered workqueues. */ if (WARN_ON(wq->flags & __WQ_ORDERED)) return -EINVAL; wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); if (!wq_dev) return -ENOMEM; wq_dev->wq = wq; wq_dev->dev.bus = &wq_subsys; wq_dev->dev.release = wq_device_release; dev_set_name(&wq_dev->dev, "%s", wq->name); /* * unbound_attrs are created separately. Suppress uevent until * everything is ready. */ dev_set_uevent_suppress(&wq_dev->dev, true); ret = device_register(&wq_dev->dev); if (ret) { put_device(&wq_dev->dev); wq->wq_dev = NULL; return ret; } if (wq->flags & WQ_UNBOUND) { struct device_attribute *attr; for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { ret = device_create_file(&wq_dev->dev, attr); if (ret) { device_unregister(&wq_dev->dev); wq->wq_dev = NULL; return ret; } } } dev_set_uevent_suppress(&wq_dev->dev, false); kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); return 0; } /** * workqueue_sysfs_unregister - undo workqueue_sysfs_register() * @wq: the workqueue to unregister * * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { struct wq_device *wq_dev = wq->wq_dev; if (!wq->wq_dev) return; wq->wq_dev = NULL; device_unregister(&wq_dev->dev); } #else /* CONFIG_SYSFS */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } #endif /* CONFIG_SYSFS */ /* * Workqueue watchdog. * * Stall may be caused by various bugs - missing WQ_MEM_RECLAIM, illegal * flush dependency, a concurrency managed work item which stays RUNNING * indefinitely. Workqueue stalls can be very difficult to debug as the * usual warning mechanisms don't trigger and internal workqueue state is * largely opaque. * * Workqueue watchdog monitors all worker pools periodically and dumps * state if some pools failed to make forward progress for a while where * forward progress is defined as the first item on ->worklist changing. * * This mechanism is controlled through the kernel parameter * "workqueue.watchdog_thresh" which can be updated at runtime through the * corresponding sysfs parameter file. */ #ifdef CONFIG_WQ_WATCHDOG static unsigned long wq_watchdog_thresh = 30; static struct timer_list wq_watchdog_timer; static unsigned long wq_watchdog_touched = INITIAL_JIFFIES; static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; static unsigned int wq_panic_on_stall; module_param_named(panic_on_stall, wq_panic_on_stall, uint, 0644); /* * Show workers that might prevent the processing of pending work items. * The only candidates are CPU-bound workers in the running state. * Pending work items should be handled by another idle worker * in all other situations. */ static void show_cpu_pool_hog(struct worker_pool *pool) { struct worker *worker; unsigned long irq_flags; int bkt; raw_spin_lock_irqsave(&pool->lock, irq_flags); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (task_is_running(worker->task)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); pr_info("pool %d:\n", pool->id); sched_show_task(worker->task); printk_deferred_exit(); } } raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } static void show_cpu_pools_hogs(void) { struct worker_pool *pool; int pi; pr_info("Showing backtraces of running workers in stalled CPU-bound worker pools:\n"); rcu_read_lock(); for_each_pool(pool, pi) { if (pool->cpu_stall) show_cpu_pool_hog(pool); } rcu_read_unlock(); } static void panic_on_wq_watchdog(void) { static unsigned int wq_stall; if (wq_panic_on_stall) { wq_stall++; BUG_ON(wq_stall >= wq_panic_on_stall); } } static void wq_watchdog_reset_touched(void) { int cpu; wq_watchdog_touched = jiffies; for_each_possible_cpu(cpu) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; } static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; bool cpu_pool_stall = false; unsigned long now = jiffies; struct worker_pool *pool; int pi; if (!thresh) return; for_each_pool(pool, pi) { unsigned long pool_ts, touched, ts; pool->cpu_stall = false; if (list_empty(&pool->worklist)) continue; /* * If a virtual machine is stopped by the host it can look to * the watchdog like a stall. */ kvm_check_and_clear_guest_paused(); /* get the latest of pool and touched timestamps */ if (pool->cpu >= 0) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); else touched = READ_ONCE(wq_watchdog_touched); pool_ts = READ_ONCE(pool->watchdog_ts); if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; /* did we stall? */ if (time_after(now, ts + thresh)) { lockup_detected = true; if (pool->cpu >= 0 && !(pool->flags & POOL_BH)) { pool->cpu_stall = true; cpu_pool_stall = true; } pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", jiffies_to_msecs(now - pool_ts) / 1000); } } if (lockup_detected) show_all_workqueues(); if (cpu_pool_stall) show_cpu_pools_hogs(); if (lockup_detected) panic_on_wq_watchdog(); wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh); } notrace void wq_watchdog_touch(int cpu) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; unsigned long touch_ts = READ_ONCE(wq_watchdog_touched); unsigned long now = jiffies; if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = now; else WARN_ONCE(1, "%s should be called with valid CPU", __func__); /* Don't unnecessarily store to global cacheline */ if (time_after(now, touch_ts + thresh / 4)) WRITE_ONCE(wq_watchdog_touched, jiffies); } static void wq_watchdog_set_thresh(unsigned long thresh) { wq_watchdog_thresh = 0; timer_delete_sync(&wq_watchdog_timer); if (thresh) { wq_watchdog_thresh = thresh; wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ); } } static int wq_watchdog_param_set_thresh(const char *val, const struct kernel_param *kp) { unsigned long thresh; int ret; ret = kstrtoul(val, 0, &thresh); if (ret) return ret; if (system_percpu_wq) wq_watchdog_set_thresh(thresh); else wq_watchdog_thresh = thresh; return 0; } static const struct kernel_param_ops wq_watchdog_thresh_ops = { .set = wq_watchdog_param_set_thresh, .get = param_get_ulong, }; module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh, 0644); static void wq_watchdog_init(void) { timer_setup(&wq_watchdog_timer, wq_watchdog_timer_fn, TIMER_DEFERRABLE); wq_watchdog_set_thresh(wq_watchdog_thresh); } #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ static void bh_pool_kick_normal(struct irq_work *irq_work) { raise_softirq_irqoff(TASKLET_SOFTIRQ); } static void bh_pool_kick_highpri(struct irq_work *irq_work) { raise_softirq_irqoff(HI_SOFTIRQ); } static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask) { if (!cpumask_intersects(wq_unbound_cpumask, mask)) { pr_warn("workqueue: Restricting unbound_cpumask (%*pb) with %s (%*pb) leaves no CPU, ignoring\n", cpumask_pr_args(wq_unbound_cpumask), name, cpumask_pr_args(mask)); return; } cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask); } static void __init init_cpu_worker_pool(struct worker_pool *pool, int cpu, int nice) { BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu)); pool->attrs->nice = nice; pool->attrs->affn_strict = true; pool->node = cpu_to_node(cpu); /* alloc pool ID */ mutex_lock(&wq_pool_mutex); BUG_ON(worker_pool_assign_id(pool)); mutex_unlock(&wq_pool_mutex); } /** * workqueue_init_early - early init for workqueue subsystem * * This is the first step of three-staged workqueue subsystem initialization and * invoked as soon as the bare basics - memory allocation, cpumasks and idr are * up. It sets up all the data structures and system workqueues and allows early * boot code to create workqueues and queue/cancel work items. Actual work item * execution starts only after kthreads can be created and scheduled right * before early initcalls. */ void __init workqueue_init_early(void) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_SYSTEM]; int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; void (*irq_work_fns[2])(struct irq_work *) = { bh_pool_kick_normal, bh_pool_kick_highpri }; int i, cpu; BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_online_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&wq_requested_unbound_cpumask, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&wq_isolated_cpumask, GFP_KERNEL)); cpumask_copy(wq_online_cpumask, cpu_online_mask); cpumask_copy(wq_unbound_cpumask, cpu_possible_mask); restrict_unbound_cpumask("HK_TYPE_WQ", housekeeping_cpumask(HK_TYPE_WQ)); restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN)); if (!cpumask_empty(&wq_cmdline_cpumask)) restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask); cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask); cpumask_andnot(wq_isolated_cpumask, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); unbound_wq_update_pwq_attrs_buf = alloc_workqueue_attrs(); BUG_ON(!unbound_wq_update_pwq_attrs_buf); /* * If nohz_full is enabled, set power efficient workqueue as unbound. * This allows workqueue items to be moved to HK CPUs. */ if (housekeeping_enabled(HK_TYPE_TICK)) wq_power_efficient = true; /* initialize WQ_AFFN_SYSTEM pods */ pt->pod_cpus = kcalloc(1, sizeof(pt->pod_cpus[0]), GFP_KERNEL); pt->pod_node = kcalloc(1, sizeof(pt->pod_node[0]), GFP_KERNEL); pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL); BUG_ON(!pt->pod_cpus || !pt->pod_node || !pt->cpu_pod); BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[0], GFP_KERNEL, NUMA_NO_NODE)); pt->nr_pods = 1; cpumask_copy(pt->pod_cpus[0], cpu_possible_mask); pt->pod_node[0] = NUMA_NO_NODE; pt->cpu_pod[0] = 0; /* initialize BH and CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; i = 0; for_each_bh_worker_pool(pool, cpu) { init_cpu_worker_pool(pool, cpu, std_nice[i]); pool->flags |= POOL_BH; init_irq_work(bh_pool_irq_work(pool), irq_work_fns[i]); i++; } i = 0; for_each_cpu_worker_pool(pool, cpu) init_cpu_worker_pool(pool, cpu, std_nice[i++]); } /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; unbound_std_wq_attrs[i] = attrs; /* * An ordered wq should have only one pwq as ordering is * guaranteed by max_active which is enforced by pwqs. */ BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; attrs->ordered = true; ordered_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", WQ_PERCPU, 0); system_percpu_wq = alloc_workqueue("events", WQ_PERCPU, 0); system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI | WQ_PERCPU, 0); system_long_wq = alloc_workqueue("events_long", WQ_PERCPU, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE); system_dfl_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE | WQ_PERCPU, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT | WQ_PERCPU, 0); system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_pwr_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT | WQ_PERCPU, 0); system_bh_wq = alloc_workqueue("events_bh", WQ_BH | WQ_PERCPU, 0); system_bh_highpri_wq = alloc_workqueue("events_bh_highpri", WQ_BH | WQ_HIGHPRI | WQ_PERCPU, 0); BUG_ON(!system_wq || !system_percpu_wq|| !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !system_dfl_wq || !system_power_efficient_wq || !system_freezable_power_efficient_wq || !system_bh_wq || !system_bh_highpri_wq); } static void __init wq_cpu_intensive_thresh_init(void) { unsigned long thresh; unsigned long bogo; pwq_release_worker = kthread_run_worker(0, "pool_workqueue_release"); BUG_ON(IS_ERR(pwq_release_worker)); /* if the user set it to a specific value, keep it */ if (wq_cpu_intensive_thresh_us != ULONG_MAX) return; /* * The default of 10ms is derived from the fact that most modern (as of * 2023) processors can do a lot in 10ms and that it's just below what * most consider human-perceivable. However, the kernel also runs on a * lot slower CPUs including microcontrollers where the threshold is way * too low. * * Let's scale up the threshold upto 1 second if BogoMips is below 4000. * This is by no means accurate but it doesn't have to be. The mechanism * is still useful even when the threshold is fully scaled up. Also, as * the reports would usually be applicable to everyone, some machines * operating on longer thresholds won't significantly diminish their * usefulness. */ thresh = 10 * USEC_PER_MSEC; /* see init/calibrate.c for lpj -> BogoMIPS calculation */ bogo = max_t(unsigned long, loops_per_jiffy / 500000 * HZ, 1); if (bogo < 4000) thresh = min_t(unsigned long, thresh * 4000 / bogo, USEC_PER_SEC); pr_debug("wq_cpu_intensive_thresh: lpj=%lu BogoMIPS=%lu thresh_us=%lu\n", loops_per_jiffy, bogo, thresh); wq_cpu_intensive_thresh_us = thresh; } /** * workqueue_init - bring workqueue subsystem fully online * * This is the second step of three-staged workqueue subsystem initialization * and invoked as soon as kthreads can be created and scheduled. Workqueues have * been created and work items queued on them, but there are no kworkers * executing the work items yet. Populate the worker pools with the initial * workers and enable future kworker creations. */ void __init workqueue_init(void) { struct workqueue_struct *wq; struct worker_pool *pool; int cpu, bkt; wq_cpu_intensive_thresh_init(); mutex_lock(&wq_pool_mutex); /* * Per-cpu pools created earlier could be missing node hint. Fix them * up. Also, create a rescuer for workqueues that requested it. */ for_each_possible_cpu(cpu) { for_each_bh_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); for_each_cpu_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); } list_for_each_entry(wq, &workqueues, list) { WARN(init_rescuer(wq), "workqueue: failed to create early rescuer for %s", wq->name); } mutex_unlock(&wq_pool_mutex); /* * Create the initial workers. A BH pool has one pseudo worker that * represents the shared BH execution context and thus doesn't get * affected by hotplug events. Create the BH pseudo workers for all * possible CPUs here. */ for_each_possible_cpu(cpu) for_each_bh_worker_pool(pool, cpu) BUG_ON(!create_worker(pool)); for_each_online_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->flags &= ~POOL_DISASSOCIATED; BUG_ON(!create_worker(pool)); } } hash_for_each(unbound_pool_hash, bkt, pool, hash_node) BUG_ON(!create_worker(pool)); wq_online = true; wq_watchdog_init(); } /* * Initialize @pt by first initializing @pt->cpu_pod[] with pod IDs according to * @cpu_shares_pod(). Each subset of CPUs that share a pod is assigned a unique * and consecutive pod ID. The rest of @pt is initialized accordingly. */ static void __init init_pod_type(struct wq_pod_type *pt, bool (*cpus_share_pod)(int, int)) { int cur, pre, cpu, pod; pt->nr_pods = 0; /* init @pt->cpu_pod[] according to @cpus_share_pod() */ pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL); BUG_ON(!pt->cpu_pod); for_each_possible_cpu(cur) { for_each_possible_cpu(pre) { if (pre >= cur) { pt->cpu_pod[cur] = pt->nr_pods++; break; } if (cpus_share_pod(cur, pre)) { pt->cpu_pod[cur] = pt->cpu_pod[pre]; break; } } } /* init the rest to match @pt->cpu_pod[] */ pt->pod_cpus = kcalloc(pt->nr_pods, sizeof(pt->pod_cpus[0]), GFP_KERNEL); pt->pod_node = kcalloc(pt->nr_pods, sizeof(pt->pod_node[0]), GFP_KERNEL); BUG_ON(!pt->pod_cpus || !pt->pod_node); for (pod = 0; pod < pt->nr_pods; pod++) BUG_ON(!zalloc_cpumask_var(&pt->pod_cpus[pod], GFP_KERNEL)); for_each_possible_cpu(cpu) { cpumask_set_cpu(cpu, pt->pod_cpus[pt->cpu_pod[cpu]]); pt->pod_node[pt->cpu_pod[cpu]] = cpu_to_node(cpu); } } static bool __init cpus_dont_share(int cpu0, int cpu1) { return false; } static bool __init cpus_share_smt(int cpu0, int cpu1) { #ifdef CONFIG_SCHED_SMT return cpumask_test_cpu(cpu0, cpu_smt_mask(cpu1)); #else return false; #endif } static bool __init cpus_share_numa(int cpu0, int cpu1) { return cpu_to_node(cpu0) == cpu_to_node(cpu1); } /** * workqueue_init_topology - initialize CPU pods for unbound workqueues * * This is the third step of three-staged workqueue subsystem initialization and * invoked after SMP and topology information are fully initialized. It * initializes the unbound CPU pods accordingly. */ void __init workqueue_init_topology(void) { struct workqueue_struct *wq; int cpu; init_pod_type(&wq_pod_types[WQ_AFFN_CPU], cpus_dont_share); init_pod_type(&wq_pod_types[WQ_AFFN_SMT], cpus_share_smt); init_pod_type(&wq_pod_types[WQ_AFFN_CACHE], cpus_share_cache); init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa); wq_topo_initialized = true; mutex_lock(&wq_pool_mutex); /* * Workqueues allocated earlier would have all CPUs sharing the default * worker pool. Explicitly call unbound_wq_update_pwq() on all workqueue * and CPU combinations to apply per-pod sharing. */ list_for_each_entry(wq, &workqueues, list) { for_each_online_cpu(cpu) unbound_wq_update_pwq(wq, cpu); if (wq->flags & WQ_UNBOUND) { mutex_lock(&wq->mutex); wq_update_node_max_active(wq, -1); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); } void __warn_flushing_systemwide_wq(void) { pr_warn("WARNING: Flushing system-wide workqueues will be prohibited in near future.\n"); dump_stack(); } EXPORT_SYMBOL(__warn_flushing_systemwide_wq); static int __init workqueue_unbound_cpus_setup(char *str) { if (cpulist_parse(str, &wq_cmdline_cpumask) < 0) { cpumask_clear(&wq_cmdline_cpumask); pr_warn("workqueue.unbound_cpus: incorrect CPU range, using default\n"); } return 1; } __setup("workqueue.unbound_cpus=", workqueue_unbound_cpus_setup); |
| 822 782 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BSEARCH_H #define _LINUX_BSEARCH_H #include <linux/types.h> static __always_inline void *__inline_bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { const char *pivot; int result; while (num > 0) { pivot = base + (num >> 1) * size; result = cmp(key, pivot); if (result == 0) return (void *)pivot; if (result > 0) { base = pivot + size; num--; } num >>= 1; } return NULL; } extern void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp); #endif /* _LINUX_BSEARCH_H */ |
| 444 442 444 444 444 443 73 121 289 312 313 | 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 |
| 373 374 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/blkdev.h> #include <linux/wait.h> #include <linux/rbtree.h> #include <linux/kthread.h> #include <linux/backing-dev.h> #include <linux/blk-cgroup.h> #include <linux/freezer.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/writeback.h> #include <linux/device.h> #include <trace/events/writeback.h> #include "internal.h" struct backing_dev_info noop_backing_dev_info; EXPORT_SYMBOL_GPL(noop_backing_dev_info); static const char *bdi_unknown_name = "(unknown)"; /* * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU * reader side locking. */ DEFINE_SPINLOCK(bdi_lock); static u64 bdi_id_cursor; static struct rb_root bdi_tree = RB_ROOT; LIST_HEAD(bdi_list); /* bdi_wq serves all asynchronous writeback tasks */ struct workqueue_struct *bdi_wq; #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #include <linux/seq_file.h> struct wb_stats { unsigned long nr_dirty; unsigned long nr_io; unsigned long nr_more_io; unsigned long nr_dirty_time; unsigned long nr_writeback; unsigned long nr_reclaimable; unsigned long nr_dirtied; unsigned long nr_written; unsigned long dirty_thresh; unsigned long wb_thresh; }; static struct dentry *bdi_debug_root; static void bdi_debug_init(void) { bdi_debug_root = debugfs_create_dir("bdi", NULL); } static void collect_wb_stats(struct wb_stats *stats, struct bdi_writeback *wb) { struct inode *inode; spin_lock(&wb->list_lock); list_for_each_entry(inode, &wb->b_dirty, i_io_list) stats->nr_dirty++; list_for_each_entry(inode, &wb->b_io, i_io_list) stats->nr_io++; list_for_each_entry(inode, &wb->b_more_io, i_io_list) stats->nr_more_io++; list_for_each_entry(inode, &wb->b_dirty_time, i_io_list) if (inode->i_state & I_DIRTY_TIME) stats->nr_dirty_time++; spin_unlock(&wb->list_lock); stats->nr_writeback += wb_stat(wb, WB_WRITEBACK); stats->nr_reclaimable += wb_stat(wb, WB_RECLAIMABLE); stats->nr_dirtied += wb_stat(wb, WB_DIRTIED); stats->nr_written += wb_stat(wb, WB_WRITTEN); stats->wb_thresh += wb_calc_thresh(wb, stats->dirty_thresh); } #ifdef CONFIG_CGROUP_WRITEBACK static void bdi_collect_stats(struct backing_dev_info *bdi, struct wb_stats *stats) { struct bdi_writeback *wb; rcu_read_lock(); list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { if (!wb_tryget(wb)) continue; collect_wb_stats(stats, wb); wb_put(wb); } rcu_read_unlock(); } #else static void bdi_collect_stats(struct backing_dev_info *bdi, struct wb_stats *stats) { collect_wb_stats(stats, &bdi->wb); } #endif static int bdi_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; unsigned long background_thresh; unsigned long dirty_thresh; struct wb_stats stats; unsigned long tot_bw; global_dirty_limits(&background_thresh, &dirty_thresh); memset(&stats, 0, sizeof(stats)); stats.dirty_thresh = dirty_thresh; bdi_collect_stats(bdi, &stats); tot_bw = atomic_long_read(&bdi->tot_write_bandwidth); seq_printf(m, "BdiWriteback: %10lu kB\n" "BdiReclaimable: %10lu kB\n" "BdiDirtyThresh: %10lu kB\n" "DirtyThresh: %10lu kB\n" "BackgroundThresh: %10lu kB\n" "BdiDirtied: %10lu kB\n" "BdiWritten: %10lu kB\n" "BdiWriteBandwidth: %10lu kBps\n" "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" "b_dirty_time: %10lu\n" "bdi_list: %10u\n" "state: %10lx\n", K(stats.nr_writeback), K(stats.nr_reclaimable), K(stats.wb_thresh), K(dirty_thresh), K(background_thresh), K(stats.nr_dirtied), K(stats.nr_written), K(tot_bw), stats.nr_dirty, stats.nr_io, stats.nr_more_io, stats.nr_dirty_time, !list_empty(&bdi->bdi_list), bdi->wb.state); return 0; } DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats); static void wb_stats_show(struct seq_file *m, struct bdi_writeback *wb, struct wb_stats *stats) { seq_printf(m, "WbCgIno: %10lu\n" "WbWriteback: %10lu kB\n" "WbReclaimable: %10lu kB\n" "WbDirtyThresh: %10lu kB\n" "WbDirtied: %10lu kB\n" "WbWritten: %10lu kB\n" "WbWriteBandwidth: %10lu kBps\n" "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" "b_dirty_time: %10lu\n" "state: %10lx\n\n", #ifdef CONFIG_CGROUP_WRITEBACK cgroup_ino(wb->memcg_css->cgroup), #else 1ul, #endif K(stats->nr_writeback), K(stats->nr_reclaimable), K(stats->wb_thresh), K(stats->nr_dirtied), K(stats->nr_written), K(wb->avg_write_bandwidth), stats->nr_dirty, stats->nr_io, stats->nr_more_io, stats->nr_dirty_time, wb->state); } static int cgwb_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; unsigned long background_thresh; unsigned long dirty_thresh; struct bdi_writeback *wb; global_dirty_limits(&background_thresh, &dirty_thresh); rcu_read_lock(); list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { struct wb_stats stats = { .dirty_thresh = dirty_thresh }; if (!wb_tryget(wb)) continue; collect_wb_stats(&stats, wb); /* * Calculate thresh of wb in writeback cgroup which is min of * thresh in global domain and thresh in cgroup domain. Drop * rcu lock because cgwb_calc_thresh may sleep in * cgroup_rstat_flush. We can do so here because we have a ref. */ if (mem_cgroup_wb_domain(wb)) { rcu_read_unlock(); stats.wb_thresh = min(stats.wb_thresh, cgwb_calc_thresh(wb)); rcu_read_lock(); } wb_stats_show(m, wb, &stats); wb_put(wb); } rcu_read_unlock(); return 0; } DEFINE_SHOW_ATTRIBUTE(cgwb_debug_stats); static void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root); debugfs_create_file("stats", 0444, bdi->debug_dir, bdi, &bdi_debug_stats_fops); debugfs_create_file("wb_stats", 0444, bdi->debug_dir, bdi, &cgwb_debug_stats_fops); } static void bdi_debug_unregister(struct backing_dev_info *bdi) { debugfs_remove_recursive(bdi->debug_dir); } #else /* CONFIG_DEBUG_FS */ static inline void bdi_debug_init(void) { } static inline void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { } static inline void bdi_debug_unregister(struct backing_dev_info *bdi) { } #endif /* CONFIG_DEBUG_FS */ static ssize_t read_ahead_kb_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned long read_ahead_kb; ssize_t ret; ret = kstrtoul(buf, 10, &read_ahead_kb); if (ret < 0) return ret; bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10); return count; } #define BDI_SHOW(name, expr) \ static ssize_t name##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct backing_dev_info *bdi = dev_get_drvdata(dev); \ \ return sysfs_emit(buf, "%lld\n", (long long)expr); \ } \ static DEVICE_ATTR_RW(name); BDI_SHOW(read_ahead_kb, K(bdi->ra_pages)) static ssize_t min_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_min_ratio(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(min_ratio, bdi->min_ratio / BDI_RATIO_SCALE) static ssize_t min_ratio_fine_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_min_ratio_no_scale(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(min_ratio_fine, bdi->min_ratio) static ssize_t max_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_max_ratio(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(max_ratio, bdi->max_ratio / BDI_RATIO_SCALE) static ssize_t max_ratio_fine_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_max_ratio_no_scale(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(max_ratio_fine, bdi->max_ratio) static ssize_t min_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%llu\n", bdi_get_min_bytes(bdi)); } static ssize_t min_bytes_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); u64 bytes; ssize_t ret; ret = kstrtoull(buf, 10, &bytes); if (ret < 0) return ret; ret = bdi_set_min_bytes(bdi, bytes); if (!ret) ret = count; return ret; } static DEVICE_ATTR_RW(min_bytes); static ssize_t max_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%llu\n", bdi_get_max_bytes(bdi)); } static ssize_t max_bytes_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); u64 bytes; ssize_t ret; ret = kstrtoull(buf, 10, &bytes); if (ret < 0) return ret; ret = bdi_set_max_bytes(bdi, bytes); if (!ret) ret = count; return ret; } static DEVICE_ATTR_RW(max_bytes); static ssize_t stable_pages_required_show(struct device *dev, struct device_attribute *attr, char *buf) { dev_warn_once(dev, "the stable_pages_required attribute has been removed. Use the stable_writes queue attribute instead.\n"); return sysfs_emit(buf, "%d\n", 0); } static DEVICE_ATTR_RO(stable_pages_required); static ssize_t strict_limit_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int strict_limit; ssize_t ret; ret = kstrtouint(buf, 10, &strict_limit); if (ret < 0) return ret; ret = bdi_set_strict_limit(bdi, strict_limit); if (!ret) ret = count; return ret; } static ssize_t strict_limit_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%d\n", !!(bdi->capabilities & BDI_CAP_STRICTLIMIT)); } static DEVICE_ATTR_RW(strict_limit); static struct attribute *bdi_dev_attrs[] = { &dev_attr_read_ahead_kb.attr, &dev_attr_min_ratio.attr, &dev_attr_min_ratio_fine.attr, &dev_attr_max_ratio.attr, &dev_attr_max_ratio_fine.attr, &dev_attr_min_bytes.attr, &dev_attr_max_bytes.attr, &dev_attr_stable_pages_required.attr, &dev_attr_strict_limit.attr, NULL, }; ATTRIBUTE_GROUPS(bdi_dev); static const struct class bdi_class = { .name = "bdi", .dev_groups = bdi_dev_groups, }; static __init int bdi_class_init(void) { int ret; ret = class_register(&bdi_class); if (ret) return ret; bdi_debug_init(); return 0; } postcore_initcall(bdi_class_init); static int __init default_bdi_init(void) { bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND | WQ_SYSFS, 0); if (!bdi_wq) return -ENOMEM; return 0; } subsys_initcall(default_bdi_init); static void wb_update_bandwidth_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, bw_dwork); wb_update_bandwidth(wb); } /* * Initial write bandwidth: 100 MB/s */ #define INIT_BW MB_TO_PAGES(100) static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, gfp_t gfp) { int err; memset(wb, 0, sizeof(*wb)); wb->bdi = bdi; wb->last_old_flush = jiffies; INIT_LIST_HEAD(&wb->b_dirty); INIT_LIST_HEAD(&wb->b_io); INIT_LIST_HEAD(&wb->b_more_io); INIT_LIST_HEAD(&wb->b_dirty_time); spin_lock_init(&wb->list_lock); atomic_set(&wb->writeback_inodes, 0); wb->bw_time_stamp = jiffies; wb->balanced_dirty_ratelimit = INIT_BW; wb->dirty_ratelimit = INIT_BW; wb->write_bandwidth = INIT_BW; wb->avg_write_bandwidth = INIT_BW; spin_lock_init(&wb->work_lock); INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn); err = fprop_local_init_percpu(&wb->completions, gfp); if (err) return err; err = percpu_counter_init_many(wb->stat, 0, gfp, NR_WB_STAT_ITEMS); if (err) fprop_local_destroy_percpu(&wb->completions); return err; } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb); /* * Remove bdi from the global list and shutdown any threads we have running */ static void wb_shutdown(struct bdi_writeback *wb) { /* Make sure nobody queues further work */ spin_lock_irq(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { spin_unlock_irq(&wb->work_lock); return; } spin_unlock_irq(&wb->work_lock); cgwb_remove_from_bdi_list(wb); /* * Drain work list and shutdown the delayed_work. !WB_registered * tells wb_workfn() that @wb is dying and its work_list needs to * be drained no matter what. */ mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); flush_delayed_work(&wb->bw_dwork); } static void wb_exit(struct bdi_writeback *wb) { WARN_ON(delayed_work_pending(&wb->dwork)); percpu_counter_destroy_many(wb->stat, NR_WB_STAT_ITEMS); fprop_local_destroy_percpu(&wb->completions); } #ifdef CONFIG_CGROUP_WRITEBACK #include <linux/memcontrol.h> /* * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, offline_cgwbs and * memcg->cgwb_list. bdi->cgwb_tree is also RCU protected. */ static DEFINE_SPINLOCK(cgwb_lock); static struct workqueue_struct *cgwb_release_wq; static LIST_HEAD(offline_cgwbs); static void cleanup_offline_cgwbs_workfn(struct work_struct *work); static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn); static void cgwb_free_rcu(struct rcu_head *rcu_head) { struct bdi_writeback *wb = container_of(rcu_head, struct bdi_writeback, rcu); percpu_ref_exit(&wb->refcnt); kfree(wb); } static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); struct backing_dev_info *bdi = wb->bdi; mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); css_put(wb->memcg_css); css_put(wb->blkcg_css); mutex_unlock(&wb->bdi->cgwb_release_mutex); /* triggers blkg destruction if no online users left */ blkcg_unpin_online(wb->blkcg_css); fprop_local_destroy_percpu(&wb->memcg_completions); spin_lock_irq(&cgwb_lock); list_del(&wb->offline_node); spin_unlock_irq(&cgwb_lock); wb_exit(wb); bdi_put(bdi); WARN_ON_ONCE(!list_empty(&wb->b_attached)); WARN_ON_ONCE(work_pending(&wb->switch_work)); call_rcu(&wb->rcu, cgwb_free_rcu); } static void cgwb_release(struct percpu_ref *refcnt) { struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback, refcnt); queue_work(cgwb_release_wq, &wb->release_work); } static void cgwb_kill(struct bdi_writeback *wb) { lockdep_assert_held(&cgwb_lock); WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id)); list_del(&wb->memcg_node); list_del(&wb->blkcg_node); list_add(&wb->offline_node, &offline_cgwbs); percpu_ref_kill(&wb->refcnt); } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) { spin_lock_irq(&cgwb_lock); list_del_rcu(&wb->bdi_node); spin_unlock_irq(&cgwb_lock); } static int cgwb_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct mem_cgroup *memcg; struct cgroup_subsys_state *blkcg_css; struct list_head *memcg_cgwb_list, *blkcg_cgwb_list; struct bdi_writeback *wb; unsigned long flags; int ret = 0; memcg = mem_cgroup_from_css(memcg_css); blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); memcg_cgwb_list = &memcg->cgwb_list; blkcg_cgwb_list = blkcg_get_cgwb_list(blkcg_css); /* look up again under lock and discard on blkcg mismatch */ spin_lock_irqsave(&cgwb_lock, flags); wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); if (wb && wb->blkcg_css != blkcg_css) { cgwb_kill(wb); wb = NULL; } spin_unlock_irqrestore(&cgwb_lock, flags); if (wb) goto out_put; /* need to create a new one */ wb = kmalloc(sizeof(*wb), gfp); if (!wb) { ret = -ENOMEM; goto out_put; } ret = wb_init(wb, bdi, gfp); if (ret) goto err_free; ret = percpu_ref_init(&wb->refcnt, cgwb_release, 0, gfp); if (ret) goto err_wb_exit; ret = fprop_local_init_percpu(&wb->memcg_completions, gfp); if (ret) goto err_ref_exit; wb->memcg_css = memcg_css; wb->blkcg_css = blkcg_css; INIT_LIST_HEAD(&wb->b_attached); INIT_WORK(&wb->switch_work, inode_switch_wbs_work_fn); init_llist_head(&wb->switch_wbs_ctxs); INIT_WORK(&wb->release_work, cgwb_release_workfn); set_bit(WB_registered, &wb->state); bdi_get(bdi); /* * The root wb determines the registered state of the whole bdi and * memcg_cgwb_list and blkcg_cgwb_list's next pointers indicate * whether they're still online. Don't link @wb if any is dead. * See wb_memcg_offline() and wb_blkcg_offline(). */ ret = -ENODEV; spin_lock_irqsave(&cgwb_lock, flags); if (test_bit(WB_registered, &bdi->wb.state) && blkcg_cgwb_list->next && memcg_cgwb_list->next) { /* we might have raced another instance of this function */ ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb); if (!ret) { list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); blkcg_pin_online(blkcg_css); css_get(memcg_css); css_get(blkcg_css); } } spin_unlock_irqrestore(&cgwb_lock, flags); if (ret) { if (ret == -EEXIST) ret = 0; goto err_fprop_exit; } goto out_put; err_fprop_exit: bdi_put(bdi); fprop_local_destroy_percpu(&wb->memcg_completions); err_ref_exit: percpu_ref_exit(&wb->refcnt); err_wb_exit: wb_exit(wb); err_free: kfree(wb); out_put: css_put(blkcg_css); return ret; } /** * wb_get_lookup - get wb for a given memcg * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) * * Try to get the wb for @memcg_css on @bdi. The returned wb has its * refcount incremented. * * This function uses css_get() on @memcg_css and thus expects its refcnt * to be positive on invocation. IOW, rcu_read_lock() protection on * @memcg_css isn't enough. try_get it before calling this function. * * A wb is keyed by its associated memcg. As blkcg implicitly enables * memcg on the default hierarchy, memcg association is guaranteed to be * more specific (equal or descendant to the associated blkcg) and thus can * identify both the memcg and blkcg associations. * * Because the blkcg associated with a memcg may change as blkcg is enabled * and disabled closer to root in the hierarchy, each wb keeps track of * both the memcg and blkcg associated with it and verifies the blkcg on * each lookup. On mismatch, the existing wb is discarded and a new one is * created. */ struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css) { struct bdi_writeback *wb; if (!memcg_css->parent) return &bdi->wb; rcu_read_lock(); wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); if (wb) { struct cgroup_subsys_state *blkcg_css; /* see whether the blkcg association has changed */ blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); if (unlikely(wb->blkcg_css != blkcg_css || !wb_tryget(wb))) wb = NULL; css_put(blkcg_css); } rcu_read_unlock(); return wb; } /** * wb_get_create - get wb for a given memcg, create if necessary * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) * @gfp: allocation mask to use * * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to * create one. See wb_get_lookup() for more details. */ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct bdi_writeback *wb; might_alloc(gfp); do { wb = wb_get_lookup(bdi, memcg_css); } while (!wb && !cgwb_create(bdi, memcg_css, gfp)); return wb; } static int cgwb_bdi_init(struct backing_dev_info *bdi) { int ret; INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); mutex_init(&bdi->cgwb_release_mutex); init_rwsem(&bdi->wb_switch_rwsem); ret = wb_init(&bdi->wb, bdi, GFP_KERNEL); if (!ret) { bdi->wb.memcg_css = &root_mem_cgroup->css; bdi->wb.blkcg_css = blkcg_root_css; INIT_WORK(&bdi->wb.switch_work, inode_switch_wbs_work_fn); init_llist_head(&bdi->wb.switch_wbs_ctxs); } return ret; } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { struct radix_tree_iter iter; void **slot; struct bdi_writeback *wb; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); spin_lock_irq(&cgwb_lock); radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); spin_unlock_irq(&cgwb_lock); mutex_lock(&bdi->cgwb_release_mutex); spin_lock_irq(&cgwb_lock); while (!list_empty(&bdi->wb_list)) { wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); spin_unlock_irq(&cgwb_lock); wb_shutdown(wb); spin_lock_irq(&cgwb_lock); } spin_unlock_irq(&cgwb_lock); mutex_unlock(&bdi->cgwb_release_mutex); } /* * cleanup_offline_cgwbs_workfn - try to release dying cgwbs * * Try to release dying cgwbs by switching attached inodes to the nearest * living ancestor's writeback. Processed wbs are placed at the end * of the list to guarantee the forward progress. */ static void cleanup_offline_cgwbs_workfn(struct work_struct *work) { struct bdi_writeback *wb; LIST_HEAD(processed); spin_lock_irq(&cgwb_lock); while (!list_empty(&offline_cgwbs)) { wb = list_first_entry(&offline_cgwbs, struct bdi_writeback, offline_node); list_move(&wb->offline_node, &processed); /* * If wb is dirty, cleaning up the writeback by switching * attached inodes will result in an effective removal of any * bandwidth restrictions, which isn't the goal. Instead, * it can be postponed until the next time, when all io * will be likely completed. If in the meantime some inodes * will get re-dirtied, they should be eventually switched to * a new cgwb. */ if (wb_has_dirty_io(wb)) continue; if (!wb_tryget(wb)) continue; spin_unlock_irq(&cgwb_lock); while (cleanup_offline_cgwb(wb)) cond_resched(); spin_lock_irq(&cgwb_lock); wb_put(wb); } if (!list_empty(&processed)) list_splice_tail(&processed, &offline_cgwbs); spin_unlock_irq(&cgwb_lock); } /** * wb_memcg_offline - kill all wb's associated with a memcg being offlined * @memcg: memcg being offlined * * Also prevents creation of any new wb's associated with @memcg. */ void wb_memcg_offline(struct mem_cgroup *memcg) { struct list_head *memcg_cgwb_list = &memcg->cgwb_list; struct bdi_writeback *wb, *next; spin_lock_irq(&cgwb_lock); list_for_each_entry_safe(wb, next, memcg_cgwb_list, memcg_node) cgwb_kill(wb); memcg_cgwb_list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); queue_work(system_unbound_wq, &cleanup_offline_cgwbs_work); } /** * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined * @css: blkcg being offlined * * Also prevents creation of any new wb's associated with @blkcg. */ void wb_blkcg_offline(struct cgroup_subsys_state *css) { struct bdi_writeback *wb, *next; struct list_head *list = blkcg_get_cgwb_list(css); spin_lock_irq(&cgwb_lock); list_for_each_entry_safe(wb, next, list, blkcg_node) cgwb_kill(wb); list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); } static void cgwb_bdi_register(struct backing_dev_info *bdi) { spin_lock_irq(&cgwb_lock); list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); spin_unlock_irq(&cgwb_lock); } static int __init cgwb_init(void) { /* * There can be many concurrent release work items overwhelming * system_wq. Put them in a separate wq and limit concurrency. * There's no point in executing many of these in parallel. */ cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1); if (!cgwb_release_wq) return -ENOMEM; return 0; } subsys_initcall(cgwb_init); #else /* CONFIG_CGROUP_WRITEBACK */ static int cgwb_bdi_init(struct backing_dev_info *bdi) { return wb_init(&bdi->wb, bdi, GFP_KERNEL); } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { } static void cgwb_bdi_register(struct backing_dev_info *bdi) { list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) { list_del_rcu(&wb->bdi_node); } #endif /* CONFIG_CGROUP_WRITEBACK */ int bdi_init(struct backing_dev_info *bdi) { bdi->dev = NULL; kref_init(&bdi->refcnt); bdi->min_ratio = 0; bdi->max_ratio = 100 * BDI_RATIO_SCALE; bdi->max_prop_frac = FPROP_FRAC_BASE; INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); init_waitqueue_head(&bdi->wb_waitq); bdi->last_bdp_sleep = jiffies; return cgwb_bdi_init(bdi); } struct backing_dev_info *bdi_alloc(int node_id) { struct backing_dev_info *bdi; bdi = kzalloc_node(sizeof(*bdi), GFP_KERNEL, node_id); if (!bdi) return NULL; if (bdi_init(bdi)) { kfree(bdi); return NULL; } bdi->capabilities = BDI_CAP_WRITEBACK; bdi->ra_pages = VM_READAHEAD_PAGES; bdi->io_pages = VM_READAHEAD_PAGES; timer_setup(&bdi->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); return bdi; } EXPORT_SYMBOL(bdi_alloc); static struct rb_node **bdi_lookup_rb_node(u64 id, struct rb_node **parentp) { struct rb_node **p = &bdi_tree.rb_node; struct rb_node *parent = NULL; struct backing_dev_info *bdi; lockdep_assert_held(&bdi_lock); while (*p) { parent = *p; bdi = rb_entry(parent, struct backing_dev_info, rb_node); if (bdi->id > id) p = &(*p)->rb_left; else if (bdi->id < id) p = &(*p)->rb_right; else break; } if (parentp) *parentp = parent; return p; } /** * bdi_get_by_id - lookup and get bdi from its id * @id: bdi id to lookup * * Find bdi matching @id and get it. Returns NULL if the matching bdi * doesn't exist or is already unregistered. */ struct backing_dev_info *bdi_get_by_id(u64 id) { struct backing_dev_info *bdi = NULL; struct rb_node **p; spin_lock_bh(&bdi_lock); p = bdi_lookup_rb_node(id, NULL); if (*p) { bdi = rb_entry(*p, struct backing_dev_info, rb_node); bdi_get(bdi); } spin_unlock_bh(&bdi_lock); return bdi; } int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) { struct device *dev; struct rb_node *parent, **p; if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); dev = device_create(&bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); if (IS_ERR(dev)) return PTR_ERR(dev); cgwb_bdi_register(bdi); bdi->dev = dev; bdi_debug_register(bdi, dev_name(dev)); set_bit(WB_registered, &bdi->wb.state); spin_lock_bh(&bdi_lock); bdi->id = ++bdi_id_cursor; p = bdi_lookup_rb_node(bdi->id, &parent); rb_link_node(&bdi->rb_node, parent, p); rb_insert_color(&bdi->rb_node, &bdi_tree); list_add_tail_rcu(&bdi->bdi_list, &bdi_list); spin_unlock_bh(&bdi_lock); trace_writeback_bdi_register(bdi); return 0; } int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); ret = bdi_register_va(bdi, fmt, args); va_end(args); return ret; } EXPORT_SYMBOL(bdi_register); void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner) { WARN_ON_ONCE(bdi->owner); bdi->owner = owner; get_device(owner); } /* * Remove bdi from bdi_list, and ensure that it is no longer visible */ static void bdi_remove_from_list(struct backing_dev_info *bdi) { spin_lock_bh(&bdi_lock); rb_erase(&bdi->rb_node, &bdi_tree); list_del_rcu(&bdi->bdi_list); spin_unlock_bh(&bdi_lock); synchronize_rcu_expedited(); } void bdi_unregister(struct backing_dev_info *bdi) { timer_delete_sync(&bdi->laptop_mode_wb_timer); /* make sure nobody finds us on the bdi_list anymore */ bdi_remove_from_list(bdi); wb_shutdown(&bdi->wb); cgwb_bdi_unregister(bdi); /* * If this BDI's min ratio has been set, use bdi_set_min_ratio() to * update the global bdi_min_ratio. */ if (bdi->min_ratio) bdi_set_min_ratio(bdi, 0); if (bdi->dev) { bdi_debug_unregister(bdi); device_unregister(bdi->dev); bdi->dev = NULL; } if (bdi->owner) { put_device(bdi->owner); bdi->owner = NULL; } } EXPORT_SYMBOL(bdi_unregister); static void release_bdi(struct kref *ref) { struct backing_dev_info *bdi = container_of(ref, struct backing_dev_info, refcnt); WARN_ON_ONCE(test_bit(WB_registered, &bdi->wb.state)); WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); kfree(bdi); } void bdi_put(struct backing_dev_info *bdi) { kref_put(&bdi->refcnt, release_bdi); } EXPORT_SYMBOL(bdi_put); struct backing_dev_info *inode_to_bdi(struct inode *inode) { struct super_block *sb; if (!inode) return &noop_backing_dev_info; sb = inode->i_sb; #ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) return I_BDEV(inode)->bd_disk->bdi; #endif return sb->s_bdi; } EXPORT_SYMBOL(inode_to_bdi); const char *bdi_dev_name(struct backing_dev_info *bdi) { if (!bdi || !bdi->dev) return bdi_unknown_name; return bdi->dev_name; } EXPORT_SYMBOL_GPL(bdi_dev_name); |
| 524 524 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/blkdev.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blk-cgroup.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/sort.h> #include <linux/completion.h> #include <linux/suspend.h> #include <linux/zswap.h> #include <linux/plist.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> #include "swap_table.h" #include "internal.h" #include "swap.h" static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); static void swap_entries_free(struct swap_info_struct *si, struct swap_cluster_info *ci, swp_entry_t entry, unsigned int nr_pages); static void swap_range_alloc(struct swap_info_struct *si, unsigned int nr_entries); static bool folio_swapcache_freeable(struct folio *folio); static void move_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, struct list_head *list, enum swap_cluster_flags new_flags); static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; unsigned long swapfile_maximum_size; #ifdef CONFIG_MIGRATION bool swap_migration_ad_supported; #endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by folio_alloc_swap() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but folio_alloc_swap() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; static struct kmem_cache *swap_table_cachep; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); struct percpu_swap_cluster { struct swap_info_struct *si[SWAP_NR_ORDERS]; unsigned long offset[SWAP_NR_ORDERS]; local_lock_t lock; }; static DEFINE_PER_CPU(struct percpu_swap_cluster, percpu_swap_cluster) = { .si = { NULL }, .offset = { SWAP_ENTRY_INVALID }, .lock = INIT_LOCAL_LOCK(), }; /* May return NULL on invalid type, caller must check for NULL return */ static struct swap_info_struct *swap_type_to_info(int type) { if (type >= MAX_SWAPFILES) return NULL; return READ_ONCE(swap_info[type]); /* rcu_dereference() */ } /* May return NULL on invalid entry, caller must check for NULL return */ static struct swap_info_struct *swap_entry_to_info(swp_entry_t entry) { return swap_type_to_info(swp_type(entry)); } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* * Use the second highest bit of inuse_pages counter as the indicator * if one swap device is on the available plist, so the atomic can * still be updated arithmetically while having special data embedded. * * inuse_pages counter is the only thing indicating if a device should * be on avail_lists or not (except swapon / swapoff). By embedding the * off-list bit in the atomic counter, updates no longer need any lock * to check the list status. * * This bit will be set if the device is not on the plist and not * usable, will be cleared if the device is on the plist. */ #define SWAP_USAGE_OFFLIST_BIT (1UL << (BITS_PER_TYPE(atomic_t) - 2)) #define SWAP_USAGE_COUNTER_MASK (~SWAP_USAGE_OFFLIST_BIT) static long swap_usage_in_pages(struct swap_info_struct *si) { return atomic_long_read(&si->inuse_pages) & SWAP_USAGE_COUNTER_MASK; } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full */ #define TTRS_FULL 0x4 static bool swap_only_has_cache(struct swap_info_struct *si, unsigned long offset, int nr_pages) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; do { VM_BUG_ON(!(*map & SWAP_HAS_CACHE)); if (*map != SWAP_HAS_CACHE) return false; } while (++map < map_end); return true; } static bool swap_is_last_map(struct swap_info_struct *si, unsigned long offset, int nr_pages, bool *has_cache) { unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; unsigned char count = *map; if (swap_count(count) != 1 && swap_count(count) != SWAP_MAP_SHMEM) return false; while (++map < map_end) { if (*map != count) return false; } *has_cache = !!(count & SWAP_HAS_CACHE); return true; } /* * returns number of pages in the folio that backs the swap entry. If positive, * the folio was reclaimed. If negative, the folio was not reclaimed. If 0, no * folio was associated with the swap entry. */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { const swp_entry_t entry = swp_entry(si->type, offset); struct swap_cluster_info *ci; struct folio *folio; int ret, nr_pages; bool need_reclaim; again: folio = swap_cache_get_folio(entry); if (!folio) return 0; nr_pages = folio_nr_pages(folio); ret = -nr_pages; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming folios. So we hold a folio lock * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use folio_free_swap() with explicit folio_lock() * in usual operations. */ if (!folio_trylock(folio)) goto out; /* * Offset could point to the middle of a large folio, or folio * may no longer point to the expected offset before it's locked. */ if (!folio_matches_swap_entry(folio, entry)) { folio_unlock(folio); folio_put(folio); goto again; } offset = swp_offset(folio->swap); need_reclaim = ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !folio_mapped(folio)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(folio))); if (!need_reclaim || !folio_swapcache_freeable(folio)) goto out_unlock; /* * It's safe to delete the folio from swap cache only if the folio's * swap_map is HAS_CACHE only, which means the slots have no page table * reference or pending writeback, and can't be allocated to others. */ ci = swap_cluster_lock(si, offset); need_reclaim = swap_only_has_cache(si, offset, nr_pages); swap_cluster_unlock(ci); if (!need_reclaim) goto out_unlock; swap_cache_del_folio(folio); folio_set_dirty(folio); ret = nr_pages; out_unlock: folio_unlock(folio); out: folio_put(folio); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_folio_sector(struct folio *folio) { struct swap_info_struct *sis = __swap_entry_to_info(folio->swap); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = swp_offset(folio->swap); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO)) break; se = next_se(se); } } #define LATENCY_LIMIT 256 static inline bool cluster_is_empty(struct swap_cluster_info *info) { return info->count == 0; } static inline bool cluster_is_discard(struct swap_cluster_info *info) { return info->flags == CLUSTER_FLAG_DISCARD; } static inline bool cluster_table_is_alloced(struct swap_cluster_info *ci) { return rcu_dereference_protected(ci->table, lockdep_is_held(&ci->lock)); } static inline bool cluster_is_usable(struct swap_cluster_info *ci, int order) { if (unlikely(ci->flags > CLUSTER_FLAG_USABLE)) return false; if (!cluster_table_is_alloced(ci)) return false; if (!order) return true; return cluster_is_empty(ci) || order == ci->order; } static inline unsigned int cluster_index(struct swap_info_struct *si, struct swap_cluster_info *ci) { return ci - si->cluster_info; } static inline unsigned int cluster_offset(struct swap_info_struct *si, struct swap_cluster_info *ci) { return cluster_index(si, ci) * SWAPFILE_CLUSTER; } static struct swap_table *swap_table_alloc(gfp_t gfp) { struct folio *folio; if (!SWP_TABLE_USE_PAGE) return kmem_cache_zalloc(swap_table_cachep, gfp); folio = folio_alloc(gfp | __GFP_ZERO, 0); if (folio) return folio_address(folio); return NULL; } static void swap_table_free_folio_rcu_cb(struct rcu_head *head) { struct folio *folio; folio = page_folio(container_of(head, struct page, rcu_head)); folio_put(folio); } static void swap_table_free(struct swap_table *table) { if (!SWP_TABLE_USE_PAGE) { kmem_cache_free(swap_table_cachep, table); return; } call_rcu(&(folio_page(virt_to_folio(table), 0)->rcu_head), swap_table_free_folio_rcu_cb); } static void swap_cluster_free_table(struct swap_cluster_info *ci) { unsigned int ci_off; struct swap_table *table; /* Only empty cluster's table is allow to be freed */ lockdep_assert_held(&ci->lock); VM_WARN_ON_ONCE(!cluster_is_empty(ci)); for (ci_off = 0; ci_off < SWAPFILE_CLUSTER; ci_off++) VM_WARN_ON_ONCE(!swp_tb_is_null(__swap_table_get(ci, ci_off))); table = (void *)rcu_dereference_protected(ci->table, true); rcu_assign_pointer(ci->table, NULL); swap_table_free(table); } /* * Allocate swap table for one cluster. Attempt an atomic allocation first, * then fallback to sleeping allocation. */ static struct swap_cluster_info * swap_cluster_alloc_table(struct swap_info_struct *si, struct swap_cluster_info *ci) { struct swap_table *table; /* * Only cluster isolation from the allocator does table allocation. * Swap allocator uses percpu clusters and holds the local lock. */ lockdep_assert_held(&ci->lock); lockdep_assert_held(&this_cpu_ptr(&percpu_swap_cluster)->lock); /* The cluster must be free and was just isolated from the free list. */ VM_WARN_ON_ONCE(ci->flags || !cluster_is_empty(ci)); table = swap_table_alloc(__GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN); if (table) { rcu_assign_pointer(ci->table, table); return ci; } /* * Try a sleep allocation. Each isolated free cluster may cause * a sleep allocation, but there is a limited number of them, so * the potential recursive allocation is limited. */ spin_unlock(&ci->lock); if (!(si->flags & SWP_SOLIDSTATE)) spin_unlock(&si->global_cluster_lock); local_unlock(&percpu_swap_cluster.lock); table = swap_table_alloc(__GFP_HIGH | __GFP_NOMEMALLOC | GFP_KERNEL); /* * Back to atomic context. We might have migrated to a new CPU with a * usable percpu cluster. But just keep using the isolated cluster to * make things easier. Migration indicates a slight change of workload * so using a new free cluster might not be a bad idea, and the worst * could happen with ignoring the percpu cluster is fragmentation, * which is acceptable since this fallback and race is rare. */ local_lock(&percpu_swap_cluster.lock); if (!(si->flags & SWP_SOLIDSTATE)) spin_lock(&si->global_cluster_lock); spin_lock(&ci->lock); /* Nothing except this helper should touch a dangling empty cluster. */ if (WARN_ON_ONCE(cluster_table_is_alloced(ci))) { if (table) swap_table_free(table); return ci; } if (!table) { move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE); spin_unlock(&ci->lock); return NULL; } rcu_assign_pointer(ci->table, table); return ci; } static void move_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, struct list_head *list, enum swap_cluster_flags new_flags) { VM_WARN_ON(ci->flags == new_flags); BUILD_BUG_ON(1 << sizeof(ci->flags) * BITS_PER_BYTE < CLUSTER_FLAG_MAX); lockdep_assert_held(&ci->lock); spin_lock(&si->lock); if (ci->flags == CLUSTER_FLAG_NONE) list_add_tail(&ci->list, list); else list_move_tail(&ci->list, list); spin_unlock(&si->lock); ci->flags = new_flags; } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); move_cluster(si, ci, &si->discard_clusters, CLUSTER_FLAG_DISCARD); schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { swap_cluster_free_table(ci); move_cluster(si, ci, &si->free_clusters, CLUSTER_FLAG_FREE); ci->order = 0; } /* * Isolate and lock the first cluster that is not contented on a list, * clean its flag before taken off-list. Cluster flag must be in sync * with list status, so cluster updaters can always know the cluster * list status without touching si lock. * * Note it's possible that all clusters on a list are contented so * this returns NULL for an non-empty list. */ static struct swap_cluster_info *isolate_lock_cluster( struct swap_info_struct *si, struct list_head *list, int order) { struct swap_cluster_info *ci, *found = NULL; spin_lock(&si->lock); list_for_each_entry(ci, list, list) { if (!spin_trylock(&ci->lock)) continue; /* We may only isolate and clear flags of following lists */ VM_BUG_ON(!ci->flags); VM_BUG_ON(ci->flags > CLUSTER_FLAG_USABLE && ci->flags != CLUSTER_FLAG_FULL); list_del(&ci->list); ci->flags = CLUSTER_FLAG_NONE; found = ci; break; } spin_unlock(&si->lock); if (found && !cluster_table_is_alloced(found)) { /* Only an empty free cluster's swap table can be freed. */ VM_WARN_ON_ONCE(list != &si->free_clusters); VM_WARN_ON_ONCE(!cluster_is_empty(found)); return swap_cluster_alloc_table(si, found); } return found; } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. Discard cluster is a bit special as * they don't participate in allocation or reclaim, so clusters marked as * CLUSTER_FLAG_DISCARD must remain off-list or on discard list. */ static bool swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *ci; bool ret = false; unsigned int idx; spin_lock(&si->lock); while (!list_empty(&si->discard_clusters)) { ci = list_first_entry(&si->discard_clusters, struct swap_cluster_info, list); /* * Delete the cluster from list to prepare for discard, but keep * the CLUSTER_FLAG_DISCARD flag, percpu_swap_cluster could be * pointing to it, or ran into by relocate_cluster. */ list_del(&ci->list); idx = cluster_index(si, ci); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&ci->lock); /* * Discard is done, clear its flags as it's off-list, then * return the cluster to allocation list. */ ci->flags = CLUSTER_FLAG_NONE; __free_cluster(si, ci); spin_unlock(&ci->lock); ret = true; spin_lock(&si->lock); } spin_unlock(&si->lock); return ret; } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); swap_do_scheduled_discard(si); } static void swap_users_ref_free(struct percpu_ref *ref) { struct swap_info_struct *si; si = container_of(ref, struct swap_info_struct, users); complete(&si->comp); } /* * Must be called after freeing if ci->count == 0, moves the cluster to free * or discard list. */ static void free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(ci->count != 0); VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE); lockdep_assert_held(&ci->lock); /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, ci); return; } __free_cluster(si, ci); } /* * Must be called after freeing if ci->count != 0, moves the cluster to * nonfull list. */ static void partial_free_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { VM_BUG_ON(!ci->count || ci->count == SWAPFILE_CLUSTER); lockdep_assert_held(&ci->lock); if (ci->flags != CLUSTER_FLAG_NONFULL) move_cluster(si, ci, &si->nonfull_clusters[ci->order], CLUSTER_FLAG_NONFULL); } /* * Must be called after allocation, moves the cluster to full or frag list. * Note: allocation doesn't acquire si lock, and may drop the ci lock for * reclaim, so the cluster could be any where when called. */ static void relocate_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci) { lockdep_assert_held(&ci->lock); /* Discard cluster must remain off-list or on discard list */ if (cluster_is_discard(ci)) return; if (!ci->count) { if (ci->flags != CLUSTER_FLAG_FREE) free_cluster(si, ci); } else if (ci->count != SWAPFILE_CLUSTER) { if (ci->flags != CLUSTER_FLAG_FRAG) move_cluster(si, ci, &si->frag_clusters[ci->order], CLUSTER_FLAG_FRAG); } else { if (ci->flags != CLUSTER_FLAG_FULL) move_cluster(si, ci, &si->full_clusters, CLUSTER_FLAG_FULL); } } /* * The cluster corresponding to page_nr will be used. The cluster will not be * added to free cluster list and its usage counter will be increased by 1. * Only used for initialization. */ static int inc_cluster_info_page(struct swap_info_struct *si, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; struct swap_table *table; struct swap_cluster_info *ci; ci = cluster_info + idx; if (!ci->table) { table = swap_table_alloc(GFP_KERNEL); if (!table) return -ENOMEM; rcu_assign_pointer(ci->table, table); } ci->count++; VM_BUG_ON(ci->count > SWAPFILE_CLUSTER); VM_BUG_ON(ci->flags); return 0; } static bool cluster_reclaim_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned long end) { unsigned char *map = si->swap_map; unsigned long offset = start; int nr_reclaim; spin_unlock(&ci->lock); do { switch (READ_ONCE(map[offset])) { case 0: offset++; break; case SWAP_HAS_CACHE: nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); if (nr_reclaim > 0) offset += nr_reclaim; else goto out; break; default: goto out; } } while (offset < end); out: spin_lock(&ci->lock); /* * Recheck the range no matter reclaim succeeded or not, the slot * could have been be freed while we are not holding the lock. */ for (offset = start; offset < end; offset++) if (READ_ONCE(map[offset])) return false; return true; } static bool cluster_scan_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long start, unsigned int nr_pages, bool *need_reclaim) { unsigned long offset, end = start + nr_pages; unsigned char *map = si->swap_map; if (cluster_is_empty(ci)) return true; for (offset = start; offset < end; offset++) { switch (READ_ONCE(map[offset])) { case 0: continue; case SWAP_HAS_CACHE: if (!vm_swap_full()) return false; *need_reclaim = true; continue; default: return false; } } return true; } /* * Currently, the swap table is not used for count tracking, just * do a sanity check here to ensure nothing leaked, so the swap * table should be empty upon freeing. */ static void swap_cluster_assert_table_empty(struct swap_cluster_info *ci, unsigned int start, unsigned int nr) { unsigned int ci_off = start % SWAPFILE_CLUSTER; unsigned int ci_end = ci_off + nr; unsigned long swp_tb; if (IS_ENABLED(CONFIG_DEBUG_VM)) { do { swp_tb = __swap_table_get(ci, ci_off); VM_WARN_ON_ONCE(!swp_tb_is_null(swp_tb)); } while (++ci_off < ci_end); } } static bool cluster_alloc_range(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned int start, unsigned char usage, unsigned int order) { unsigned int nr_pages = 1 << order; lockdep_assert_held(&ci->lock); if (!(si->flags & SWP_WRITEOK)) return false; /* * The first allocation in a cluster makes the * cluster exclusive to this order */ if (cluster_is_empty(ci)) ci->order = order; memset(si->swap_map + start, usage, nr_pages); swap_cluster_assert_table_empty(ci, start, nr_pages); swap_range_alloc(si, nr_pages); ci->count += nr_pages; return true; } /* Try use a new cluster for current CPU and allocate from it. */ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, struct swap_cluster_info *ci, unsigned long offset, unsigned int order, unsigned char usage) { unsigned int next = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID; unsigned long start = ALIGN_DOWN(offset, SWAPFILE_CLUSTER); unsigned long end = min(start + SWAPFILE_CLUSTER, si->max); unsigned int nr_pages = 1 << order; bool need_reclaim, ret; lockdep_assert_held(&ci->lock); if (end < nr_pages || ci->count + nr_pages > SWAPFILE_CLUSTER) goto out; for (end -= nr_pages; offset <= end; offset += nr_pages) { need_reclaim = false; if (!cluster_scan_range(si, ci, offset, nr_pages, &need_reclaim)) continue; if (need_reclaim) { ret = cluster_reclaim_range(si, ci, offset, offset + nr_pages); /* * Reclaim drops ci->lock and cluster could be used * by another order. Not checking flag as off-list * cluster has no flag set, and change of list * won't cause fragmentation. */ if (!cluster_is_usable(ci, order)) goto out; if (cluster_is_empty(ci)) offset = start; /* Reclaim failed but cluster is usable, try next */ if (!ret) continue; } if (!cluster_alloc_range(si, ci, offset, usage, order)) break; found = offset; offset += nr_pages; if (ci->count < SWAPFILE_CLUSTER && offset <= end) next = offset; break; } out: relocate_cluster(si, ci); swap_cluster_unlock(ci); if (si->flags & SWP_SOLIDSTATE) { this_cpu_write(percpu_swap_cluster.offset[order], next); this_cpu_write(percpu_swap_cluster.si[order], si); } else { si->global_cluster->next[order] = next; } return found; } static unsigned int alloc_swap_scan_list(struct swap_info_struct *si, struct list_head *list, unsigned int order, unsigned char usage, bool scan_all) { unsigned int found = SWAP_ENTRY_INVALID; do { struct swap_cluster_info *ci = isolate_lock_cluster(si, list, order); unsigned long offset; if (!ci) break; offset = cluster_offset(si, ci); found = alloc_swap_scan_cluster(si, ci, offset, order, usage); if (found) break; } while (scan_all); return found; } static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force) { long to_scan = 1; unsigned long offset, end; struct swap_cluster_info *ci; unsigned char *map = si->swap_map; int nr_reclaim; if (force) to_scan = swap_usage_in_pages(si) / SWAPFILE_CLUSTER; while ((ci = isolate_lock_cluster(si, &si->full_clusters, 0))) { offset = cluster_offset(si, ci); end = min(si->max, offset + SWAPFILE_CLUSTER); to_scan--; while (offset < end) { if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) { spin_unlock(&ci->lock); nr_reclaim = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&ci->lock); if (nr_reclaim) { offset += abs(nr_reclaim); continue; } } offset++; } /* in case no swap cache is reclaimed */ if (ci->flags == CLUSTER_FLAG_NONE) relocate_cluster(si, ci); swap_cluster_unlock(ci); if (to_scan <= 0) break; } } static void swap_reclaim_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, reclaim_work); swap_reclaim_full_clusters(si, true); } /* * Try to allocate swap entries with specified order and try set a new * cluster for current CPU too. */ static unsigned long cluster_alloc_swap_entry(struct swap_info_struct *si, int order, unsigned char usage) { struct swap_cluster_info *ci; unsigned int offset = SWAP_ENTRY_INVALID, found = SWAP_ENTRY_INVALID; /* * Swapfile is not block device so unable * to allocate large entries. */ if (order && !(si->flags & SWP_BLKDEV)) return 0; if (!(si->flags & SWP_SOLIDSTATE)) { /* Serialize HDD SWAP allocation for each device. */ spin_lock(&si->global_cluster_lock); offset = si->global_cluster->next[order]; if (offset == SWAP_ENTRY_INVALID) goto new_cluster; ci = swap_cluster_lock(si, offset); /* Cluster could have been used by another order */ if (cluster_is_usable(ci, order)) { if (cluster_is_empty(ci)) offset = cluster_offset(si, ci); found = alloc_swap_scan_cluster(si, ci, offset, order, usage); } else { swap_cluster_unlock(ci); } if (found) goto done; } new_cluster: /* * If the device need discard, prefer new cluster over nonfull * to spread out the writes. */ if (si->flags & SWP_PAGE_DISCARD) { found = alloc_swap_scan_list(si, &si->free_clusters, order, usage, false); if (found) goto done; } if (order < PMD_ORDER) { found = alloc_swap_scan_list(si, &si->nonfull_clusters[order], order, usage, true); if (found) goto done; } if (!(si->flags & SWP_PAGE_DISCARD)) { found = alloc_swap_scan_list(si, &si->free_clusters, order, usage, false); if (found) goto done; } /* Try reclaim full clusters if free and nonfull lists are drained */ if (vm_swap_full()) swap_reclaim_full_clusters(si, false); if (order < PMD_ORDER) { /* * Scan only one fragment cluster is good enough. Order 0 * allocation will surely success, and large allocation * failure is not critical. Scanning one cluster still * keeps the list rotated and reclaimed (for HAS_CACHE). */ found = alloc_swap_scan_list(si, &si->frag_clusters[order], order, usage, false); if (found) goto done; } /* * We don't have free cluster but have some clusters in discarding, * do discard now and reclaim them. */ if ((si->flags & SWP_PAGE_DISCARD) && swap_do_scheduled_discard(si)) goto new_cluster; if (order) goto done; /* Order 0 stealing from higher order */ for (int o = 1; o < SWAP_NR_ORDERS; o++) { /* * Clusters here have at least one usable slots and can't fail order 0 * allocation, but reclaim may drop si->lock and race with another user. */ found = alloc_swap_scan_list(si, &si->frag_clusters[o], 0, usage, true); if (found) goto done; found = alloc_swap_scan_list(si, &si->nonfull_clusters[o], 0, usage, true); if (found) goto done; } done: if (!(si->flags & SWP_SOLIDSTATE)) spin_unlock(&si->global_cluster_lock); return found; } /* SWAP_USAGE_OFFLIST_BIT can only be set by this helper. */ static void del_from_avail_list(struct swap_info_struct *si, bool swapoff) { int nid; unsigned long pages; spin_lock(&swap_avail_lock); if (swapoff) { /* * Forcefully remove it. Clear the SWP_WRITEOK flags for * swapoff here so it's synchronized by both si->lock and * swap_avail_lock, to ensure the result can be seen by * add_to_avail_list. */ lockdep_assert_held(&si->lock); si->flags &= ~SWP_WRITEOK; atomic_long_or(SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); } else { /* * If not called by swapoff, take it off-list only if it's * full and SWAP_USAGE_OFFLIST_BIT is not set (strictly * si->inuse_pages == pages), any concurrent slot freeing, * or device already removed from plist by someone else * will make this return false. */ pages = si->pages; if (!atomic_long_try_cmpxchg(&si->inuse_pages, &pages, pages | SWAP_USAGE_OFFLIST_BIT)) goto skip; } for_each_node(nid) plist_del(&si->avail_lists[nid], &swap_avail_heads[nid]); skip: spin_unlock(&swap_avail_lock); } /* SWAP_USAGE_OFFLIST_BIT can only be cleared by this helper. */ static void add_to_avail_list(struct swap_info_struct *si, bool swapon) { int nid; long val; unsigned long pages; spin_lock(&swap_avail_lock); /* Corresponding to SWP_WRITEOK clearing in del_from_avail_list */ if (swapon) { lockdep_assert_held(&si->lock); si->flags |= SWP_WRITEOK; } else { if (!(READ_ONCE(si->flags) & SWP_WRITEOK)) goto skip; } if (!(atomic_long_read(&si->inuse_pages) & SWAP_USAGE_OFFLIST_BIT)) goto skip; val = atomic_long_fetch_and_relaxed(~SWAP_USAGE_OFFLIST_BIT, &si->inuse_pages); /* * When device is full and device is on the plist, only one updater will * see (inuse_pages == si->pages) and will call del_from_avail_list. If * that updater happen to be here, just skip adding. */ pages = si->pages; if (val == pages) { /* Just like the cmpxchg in del_from_avail_list */ if (atomic_long_try_cmpxchg(&si->inuse_pages, &pages, pages | SWAP_USAGE_OFFLIST_BIT)) goto skip; } for_each_node(nid) plist_add(&si->avail_lists[nid], &swap_avail_heads[nid]); skip: spin_unlock(&swap_avail_lock); } /* * swap_usage_add / swap_usage_sub of each slot are serialized by ci->lock * within each cluster, so the total contribution to the global counter should * always be positive and cannot exceed the total number of usable slots. */ static bool swap_usage_add(struct swap_info_struct *si, unsigned int nr_entries) { long val = atomic_long_add_return_relaxed(nr_entries, &si->inuse_pages); /* * If device is full, and SWAP_USAGE_OFFLIST_BIT is not set, * remove it from the plist. */ if (unlikely(val == si->pages)) { del_from_avail_list(si, false); return true; } return false; } static void swap_usage_sub(struct swap_info_struct *si, unsigned int nr_entries) { long val = atomic_long_sub_return_relaxed(nr_entries, &si->inuse_pages); /* * If device is not full, and SWAP_USAGE_OFFLIST_BIT is set, * add it to the plist. */ if (unlikely(val & SWAP_USAGE_OFFLIST_BIT)) add_to_avail_list(si, false); } static void swap_range_alloc(struct swap_info_struct *si, unsigned int nr_entries) { if (swap_usage_add(si, nr_entries)) { if (vm_swap_full()) schedule_work(&si->reclaim_work); } atomic_long_sub(nr_entries, &nr_swap_pages); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long begin = offset; unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); unsigned int i; /* * Use atomic clear_bit operations only on zeromap instead of non-atomic * bitmap_clear to prevent adjacent bits corruption due to simultaneous writes. */ for (i = 0; i < nr_entries; i++) { clear_bit(offset + i, si->zeromap); zswap_invalidate(swp_entry(si->type, offset + i)); } if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { arch_swap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } __swap_cache_clear_shadow(swp_entry(si->type, begin), nr_entries); /* * Make sure that try_to_unuse() observes si->inuse_pages reaching 0 * only after the above cleanups are done. */ smp_wmb(); atomic_long_add(nr_entries, &nr_swap_pages); swap_usage_sub(si, nr_entries); } static bool get_swap_device_info(struct swap_info_struct *si) { if (!percpu_ref_tryget_live(&si->users)) return false; /* * Guarantee the si->users are checked before accessing other * fields of swap_info_struct, and si->flags (SWP_WRITEOK) is * up to dated. * * Paired with the spin_unlock() after setup_swap_info() in * enable_swap_info(), and smp_wmb() in swapoff. */ smp_rmb(); return true; } /* * Fast path try to get swap entries with specified order from current * CPU's swap entry pool (a cluster). */ static bool swap_alloc_fast(swp_entry_t *entry, int order) { struct swap_cluster_info *ci; struct swap_info_struct *si; unsigned int offset, found = SWAP_ENTRY_INVALID; /* * Once allocated, swap_info_struct will never be completely freed, * so checking it's liveness by get_swap_device_info is enough. */ si = this_cpu_read(percpu_swap_cluster.si[order]); offset = this_cpu_read(percpu_swap_cluster.offset[order]); if (!si || !offset || !get_swap_device_info(si)) return false; ci = swap_cluster_lock(si, offset); if (cluster_is_usable(ci, order)) { if (cluster_is_empty(ci)) offset = cluster_offset(si, ci); found = alloc_swap_scan_cluster(si, ci, offset, order, SWAP_HAS_CACHE); if (found) *entry = swp_entry(si->type, found); } else { swap_cluster_unlock(ci); } put_swap_device(si); return !!found; } /* Rotate the device and switch to a new cluster */ static bool swap_alloc_slow(swp_entry_t *entry, int order) { int node; unsigned long offset; struct swap_info_struct *si, *next; node = numa_node_id(); spin_lock(&swap_avail_lock); start_over: plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* Rotate the device and switch to a new cluster */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); if (get_swap_device_info(si)) { offset = cluster_alloc_swap_entry(si, order, SWAP_HAS_CACHE); put_swap_device(si); if (offset) { *entry = swp_entry(si->type, offset); return true; } if (order) return false; } spin_lock(&swap_avail_lock); /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map_slots() can drop the si->lock, * multiple callers probably all tried to get a page from the * same si and it filled up before we could get one; or, the si * filled up between us dropping swap_avail_lock and taking * si->lock. Since we dropped the swap_avail_lock, the * swap_avail_head list may have been modified; so if next is * still in the swap_avail_head list then try it, otherwise * start over if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); return false; } /** * folio_alloc_swap - allocate swap space for a folio * @folio: folio we want to move to swap * @gfp: gfp mask for shadow nodes * * Allocate swap space for the folio and add the folio to the * swap cache. * * Context: Caller needs to hold the folio lock. * Return: Whether the folio was added to the swap cache. */ int folio_alloc_swap(struct folio *folio, gfp_t gfp) { unsigned int order = folio_order(folio); unsigned int size = 1 << order; swp_entry_t entry = {}; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio); if (order) { /* * Reject large allocation when THP_SWAP is disabled, * the caller should split the folio and try again. */ if (!IS_ENABLED(CONFIG_THP_SWAP)) return -EAGAIN; /* * Allocation size should never exceed cluster size * (HPAGE_PMD_SIZE). */ if (size > SWAPFILE_CLUSTER) { VM_WARN_ON_ONCE(1); return -EINVAL; } } local_lock(&percpu_swap_cluster.lock); if (!swap_alloc_fast(&entry, order)) swap_alloc_slow(&entry, order); local_unlock(&percpu_swap_cluster.lock); /* Need to call this even if allocation failed, for MEMCG_SWAP_FAIL. */ if (mem_cgroup_try_charge_swap(folio, entry)) goto out_free; if (!entry.val) return -ENOMEM; swap_cache_add_folio(folio, entry, NULL); return 0; out_free: put_swap_folio(folio, entry); return -ENOMEM; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swap_entry_to_info(entry); if (!si) goto bad_nofile; if (data_race(!(si->flags & SWP_USED))) goto bad_device; offset = swp_offset(entry); if (offset >= si->max) goto bad_offset; if (data_race(!si->swap_map[swp_offset(entry)])) goto bad_free; return si; bad_free: pr_err("%s: %s%08lx\n", __func__, Unused_offset, entry.val); goto out; bad_offset: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); goto out; bad_device: pr_err("%s: %s%08lx\n", __func__, Unused_file, entry.val); goto out; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; } static unsigned char swap_entry_put_locked(struct swap_info_struct *si, struct swap_cluster_info *ci, swp_entry_t entry, unsigned char usage) { unsigned long offset = swp_offset(entry); unsigned char count; unsigned char has_cache; count = si->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(si, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; if (usage) WRITE_ONCE(si->swap_map[offset], usage); else swap_entries_free(si, ci, entry, 1); return usage; } /* * When we get a swap entry, if there aren't some other ways to * prevent swapoff, such as the folio in swap cache is locked, RCU * reader side is locked, etc., the swap entry may become invalid * because of swapoff. Then, we need to enclose all swap related * functions with get_swap_device() and put_swap_device(), unless the * swap functions call get/put_swap_device() by themselves. * * RCU reader side lock (including any spinlock) is sufficient to * prevent swapoff, because synchronize_rcu() is called in swapoff() * before freeing data structures. * * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * Notice that swapoff or swapoff+swapon can still happen before the * percpu_ref_tryget_live() in get_swap_device() or after the * percpu_ref_put() in put_swap_device() if there isn't any other way * to prevent swapoff. The caller must be prepared for that. For * example, the following situation is possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swap_entry_to_info(entry); if (!si) goto bad_nofile; if (!get_swap_device_info(si)) goto out; offset = swp_offset(entry); if (offset >= si->max) goto put_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; put_out: pr_err("%s: %s%08lx\n", __func__, Bad_offset, entry.val); percpu_ref_put(&si->users); return NULL; } static void swap_entries_put_cache(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); struct swap_cluster_info *ci; ci = swap_cluster_lock(si, offset); if (swap_only_has_cache(si, offset, nr)) { swap_entries_free(si, ci, entry, nr); } else { for (int i = 0; i < nr; i++, entry.val++) swap_entry_put_locked(si, ci, entry, SWAP_HAS_CACHE); } swap_cluster_unlock(ci); } static bool swap_entries_put_map(struct swap_info_struct *si, swp_entry_t entry, int nr) { unsigned long offset = swp_offset(entry); struct swap_cluster_info *ci; bool has_cache = false; unsigned char count; int i; if (nr <= 1) goto fallback; count = swap_count(data_race(si->swap_map[offset])); if (count != 1 && count != SWAP_MAP_SHMEM) goto fallback; ci = swap_cluster_lock(si, offset); if (!swap_is_last_map(si, offset, nr, &has_cache)) { goto locked_fallback; } if (!has_cache) swap_entries_free(si, ci, entry, nr); else for (i = 0; i < nr; i++) WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE); swap_cluster_unlock(ci); return has_cache; fallback: ci = swap_cluster_lock(si, offset); locked_fallback: for (i = 0; i < nr; i++, entry.val++) { count = swap_entry_put_locked(si, ci, entry, 1); if (count == SWAP_HAS_CACHE) has_cache = true; } swap_cluster_unlock(ci); return has_cache; } /* * Only functions with "_nr" suffix are able to free entries spanning * cross multi clusters, so ensure the range is within a single cluster * when freeing entries with functions without "_nr" suffix. */ static bool swap_entries_put_map_nr(struct swap_info_struct *si, swp_entry_t entry, int nr) { int cluster_nr, cluster_rest; unsigned long offset = swp_offset(entry); bool has_cache = false; cluster_rest = SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER; while (nr) { cluster_nr = min(nr, cluster_rest); has_cache |= swap_entries_put_map(si, entry, cluster_nr); cluster_rest = SWAPFILE_CLUSTER; nr -= cluster_nr; entry.val += cluster_nr; } return has_cache; } /* * Check if it's the last ref of swap entry in the freeing path. * Qualified vlaue includes 1, SWAP_HAS_CACHE or SWAP_MAP_SHMEM. */ static inline bool __maybe_unused swap_is_last_ref(unsigned char count) { return (count == SWAP_HAS_CACHE) || (count == 1) || (count == SWAP_MAP_SHMEM); } /* * Drop the last ref of swap entries, caller have to ensure all entries * belong to the same cgroup and cluster. */ static void swap_entries_free(struct swap_info_struct *si, struct swap_cluster_info *ci, swp_entry_t entry, unsigned int nr_pages) { unsigned long offset = swp_offset(entry); unsigned char *map = si->swap_map + offset; unsigned char *map_end = map + nr_pages; /* It should never free entries across different clusters */ VM_BUG_ON(ci != __swap_offset_to_cluster(si, offset + nr_pages - 1)); VM_BUG_ON(cluster_is_empty(ci)); VM_BUG_ON(ci->count < nr_pages); ci->count -= nr_pages; do { VM_BUG_ON(!swap_is_last_ref(*map)); *map = 0; } while (++map < map_end); mem_cgroup_uncharge_swap(entry, nr_pages); swap_range_free(si, offset, nr_pages); swap_cluster_assert_table_empty(ci, offset, nr_pages); if (!ci->count) free_cluster(si, ci); else partial_free_cluster(si, ci); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free_nr(swp_entry_t entry, int nr_pages) { int nr; struct swap_info_struct *sis; unsigned long offset = swp_offset(entry); sis = _swap_info_get(entry); if (!sis) return; while (nr_pages) { nr = min_t(int, nr_pages, SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); swap_entries_put_map(sis, swp_entry(sis->type, offset), nr); offset += nr; nr_pages -= nr; } } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_folio(struct folio *folio, swp_entry_t entry) { struct swap_info_struct *si; int size = 1 << swap_entry_order(folio_order(folio)); si = _swap_info_get(entry); if (!si) return; swap_entries_put_cache(si, entry, size); } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si = __swap_entry_to_info(entry); pgoff_t offset = swp_offset(entry); return swap_count(si->swap_map[offset]); } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry) { pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; int count; ci = swap_cluster_lock(si, offset); count = swap_count(si->swap_map[offset]); swap_cluster_unlock(ci); return !!count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; si = _swap_info_get(entry); if (!si) return 0; offset = swp_offset(entry); ci = swap_cluster_lock(si, offset); count = swap_count(si->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_local_page(page); tmp_count = map[offset]; kunmap_local(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: swap_cluster_unlock(ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry, int order) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned int nr_pages = 1 << order; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, nr_pages); int i; bool ret = false; ci = swap_cluster_lock(si, offset); if (nr_pages == 1) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < nr_pages; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: swap_cluster_unlock(ci); return ret; } static bool folio_swapped(struct folio *folio) { swp_entry_t entry = folio->swap; struct swap_info_struct *si = _swap_info_get(entry); if (!si) return false; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!folio_test_large(folio))) return swap_entry_swapped(si, entry); return swap_page_trans_huge_swapped(si, entry, folio_order(folio)); } static bool folio_swapcache_freeable(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio_test_swapcache(folio)) return false; if (folio_test_writeback(folio)) return false; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to folio_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a folio which has already been recorded in the * image as a clean swapcache folio, and then reuse its swap for * another page of the image. On waking from hibernation, the * original folio might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return false; return true; } /** * folio_free_swap() - Free the swap space used for this folio. * @folio: The folio to remove. * * If swap is getting full, or if there are no more mappings of this folio, * then call folio_free_swap to free its swap space. * * Return: true if we were able to release the swap space. */ bool folio_free_swap(struct folio *folio) { if (!folio_swapcache_freeable(folio)) return false; if (folio_swapped(folio)) return false; swap_cache_del_folio(folio); folio_set_dirty(folio); return true; } /** * free_swap_and_cache_nr() - Release reference on range of swap entries and * reclaim their cache if no more references remain. * @entry: First entry of range. * @nr: Number of entries in range. * * For each swap entry in the contiguous range, release a reference. If any swap * entries become free, try to reclaim their underlying folios, if present. The * offset range is defined by [entry.offset, entry.offset + nr). */ void free_swap_and_cache_nr(swp_entry_t entry, int nr) { const unsigned long start_offset = swp_offset(entry); const unsigned long end_offset = start_offset + nr; struct swap_info_struct *si; bool any_only_cache = false; unsigned long offset; si = get_swap_device(entry); if (!si) return; if (WARN_ON(end_offset > si->max)) goto out; /* * First free all entries in the range. */ any_only_cache = swap_entries_put_map_nr(si, entry, nr); /* * Short-circuit the below loop if none of the entries had their * reference drop to zero. */ if (!any_only_cache) goto out; /* * Now go back over the range trying to reclaim the swap cache. */ for (offset = start_offset; offset < end_offset; offset += nr) { nr = 1; if (READ_ONCE(si->swap_map[offset]) == SWAP_HAS_CACHE) { /* * Folios are always naturally aligned in swap so * advance forward to the next boundary. Zero means no * folio was found for the swap entry, so advance by 1 * in this case. Negative value means folio was found * but could not be reclaimed. Here we can still advance * to the next boundary. */ nr = __try_to_reclaim_swap(si, offset, TTRS_UNMAPPED | TTRS_FULL); if (nr == 0) nr = 1; else if (nr < 0) nr = -nr; nr = ALIGN(offset + 1, nr) - offset; } } out: put_swap_device(si); } #ifdef CONFIG_HIBERNATION swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_info(type); unsigned long offset; swp_entry_t entry = {0}; if (!si) goto fail; /* This is called for allocating swap entry, not cache */ if (get_swap_device_info(si)) { if (si->flags & SWP_WRITEOK) { /* * Grab the local lock to be complaint * with swap table allocation. */ local_lock(&percpu_swap_cluster.lock); offset = cluster_alloc_swap_entry(si, 0, 1); local_unlock(&percpu_swap_cluster.lock); if (offset) { entry = swp_entry(si->type, offset); atomic_long_dec(&nr_swap_pages); } } put_swap_device(si); } fail: return entry; } /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset) { int type; if (!device) return -1; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (device == sis->bdev->bd_dev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { spin_unlock(&swap_lock); return type; } } } spin_unlock(&swap_lock); return -ENODEV; } int find_first_swap(dev_t *device) { int type; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; *device = sis->bdev->bd_dev; spin_unlock(&swap_lock); return type; } spin_unlock(&swap_lock); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct swap_info_struct *si = swap_type_to_info(type); struct swap_extent *se; if (!si || !(si->flags & SWP_WRITEOK)) return 0; se = offset_to_swap_extent(si, offset); return se->start_block + (offset - se->start_page); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= swap_usage_in_pages(sis); } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_flags(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct folio *folio) { struct page *page; struct folio *swapcache; spinlock_t *ptl; pte_t *pte, new_pte, old_pte; bool hwpoisoned = false; int ret = 1; /* * If the folio is removed from swap cache by others, continue to * unuse other PTEs. try_to_unuse may try again if we missed this one. */ if (!folio_matches_swap_entry(folio, entry)) return 0; swapcache = folio; folio = ksm_might_need_to_copy(folio, vma, addr); if (unlikely(!folio)) return -ENOMEM; else if (unlikely(folio == ERR_PTR(-EHWPOISON))) { hwpoisoned = true; folio = swapcache; } page = folio_file_page(folio, swp_offset(entry)); if (PageHWPoison(page)) hwpoisoned = true; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte || !pte_same_as_swp(ptep_get(pte), swp_entry_to_pte(entry)))) { ret = 0; goto out; } old_pte = ptep_get(pte); if (unlikely(hwpoisoned || !folio_test_uptodate(folio))) { swp_entry_t swp_entry; dec_mm_counter(vma->vm_mm, MM_SWAPENTS); if (hwpoisoned) { swp_entry = make_hwpoison_entry(page); } else { swp_entry = make_poisoned_swp_entry(); } new_pte = swp_entry_to_pte(swp_entry); ret = 0; goto setpte; } /* * Some architectures may have to restore extra metadata to the page * when reading from swap. This metadata may be indexed by swap entry * so this must be called before swap_free(). */ arch_swap_restore(folio_swap(entry, folio), folio); dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); folio_get(folio); if (folio == swapcache) { rmap_t rmap_flags = RMAP_NONE; /* * See do_swap_page(): writeback would be problematic. * However, we do a folio_wait_writeback() just before this * call and have the folio locked. */ VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); if (pte_swp_exclusive(old_pte)) rmap_flags |= RMAP_EXCLUSIVE; /* * We currently only expect small !anon folios, which are either * fully exclusive or fully shared. If we ever get large folios * here, we have to be careful. */ if (!folio_test_anon(folio)) { VM_WARN_ON_ONCE(folio_test_large(folio)); VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); folio_add_new_anon_rmap(folio, vma, addr, rmap_flags); } else { folio_add_anon_rmap_pte(folio, page, vma, addr, rmap_flags); } } else { /* ksm created a completely new copy */ folio_add_new_anon_rmap(folio, vma, addr, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); } new_pte = pte_mkold(mk_pte(page, vma->vm_page_prot)); if (pte_swp_soft_dirty(old_pte)) new_pte = pte_mksoft_dirty(new_pte); if (pte_swp_uffd_wp(old_pte)) new_pte = pte_mkuffd_wp(new_pte); setpte: set_pte_at(vma->vm_mm, addr, pte, new_pte); swap_free(entry); out: if (pte) pte_unmap_unlock(pte, ptl); if (folio != swapcache) { folio_unlock(folio); folio_put(folio); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type) { pte_t *pte = NULL; struct swap_info_struct *si; si = swap_info[type]; do { struct folio *folio; unsigned long offset; unsigned char swp_count; swp_entry_t entry; int ret; pte_t ptent; if (!pte++) { pte = pte_offset_map(pmd, addr); if (!pte) break; } ptent = ptep_get_lockless(pte); if (!is_swap_pte(ptent)) continue; entry = pte_to_swp_entry(ptent); if (swp_type(entry) != type) continue; offset = swp_offset(entry); pte_unmap(pte); pte = NULL; folio = swap_cache_get_folio(entry); if (!folio) { struct vm_fault vmf = { .vma = vma, .address = addr, .real_address = addr, .pmd = pmd, }; folio = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); } if (!folio) { swp_count = READ_ONCE(si->swap_map[offset]); if (swp_count == 0 || swp_count == SWAP_MAP_BAD) continue; return -ENOMEM; } folio_lock(folio); folio_wait_writeback(folio); ret = unuse_pte(vma, pmd, addr, entry, folio); if (ret < 0) { folio_unlock(folio); folio_put(folio); return ret; } folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } while (addr += PAGE_SIZE, addr != end); if (pte) pte_unmap(pte); return 0; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); if (check_stable_address_space(mm)) goto unlock; for_each_vma(vmi, vma) { if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { ret = unuse_vma(vma, type); if (ret) break; } cond_resched(); } unlock: mmap_read_unlock(mm); return ret; } /* * Scan swap_map from current position to next entry still in use. * Return 0 if there are no inuse entries after prev till end of * the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct folio *folio; swp_entry_t entry; unsigned int i; if (!swap_usage_in_pages(si)) goto success; retry: retval = shmem_unuse(type); if (retval) return retval; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (swap_usage_in_pages(si) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); return retval; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (swap_usage_in_pages(si) && !signal_pending(current) && (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); folio = swap_cache_get_folio(entry); if (!folio) continue; /* * It is conceivable that a racing task removed this folio from * swap cache just before we acquired the page lock. The folio * might even be back in swap cache on another swap area. But * that is okay, folio_free_swap() only removes stale folios. */ folio_lock(folio); folio_wait_writeback(folio); folio_free_swap(folio); folio_unlock(folio); folio_put(folio); } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() * above fails, that mm is likely to be freeing swap from * exit_mmap(), which proceeds at its own independent pace; * and even shmem_writeout() could have been preempted after * folio_alloc_swap(), temporarily hiding that swap. It's easy * and robust (though cpu-intensive) just to keep retrying. */ if (swap_usage_in_pages(si)) { if (!signal_pending(current)) goto retry; return -EINTR; } success: /* * Make sure that further cleanups after try_to_unuse() returns happen * after swap_range_free() reduces si->inuse_pages to 0. */ smp_mb(); return 0; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_usage_in_pages(swap_info[type])) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. A rbtree of swap extents is * built at swapon time and is then used at swap_writepage/swap_read_folio * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent rbtree operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into a rbtree, in PAGE_SIZE chunks. If some stray * blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the rbtree. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret < 0) return ret; sis->flags |= SWP_ACTIVATED; if ((sis->flags & SWP_FS_OPS) && sio_pool_init() != 0) { destroy_swap_extents(sis); return -ENOMEM; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *si) { struct block_device *bdev; if (si->bdev) bdev = si->bdev; else bdev = si->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { int i; if (prio >= 0) si->prio = prio; else si->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ si->list.prio = -si->prio; for_each_node(i) { if (si->prio >= 0) si->avail_lists[i].prio = -si->prio; else { if (swap_node(si) == i) si->avail_lists[i].prio = 1; else si->avail_lists[i].prio = -si->prio; } } si->swap_map = swap_map; si->cluster_info = cluster_info; si->zeromap = zeromap; } static void _enable_swap_info(struct swap_info_struct *si) { atomic_long_add(si->pages, &nr_swap_pages); total_swap_pages += si->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for folio_alloc_swap(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&si->list, &swap_active_head); /* Add back to available list */ add_to_avail_list(si, true); } static void enable_swap_info(struct swap_info_struct *si, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *zeromap) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, prio, swap_map, cluster_info, zeromap); spin_unlock(&si->lock); spin_unlock(&swap_lock); /* * Finished initializing swap device, now it's safe to reference it. */ percpu_ref_resurrect(&si->users); spin_lock(&swap_lock); spin_lock(&si->lock); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *si) { spin_lock(&swap_lock); spin_lock(&si->lock); setup_swap_info(si, si->prio, si->swap_map, si->cluster_info, si->zeromap); _enable_swap_info(si); spin_unlock(&si->lock); spin_unlock(&swap_lock); } /* * Called after clearing SWP_WRITEOK, ensures cluster_alloc_range * see the updated flags, so there will be no more allocations. */ static void wait_for_allocation(struct swap_info_struct *si) { unsigned long offset; unsigned long end = ALIGN(si->max, SWAPFILE_CLUSTER); struct swap_cluster_info *ci; BUG_ON(si->flags & SWP_WRITEOK); for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) { ci = swap_cluster_lock(si, offset); swap_cluster_unlock(ci); } } static void free_cluster_info(struct swap_cluster_info *cluster_info, unsigned long maxpages) { struct swap_cluster_info *ci; int i, nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); if (!cluster_info) return; for (i = 0; i < nr_clusters; i++) { ci = cluster_info + i; /* Cluster with bad marks count will have a remaining table */ spin_lock(&ci->lock); if (rcu_dereference_protected(ci->table, true)) { ci->count = 0; swap_cluster_free_table(ci); } spin_unlock(&ci->lock); } kvfree(cluster_info); } /* * Called after swap device's reference count is dead, so * neither scan nor allocation will use it. */ static void flush_percpu_swap_cluster(struct swap_info_struct *si) { int cpu, i; struct swap_info_struct **pcp_si; for_each_possible_cpu(cpu) { pcp_si = per_cpu_ptr(percpu_swap_cluster.si, cpu); /* * Invalidate the percpu swap cluster cache, si->users * is dead, so no new user will point to it, just flush * any existing user. */ for (i = 0; i < SWAP_NR_ORDERS; i++) cmpxchg(&pcp_si[i], si, NULL); } } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; unsigned long *zeromap; struct swap_cluster_info *cluster_info; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; unsigned int maxpages; int err, found = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p, true); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; spin_unlock(&p->lock); spin_unlock(&swap_lock); wait_for_allocation(p); set_current_oom_origin(); err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); goto out_dput; } /* * Wait for swap operations protected by get/put_swap_device() * to complete. Because of synchronize_rcu() here, all swap * operations protected by RCU reader side lock (including any * spinlock) will be waited too. This makes it easy to * prevent folio_test_swapcache() and the following swap cache * operations from racing with swapoff. */ percpu_ref_kill(&p->users); synchronize_rcu(); wait_for_completion(&p->comp); flush_work(&p->discard_work); flush_work(&p->reclaim_work); flush_percpu_swap_cluster(p); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || !bdev_nonrot(p->bdev)) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); swap_file = p->swap_file; p->swap_file = NULL; swap_map = p->swap_map; p->swap_map = NULL; zeromap = p->zeromap; p->zeromap = NULL; maxpages = p->max; cluster_info = p->cluster_info; p->max = 0; p->cluster_info = NULL; spin_unlock(&p->lock); spin_unlock(&swap_lock); arch_swap_invalidate_area(p->type); zswap_swapoff(p->type); mutex_unlock(&swapon_mutex); kfree(p->global_cluster); p->global_cluster = NULL; vfree(swap_map); kvfree(zeromap); free_cluster_info(cluster_info, maxpages); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); inode = mapping->host; inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; unsigned long bytes, inuse; if (si == SEQ_START_TOKEN) { seq_puts(swap, "Filename\t\t\t\tType\t\tSize\t\tUsed\t\tPriority\n"); return 0; } bytes = K(si->pages); inuse = K(swap_usage_in_pages(si)); file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%lu\t%s%lu\t%s%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", bytes, bytes < 10000000 ? "\t" : "", inuse, inuse < 10000000 ? "\t" : "", si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct proc_ops swaps_proc_ops = { .proc_flags = PROC_ENTRY_PERMANENT, .proc_open = swaps_open, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_release = seq_release, .proc_poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &swaps_proc_ops); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (percpu_ref_init(&p->users, swap_users_ref_free, PERCPU_REF_INIT_DEAD, GFP_KERNEL)) { kvfree(p); return ERR_PTR(-ENOMEM); } spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); percpu_ref_exit(&p->users); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; /* * Publish the swap_info_struct after initializing it. * Note that kvzalloc() above zeroes all its fields. */ smp_store_release(&swap_info[type], p); /* rcu_assign_pointer() */ nr_swapfiles++; } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); if (defer) { percpu_ref_exit(&defer->users); kvfree(defer); } spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); atomic_long_set(&p->inuse_pages, SWAP_USAGE_OFFLIST_BIT); init_completion(&p->comp); return p; } static int claim_swapfile(struct swap_info_struct *si, struct inode *inode) { if (S_ISBLK(inode->i_mode)) { si->bdev = I_BDEV(inode); /* * Zoned block devices contain zones that have a sequential * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ if (bdev_is_zoned(si->bdev)) return -EINVAL; si->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { si->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *si, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianness hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", K(maxpages), K(last_page)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } static int setup_swap_map(struct swap_info_struct *si, union swap_header *swap_header, unsigned char *swap_map, unsigned long maxpages) { unsigned long i; swap_map[0] = SWAP_MAP_BAD; /* omit header page */ for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; si->pages--; } } if (!si->pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } return 0; } static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si, union swap_header *swap_header, unsigned long maxpages) { unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); struct swap_cluster_info *cluster_info; int err = -ENOMEM; unsigned long i; cluster_info = kvcalloc(nr_clusters, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) goto err; for (i = 0; i < nr_clusters; i++) spin_lock_init(&cluster_info[i].lock); if (!(si->flags & SWP_SOLIDSTATE)) { si->global_cluster = kmalloc(sizeof(*si->global_cluster), GFP_KERNEL); if (!si->global_cluster) goto err_free; for (i = 0; i < SWAP_NR_ORDERS; i++) si->global_cluster->next[i] = SWAP_ENTRY_INVALID; spin_lock_init(&si->global_cluster_lock); } /* * Mark unusable pages as unavailable. The clusters aren't * marked free yet, so no list operations are involved yet. * * See setup_swap_map(): header page, bad pages, * and the EOF part of the last cluster. */ err = inc_cluster_info_page(si, cluster_info, 0); if (err) goto err; for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr >= maxpages) continue; err = inc_cluster_info_page(si, cluster_info, page_nr); if (err) goto err; } for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) { err = inc_cluster_info_page(si, cluster_info, i); if (err) goto err; } INIT_LIST_HEAD(&si->free_clusters); INIT_LIST_HEAD(&si->full_clusters); INIT_LIST_HEAD(&si->discard_clusters); for (i = 0; i < SWAP_NR_ORDERS; i++) { INIT_LIST_HEAD(&si->nonfull_clusters[i]); INIT_LIST_HEAD(&si->frag_clusters[i]); } for (i = 0; i < nr_clusters; i++) { struct swap_cluster_info *ci = &cluster_info[i]; if (ci->count) { ci->flags = CLUSTER_FLAG_NONFULL; list_add_tail(&ci->list, &si->nonfull_clusters[0]); } else { ci->flags = CLUSTER_FLAG_FREE; list_add_tail(&ci->list, &si->free_clusters); } } return cluster_info; err_free: free_cluster_info(cluster_info, maxpages); err: return ERR_PTR(err); } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *si; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; struct dentry *dentry; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; unsigned long *zeromap = NULL; struct swap_cluster_info *cluster_info = NULL; struct folio *folio = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; si = alloc_swap_info(); if (IS_ERR(si)) return PTR_ERR(si); INIT_WORK(&si->discard_work, swap_discard_work); INIT_WORK(&si->reclaim_work, swap_reclaim_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR | O_LARGEFILE | O_EXCL, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } si->swap_file = swap_file; mapping = swap_file->f_mapping; dentry = swap_file->f_path.dentry; inode = mapping->host; error = claim_swapfile(si, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (d_unlinked(dentry) || cant_mount(dentry)) { error = -ENOENT; goto bad_swap_unlock_inode; } if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * The swap subsystem needs a major overhaul to support this. * It doesn't work yet so just disable it for now. */ if (mapping_min_folio_order(mapping) > 0) { error = -EINVAL; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { error = -EINVAL; goto bad_swap_unlock_inode; } folio = read_mapping_folio(mapping, 0, swap_file); if (IS_ERR(folio)) { error = PTR_ERR(folio); goto bad_swap_unlock_inode; } swap_header = kmap_local_folio(folio, 0); maxpages = read_swap_header(si, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } si->max = maxpages; si->pages = maxpages - 1; nr_extents = setup_swap_extents(si, &span); if (nr_extents < 0) { error = nr_extents; goto bad_swap_unlock_inode; } if (si->pages != si->max - 1) { pr_err("swap:%u != (max:%u - 1)\n", si->pages, si->max); error = -EINVAL; goto bad_swap_unlock_inode; } maxpages = si->max; /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } error = swap_cgroup_swapon(si->type, maxpages); if (error) goto bad_swap_unlock_inode; error = setup_swap_map(si, swap_header, swap_map, maxpages); if (error) goto bad_swap_unlock_inode; /* * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might * be above MAX_PAGE_ORDER incase of a large swap file. */ zeromap = kvmalloc_array(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL | __GFP_ZERO); if (!zeromap) { error = -ENOMEM; goto bad_swap_unlock_inode; } if (si->bdev && bdev_stable_writes(si->bdev)) si->flags |= SWP_STABLE_WRITES; if (si->bdev && bdev_synchronous(si->bdev)) si->flags |= SWP_SYNCHRONOUS_IO; if (si->bdev && bdev_nonrot(si->bdev)) { si->flags |= SWP_SOLIDSTATE; } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } cluster_info = setup_clusters(si, swap_header, maxpages); if (IS_ERR(cluster_info)) { error = PTR_ERR(cluster_info); cluster_info = NULL; goto bad_swap_unlock_inode; } if ((swap_flags & SWAP_FLAG_DISCARD) && si->bdev && bdev_max_discard_sectors(si->bdev)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ si->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) si->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) si->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (si->flags & SWP_AREA_DISCARD) { int err = discard_swap(si); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", si, err); } } error = zswap_swapon(si->type, maxpages); if (error) goto bad_swap_unlock_inode; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_zswap; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = swap_flags & SWAP_FLAG_PRIO_MASK; enable_swap_info(si, prio, swap_map, cluster_info, zeromap); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s\n", K(si->pages), name->name, si->prio, nr_extents, K((unsigned long long)span), (si->flags & SWP_SOLIDSTATE) ? "SS" : "", (si->flags & SWP_DISCARDABLE) ? "D" : "", (si->flags & SWP_AREA_DISCARD) ? "s" : "", (si->flags & SWP_PAGE_DISCARD) ? "c" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_zswap: zswap_swapoff(si->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: kfree(si->global_cluster); si->global_cluster = NULL; inode = NULL; destroy_swap_extents(si); swap_cgroup_swapoff(si->type); spin_lock(&swap_lock); si->swap_file = NULL; si->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(zeromap); if (cluster_info) free_cluster_info(cluster_info, maxpages); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (!IS_ERR_OR_NULL(folio)) folio_release_kmap(folio, swap_header); if (name) putname(name); if (inode) inode_unlock(inode); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += swap_usage_in_pages(si); } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } /* * Verify that nr swap entries are valid and increment their swap map counts. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; int err, i; si = swap_entry_to_info(entry); if (WARN_ON_ONCE(!si)) { pr_err("%s%08lx\n", Bad_file, entry.val); return -EINVAL; } offset = swp_offset(entry); VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER); VM_WARN_ON(usage == 1 && nr > 1); ci = swap_cluster_lock(si, offset); err = 0; for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (!count && !has_cache) { err = -ENOENT; } else if (usage == SWAP_HAS_CACHE) { if (has_cache) err = -EEXIST; } else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) { err = -EINVAL; } if (err) goto unlock_out; } for (i = 0; i < nr; i++) { count = si->swap_map[offset + i]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) has_cache = SWAP_HAS_CACHE; else if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if (swap_count_continued(si, offset + i, count)) count = COUNT_CONTINUED; else { /* * Don't need to rollback changes, because if * usage == 1, there must be nr == 1. */ err = -ENOMEM; goto unlock_out; } WRITE_ONCE(si->swap_map[offset + i], count | has_cache); } unlock_out: swap_cluster_unlock(ci); return err; } /* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ void swap_shmem_alloc(swp_entry_t entry, int nr) { __swap_duplicate(entry, SWAP_MAP_SHMEM, nr); } /* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* * @entry: first swap entry from which we allocate nr swap cache. * * Called when allocating swap cache for existing swap entries, * This can return error codes. Returns 0 at success. * -EEXIST means there is a swap cache. * Note: return code is different from swap_duplicate(). */ int swapcache_prepare(swp_entry_t entry, int nr) { return __swap_duplicate(entry, SWAP_HAS_CACHE, nr); } /* * Caller should ensure entries belong to the same folio so * the entries won't span cross cluster boundary. */ void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr) { swap_entries_put_cache(si, entry, nr); } /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap device may be swapoff */ goto outer; } offset = swp_offset(entry); ci = swap_cluster_lock(si, offset); count = swap_count(si->swap_map[offset]); if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { ret = -ENOMEM; goto out; } head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; map = kmap_local_page(list_page) + offset; count = *map; kunmap_local(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out_unlock_cont: spin_unlock(&si->cont_lock); out: swap_cluster_unlock(ci); put_swap_device(si); outer: if (page) __free_page(page); return ret; } /* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or caller of swap_entry_put_locked() * holds cluster lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_next_entry(head, lru); map = kmap_local_page(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_local(map); page = list_next_entry(page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } map = kmap_local_page(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = COUNT_CONTINUED; kunmap_local(map); } ret = true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_local(map); page = list_next_entry(page, lru); BUG_ON(page == head); map = kmap_local_page(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_local(map); while ((page = list_prev_entry(page, lru)) != head) { map = kmap_local_page(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_local(map); } ret = count == COUNT_CONTINUED; } out: spin_unlock(&si->cont_lock); return ret; } /* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */ static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) static bool __has_usable_swap(void) { return !plist_head_empty(&swap_active_head); } void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { struct swap_info_struct *si, *next; int nid = folio_nid(folio); if (!(gfp & __GFP_IO)) return; if (!__has_usable_swap()) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_disk) return; spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[nid], avail_lists[nid]) { if (si->bdev) { blkcg_schedule_throttle(si->bdev->bd_disk, true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { int nid; swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), GFP_KERNEL); if (!swap_avail_heads) { pr_emerg("Not enough memory for swap heads, swap is disabled\n"); return -ENOMEM; } for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); swapfile_maximum_size = arch_max_swapfile_size(); /* * Once a cluster is freed, it's swap table content is read * only, and all swap cache readers (swap_cache_*) verifies * the content before use. So it's safe to use RCU slab here. */ if (!SWP_TABLE_USE_PAGE) swap_table_cachep = kmem_cache_create("swap_table", sizeof(struct swap_table), 0, SLAB_PANIC | SLAB_TYPESAFE_BY_RCU, NULL); #ifdef CONFIG_MIGRATION if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) swap_migration_ad_supported = true; #endif /* CONFIG_MIGRATION */ return 0; } subsys_initcall(swapfile_init); |
| 3 3 3 3 3 3 3 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux INET6 implementation * FIB front-end. * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ /* Changes: * * YOSHIFUJI Hideaki @USAGI * reworked default router selection. * - respect outgoing interface * - select from (probably) reachable routers (i.e. * routers in REACHABLE, STALE, DELAY or PROBE states). * - always select the same router if it is (probably) * reachable. otherwise, round-robin the list. * Ville Nuorvala * Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/capability.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/types.h> #include <linux/times.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/route.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/mroute6.h> #include <linux/init.h> #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/jhash.h> #include <linux/siphash.h> #include <net/net_namespace.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/tcp.h> #include <linux/rtnetlink.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/xfrm.h> #include <net/netevent.h> #include <net/netlink.h> #include <net/rtnh.h> #include <net/lwtunnel.h> #include <net/ip_tunnels.h> #include <net/l3mdev.h> #include <net/ip.h> #include <linux/uaccess.h> #include <linux/btf_ids.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif static int ip6_rt_type_to_error(u8 fib6_type); #define CREATE_TRACE_POINTS #include <trace/events/fib6.h> EXPORT_TRACEPOINT_SYMBOL_GPL(fib6_table_lookup); #undef CREATE_TRACE_POINTS enum rt6_nud_state { RT6_NUD_FAIL_HARD = -3, RT6_NUD_FAIL_PROBE = -2, RT6_NUD_FAIL_DO_RR = -1, RT6_NUD_SUCCEED = 1 }; INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst); static void ip6_negative_advice(struct sock *sk, struct dst_entry *dst); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev); static void ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static int ip6_pkt_prohibit(struct sk_buff *skb); static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, int strict); static size_t rt6_nlmsg_size(struct fib6_info *f6i); static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct fib6_info *rt, struct dst_entry *dst, struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags); static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr); #ifdef CONFIG_IPV6_ROUTE_INFO static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref); static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev); #endif struct uncached_list { spinlock_t lock; struct list_head head; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); rt->dst.rt_uncached_list = ul; spin_lock_bh(&ul->lock); list_add_tail(&rt->dst.rt_uncached, &ul->head); spin_unlock_bh(&ul->lock); } void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->dst.rt_uncached)) { struct uncached_list *ul = rt->dst.rt_uncached_list; spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); } } static void rt6_uncached_list_flush_dev(struct net_device *dev) { int cpu; for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); struct rt6_info *rt, *safe; if (list_empty(&ul->head)) continue; spin_lock_bh(&ul->lock); list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) { struct inet6_dev *rt_idev = rt->rt6i_idev; struct net_device *rt_dev = rt->dst.dev; bool handled = false; if (rt_idev && rt_idev->dev == dev) { rt->rt6i_idev = in6_dev_get(blackhole_netdev); in6_dev_put(rt_idev); handled = true; } if (rt_dev == dev) { rt->dst.dev = blackhole_netdev; netdev_ref_replace(rt_dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); handled = true; } if (handled) list_del_init(&rt->dst.rt_uncached); } spin_unlock_bh(&ul->lock); } } static inline const void *choose_neigh_daddr(const struct in6_addr *p, struct sk_buff *skb, const void *daddr) { if (!ipv6_addr_any(p)) return (const void *) p; else if (skb) return &ipv6_hdr(skb)->daddr; return daddr; } struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, struct net_device *dev, struct sk_buff *skb, const void *daddr) { struct neighbour *n; daddr = choose_neigh_daddr(gw, skb, daddr); n = __ipv6_neigh_lookup(dev, daddr); if (n) return n; n = neigh_create(&nd_tbl, daddr, dev); return IS_ERR(n) ? NULL : n; } static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any), dst_dev(dst), skb, daddr); } static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); struct net_device *dev = dst_dev(dst); daddr = choose_neigh_daddr(rt6_nexthop(rt, &in6addr_any), NULL, daddr); if (!daddr) return; if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) return; if (ipv6_addr_is_multicast((const struct in6_addr *)daddr)) return; __ipv6_confirm_neigh(dev, daddr); } static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, .gc = ip6_dst_gc, .gc_thresh = 1024, .check = ip6_dst_check, .default_advmss = ip6_default_advmss, .mtu = ip6_mtu, .cow_metrics = dst_cow_metrics_generic, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, .negative_advice = ip6_negative_advice, .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, .redirect = rt6_do_redirect, .local_out = __ip6_local_out, .neigh_lookup = ip6_dst_neigh_lookup, .confirm_neigh = ip6_confirm_neigh, }; static struct dst_ops ip6_dst_blackhole_ops = { .family = AF_INET6, .default_advmss = ip6_default_advmss, .neigh_lookup = ip6_dst_neigh_lookup, .check = ip6_dst_check, .destroy = ip6_dst_destroy, .cow_metrics = dst_cow_metrics_generic, .update_pmtu = dst_blackhole_update_pmtu, .redirect = dst_blackhole_redirect, .mtu = dst_blackhole_mtu, }; static const u32 ip6_template_metrics[RTAX_MAX] = { [RTAX_HOPLIMIT - 1] = 0, }; static const struct fib6_info fib6_null_entry_template = { .fib6_flags = (RTF_REJECT | RTF_NONEXTHOP), .fib6_protocol = RTPROT_KERNEL, .fib6_metric = ~(u32)0, .fib6_ref = REFCOUNT_INIT(1), .fib6_type = RTN_UNREACHABLE, .fib6_metrics = (struct dst_metrics *)&dst_default_metrics, }; static const struct rt6_info ip6_null_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -ENETUNREACH, .input = ip6_pkt_discard, .output = ip6_pkt_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; #ifdef CONFIG_IPV6_MULTIPLE_TABLES static const struct rt6_info ip6_prohibit_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EACCES, .input = ip6_pkt_prohibit, .output = ip6_pkt_prohibit_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; static const struct rt6_info ip6_blk_hole_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, .input = dst_discard, .output = dst_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; #endif static void rt6_info_init(struct rt6_info *rt) { memset_after(rt, 0, dst); } /* allocate dst with ip6_dst_ops */ struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, int flags) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, DST_OBSOLETE_FORCE_CHK, flags); if (rt) { rt6_info_init(rt); atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); } return rt; } EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); struct fib6_info *from; struct inet6_dev *idev; ip_dst_metrics_put(dst); rt6_uncached_list_del(rt); idev = rt->rt6i_idev; if (idev) { rt->rt6i_idev = NULL; in6_dev_put(idev); } from = unrcu_pointer(xchg(&rt->from, NULL)); fib6_info_release(from); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { struct rt6_info *rt = dst_rt6_info(dst); struct inet6_dev *idev = rt->rt6i_idev; struct fib6_info *from; if (idev && idev->dev != blackhole_netdev) { struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev); if (blackhole_idev) { rt->rt6i_idev = blackhole_idev; in6_dev_put(idev); } } from = unrcu_pointer(xchg(&rt->from, NULL)); fib6_info_release(from); } static bool __rt6_check_expired(const struct rt6_info *rt) { if (rt->rt6i_flags & RTF_EXPIRES) return time_after(jiffies, READ_ONCE(rt->dst.expires)); return false; } static bool rt6_check_expired(const struct rt6_info *rt) { struct fib6_info *from; from = rcu_dereference(rt->from); if (rt->rt6i_flags & RTF_EXPIRES) { if (time_after(jiffies, READ_ONCE(rt->dst.expires))) return true; } else if (from) { return READ_ONCE(rt->dst.obsolete) != DST_OBSOLETE_FORCE_CHK || fib6_check_expired(from); } return false; } static struct fib6_info * rt6_multipath_first_sibling_rcu(const struct fib6_info *rt) { struct fib6_info *iter; struct fib6_node *fn; fn = rcu_dereference(rt->fib6_node); if (!fn) goto out; iter = rcu_dereference(fn->leaf); if (!iter) goto out; while (iter) { if (iter->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(iter)) return iter; iter = rcu_dereference(iter->fib6_next); } out: return NULL; } void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { struct fib6_info *first, *match = res->f6i; struct fib6_info *sibling; int hash; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; if (match->nh && have_oif_match && res->nh) return; if (skb) IP6CB(skb)->flags |= IP6SKB_MULTIPATH; /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. */ if (!fl6->mp_hash && (!match->nh || nexthop_is_multipath(match->nh))) fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL); if (unlikely(match->nh)) { nexthop_path_fib6_result(res, fl6->mp_hash); return; } first = rt6_multipath_first_sibling_rcu(match); if (!first) goto out; hash = fl6->mp_hash; if (hash <= atomic_read(&first->fib6_nh->fib_nh_upper_bound)) { if (rt6_score_route(first->fib6_nh, first->fib6_flags, oif, strict) >= 0) match = first; goto out; } list_for_each_entry_rcu(sibling, &first->fib6_siblings, fib6_siblings) { const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound); if (hash > nh_upper_bound) continue; if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0) break; match = sibling; break; } out: res->f6i = match; res->nh = match->fib6_nh; } /* * Route lookup. rcu_read_lock() should be held. */ static bool __rt6_device_match(struct net *net, const struct fib6_nh *nh, const struct in6_addr *saddr, int oif, int flags) { const struct net_device *dev; if (nh->fib_nh_flags & RTNH_F_DEAD) return false; dev = nh->fib_nh_dev; if (oif) { if (dev->ifindex == oif) return true; } else { if (ipv6_chk_addr(net, saddr, dev, flags & RT6_LOOKUP_F_IFACE)) return true; } return false; } struct fib6_nh_dm_arg { struct net *net; const struct in6_addr *saddr; int oif; int flags; struct fib6_nh *nh; }; static int __rt6_nh_dev_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_dm_arg *arg = _arg; arg->nh = nh; return __rt6_device_match(arg->net, nh, arg->saddr, arg->oif, arg->flags); } /* returns fib6_nh from nexthop or NULL */ static struct fib6_nh *rt6_nh_dev_match(struct net *net, struct nexthop *nh, struct fib6_result *res, const struct in6_addr *saddr, int oif, int flags) { struct fib6_nh_dm_arg arg = { .net = net, .saddr = saddr, .oif = oif, .flags = flags, }; if (nexthop_is_blackhole(nh)) return NULL; if (nexthop_for_each_fib6_nh(nh, __rt6_nh_dev_match, &arg)) return arg.nh; return NULL; } static void rt6_device_match(struct net *net, struct fib6_result *res, const struct in6_addr *saddr, int oif, int flags) { struct fib6_info *f6i = res->f6i; struct fib6_info *spf6i; struct fib6_nh *nh; if (!oif && ipv6_addr_any(saddr)) { if (unlikely(f6i->nh)) { nh = nexthop_fib6_nh(f6i->nh); if (nexthop_is_blackhole(f6i->nh)) goto out_blackhole; } else { nh = f6i->fib6_nh; } if (!(nh->fib_nh_flags & RTNH_F_DEAD)) goto out; } for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) { bool matched = false; if (unlikely(spf6i->nh)) { nh = rt6_nh_dev_match(net, spf6i->nh, res, saddr, oif, flags); if (nh) matched = true; } else { nh = spf6i->fib6_nh; if (__rt6_device_match(net, nh, saddr, oif, flags)) matched = true; } if (matched) { res->f6i = spf6i; goto out; } } if (oif && flags & RT6_LOOKUP_F_IFACE) { res->f6i = net->ipv6.fib6_null_entry; nh = res->f6i->fib6_nh; goto out; } if (unlikely(f6i->nh)) { nh = nexthop_fib6_nh(f6i->nh); if (nexthop_is_blackhole(f6i->nh)) goto out_blackhole; } else { nh = f6i->fib6_nh; } if (nh->fib_nh_flags & RTNH_F_DEAD) { res->f6i = net->ipv6.fib6_null_entry; nh = res->f6i->fib6_nh; } out: res->nh = nh; res->fib6_type = res->f6i->fib6_type; res->fib6_flags = res->f6i->fib6_flags; return; out_blackhole: res->fib6_flags |= RTF_REJECT; res->fib6_type = RTN_BLACKHOLE; res->nh = nh; } #ifdef CONFIG_IPV6_ROUTER_PREF struct __rt6_probe_work { struct work_struct work; struct in6_addr target; struct net_device *dev; netdevice_tracker dev_tracker; }; static void rt6_probe_deferred(struct work_struct *w) { struct in6_addr mcaddr; struct __rt6_probe_work *work = container_of(w, struct __rt6_probe_work, work); addrconf_addr_solict_mult(&work->target, &mcaddr); ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, 0); netdev_put(work->dev, &work->dev_tracker); kfree(work); } static void rt6_probe(struct fib6_nh *fib6_nh) { struct __rt6_probe_work *work = NULL; const struct in6_addr *nh_gw; unsigned long last_probe; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; /* * Okay, this does not seem to be appropriate * for now, however, we need to check if it * is really so; aka Router Reachability Probing. * * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ if (!fib6_nh->fib_nh_gw_family) return; nh_gw = &fib6_nh->fib_nh_gw6; dev = fib6_nh->fib_nh_dev; rcu_read_lock(); last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); if (!idev) goto out; neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { if (READ_ONCE(neigh->nud_state) & NUD_VALID) goto out; write_lock_bh(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, neigh->updated + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) __neigh_set_probe_once(neigh); } write_unlock_bh(&neigh->lock); } else if (time_after(jiffies, last_probe + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc(sizeof(*work), GFP_ATOMIC); } if (!work || cmpxchg(&fib6_nh->last_probe, last_probe, jiffies) != last_probe) { kfree(work); } else { INIT_WORK(&work->work, rt6_probe_deferred); work->target = *nh_gw; netdev_hold(dev, &work->dev_tracker, GFP_ATOMIC); work->dev = dev; schedule_work(&work->work); } out: rcu_read_unlock(); } #else static inline void rt6_probe(struct fib6_nh *fib6_nh) { } #endif /* * Default Router Selection (RFC 2461 6.3.6) */ static enum rt6_nud_state rt6_check_neigh(const struct fib6_nh *fib6_nh) { enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; struct neighbour *neigh; rcu_read_lock(); neigh = __ipv6_neigh_lookup_noref(fib6_nh->fib_nh_dev, &fib6_nh->fib_nh_gw6); if (neigh) { u8 nud_state = READ_ONCE(neigh->nud_state); if (nud_state & NUD_VALID) ret = RT6_NUD_SUCCEED; #ifdef CONFIG_IPV6_ROUTER_PREF else if (!(nud_state & NUD_FAILED)) ret = RT6_NUD_SUCCEED; else ret = RT6_NUD_FAIL_PROBE; #endif } else { ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR; } rcu_read_unlock(); return ret; } static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, int strict) { int m = 0; if (!oif || nh->fib_nh_dev->ifindex == oif) m = 2; if (!m && (strict & RT6_LOOKUP_F_IFACE)) return RT6_NUD_FAIL_HARD; #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(fib6_flags)) << 2; #endif if ((strict & RT6_LOOKUP_F_REACHABLE) && !(fib6_flags & RTF_NONEXTHOP) && nh->fib_nh_gw_family) { int n = rt6_check_neigh(nh); if (n < 0) return n; } return m; } static bool find_match(struct fib6_nh *nh, u32 fib6_flags, int oif, int strict, int *mpri, bool *do_rr) { bool match_do_rr = false; bool rc = false; int m; if (nh->fib_nh_flags & RTNH_F_DEAD) goto out; if (ip6_ignore_linkdown(nh->fib_nh_dev) && nh->fib_nh_flags & RTNH_F_LINKDOWN && !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE)) goto out; m = rt6_score_route(nh, fib6_flags, oif, strict); if (m == RT6_NUD_FAIL_DO_RR) { match_do_rr = true; m = 0; /* lowest valid score */ } else if (m == RT6_NUD_FAIL_HARD) { goto out; } if (strict & RT6_LOOKUP_F_REACHABLE) rt6_probe(nh); /* note that m can be RT6_NUD_FAIL_PROBE at this point */ if (m > *mpri) { *do_rr = match_do_rr; *mpri = m; rc = true; } out: return rc; } struct fib6_nh_frl_arg { u32 flags; int oif; int strict; int *mpri; bool *do_rr; struct fib6_nh *nh; }; static int rt6_nh_find_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_frl_arg *arg = _arg; arg->nh = nh; return find_match(nh, arg->flags, arg->oif, arg->strict, arg->mpri, arg->do_rr); } static void __find_rr_leaf(struct fib6_info *f6i_start, struct fib6_info *nomatch, u32 metric, struct fib6_result *res, struct fib6_info **cont, int oif, int strict, bool *do_rr, int *mpri) { struct fib6_info *f6i; for (f6i = f6i_start; f6i && f6i != nomatch; f6i = rcu_dereference(f6i->fib6_next)) { bool matched = false; struct fib6_nh *nh; if (cont && f6i->fib6_metric != metric) { *cont = f6i; return; } if (fib6_check_expired(f6i)) continue; if (unlikely(f6i->nh)) { struct fib6_nh_frl_arg arg = { .flags = f6i->fib6_flags, .oif = oif, .strict = strict, .mpri = mpri, .do_rr = do_rr }; if (nexthop_is_blackhole(f6i->nh)) { res->fib6_flags = RTF_REJECT; res->fib6_type = RTN_BLACKHOLE; res->f6i = f6i; res->nh = nexthop_fib6_nh(f6i->nh); return; } if (nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_find_match, &arg)) { matched = true; nh = arg.nh; } } else { nh = f6i->fib6_nh; if (find_match(nh, f6i->fib6_flags, oif, strict, mpri, do_rr)) matched = true; } if (matched) { res->f6i = f6i; res->nh = nh; res->fib6_flags = f6i->fib6_flags; res->fib6_type = f6i->fib6_type; } } } static void find_rr_leaf(struct fib6_node *fn, struct fib6_info *leaf, struct fib6_info *rr_head, int oif, int strict, bool *do_rr, struct fib6_result *res) { u32 metric = rr_head->fib6_metric; struct fib6_info *cont = NULL; int mpri = -1; __find_rr_leaf(rr_head, NULL, metric, res, &cont, oif, strict, do_rr, &mpri); __find_rr_leaf(leaf, rr_head, metric, res, &cont, oif, strict, do_rr, &mpri); if (res->f6i || !cont) return; __find_rr_leaf(cont, NULL, metric, res, NULL, oif, strict, do_rr, &mpri); } static void rt6_select(struct net *net, struct fib6_node *fn, int oif, struct fib6_result *res, int strict) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct fib6_info *rt0; bool do_rr = false; int key_plen; /* make sure this function or its helpers sets f6i */ res->f6i = NULL; if (!leaf || leaf == net->ipv6.fib6_null_entry) goto out; rt0 = rcu_dereference(fn->rr_ptr); if (!rt0) rt0 = leaf; /* Double check to make sure fn is not an intermediate node * and fn->leaf does not points to its child's leaf * (This might happen if all routes under fn are deleted from * the tree and fib6_repair_tree() is called on the node.) */ key_plen = rt0->fib6_dst.plen; #ifdef CONFIG_IPV6_SUBTREES if (rt0->fib6_src.plen) key_plen = rt0->fib6_src.plen; #endif if (fn->fn_bit != key_plen) goto out; find_rr_leaf(fn, leaf, rt0, oif, strict, &do_rr, res); if (do_rr) { struct fib6_info *next = rcu_dereference(rt0->fib6_next); /* no entries matched; do round-robin */ if (!next || next->fib6_metric != rt0->fib6_metric) next = leaf; if (next != rt0) { spin_lock_bh(&leaf->fib6_table->tb6_lock); /* make sure next is not being deleted from the tree */ if (next->fib6_node) rcu_assign_pointer(fn->rr_ptr, next); spin_unlock_bh(&leaf->fib6_table->tb6_lock); } } out: if (!res->f6i) { res->f6i = net->ipv6.fib6_null_entry; res->nh = res->f6i->fib6_nh; res->fib6_flags = res->f6i->fib6_flags; res->fib6_type = res->f6i->fib6_type; } } static bool rt6_is_gw_or_nonexthop(const struct fib6_result *res) { return (res->f6i->fib6_flags & RTF_NONEXTHOP) || res->nh->fib_nh_gw_family; } #ifdef CONFIG_IPV6_ROUTE_INFO int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr) { struct net *net = dev_net(dev); struct route_info *rinfo = (struct route_info *) opt; struct in6_addr prefix_buf, *prefix; struct fib6_table *table; unsigned int pref; unsigned long lifetime; struct fib6_info *rt; if (len < sizeof(struct route_info)) { return -EINVAL; } /* Sanity check for prefix_len and length */ if (rinfo->length > 3) { return -EINVAL; } else if (rinfo->prefix_len > 128) { return -EINVAL; } else if (rinfo->prefix_len > 64) { if (rinfo->length < 2) { return -EINVAL; } } else if (rinfo->prefix_len > 0) { if (rinfo->length < 1) { return -EINVAL; } } pref = rinfo->route_pref; if (pref == ICMPV6_ROUTER_PREF_INVALID) return -EINVAL; lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ); if (rinfo->length == 3) prefix = (struct in6_addr *)rinfo->prefix; else { /* this function is safe */ ipv6_addr_prefix(&prefix_buf, (struct in6_addr *)rinfo->prefix, rinfo->prefix_len); prefix = &prefix_buf; } if (rinfo->prefix_len == 0) rt = rt6_get_dflt_router(net, gwaddr, dev); else rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev); if (rt && !lifetime) { ip6_del_rt(net, rt, false); rt = NULL; } if (!rt && lifetime) rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev, pref); else if (rt) rt->fib6_flags = RTF_ROUTEINFO | (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); if (!addrconf_finite_timeout(lifetime)) { fib6_clean_expires(rt); fib6_remove_gc_list(rt); } else { fib6_set_expires(rt, jiffies + HZ * lifetime); fib6_add_gc_list(rt); } spin_unlock_bh(&table->tb6_lock); fib6_info_release(rt); } return 0; } #endif /* * Misc support functions */ /* called with rcu_lock held */ static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res) { struct net_device *dev = res->nh->fib_nh_dev; if (res->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) { /* for copies of local routes, dst->dev needs to be the * device if it is a master device, the master device if * device is enslaved, and the loopback as the default */ if (netif_is_l3_slave(dev) && !rt6_need_strict(&res->f6i->fib6_dst.addr)) dev = l3mdev_master_dev_rcu(dev); else if (!netif_is_l3_master(dev)) dev = dev_net(dev)->loopback_dev; /* last case is netif_is_l3_master(dev) is true in which * case we want dev returned to be dev */ } return dev; } static const int fib6_prop[RTN_MAX + 1] = { [RTN_UNSPEC] = 0, [RTN_UNICAST] = 0, [RTN_LOCAL] = 0, [RTN_BROADCAST] = 0, [RTN_ANYCAST] = 0, [RTN_MULTICAST] = 0, [RTN_BLACKHOLE] = -EINVAL, [RTN_UNREACHABLE] = -EHOSTUNREACH, [RTN_PROHIBIT] = -EACCES, [RTN_THROW] = -EAGAIN, [RTN_NAT] = -EINVAL, [RTN_XRESOLVE] = -EINVAL, }; static int ip6_rt_type_to_error(u8 fib6_type) { return fib6_prop[fib6_type]; } static unsigned short fib6_info_dst_flags(struct fib6_info *rt) { unsigned short flags = 0; if (rt->dst_nocount) flags |= DST_NOCOUNT; if (rt->dst_nopolicy) flags |= DST_NOPOLICY; return flags; } static void ip6_rt_init_dst_reject(struct rt6_info *rt, u8 fib6_type) { rt->dst.error = ip6_rt_type_to_error(fib6_type); switch (fib6_type) { case RTN_BLACKHOLE: rt->dst.output = dst_discard_out; rt->dst.input = dst_discard; break; case RTN_PROHIBIT: rt->dst.output = ip6_pkt_prohibit_out; rt->dst.input = ip6_pkt_prohibit; break; case RTN_THROW: case RTN_UNREACHABLE: default: rt->dst.output = ip6_pkt_discard_out; rt->dst.input = ip6_pkt_discard; break; } } static void ip6_rt_init_dst(struct rt6_info *rt, const struct fib6_result *res) { struct fib6_info *f6i = res->f6i; if (res->fib6_flags & RTF_REJECT) { ip6_rt_init_dst_reject(rt, res->fib6_type); return; } rt->dst.error = 0; rt->dst.output = ip6_output; if (res->fib6_type == RTN_LOCAL || res->fib6_type == RTN_ANYCAST) { rt->dst.input = ip6_input; } else if (ipv6_addr_type(&f6i->fib6_dst.addr) & IPV6_ADDR_MULTICAST) { rt->dst.input = ip6_mc_input; rt->dst.output = ip6_mr_output; } else { rt->dst.input = ip6_forward; } if (res->nh->fib_nh_lws) { rt->dst.lwtstate = lwtstate_get(res->nh->fib_nh_lws); lwtunnel_set_redirect(&rt->dst); } rt->dst.lastuse = jiffies; } /* Caller must already hold reference to @from */ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) { rt->rt6i_flags &= ~RTF_EXPIRES; rcu_assign_pointer(rt->from, from); ip_dst_init_metrics(&rt->dst, from->fib6_metrics); } /* Caller must already hold reference to f6i in result */ static void ip6_rt_copy_init(struct rt6_info *rt, const struct fib6_result *res) { const struct fib6_nh *nh = res->nh; const struct net_device *dev = nh->fib_nh_dev; struct fib6_info *f6i = res->f6i; ip6_rt_init_dst(rt, res); rt->rt6i_dst = f6i->fib6_dst; rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL; rt->rt6i_flags = res->fib6_flags; if (nh->fib_nh_gw_family) { rt->rt6i_gateway = nh->fib_nh_gw6; rt->rt6i_flags |= RTF_GATEWAY; } rt6_set_from(rt, f6i); #ifdef CONFIG_IPV6_SUBTREES rt->rt6i_src = f6i->fib6_src; #endif } static struct fib6_node* fib6_backtrack(struct fib6_node *fn, struct in6_addr *saddr) { struct fib6_node *pn, *sn; while (1) { if (fn->fn_flags & RTN_TL_ROOT) return NULL; pn = rcu_dereference(fn->parent); sn = FIB6_SUBTREE(pn); if (sn && sn != fn) fn = fib6_node_lookup(sn, NULL, saddr); else fn = pn; if (fn->fn_flags & RTN_RTINFO) return fn; } } static bool ip6_hold_safe(struct net *net, struct rt6_info **prt) { struct rt6_info *rt = *prt; if (dst_hold_safe(&rt->dst)) return true; if (net) { rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); } else { rt = NULL; } *prt = rt; return false; } /* called with rcu_lock held */ static struct rt6_info *ip6_create_rt_rcu(const struct fib6_result *res) { struct net_device *dev = res->nh->fib_nh_dev; struct fib6_info *f6i = res->f6i; unsigned short flags; struct rt6_info *nrt; if (!fib6_info_hold_safe(f6i)) goto fallback; flags = fib6_info_dst_flags(f6i); nrt = ip6_dst_alloc(dev_net(dev), dev, flags); if (!nrt) { fib6_info_release(f6i); goto fallback; } ip6_rt_copy_init(nrt, res); return nrt; fallback: nrt = dev_net(dev)->ipv6.ip6_null_entry; dst_hold(&nrt->dst); return nrt; } INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct fib6_result res = {}; struct fib6_node *fn; struct rt6_info *rt; rcu_read_lock(); fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: res.f6i = rcu_dereference(fn->leaf); if (!res.f6i) res.f6i = net->ipv6.fib6_null_entry; else rt6_device_match(net, &res, &fl6->saddr, fl6->flowi6_oif, flags); if (res.f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); goto out; } else if (res.fib6_flags & RTF_REJECT) { goto do_create; } fib6_select_path(net, &res, fl6, fl6->flowi6_oif, fl6->flowi6_oif != 0, skb, flags); /* Search through exception table */ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr); if (rt) { if (ip6_hold_safe(net, &rt)) dst_use_noref(&rt->dst, jiffies); } else { do_create: rt = ip6_create_rt_rcu(&res); } out: trace_fib6_table_lookup(net, &res, table, fl6); rcu_read_unlock(); return rt; } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_lookup); } EXPORT_SYMBOL_GPL(ip6_route_lookup); struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, const struct sk_buff *skb, int strict) { struct flowi6 fl6 = { .flowi6_oif = oif, .daddr = *daddr, }; struct dst_entry *dst; int flags = strict ? RT6_LOOKUP_F_IFACE : 0; if (saddr) { memcpy(&fl6.saddr, saddr, sizeof(*saddr)); flags |= RT6_LOOKUP_F_HAS_SADDR; } dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup); if (dst->error == 0) return dst_rt6_info(dst); dst_release(dst); return NULL; } EXPORT_SYMBOL(rt6_lookup); /* ip6_ins_rt is called with FREE table->tb6_lock. * It takes new route entry, the addition fails by any reason the * route is released. * Caller must hold dst before calling it. */ static int __ip6_ins_rt(struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { int err; struct fib6_table *table; table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); err = fib6_add(&table->tb6_root, rt, info, extack); spin_unlock_bh(&table->tb6_lock); return err; } int ip6_ins_rt(struct net *net, struct fib6_info *rt) { struct nl_info info = { .nl_net = net, }; return __ip6_ins_rt(rt, &info, NULL); } static struct rt6_info *ip6_rt_cache_alloc(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct fib6_info *f6i = res->f6i; struct net_device *dev; struct rt6_info *rt; /* * Clone the route. */ if (!fib6_info_hold_safe(f6i)) return NULL; dev = ip6_rt_get_dev_rcu(res); rt = ip6_dst_alloc(dev_net(dev), dev, 0); if (!rt) { fib6_info_release(f6i); return NULL; } ip6_rt_copy_init(rt, res); rt->rt6i_flags |= RTF_CACHE; rt->rt6i_dst.addr = *daddr; rt->rt6i_dst.plen = 128; if (!rt6_is_gw_or_nonexthop(res)) { if (f6i->fib6_dst.plen != 128 && ipv6_addr_equal(&f6i->fib6_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen && saddr) { rt->rt6i_src.addr = *saddr; rt->rt6i_src.plen = 128; } #endif } return rt; } static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res) { struct fib6_info *f6i = res->f6i; unsigned short flags = fib6_info_dst_flags(f6i); struct net_device *dev; struct rt6_info *pcpu_rt; if (!fib6_info_hold_safe(f6i)) return NULL; rcu_read_lock(); dev = ip6_rt_get_dev_rcu(res); pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags | DST_NOCOUNT); rcu_read_unlock(); if (!pcpu_rt) { fib6_info_release(f6i); return NULL; } ip6_rt_copy_init(pcpu_rt, res); pcpu_rt->rt6i_flags |= RTF_PCPU; if (f6i->nh) pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev)); return pcpu_rt; } static bool rt6_is_valid(const struct rt6_info *rt6) { return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev)); } /* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) { struct rt6_info *pcpu_rt; pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu); if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) { struct rt6_info *prev, **p; p = this_cpu_ptr(res->nh->rt6i_pcpu); /* Paired with READ_ONCE() in __fib6_drop_pcpu_from() */ prev = xchg(p, NULL); if (prev) { dst_dev_put(&prev->dst); dst_release(&prev->dst); } pcpu_rt = NULL; } return pcpu_rt; } static struct rt6_info *rt6_make_pcpu_route(struct net *net, const struct fib6_result *res) { struct rt6_info *pcpu_rt, *prev, **p; pcpu_rt = ip6_rt_pcpu_alloc(res); if (!pcpu_rt) return NULL; p = this_cpu_ptr(res->nh->rt6i_pcpu); prev = cmpxchg(p, NULL, pcpu_rt); BUG_ON(prev); if (res->f6i->fib6_destroying) { struct fib6_info *from; from = unrcu_pointer(xchg(&pcpu_rt->from, NULL)); fib6_info_release(from); } return pcpu_rt; } /* exception hash table implementation */ static DEFINE_SPINLOCK(rt6_exception_lock); /* Remove rt6_ex from hash table and free the memory * Caller must hold rt6_exception_lock */ static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { struct net *net; if (!bucket || !rt6_ex) return; net = dev_net(rt6_ex->rt6i->dst.dev); net->ipv6.rt6_stats->fib_rt_cache--; /* purge completely the exception to allow releasing the held resources: * some [sk] cache may keep the dst around for unlimited time */ dst_dev_put(&rt6_ex->rt6i->dst); hlist_del_rcu(&rt6_ex->hlist); dst_release(&rt6_ex->rt6i->dst); kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; } /* Remove oldest rt6_ex in bucket and free the memory * Caller must hold rt6_exception_lock */ static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) { struct rt6_exception *rt6_ex, *oldest = NULL; if (!bucket) return; hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { if (!oldest || time_before(rt6_ex->stamp, oldest->stamp)) oldest = rt6_ex; } rt6_remove_exception(bucket, oldest); } static u32 rt6_exception_hash(const struct in6_addr *dst, const struct in6_addr *src) { static siphash_aligned_key_t rt6_exception_key; struct { struct in6_addr dst; struct in6_addr src; } __aligned(SIPHASH_ALIGNMENT) combined = { .dst = *dst, }; u64 val; net_get_random_once(&rt6_exception_key, sizeof(rt6_exception_key)); #ifdef CONFIG_IPV6_SUBTREES if (src) combined.src = *src; #endif val = siphash(&combined, sizeof(combined), &rt6_exception_key); return hash_64(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); } /* Helper function to find the cached rt in the hash table * and update bucket pointer to point to the bucket for this * (daddr, saddr) pair * Caller must hold rt6_exception_lock */ static struct rt6_exception * __rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct rt6_exception *rt6_ex; u32 hval; if (!(*bucket) || !daddr) return NULL; hval = rt6_exception_hash(daddr, saddr); *bucket += hval; hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) { struct rt6_info *rt6 = rt6_ex->rt6i; bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (matched && saddr) matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); #endif if (matched) return rt6_ex; } return NULL; } /* Helper function to find the cached rt in the hash table * and update bucket pointer to point to the bucket for this * (daddr, saddr) pair * Caller must hold rcu_read_lock() */ static struct rt6_exception * __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct rt6_exception *rt6_ex; u32 hval; WARN_ON_ONCE(!rcu_read_lock_held()); if (!(*bucket) || !daddr) return NULL; hval = rt6_exception_hash(daddr, saddr); *bucket += hval; hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) { struct rt6_info *rt6 = rt6_ex->rt6i; bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (matched && saddr) matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); #endif if (matched) return rt6_ex; } return NULL; } static unsigned int fib6_mtu(const struct fib6_result *res) { const struct fib6_nh *nh = res->nh; unsigned int mtu; if (res->f6i->fib6_pmtu) { mtu = res->f6i->fib6_pmtu; } else { struct net_device *dev = nh->fib_nh_dev; struct inet6_dev *idev; rcu_read_lock(); idev = __in6_dev_get(dev); mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); } mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu); } #define FIB6_EXCEPTION_BUCKET_FLUSHED 0x1UL /* used when the flushed bit is not relevant, only access to the bucket * (ie., all bucket users except rt6_insert_exception); * * called under rcu lock; sometimes called with rt6_exception_lock held */ static struct rt6_exception_bucket *fib6_nh_get_excptn_bucket(const struct fib6_nh *nh, spinlock_t *lock) { struct rt6_exception_bucket *bucket; if (lock) bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(lock)); else bucket = rcu_dereference(nh->rt6i_exception_bucket); /* remove bucket flushed bit if set */ if (bucket) { unsigned long p = (unsigned long)bucket; p &= ~FIB6_EXCEPTION_BUCKET_FLUSHED; bucket = (struct rt6_exception_bucket *)p; } return bucket; } static bool fib6_nh_excptn_bucket_flushed(struct rt6_exception_bucket *bucket) { unsigned long p = (unsigned long)bucket; return !!(p & FIB6_EXCEPTION_BUCKET_FLUSHED); } /* called with rt6_exception_lock held */ static void fib6_nh_excptn_bucket_set_flushed(struct fib6_nh *nh, spinlock_t *lock) { struct rt6_exception_bucket *bucket; unsigned long p; bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(lock)); p = (unsigned long)bucket; p |= FIB6_EXCEPTION_BUCKET_FLUSHED; bucket = (struct rt6_exception_bucket *)p; rcu_assign_pointer(nh->rt6i_exception_bucket, bucket); } static int rt6_insert_exception(struct rt6_info *nrt, const struct fib6_result *res) { struct net *net = dev_net(nrt->dst.dev); struct rt6_exception_bucket *bucket; struct fib6_info *f6i = res->f6i; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; struct fib6_nh *nh = res->nh; int max_depth; int err = 0; spin_lock_bh(&rt6_exception_lock); bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(&rt6_exception_lock)); if (!bucket) { bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket), GFP_ATOMIC); if (!bucket) { err = -ENOMEM; goto out; } rcu_assign_pointer(nh->rt6i_exception_bucket, bucket); } else if (fib6_nh_excptn_bucket_flushed(bucket)) { err = -EINVAL; goto out; } #ifdef CONFIG_IPV6_SUBTREES /* fib6_src.plen != 0 indicates f6i is in subtree * and exception table is indexed by a hash of * both fib6_dst and fib6_src. * Otherwise, the exception table is indexed by * a hash of only fib6_dst. */ if (f6i->fib6_src.plen) src_key = &nrt->rt6i_src.addr; #endif /* rt6_mtu_change() might lower mtu on f6i. * Only insert this exception route if its mtu * is less than f6i's mtu value. */ if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(res)) { err = -EINVAL; goto out; } rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr, src_key); if (rt6_ex) rt6_remove_exception(bucket, rt6_ex); rt6_ex = kzalloc(sizeof(*rt6_ex), GFP_ATOMIC); if (!rt6_ex) { err = -ENOMEM; goto out; } rt6_ex->rt6i = nrt; rt6_ex->stamp = jiffies; hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain); bucket->depth++; net->ipv6.rt6_stats->fib_rt_cache++; /* Randomize max depth to avoid some side channels attacks. */ max_depth = FIB6_MAX_DEPTH + get_random_u32_below(FIB6_MAX_DEPTH); while (bucket->depth > max_depth) rt6_exception_remove_oldest(bucket); out: spin_unlock_bh(&rt6_exception_lock); /* Update fn->fn_sernum to invalidate all cached dst */ if (!err) { spin_lock_bh(&f6i->fib6_table->tb6_lock); fib6_update_sernum(net, f6i); fib6_add_gc_list(f6i); spin_unlock_bh(&f6i->fib6_table->tb6_lock); fib6_force_start_gc(net); } return err; } static void fib6_nh_flush_exceptions(struct fib6_nh *nh, struct fib6_info *from) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (!bucket) goto out; /* Prevent rt6_insert_exception() to recreate the bucket list */ if (!from) fib6_nh_excptn_bucket_set_flushed(nh, &rt6_exception_lock); for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { if (!from || rcu_access_pointer(rt6_ex->rt6i->from) == from) rt6_remove_exception(bucket, rt6_ex); } WARN_ON_ONCE(!from && bucket->depth); bucket++; } out: spin_unlock_bh(&rt6_exception_lock); } static int rt6_nh_flush_exceptions(struct fib6_nh *nh, void *arg) { struct fib6_info *f6i = arg; fib6_nh_flush_exceptions(nh, f6i); return 0; } void rt6_flush_exceptions(struct fib6_info *f6i) { if (f6i->nh) { rcu_read_lock(); nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions, f6i); rcu_read_unlock(); } else { fib6_nh_flush_exceptions(f6i->fib6_nh, f6i); } } /* Find cached rt in the hash table inside passed in rt * Caller has to hold rcu_read_lock() */ static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct rt6_info *ret = NULL; #ifdef CONFIG_IPV6_SUBTREES /* fib6i_src.plen != 0 indicates f6i is in subtree * and exception table is indexed by a hash of * both fib6_dst and fib6_src. * However, the src addr used to create the hash * might not be exactly the passed in saddr which * is a /128 addr from the flow. * So we need to use f6i->fib6_src to redo lookup * if the passed in saddr does not find anything. * (See the logic in ip6_rt_cache_alloc() on how * rt->rt6i_src is updated.) */ if (res->f6i->fib6_src.plen) src_key = saddr; find_ex: #endif bucket = fib6_nh_get_excptn_bucket(res->nh, NULL); rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) ret = rt6_ex->rt6i; #ifdef CONFIG_IPV6_SUBTREES /* Use fib6_src as src_key and redo lookup */ if (!ret && src_key && src_key != &res->f6i->fib6_src.addr) { src_key = &res->f6i->fib6_src.addr; goto find_ex; } #endif return ret; } /* Remove the passed in cached rt from the hash table that contains it */ static int fib6_nh_remove_exception(const struct fib6_nh *nh, int plen, const struct rt6_info *rt) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int err; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return -ENOENT; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates 'from' is in subtree * and exception table is indexed by a hash of * both rt6i_dst and rt6i_src. * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ if (plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_spinlock(&bucket, &rt->rt6i_dst.addr, src_key); if (rt6_ex) { rt6_remove_exception(bucket, rt6_ex); err = 0; } else { err = -ENOENT; } spin_unlock_bh(&rt6_exception_lock); return err; } struct fib6_nh_excptn_arg { struct rt6_info *rt; int plen; }; static int rt6_nh_remove_exception_rt(struct fib6_nh *nh, void *_arg) { struct fib6_nh_excptn_arg *arg = _arg; int err; err = fib6_nh_remove_exception(nh, arg->plen, arg->rt); if (err == 0) return 1; return 0; } static int rt6_remove_exception_rt(struct rt6_info *rt) { struct fib6_info *from; from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) return -EINVAL; if (from->nh) { struct fib6_nh_excptn_arg arg = { .rt = rt, .plen = from->fib6_src.plen }; int rc; /* rc = 1 means an entry was found */ rc = nexthop_for_each_fib6_nh(from->nh, rt6_nh_remove_exception_rt, &arg); return rc ? 0 : -ENOENT; } return fib6_nh_remove_exception(from->fib6_nh, from->fib6_src.plen, rt); } /* Find rt6_ex which contains the passed in rt cache and * refresh its stamp */ static void fib6_nh_update_exception(const struct fib6_nh *nh, int plen, const struct rt6_info *rt) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; bucket = fib6_nh_get_excptn_bucket(nh, NULL); #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates 'from' is in subtree * and exception table is indexed by a hash of * both rt6i_dst and rt6i_src. * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ if (plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_rcu(&bucket, &rt->rt6i_dst.addr, src_key); if (rt6_ex) rt6_ex->stamp = jiffies; } struct fib6_nh_match_arg { const struct net_device *dev; const struct in6_addr *gw; struct fib6_nh *match; }; /* determine if fib6_nh has given device and gateway */ static int fib6_nh_find_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_match_arg *arg = _arg; if (arg->dev != nh->fib_nh_dev || (arg->gw && !nh->fib_nh_gw_family) || (!arg->gw && nh->fib_nh_gw_family) || (arg->gw && !ipv6_addr_equal(arg->gw, &nh->fib_nh_gw6))) return 0; arg->match = nh; /* found a match, break the loop */ return 1; } static void rt6_update_exception_stamp_rt(struct rt6_info *rt) { struct fib6_info *from; struct fib6_nh *fib6_nh; rcu_read_lock(); from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) goto unlock; if (from->nh) { struct fib6_nh_match_arg arg = { .dev = rt->dst.dev, .gw = &rt->rt6i_gateway, }; nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg); if (!arg.match) goto unlock; fib6_nh = arg.match; } else { fib6_nh = from->fib6_nh; } fib6_nh_update_exception(fib6_nh, from->fib6_src.plen, rt); unlock: rcu_read_unlock(); } static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, struct rt6_info *rt, int mtu) { /* If the new MTU is lower than the route PMTU, this new MTU will be the * lowest MTU in the path: always allow updating the route PMTU to * reflect PMTU decreases. * * If the new MTU is higher, and the route PMTU is equal to the local * MTU, this means the old MTU is the lowest in the path, so allow * updating it: if other nodes now have lower MTUs, PMTU discovery will * handle this. */ if (dst_mtu(&rt->dst) >= mtu) return true; if (dst_mtu(&rt->dst) == idev->cnf.mtu6) return true; return false; } static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, const struct fib6_nh *nh, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int i; bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (!bucket) return; for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { struct rt6_info *entry = rt6_ex->rt6i; /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected * route), the metrics of its rt->from have already * been updated. */ if (dst_metric_raw(&entry->dst, RTAX_MTU) && rt6_mtu_change_route_allowed(idev, entry, mtu)) dst_metric_set(&entry->dst, RTAX_MTU, mtu); } bucket++; } } #define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) static void fib6_nh_exceptions_clean_tohost(const struct fib6_nh *nh, const struct in6_addr *gateway) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (bucket) { for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { struct rt6_info *entry = rt6_ex->rt6i; if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY && ipv6_addr_equal(gateway, &entry->rt6i_gateway)) { rt6_remove_exception(bucket, rt6_ex); } } bucket++; } } spin_unlock_bh(&rt6_exception_lock); } static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex, struct fib6_gc_args *gc_args, unsigned long now) { struct rt6_info *rt = rt6_ex->rt6i; /* we are pruning and obsoleting aged-out and non gateway exceptions * even if others have still references to them, so that on next * dst_check() such references can be dropped. * EXPIRES exceptions - e.g. pmtu-generated ones are pruned when * expired, independently from their aging, as per RFC 8201 section 4 */ if (!(rt->rt6i_flags & RTF_EXPIRES)) { if (time_after_eq(now, READ_ONCE(rt->dst.lastuse) + gc_args->timeout)) { pr_debug("aging clone %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } } else if (time_after(jiffies, READ_ONCE(rt->dst.expires))) { pr_debug("purging expired route %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } if (rt->rt6i_flags & RTF_GATEWAY) { struct neighbour *neigh; neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); if (!(neigh && (neigh->flags & NTF_ROUTER))) { pr_debug("purging route %p via non-router but gateway\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } } gc_args->more++; } static void fib6_nh_age_exceptions(const struct fib6_nh *nh, struct fib6_gc_args *gc_args, unsigned long now) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return; rcu_read_lock_bh(); spin_lock(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (bucket) { for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { rt6_age_examine_exception(bucket, rt6_ex, gc_args, now); } bucket++; } } spin_unlock(&rt6_exception_lock); rcu_read_unlock_bh(); } struct fib6_nh_age_excptn_arg { struct fib6_gc_args *gc_args; unsigned long now; }; static int rt6_nh_age_exceptions(struct fib6_nh *nh, void *_arg) { struct fib6_nh_age_excptn_arg *arg = _arg; fib6_nh_age_exceptions(nh, arg->gc_args, arg->now); return 0; } void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args, unsigned long now) { if (f6i->nh) { struct fib6_nh_age_excptn_arg arg = { .gc_args = gc_args, .now = now }; nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_age_exceptions, &arg); } else { fib6_nh_age_exceptions(f6i->fib6_nh, gc_args, now); } } /* must be called with rcu lock held */ int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int strict) { struct fib6_node *fn, *saved_fn; fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; redo_rt6_select: rt6_select(net, fn, oif, res, strict); if (res->f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto redo_rt6_select; else if (strict & RT6_LOOKUP_F_REACHABLE) { /* also consider unreachable route */ strict &= ~RT6_LOOKUP_F_REACHABLE; fn = saved_fn; goto redo_rt6_select; } } trace_fib6_table_lookup(net, res, table, fl6); return 0; } struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct fib6_result res = {}; struct rt6_info *rt = NULL; int strict = 0; WARN_ON_ONCE((flags & RT6_LOOKUP_F_DST_NOREF) && !rcu_read_lock_held()); strict |= flags & RT6_LOOKUP_F_IFACE; strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE; if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) strict |= RT6_LOOKUP_F_REACHABLE; rcu_read_lock(); fib6_table_lookup(net, table, oif, fl6, &res, strict); if (res.f6i == net->ipv6.fib6_null_entry) goto out; fib6_select_path(net, &res, fl6, oif, false, skb, strict); /*Search through exception table */ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr); if (rt) { goto out; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && !res.nh->fib_nh_gw_family)) { /* Create a RTF_CACHE clone which will not be * owned by the fib6 tree. It is for the special case where * the daddr in the skb during the neighbor look-up is different * from the fl6->daddr used to look-up route here. */ rt = ip6_rt_cache_alloc(&res, &fl6->daddr, NULL); if (rt) { /* 1 refcnt is taken during ip6_rt_cache_alloc(). * As rt6_uncached_list_add() does not consume refcnt, * this refcnt is always returned to the caller even * if caller sets RT6_LOOKUP_F_DST_NOREF flag. */ rt6_uncached_list_add(rt); rcu_read_unlock(); return rt; } } else { /* Get a percpu copy */ local_bh_disable(); rt = rt6_get_pcpu_route(&res); if (!rt) rt = rt6_make_pcpu_route(net, &res); local_bh_enable(); } out: if (!rt) rt = net->ipv6.ip6_null_entry; if (!(flags & RT6_LOOKUP_F_DST_NOREF)) ip6_hold_safe(net, &rt); rcu_read_unlock(); return rt; } EXPORT_SYMBOL_GPL(ip6_pol_route); INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, skb, flags); } struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG) flags |= RT6_LOOKUP_F_IFACE; return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_input); } EXPORT_SYMBOL_GPL(ip6_route_input_lookup); static void ip6_multipath_l3_keys(const struct sk_buff *skb, struct flow_keys *keys, struct flow_keys *flkeys) { const struct ipv6hdr *outer_iph = ipv6_hdr(skb); const struct ipv6hdr *key_iph = outer_iph; struct flow_keys *_flkeys = flkeys; const struct ipv6hdr *inner_iph; const struct icmp6hdr *icmph; struct ipv6hdr _inner_iph; struct icmp6hdr _icmph; if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6)) goto out; icmph = skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_icmph), &_icmph); if (!icmph) goto out; if (!icmpv6_is_err(icmph->icmp6_type)) goto out; inner_iph = skb_header_pointer(skb, skb_transport_offset(skb) + sizeof(*icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) goto out; key_iph = inner_iph; _flkeys = NULL; out: if (_flkeys) { keys->addrs.v6addrs.src = _flkeys->addrs.v6addrs.src; keys->addrs.v6addrs.dst = _flkeys->addrs.v6addrs.dst; keys->tags.flow_label = _flkeys->tags.flow_label; keys->basic.ip_proto = _flkeys->basic.ip_proto; } else { keys->addrs.v6addrs.src = key_iph->saddr; keys->addrs.v6addrs.dst = key_iph->daddr; keys->tags.flow_label = ip6_flowlabel(key_iph); keys->basic.ip_proto = key_iph->nexthdr; } } static u32 rt6_multipath_custom_hash_outer(const struct net *net, const struct sk_buff *skb, bool *p_has_inner) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys keys, hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_inner(const struct net *net, const struct sk_buff *skb, bool has_inner) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys keys, hash_keys; /* We assume the packet carries an encapsulation, but if none was * encountered during dissection of the outer flow, then there is no * point in calling the flow dissector again. */ if (!has_inner) return 0; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, 0); if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) return 0; if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_skb(const struct net *net, const struct sk_buff *skb) { u32 mhash, mhash_inner; bool has_inner = true; mhash = rt6_multipath_custom_hash_outer(net, skb, &has_inner); mhash_inner = rt6_multipath_custom_hash_inner(net, skb, has_inner); return jhash_2words(mhash, mhash_inner, 0); } static u32 rt6_multipath_custom_hash_fl6(const struct net *net, const struct flowi6 *fl6) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v6addrs.src = fl6->saddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v6addrs.dst = fl6->daddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = fl6->flowi6_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) { if (fl6->flowi6_flags & FLOWI_FLAG_ANY_SPORT) hash_keys.ports.src = (__force __be16)get_random_u16(); else hash_keys.ports.src = fl6->fl6_sport; } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl6->fl6_dport; return fib_multipath_hash_from_keys(net, &hash_keys); } /* if skb is set it will be used and fl6 can be NULL */ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, struct flow_keys *flkeys) { struct flow_keys hash_keys; u32 mhash = 0; switch (ip6_multipath_hash_policy(net)) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (skb) { ip6_multipath_l3_keys(skb, &hash_keys, flkeys); } else { hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 1: if (skb) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; struct flow_keys keys; /* short-circuit if we already have L4 hash present */ if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, flag); flkeys = &keys; } hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst; hash_keys.ports.src = flkeys->ports.src; hash_keys.ports.dst = flkeys->ports.dst; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; if (fl6->flowi6_flags & FLOWI_FLAG_ANY_SPORT) hash_keys.ports.src = (__force __be16)get_random_u16(); else hash_keys.ports.src = fl6->fl6_sport; hash_keys.ports.dst = fl6->fl6_dport; hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (skb) { struct flow_keys keys; if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, 0); flkeys = &keys; } /* Inner can be v4 or v6 */ if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; } else if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst; hash_keys.tags.flow_label = flkeys->tags.flow_label; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; ip6_multipath_l3_keys(skb, &hash_keys, flkeys); } } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 3: if (skb) mhash = rt6_multipath_custom_hash_skb(net, skb); else mhash = rt6_multipath_custom_hash_fl6(net, fl6); break; } return mhash >> 1; } /* Called with rcu held */ void ip6_route_input(struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct net *net = dev_net(skb->dev); int flags = RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_DST_NOREF; struct ip_tunnel_info *tun_info; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, }; struct flow_keys *flkeys = NULL, _flkeys; tun_info = skb_tunnel_info(skb); if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id; if (fib6_rules_early_flow_dissect(net, skb, &fl6, &_flkeys)) flkeys = &_flkeys; if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6)) fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, flkeys); skb_dst_drop(skb); skb_dst_set_noref(skb, ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags)); } INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, skb, flags); } static struct dst_entry *ip6_route_output_flags_noref(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags) { bool any_src; if (ipv6_addr_type(&fl6->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)) { struct dst_entry *dst; /* This function does not take refcnt on the dst */ dst = l3mdev_link_scope_lookup(net, fl6); if (dst) return dst; } fl6->flowi6_iif = LOOPBACK_IFINDEX; flags |= RT6_LOOKUP_F_DST_NOREF; any_src = ipv6_addr_any(&fl6->saddr); if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) || (fl6->flowi6_oif && any_src)) flags |= RT6_LOOKUP_F_IFACE; if (!any_src) flags |= RT6_LOOKUP_F_HAS_SADDR; else if (sk) flags |= rt6_srcprefs2flags(READ_ONCE(inet6_sk(sk)->srcprefs)); return fib6_rule_lookup(net, fl6, NULL, flags, ip6_pol_route_output); } struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags) { struct dst_entry *dst; struct rt6_info *rt6; rcu_read_lock(); dst = ip6_route_output_flags_noref(net, sk, fl6, flags); rt6 = dst_rt6_info(dst); /* For dst cached in uncached_list, refcnt is already taken. */ if (list_empty(&rt6->dst.rt_uncached) && !dst_hold_safe(dst)) { dst = &net->ipv6.ip6_null_entry->dst; dst_hold(dst); } rcu_read_unlock(); return dst; } EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { struct rt6_info *rt, *ort = dst_rt6_info(dst_orig); struct net_device *loopback_dev = net->loopback_dev; struct dst_entry *new = NULL; rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, DST_OBSOLETE_DEAD, 0); if (rt) { rt6_info_init(rt); atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_out; dst_copy_metrics(new, &ort->dst); rt->rt6i_idev = in6_dev_get(loopback_dev); rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); #ifdef CONFIG_IPV6_SUBTREES memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); #endif } dst_release(dst_orig); return new ? new : ERR_PTR(-ENOMEM); } /* * Destination cache support functions */ static bool fib6_check(struct fib6_info *f6i, u32 cookie) { u32 rt_cookie = 0; if (!fib6_get_cookie_safe(f6i, &rt_cookie) || rt_cookie != cookie) return false; if (fib6_check_expired(f6i)) return false; return true; } static struct dst_entry *rt6_check(struct rt6_info *rt, struct fib6_info *from, u32 cookie) { u32 rt_cookie = 0; if (!from || !fib6_get_cookie_safe(from, &rt_cookie) || rt_cookie != cookie) return NULL; if (rt6_check_expired(rt)) return NULL; return &rt->dst; } static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, struct fib6_info *from, u32 cookie) { if (!__rt6_check_expired(rt) && READ_ONCE(rt->dst.obsolete) == DST_OBSOLETE_FORCE_CHK && fib6_check(from, cookie)) return &rt->dst; return NULL; } INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) { struct dst_entry *dst_ret; struct fib6_info *from; struct rt6_info *rt; rt = dst_rt6_info(dst); if (rt->sernum) return rt6_is_valid(rt) ? dst : NULL; rcu_read_lock(); /* All IPV6 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ from = rcu_dereference(rt->from); if (from && (rt->rt6i_flags & RTF_PCPU || unlikely(!list_empty(&rt->dst.rt_uncached)))) dst_ret = rt6_dst_from_check(rt, from, cookie); else dst_ret = rt6_check(rt, from, cookie); rcu_read_unlock(); return dst_ret; } EXPORT_INDIRECT_CALLABLE(ip6_dst_check); static void ip6_negative_advice(struct sock *sk, struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_CACHE) { rcu_read_lock(); if (rt6_check_expired(rt)) { /* rt/dst can not be destroyed yet, * because of rcu_read_lock() */ sk_dst_reset(sk); rt6_remove_exception_rt(rt); } rcu_read_unlock(); return; } sk_dst_reset(sk); } static void ip6_link_failure(struct sk_buff *skb) { struct rt6_info *rt; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); rt = dst_rt6_info(skb_dst(skb)); if (rt) { rcu_read_lock(); if (rt->rt6i_flags & RTF_CACHE) { rt6_remove_exception_rt(rt); } else { struct fib6_info *from; struct fib6_node *fn; from = rcu_dereference(rt->from); if (from) { fn = rcu_dereference(from->fib6_node); if (fn && (rt->rt6i_flags & RTF_DEFAULT)) WRITE_ONCE(fn->fn_sernum, -1); } } rcu_read_unlock(); } } static void rt6_update_expires(struct rt6_info *rt0, int timeout) { if (!(rt0->rt6i_flags & RTF_EXPIRES)) { struct fib6_info *from; rcu_read_lock(); from = rcu_dereference(rt0->from); if (from) WRITE_ONCE(rt0->dst.expires, from->expires); rcu_read_unlock(); } dst_set_expires(&rt0->dst, timeout); rt0->rt6i_flags |= RTF_EXPIRES; } static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) { struct net *net = dev_net(rt->dst.dev); dst_metric_set(&rt->dst, RTAX_MTU, mtu); rt->rt6i_flags |= RTF_MODIFIED; rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); } static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) { return !(rt->rt6i_flags & RTF_CACHE) && (rt->rt6i_flags & RTF_PCPU || rcu_access_pointer(rt->from)); } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, const struct ipv6hdr *iph, u32 mtu, bool confirm_neigh) { const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = dst_rt6_info(dst); /* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU) * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it. * [see also comment in rt6_mtu_change_route()] */ if (iph) { daddr = &iph->daddr; saddr = &iph->saddr; } else if (sk) { daddr = &sk->sk_v6_daddr; saddr = &inet6_sk(sk)->saddr; } else { daddr = NULL; saddr = NULL; } if (confirm_neigh) dst_confirm_neigh(dst, daddr); if (mtu < IPV6_MIN_MTU) return; if (mtu >= dst_mtu(dst)) return; if (!rt6_cache_allowed_for_pmtu(rt6)) { rt6_do_update_pmtu(rt6, mtu); /* update rt6_ex->stamp for cache */ if (rt6->rt6i_flags & RTF_CACHE) rt6_update_exception_stamp_rt(rt6); } else if (daddr) { struct fib6_result res = {}; struct rt6_info *nrt6; rcu_read_lock(); res.f6i = rcu_dereference(rt6->from); if (!res.f6i) goto out_unlock; res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; if (res.f6i->nh) { struct fib6_nh_match_arg arg = { .dev = dst_dev_rcu(dst), .gw = &rt6->rt6i_gateway, }; nexthop_for_each_fib6_nh(res.f6i->nh, fib6_nh_find_match, &arg); /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev + gw. Should be impossible. */ if (!arg.match) goto out_unlock; res.nh = arg.match; } else { res.nh = res.f6i->fib6_nh; } nrt6 = ip6_rt_cache_alloc(&res, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); if (rt6_insert_exception(nrt6, &res)) dst_release_immediate(&nrt6->dst); } out_unlock: rcu_read_unlock(); } } static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu, confirm_neigh); } void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, u32 mark, kuid_t uid) { const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_oif = oif, .flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark), .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_uid = uid, }; dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) { int oif = sk->sk_bound_dev_if; struct dst_entry *dst; if (!oif && skb->dev) oif = l3mdev_master_ifindex(skb->dev); ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark), sk_uid(sk)); dst = __sk_dst_get(sk); if (!dst || !READ_ONCE(dst->obsolete) || dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) return; bh_lock_sock(sk); if (!sock_owned_by_user(sk) && !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) ip6_datagram_dst_update(sk, false); bh_unlock_sock(sk); } EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu); void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6) { #ifdef CONFIG_IPV6_SUBTREES struct ipv6_pinfo *np = inet6_sk(sk); #endif ip6_dst_store(sk, dst, ipv6_addr_equal(&fl6->daddr, &sk->sk_v6_daddr), #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_equal(&fl6->saddr, &np->saddr) ? true : #endif false); } static bool ip6_redirect_nh_match(const struct fib6_result *res, struct flowi6 *fl6, const struct in6_addr *gw, struct rt6_info **ret) { const struct fib6_nh *nh = res->nh; if (nh->fib_nh_flags & RTNH_F_DEAD || !nh->fib_nh_gw_family || fl6->flowi6_oif != nh->fib_nh_dev->ifindex) return false; /* rt_cache's gateway might be different from its 'parent' * in the case of an ip redirect. * So we keep searching in the exception table if the gateway * is different. */ if (!ipv6_addr_equal(gw, &nh->fib_nh_gw6)) { struct rt6_info *rt_cache; rt_cache = rt6_find_cached_rt(res, &fl6->daddr, &fl6->saddr); if (rt_cache && ipv6_addr_equal(gw, &rt_cache->rt6i_gateway)) { *ret = rt_cache; return true; } return false; } return true; } struct fib6_nh_rd_arg { struct fib6_result *res; struct flowi6 *fl6; const struct in6_addr *gw; struct rt6_info **ret; }; static int fib6_nh_redirect_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_rd_arg *arg = _arg; arg->res->nh = nh; return ip6_redirect_nh_match(arg->res, arg->fl6, arg->gw, arg->ret); } /* Handle redirects */ struct ip6rd_flowi { struct flowi6 fl6; struct in6_addr gateway; }; INDIRECT_CALLABLE_SCOPE struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; struct rt6_info *ret = NULL; struct fib6_result res = {}; struct fib6_nh_rd_arg arg = { .res = &res, .fl6 = fl6, .gw = &rdfl->gateway, .ret = &ret }; struct fib6_info *rt; struct fib6_node *fn; /* Get the "current" route for this destination and * check if the redirect has come from appropriate router. * * RFC 4861 specifies that redirects should only be * accepted if they come from the nexthop to the target. * Due to the way the routes are chosen, this notion * is a bit fuzzy and one might need to check all possible * routes. */ rcu_read_lock(); fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: for_each_fib6_node_rt_rcu(fn) { res.f6i = rt; if (fib6_check_expired(rt)) continue; if (rt->fib6_flags & RTF_REJECT) break; if (unlikely(rt->nh)) { if (nexthop_is_blackhole(rt->nh)) continue; /* on match, res->nh is filled in and potentially ret */ if (nexthop_for_each_fib6_nh(rt->nh, fib6_nh_redirect_match, &arg)) goto out; } else { res.nh = rt->fib6_nh; if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway, &ret)) goto out; } } if (!rt) rt = net->ipv6.fib6_null_entry; else if (rt->fib6_flags & RTF_REJECT) { ret = net->ipv6.ip6_null_entry; goto out; } if (rt == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; } res.f6i = rt; res.nh = rt->fib6_nh; out: if (ret) { ip6_hold_safe(net, &ret); } else { res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; ret = ip6_create_rt_rcu(&res); } rcu_read_unlock(); trace_fib6_table_lookup(net, &res, table, fl6); return ret; }; static struct dst_entry *ip6_route_redirect(struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, const struct in6_addr *gateway) { int flags = RT6_LOOKUP_F_HAS_SADDR; struct ip6rd_flowi rdfl; rdfl.fl6 = *fl6; rdfl.gateway = *gateway; return fib6_rule_lookup(net, &rdfl.fl6, skb, flags, __ip6_route_redirect); } void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, kuid_t uid) { const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_oif = oif, .flowi6_mark = mark, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_uid = uid, }; dst = ip6_route_redirect(net, &fl6, skb, &ipv6_hdr(skb)->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_redirect); void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct rd_msg *msg = (struct rd_msg *)icmp6_hdr(skb); struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_oif = oif, .daddr = msg->dest, .saddr = iph->daddr, .flowi6_uid = sock_net_uid(net, NULL), }; dst = ip6_route_redirect(net, &fl6, skb, &iph->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), sk_uid(sk)); } EXPORT_SYMBOL_GPL(ip6_sk_redirect); static unsigned int ip6_default_advmss(const struct dst_entry *dst) { unsigned int mtu = dst_mtu(dst); struct net *net; mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr); rcu_read_lock(); net = dst_dev_net_rcu(dst); if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss) mtu = net->ipv6.sysctl.ip6_rt_min_advmss; rcu_read_unlock(); /* * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and * corresponding MSS is IPV6_MAXPLEN - tcp_header_size. * IPV6_MAXPLEN is also valid and means: "any MSS, * rely only on pmtu discovery" */ if (mtu > IPV6_MAXPLEN - sizeof(struct tcphdr)) mtu = IPV6_MAXPLEN; return mtu; } INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst) { return ip6_dst_mtu_maybe_forward(dst, false); } EXPORT_INDIRECT_CALLABLE(ip6_mtu); /* MTU selection: * 1. mtu on route is locked - use it * 2. mtu from nexthop exception * 3. mtu from egress device * * based on ip6_dst_mtu_forward and exception logic of * rt6_find_cached_rt; called with rcu_read_lock */ u32 ip6_mtu_from_fib6(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { const struct fib6_nh *nh = res->nh; struct fib6_info *f6i = res->f6i; struct inet6_dev *idev; struct rt6_info *rt; u32 mtu = 0; if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) { mtu = f6i->fib6_pmtu; if (mtu) goto out; } rt = rt6_find_cached_rt(res, daddr, saddr); if (unlikely(rt)) { mtu = dst_metric_raw(&rt->dst, RTAX_MTU); } else { struct net_device *dev = nh->fib_nh_dev; mtu = IPV6_MIN_MTU; idev = __in6_dev_get(dev); if (idev) mtu = max_t(u32, mtu, READ_ONCE(idev->cnf.mtu6)); } mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); out: return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu); } struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6) { struct dst_entry *dst; struct rt6_info *rt; struct inet6_dev *idev = in6_dev_get(dev); struct net *net = dev_net(dev); if (unlikely(!idev)) return ERR_PTR(-ENODEV); rt = ip6_dst_alloc(net, dev, 0); if (unlikely(!rt)) { in6_dev_put(idev); dst = ERR_PTR(-ENOMEM); goto out; } rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); /* Add this dst into uncached_list so that rt6_disable_ip() can * do proper release of the net_device */ rt6_uncached_list_add(rt); dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); out: return dst; } static void ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; unsigned int val; int entries; if (time_after(rt_last_gc + rt_min_interval, jiffies)) goto out; fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1); out: val = atomic_read(&net->ipv6.ip6_rt_gc_expire); atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); } static int ip6_nh_lookup_table(struct net *net, struct fib6_config *cfg, const struct in6_addr *gw_addr, u32 tbid, int flags, struct fib6_result *res) { struct flowi6 fl6 = { .flowi6_oif = cfg->fc_ifindex, .daddr = *gw_addr, .saddr = cfg->fc_prefsrc, }; struct fib6_table *table; int err; table = fib6_get_table(net, tbid); if (!table) return -EINVAL; if (!ipv6_addr_any(&cfg->fc_prefsrc)) flags |= RT6_LOOKUP_F_HAS_SADDR; flags |= RT6_LOOKUP_F_IGNORE_LINKSTATE; err = fib6_table_lookup(net, table, cfg->fc_ifindex, &fl6, res, flags); if (!err && res->f6i != net->ipv6.fib6_null_entry) fib6_select_path(net, res, &fl6, cfg->fc_ifindex, cfg->fc_ifindex != 0, NULL, flags); return err; } static int ip6_route_check_nh_onlink(struct net *net, struct fib6_config *cfg, const struct net_device *dev, struct netlink_ext_ack *extack) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; const struct in6_addr *gw_addr = &cfg->fc_gateway; struct fib6_result res = {}; int err; err = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0, &res); if (!err && !(res.fib6_flags & RTF_REJECT) && /* ignore match if it is the default route */ !ipv6_addr_any(&res.f6i->fib6_dst.addr) && (res.fib6_type != RTN_UNICAST || dev != res.nh->fib_nh_dev)) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway or device mismatch"); err = -EINVAL; } return err; } static int ip6_route_check_nh(struct net *net, struct fib6_config *cfg, struct net_device **_dev, netdevice_tracker *dev_tracker, struct inet6_dev **idev) { const struct in6_addr *gw_addr = &cfg->fc_gateway; struct net_device *dev = _dev ? *_dev : NULL; int flags = RT6_LOOKUP_F_IFACE; struct fib6_result res = {}; int err = -EHOSTUNREACH; if (cfg->fc_table) { err = ip6_nh_lookup_table(net, cfg, gw_addr, cfg->fc_table, flags, &res); /* gw_addr can not require a gateway or resolve to a reject * route. If a device is given, it must match the result. */ if (err || res.fib6_flags & RTF_REJECT || res.nh->fib_nh_gw_family || (dev && dev != res.nh->fib_nh_dev)) err = -EHOSTUNREACH; } if (err < 0) { struct flowi6 fl6 = { .flowi6_oif = cfg->fc_ifindex, .daddr = *gw_addr, }; err = fib6_lookup(net, cfg->fc_ifindex, &fl6, &res, flags); if (err || res.fib6_flags & RTF_REJECT || res.nh->fib_nh_gw_family) err = -EHOSTUNREACH; if (err) return err; fib6_select_path(net, &res, &fl6, cfg->fc_ifindex, cfg->fc_ifindex != 0, NULL, flags); } err = 0; if (dev) { if (dev != res.nh->fib_nh_dev) err = -EHOSTUNREACH; } else { *_dev = dev = res.nh->fib_nh_dev; netdev_hold(dev, dev_tracker, GFP_ATOMIC); *idev = in6_dev_get(dev); } return err; } static int ip6_validate_gw(struct net *net, struct fib6_config *cfg, struct net_device **_dev, netdevice_tracker *dev_tracker, struct inet6_dev **idev, struct netlink_ext_ack *extack) { const struct in6_addr *gw_addr = &cfg->fc_gateway; int gwa_type = ipv6_addr_type(gw_addr); bool skip_dev = gwa_type & IPV6_ADDR_LINKLOCAL ? false : true; const struct net_device *dev = *_dev; bool need_addr_check = !dev; int err = -EINVAL; /* if gw_addr is local we will fail to detect this in case * address is still TENTATIVE (DAD in progress). rt6_lookup() * will return already-added prefix route via interface that * prefix route was assigned to, which might be non-loopback. */ if (dev && ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); goto out; } if (gwa_type != (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_UNICAST)) { /* IPv6 strictly inhibits using not link-local * addresses as nexthop address. * Otherwise, router will not able to send redirects. * It is very good, but in some (rare!) circumstances * (SIT, PtP, NBMA NOARP links) it is handy to allow * some exceptions. --ANK * We allow IPv4-mapped nexthops to support RFC4798-type * addressing */ if (!(gwa_type & (IPV6_ADDR_UNICAST | IPV6_ADDR_MAPPED))) { NL_SET_ERR_MSG(extack, "Invalid gateway address"); goto out; } rcu_read_lock(); if (cfg->fc_flags & RTNH_F_ONLINK) err = ip6_route_check_nh_onlink(net, cfg, dev, extack); else err = ip6_route_check_nh(net, cfg, _dev, dev_tracker, idev); rcu_read_unlock(); if (err) goto out; } /* reload in case device was changed */ dev = *_dev; err = -EINVAL; if (!dev) { NL_SET_ERR_MSG(extack, "Egress device not specified"); goto out; } else if (dev->flags & IFF_LOOPBACK) { NL_SET_ERR_MSG(extack, "Egress device can not be loopback device for this route"); goto out; } /* if we did not check gw_addr above, do so now that the * egress device has been resolved. */ if (need_addr_check && ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); goto out; } err = 0; out: return err; } static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type) { if ((flags & RTF_REJECT) || (dev && (dev->flags & IFF_LOOPBACK) && !(addr_type & IPV6_ADDR_LOOPBACK) && !(flags & (RTF_ANYCAST | RTF_LOCAL)))) return true; return false; } int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; int addr_type; int err; fib6_nh->fib_nh_family = AF_INET6; #ifdef CONFIG_IPV6_ROUTER_PREF fib6_nh->last_probe = jiffies; #endif if (cfg->fc_is_fdb) { fib6_nh->fib_nh_gw6 = cfg->fc_gateway; fib6_nh->fib_nh_gw_family = AF_INET6; return 0; } err = -ENODEV; if (cfg->fc_ifindex) { dev = netdev_get_by_index(net, cfg->fc_ifindex, dev_tracker, gfp_flags); if (!dev) goto out; idev = in6_dev_get(dev); if (!idev) goto out; } if (cfg->fc_flags & RTNH_F_ONLINK) { if (!dev) { NL_SET_ERR_MSG(extack, "Nexthop device required for onlink"); goto out; } if (!(dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } fib6_nh->fib_nh_flags |= RTNH_F_ONLINK; } fib6_nh->fib_nh_weight = 1; /* We cannot add true routes via loopback here, * they would result in kernel looping; promote them to reject routes */ addr_type = ipv6_addr_type(&cfg->fc_dst); if (fib6_is_reject(cfg->fc_flags, dev, addr_type)) { /* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) { if (dev) { netdev_put(dev, dev_tracker); in6_dev_put(idev); } dev = net->loopback_dev; netdev_hold(dev, dev_tracker, gfp_flags); idev = in6_dev_get(dev); if (!idev) { err = -ENODEV; goto out; } } goto pcpu_alloc; } if (cfg->fc_flags & RTF_GATEWAY) { err = ip6_validate_gw(net, cfg, &dev, dev_tracker, &idev, extack); if (err) goto out; fib6_nh->fib_nh_gw6 = cfg->fc_gateway; fib6_nh->fib_nh_gw_family = AF_INET6; } err = -ENODEV; if (!dev) goto out; if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device"); err = -EACCES; goto out; } if (!(dev->flags & IFF_UP) && !cfg->fc_ignore_dev_down) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } if (!(cfg->fc_flags & (RTF_LOCAL | RTF_ANYCAST)) && !netif_carrier_ok(dev)) fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = fib_nh_common_init(net, &fib6_nh->nh_common, cfg->fc_encap, cfg->fc_encap_type, cfg, gfp_flags, extack); if (err) goto out; pcpu_alloc: fib6_nh->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags); if (!fib6_nh->rt6i_pcpu) { err = -ENOMEM; goto out; } fib6_nh->fib_nh_dev = dev; fib6_nh->fib_nh_oif = dev->ifindex; err = 0; out: if (idev) in6_dev_put(idev); if (err) { fib_nh_common_release(&fib6_nh->nh_common); fib6_nh->nh_common.nhc_pcpu_rth_output = NULL; fib6_nh->fib_nh_lws = NULL; netdev_put(dev, dev_tracker); } return err; } void fib6_nh_release(struct fib6_nh *fib6_nh) { struct rt6_exception_bucket *bucket; rcu_read_lock(); fib6_nh_flush_exceptions(fib6_nh, NULL); bucket = fib6_nh_get_excptn_bucket(fib6_nh, NULL); if (bucket) { rcu_assign_pointer(fib6_nh->rt6i_exception_bucket, NULL); kfree(bucket); } rcu_read_unlock(); fib6_nh_release_dsts(fib6_nh); free_percpu(fib6_nh->rt6i_pcpu); fib_nh_common_release(&fib6_nh->nh_common); } void fib6_nh_release_dsts(struct fib6_nh *fib6_nh) { int cpu; if (!fib6_nh->rt6i_pcpu) return; for_each_possible_cpu(cpu) { struct rt6_info *pcpu_rt, **ppcpu_rt; ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); pcpu_rt = xchg(ppcpu_rt, NULL); if (pcpu_rt) { dst_dev_put(&pcpu_rt->dst); dst_release(&pcpu_rt->dst); } } } static int fib6_config_validate(struct fib6_config *cfg, struct netlink_ext_ack *extack) { /* RTF_PCPU is an internal flag; can not be set by userspace */ if (cfg->fc_flags & RTF_PCPU) { NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU"); goto errout; } /* RTF_CACHE is an internal flag; can not be set by userspace */ if (cfg->fc_flags & RTF_CACHE) { NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE"); goto errout; } if (cfg->fc_type > RTN_MAX) { NL_SET_ERR_MSG(extack, "Invalid route type"); goto errout; } if (cfg->fc_dst_len > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); goto errout; } #ifdef CONFIG_IPV6_SUBTREES if (cfg->fc_src_len > 128) { NL_SET_ERR_MSG(extack, "Invalid source address length"); goto errout; } if (cfg->fc_nh_id && cfg->fc_src_len) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); goto errout; } #else if (cfg->fc_src_len) { NL_SET_ERR_MSG(extack, "Specifying source address requires IPV6_SUBTREES to be enabled"); goto errout; } #endif return 0; errout: return -EINVAL; } static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; struct fib6_table *table; struct fib6_info *rt; int err; if (cfg->fc_nlinfo.nlh && !(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) { table = fib6_get_table(net, cfg->fc_table); if (!table) { pr_warn("NLM_F_CREATE should be specified when creating new route\n"); table = fib6_new_table(net, cfg->fc_table); } } else { table = fib6_new_table(net, cfg->fc_table); } if (!table) { err = -ENOBUFS; goto err; } rt = fib6_info_alloc(gfp_flags, !cfg->fc_nh_id); if (!rt) { err = -ENOMEM; goto err; } rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack); if (IS_ERR(rt->fib6_metrics)) { err = PTR_ERR(rt->fib6_metrics); goto free; } if (cfg->fc_flags & RTF_ADDRCONF) rt->dst_nocount = true; if (cfg->fc_flags & RTF_EXPIRES) fib6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; rt->fib6_protocol = cfg->fc_protocol; rt->fib6_table = table; rt->fib6_metric = cfg->fc_metric; rt->fib6_type = cfg->fc_type ? : RTN_UNICAST; rt->fib6_flags = cfg->fc_flags & ~RTF_GATEWAY; ipv6_addr_prefix(&rt->fib6_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->fib6_dst.plen = cfg->fc_dst_len; #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len); rt->fib6_src.plen = cfg->fc_src_len; #endif return rt; free: kfree(rt); err: return ERR_PTR(err); } static int ip6_route_info_create_nh(struct fib6_info *rt, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; struct fib6_nh *fib6_nh; int err; if (cfg->fc_nh_id) { struct nexthop *nh; rcu_read_lock(); nh = nexthop_find_by_id(net, cfg->fc_nh_id); if (!nh) { err = -EINVAL; NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); goto out_free; } err = fib6_check_nexthop(nh, cfg, extack); if (err) goto out_free; if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); err = -ENOENT; goto out_free; } rt->nh = nh; fib6_nh = nexthop_fib6_nh(rt->nh); rcu_read_unlock(); } else { int addr_type; err = fib6_nh_init(net, rt->fib6_nh, cfg, gfp_flags, extack); if (err) goto out_release; fib6_nh = rt->fib6_nh; /* We cannot add true routes via loopback here, they would * result in kernel looping; promote them to reject routes */ addr_type = ipv6_addr_type(&cfg->fc_dst); if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh->fib_nh_dev, addr_type)) rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP; } if (!ipv6_addr_any(&cfg->fc_prefsrc)) { struct net_device *dev = fib6_nh->fib_nh_dev; if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) { NL_SET_ERR_MSG(extack, "Invalid source address"); err = -EINVAL; goto out_release; } rt->fib6_prefsrc.addr = cfg->fc_prefsrc; rt->fib6_prefsrc.plen = 128; } return 0; out_release: fib6_info_release(rt); return err; out_free: rcu_read_unlock(); ip_fib_metrics_put(rt->fib6_metrics); kfree(rt); return err; } int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct fib6_info *rt; int err; err = fib6_config_validate(cfg, extack); if (err) return err; rt = ip6_route_info_create(cfg, gfp_flags, extack); if (IS_ERR(rt)) return PTR_ERR(rt); err = ip6_route_info_create_nh(rt, cfg, gfp_flags, extack); if (err) return err; err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack); fib6_info_release(rt); return err; } static int __ip6_del_rt(struct fib6_info *rt, struct nl_info *info) { struct net *net = info->nl_net; struct fib6_table *table; int err; if (rt == net->ipv6.fib6_null_entry) { err = -ENOENT; goto out; } table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); err = fib6_del(rt, info); spin_unlock_bh(&table->tb6_lock); out: fib6_info_release(rt); return err; } int ip6_del_rt(struct net *net, struct fib6_info *rt, bool skip_notify) { struct nl_info info = { .nl_net = net, .skip_notify = skip_notify }; return __ip6_del_rt(rt, &info); } static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) { struct nl_info *info = &cfg->fc_nlinfo; struct net *net = info->nl_net; struct sk_buff *skb = NULL; struct fib6_table *table; int err = -ENOENT; if (rt == net->ipv6.fib6_null_entry) goto out_put; table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); if (rt->fib6_nsiblings && cfg->fc_delete_all_nh) { struct fib6_info *sibling, *next_sibling; struct fib6_node *fn; /* prefer to send a single notification with all hops */ skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (skb) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; if (rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, RTM_DELROUTE, info->portid, seq, 0) < 0) { kfree_skb(skb); skb = NULL; } else info->skip_notify = 1; } /* 'rt' points to the first sibling route. If it is not the * leaf, then we do not need to send a notification. Otherwise, * we need to check if the last sibling has a next route or not * and emit a replace or delete notification, respectively. */ info->skip_notify_kernel = 1; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&table->tb6_lock)); if (rcu_access_pointer(fn->leaf) == rt) { struct fib6_info *last_sibling, *replace_rt; last_sibling = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); replace_rt = rcu_dereference_protected( last_sibling->fib6_next, lockdep_is_held(&table->tb6_lock)); if (replace_rt) call_fib6_entry_notifiers_replace(net, replace_rt); else call_fib6_multipath_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, rt->fib6_nsiblings, NULL); } list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { err = fib6_del(sibling, info); if (err) goto out_unlock; } } err = fib6_del(rt, info); out_unlock: spin_unlock_bh(&table->tb6_lock); out_put: fib6_info_release(rt); if (skb) { rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); } return err; } static int __ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg) { int rc = -ESRCH; if (cfg->fc_ifindex && rt->dst.dev->ifindex != cfg->fc_ifindex) goto out; if (cfg->fc_flags & RTF_GATEWAY && !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) goto out; rc = rt6_remove_exception_rt(rt); out: return rc; } static int ip6_del_cached_rt(struct fib6_config *cfg, struct fib6_info *rt, struct fib6_nh *nh) { struct fib6_result res = { .f6i = rt, .nh = nh, }; struct rt6_info *rt_cache; rt_cache = rt6_find_cached_rt(&res, &cfg->fc_dst, &cfg->fc_src); if (rt_cache) return __ip6_del_cached_rt(rt_cache, cfg); return 0; } struct fib6_nh_del_cached_rt_arg { struct fib6_config *cfg; struct fib6_info *f6i; }; static int fib6_nh_del_cached_rt(struct fib6_nh *nh, void *_arg) { struct fib6_nh_del_cached_rt_arg *arg = _arg; int rc; rc = ip6_del_cached_rt(arg->cfg, arg->f6i, nh); return rc != -ESRCH ? rc : 0; } static int ip6_del_cached_rt_nh(struct fib6_config *cfg, struct fib6_info *f6i) { struct fib6_nh_del_cached_rt_arg arg = { .cfg = cfg, .f6i = f6i }; return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_del_cached_rt, &arg); } static int ip6_route_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_table *table; struct fib6_info *rt; struct fib6_node *fn; int err = -ESRCH; table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); if (!table) { NL_SET_ERR_MSG(extack, "FIB table does not exist"); return err; } rcu_read_lock(); fn = fib6_locate(&table->tb6_root, &cfg->fc_dst, cfg->fc_dst_len, &cfg->fc_src, cfg->fc_src_len, !(cfg->fc_flags & RTF_CACHE)); if (fn) { for_each_fib6_node_rt_rcu(fn) { struct fib6_nh *nh; if (rt->nh && cfg->fc_nh_id && rt->nh->id != cfg->fc_nh_id) continue; if (cfg->fc_flags & RTF_CACHE) { int rc = 0; if (rt->nh) { rc = ip6_del_cached_rt_nh(cfg, rt); } else if (cfg->fc_nh_id) { continue; } else { nh = rt->fib6_nh; rc = ip6_del_cached_rt(cfg, rt, nh); } if (rc != -ESRCH) { rcu_read_unlock(); return rc; } continue; } if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric) continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol) continue; if (rt->nh) { if (!fib6_info_hold_safe(rt)) continue; err = __ip6_del_rt(rt, &cfg->fc_nlinfo); break; } if (cfg->fc_nh_id) continue; nh = rt->fib6_nh; if (cfg->fc_ifindex && (!nh->fib_nh_dev || nh->fib_nh_dev->ifindex != cfg->fc_ifindex)) continue; if (cfg->fc_flags & RTF_GATEWAY && !ipv6_addr_equal(&cfg->fc_gateway, &nh->fib_nh_gw6)) continue; if (!fib6_info_hold_safe(rt)) continue; /* if gateway was specified only delete the one hop */ if (cfg->fc_flags & RTF_GATEWAY) err = __ip6_del_rt(rt, &cfg->fc_nlinfo); else err = __ip6_del_rt_siblings(rt, cfg); break; } } rcu_read_unlock(); return err; } static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct netevent_redirect netevent; struct rt6_info *rt, *nrt = NULL; struct fib6_result res = {}; struct ndisc_options ndopts; struct inet6_dev *in6_dev; struct neighbour *neigh; struct rd_msg *msg; int optlen, on_link; u8 *lladdr; optlen = skb_tail_pointer(skb) - skb_transport_header(skb); optlen -= sizeof(*msg); if (optlen < 0) { net_dbg_ratelimited("rt6_do_redirect: packet too short\n"); return; } msg = (struct rd_msg *)icmp6_hdr(skb); if (ipv6_addr_is_multicast(&msg->dest)) { net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n"); return; } on_link = 0; if (ipv6_addr_equal(&msg->dest, &msg->target)) { on_link = 1; } else if (ipv6_addr_type(&msg->target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n"); return; } in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) return; if (READ_ONCE(in6_dev->cnf.forwarding) || !READ_ONCE(in6_dev->cnf.accept_redirects)) return; /* RFC2461 8.1: * The IP source address of the Redirect MUST be the same as the current * first-hop router for the specified ICMP Destination Address. */ if (!ndisc_parse_options(skb->dev, msg->opt, optlen, &ndopts)) { net_dbg_ratelimited("rt6_redirect: invalid ND options\n"); return; } lladdr = NULL; if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, skb->dev); if (!lladdr) { net_dbg_ratelimited("rt6_redirect: invalid link-layer address length\n"); return; } } rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_REJECT) { net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n"); return; } /* Redirect received -> path was valid. * Look, redirects are sent only in response to data packets, * so that this nexthop apparently is reachable. --ANK */ dst_confirm_neigh(&rt->dst, &ipv6_hdr(skb)->saddr); neigh = __neigh_lookup(&nd_tbl, &msg->target, skb->dev, 1); if (!neigh) return; /* * We have finally decided to accept it. */ ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| (on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER| NEIGH_UPDATE_F_ISROUTER)), NDISC_REDIRECT, &ndopts); rcu_read_lock(); res.f6i = rcu_dereference(rt->from); if (!res.f6i) goto out; if (res.f6i->nh) { struct fib6_nh_match_arg arg = { .dev = dst_dev_rcu(dst), .gw = &rt->rt6i_gateway, }; nexthop_for_each_fib6_nh(res.f6i->nh, fib6_nh_find_match, &arg); /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev. Should be impossible */ if (!arg.match) goto out; res.nh = arg.match; } else { res.nh = res.f6i->fib6_nh; } res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; nrt = ip6_rt_cache_alloc(&res, &msg->dest, NULL); if (!nrt) goto out; nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE; if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; /* rt6_insert_exception() will take care of duplicated exceptions */ if (rt6_insert_exception(nrt, &res)) { dst_release_immediate(&nrt->dst); goto out; } netevent.old = &rt->dst; netevent.new = &nrt->dst; netevent.daddr = &msg->dest; netevent.neigh = neigh; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); out: rcu_read_unlock(); neigh_release(neigh); } #ifdef CONFIG_IPV6_ROUTE_INFO static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev) { u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; int ifindex = dev->ifindex; struct fib6_node *fn; struct fib6_info *rt = NULL; struct fib6_table *table; table = fib6_get_table(net, tb_id); if (!table) return NULL; rcu_read_lock(); fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0, true); if (!fn) goto out; for_each_fib6_node_rt_rcu(fn) { /* these routes do not use nexthops */ if (rt->nh) continue; if (rt->fib6_nh->fib_nh_dev->ifindex != ifindex) continue; if (!(rt->fib6_flags & RTF_ROUTEINFO) || !rt->fib6_nh->fib_nh_gw_family) continue; if (!ipv6_addr_equal(&rt->fib6_nh->fib_nh_gw6, gwaddr)) continue; if (!fib6_info_hold_safe(rt)) continue; break; } out: rcu_read_unlock(); return rt; } static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref) { struct fib6_config cfg = { .fc_metric = IP6_RT_PRIO_USER, .fc_ifindex = dev->ifindex, .fc_dst_len = prefixlen, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref), .fc_protocol = RTPROT_RA, .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, }; cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; cfg.fc_dst = *prefix; cfg.fc_gateway = *gwaddr; /* We should treat it as a default route if prefix length is 0. */ if (!prefixlen) cfg.fc_flags |= RTF_DEFAULT; ip6_route_add(&cfg, GFP_ATOMIC, NULL); return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev); } #endif struct fib6_info *rt6_get_dflt_router(struct net *net, const struct in6_addr *addr, struct net_device *dev) { u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT; struct fib6_info *rt; struct fib6_table *table; table = fib6_get_table(net, tb_id); if (!table) return NULL; rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { struct fib6_nh *nh; /* RA routes do not use nexthops */ if (rt->nh) continue; nh = rt->fib6_nh; if (dev == nh->fib_nh_dev && ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&nh->fib_nh_gw6, addr)) break; } if (rt && !fib6_info_hold_safe(rt)) rt = NULL; rcu_read_unlock(); return rt; } struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref, u32 defrtr_usr_metric, int lifetime) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, .fc_metric = defrtr_usr_metric, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), .fc_protocol = RTPROT_RA, .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, .fc_expires = jiffies_to_clock_t(lifetime * HZ), }; cfg.fc_gateway = *gwaddr; if (!ip6_route_add(&cfg, GFP_ATOMIC, NULL)) { struct fib6_table *table; table = fib6_get_table(dev_net(dev), cfg.fc_table); if (table) table->flags |= RT6_TABLE_HAS_DFLT_ROUTER; } return rt6_get_dflt_router(net, gwaddr, dev); } static void __rt6_purge_dflt_routers(struct net *net, struct fib6_table *table) { struct fib6_info *rt; restart: rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { struct net_device *dev = fib6_info_nh_dev(rt); struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL; if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) && (!idev || idev->cnf.accept_ra != 2) && fib6_info_hold_safe(rt)) { rcu_read_unlock(); ip6_del_rt(net, rt, false); goto restart; } } rcu_read_unlock(); table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER; } void rt6_purge_dflt_routers(struct net *net) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER) __rt6_purge_dflt_routers(net, table); } } rcu_read_unlock(); } static void rtmsg_to_fib6_config(struct net *net, struct in6_rtmsg *rtmsg, struct fib6_config *cfg) { *cfg = (struct fib6_config){ .fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ? : RT6_TABLE_MAIN, .fc_ifindex = rtmsg->rtmsg_ifindex, .fc_metric = rtmsg->rtmsg_metric, .fc_expires = rtmsg->rtmsg_info, .fc_dst_len = rtmsg->rtmsg_dst_len, .fc_src_len = rtmsg->rtmsg_src_len, .fc_flags = rtmsg->rtmsg_flags, .fc_type = rtmsg->rtmsg_type, .fc_nlinfo.nl_net = net, .fc_dst = rtmsg->rtmsg_dst, .fc_src = rtmsg->rtmsg_src, .fc_gateway = rtmsg->rtmsg_gateway, }; } int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg) { struct fib6_config cfg; int err; if (cmd != SIOCADDRT && cmd != SIOCDELRT) return -EINVAL; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtmsg_to_fib6_config(net, rtmsg, &cfg); switch (cmd) { case SIOCADDRT: /* Only do the default setting of fc_metric in route adding */ if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; err = ip6_route_add(&cfg, GFP_KERNEL, NULL); break; case SIOCDELRT: err = ip6_route_del(&cfg, NULL); break; } return err; } /* * Drop the packet on the floor */ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst_dev(dst); struct net *net = dev_net(dev); struct inet6_dev *idev; SKB_DR(reason); int type; if (netif_is_l3_master(skb->dev) || dev == net->loopback_dev) idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); else idev = ip6_dst_idev(dst); switch (ipstats_mib_noroutes) { case IPSTATS_MIB_INNOROUTES: type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); if (type == IPV6_ADDR_ANY) { SKB_DR_SET(reason, IP_INADDRERRORS); IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); break; } SKB_DR_SET(reason, IP_INNOROUTES); fallthrough; case IPSTATS_MIB_OUTNOROUTES: SKB_DR_OR(reason, IP_OUTNOROUTES); IP6_INC_STATS(net, idev, ipstats_mib_noroutes); break; } /* Start over by dropping the dst for l3mdev case */ if (netif_is_l3_master(skb->dev)) skb_dst_drop(skb); icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0); kfree_skb_reason(skb, reason); return 0; } static int ip6_pkt_discard(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES); } static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst_dev(skb); return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); } static int ip6_pkt_prohibit(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); } static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst_dev(skb); return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } /* * Allocate a dst for local (unicast / anycast) address. */ struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev, const struct in6_addr *addr, bool anycast, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL, .fc_ifindex = idev->dev->ifindex, .fc_flags = RTF_UP | RTF_NONEXTHOP, .fc_dst = *addr, .fc_dst_len = 128, .fc_protocol = RTPROT_KERNEL, .fc_nlinfo.nl_net = net, .fc_ignore_dev_down = true, }; struct fib6_info *f6i; int err; if (anycast) { cfg.fc_type = RTN_ANYCAST; cfg.fc_flags |= RTF_ANYCAST; } else { cfg.fc_type = RTN_LOCAL; cfg.fc_flags |= RTF_LOCAL; } f6i = ip6_route_info_create(&cfg, gfp_flags, extack); if (IS_ERR(f6i)) return f6i; err = ip6_route_info_create_nh(f6i, &cfg, gfp_flags, extack); if (err) return ERR_PTR(err); f6i->dst_nocount = true; if (!anycast && (READ_ONCE(net->ipv6.devconf_all->disable_policy) || READ_ONCE(idev->cnf.disable_policy))) f6i->dst_nopolicy = true; return f6i; } /* remove deleted ip from prefsrc entries */ struct arg_dev_net_ip { struct net *net; struct in6_addr *addr; }; static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg) { struct net *net = ((struct arg_dev_net_ip *)arg)->net; struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr; if (!rt->nh && rt != net->ipv6.fib6_null_entry && ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr) && !ipv6_chk_addr(net, addr, rt->fib6_nh->fib_nh_dev, 0)) { spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ rt->fib6_prefsrc.plen = 0; spin_unlock_bh(&rt6_exception_lock); } return 0; } void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) { struct net *net = dev_net(ifp->idev->dev); struct arg_dev_net_ip adni = { .net = net, .addr = &ifp->addr, }; fib6_clean_all(net, fib6_remove_prefsrc, &adni); } #define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT) /* Remove routers and update dst entries when gateway turn into host. */ static int fib6_clean_tohost(struct fib6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; struct fib6_nh *nh; /* RA routes do not use nexthops */ if (rt->nh) return 0; nh = rt->fib6_nh; if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && nh->fib_nh_gw_family && ipv6_addr_equal(gateway, &nh->fib_nh_gw6)) return -1; /* Further clean up cached routes in exception table. * This is needed because cached route may have a different * gateway than its 'parent' in the case of an ip redirect. */ fib6_nh_exceptions_clean_tohost(nh, gateway); return 0; } void rt6_clean_tohost(struct net *net, struct in6_addr *gateway) { fib6_clean_all(net, fib6_clean_tohost, gateway); } struct arg_netdev_event { const struct net_device *dev; union { unsigned char nh_flags; unsigned long event; }; }; static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt) { struct fib6_info *iter; struct fib6_node *fn; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&rt->fib6_table->tb6_lock)); iter = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(iter)) return iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); } return NULL; } /* only called for fib entries with builtin fib6_nh */ static bool rt6_is_dead(const struct fib6_info *rt) { if (rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD || (rt->fib6_nh->fib_nh_flags & RTNH_F_LINKDOWN && ip6_ignore_linkdown(rt->fib6_nh->fib_nh_dev))) return true; return false; } static int rt6_multipath_total_weight(const struct fib6_info *rt) { struct fib6_info *iter; int total = 0; if (!rt6_is_dead(rt)) total += rt->fib6_nh->fib_nh_weight; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { if (!rt6_is_dead(iter)) total += iter->fib6_nh->fib_nh_weight; } return total; } static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total) { int upper_bound = -1; if (!rt6_is_dead(rt)) { *weight += rt->fib6_nh->fib_nh_weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31, total) - 1; } atomic_set(&rt->fib6_nh->fib_nh_upper_bound, upper_bound); } static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total) { struct fib6_info *iter; int weight = 0; rt6_upper_bound_set(rt, &weight, total); list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) rt6_upper_bound_set(iter, &weight, total); } void rt6_multipath_rebalance(struct fib6_info *rt) { struct fib6_info *first; int total; /* In case the entire multipath route was marked for flushing, * then there is no need to rebalance upon the removal of every * sibling route. */ if (!rt->fib6_nsiblings || rt->should_flush) return; /* During lookup routes are evaluated in order, so we need to * make sure upper bounds are assigned from the first sibling * onwards. */ first = rt6_multipath_first_sibling(rt); if (WARN_ON_ONCE(!first)) return; total = rt6_multipath_total_weight(first); rt6_multipath_upper_bound_set(first, total); } static int fib6_ifup(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; struct net *net = dev_net(arg->dev); if (rt != net->ipv6.fib6_null_entry && !rt->nh && rt->fib6_nh->fib_nh_dev == arg->dev) { rt->fib6_nh->fib_nh_flags &= ~arg->nh_flags; fib6_update_sernum_upto_root(net, rt); rt6_multipath_rebalance(rt); } return 0; } void rt6_sync_up(struct net_device *dev, unsigned char nh_flags) { struct arg_netdev_event arg = { .dev = dev, { .nh_flags = nh_flags, }, }; if (nh_flags & RTNH_F_DEAD && netif_carrier_ok(dev)) arg.nh_flags |= RTNH_F_LINKDOWN; fib6_clean_all(dev_net(dev), fib6_ifup, &arg); } /* only called for fib entries with inline fib6_nh */ static bool rt6_multipath_uses_dev(const struct fib6_info *rt, const struct net_device *dev) { struct fib6_info *iter; if (rt->fib6_nh->fib_nh_dev == dev) return true; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == dev) return true; return false; } static void rt6_multipath_flush(struct fib6_info *rt) { struct fib6_info *iter; rt->should_flush = 1; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) iter->should_flush = 1; } static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt, const struct net_device *down_dev) { struct fib6_info *iter; unsigned int dead = 0; if (rt->fib6_nh->fib_nh_dev == down_dev || rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD) dead++; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == down_dev || iter->fib6_nh->fib_nh_flags & RTNH_F_DEAD) dead++; return dead; } static void rt6_multipath_nh_flags_set(struct fib6_info *rt, const struct net_device *dev, unsigned char nh_flags) { struct fib6_info *iter; if (rt->fib6_nh->fib_nh_dev == dev) rt->fib6_nh->fib_nh_flags |= nh_flags; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == dev) iter->fib6_nh->fib_nh_flags |= nh_flags; } /* called with write lock held for table with rt */ static int fib6_ifdown(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; const struct net_device *dev = arg->dev; struct net *net = dev_net(dev); if (rt == net->ipv6.fib6_null_entry || rt->nh) return 0; switch (arg->event) { case NETDEV_UNREGISTER: return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0; case NETDEV_DOWN: if (rt->should_flush) return -1; if (!rt->fib6_nsiblings) return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0; if (rt6_multipath_uses_dev(rt, dev)) { unsigned int count; count = rt6_multipath_dead_count(rt, dev); if (rt->fib6_nsiblings + 1 == count) { rt6_multipath_flush(rt); return -1; } rt6_multipath_nh_flags_set(rt, dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); fib6_update_sernum(net, rt); rt6_multipath_rebalance(rt); } return -2; case NETDEV_CHANGE: if (rt->fib6_nh->fib_nh_dev != dev || rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) break; rt->fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; rt6_multipath_rebalance(rt); break; } return 0; } void rt6_sync_down_dev(struct net_device *dev, unsigned long event) { struct arg_netdev_event arg = { .dev = dev, { .event = event, }, }; struct net *net = dev_net(dev); if (net->ipv6.sysctl.skip_notify_on_dev_down) fib6_clean_all_skip_notify(net, fib6_ifdown, &arg); else fib6_clean_all(net, fib6_ifdown, &arg); } void rt6_disable_ip(struct net_device *dev, unsigned long event) { rt6_sync_down_dev(dev, event); rt6_uncached_list_flush_dev(dev); neigh_ifdown(&nd_tbl, dev); } struct rt6_mtu_change_arg { struct net_device *dev; unsigned int mtu; struct fib6_info *f6i; }; static int fib6_nh_mtu_change(struct fib6_nh *nh, void *_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *)_arg; struct fib6_info *f6i = arg->f6i; /* For administrative MTU increase, there is no way to discover * IPv6 PMTU increase, so PMTU increase should be updated here. * Since RFC 1981 doesn't include administrative MTU increase * update PMTU increase is a MUST. (i.e. jumbo frame) */ if (nh->fib_nh_dev == arg->dev) { struct inet6_dev *idev = __in6_dev_get(arg->dev); u32 mtu = f6i->fib6_pmtu; if (mtu >= arg->mtu || (mtu < arg->mtu && mtu == idev->cnf.mtu6)) fib6_metric_set(f6i, RTAX_MTU, arg->mtu); spin_lock_bh(&rt6_exception_lock); rt6_exceptions_update_pmtu(idev, nh, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } return 0; } static int rt6_mtu_change_route(struct fib6_info *f6i, void *p_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg; struct inet6_dev *idev; /* In IPv6 pmtu discovery is not optional, so that RTAX_MTU lock cannot disable it. We still use this lock to block changes caused by addrconf/ndisc. */ idev = __in6_dev_get(arg->dev); if (!idev) return 0; if (fib6_metric_locked(f6i, RTAX_MTU)) return 0; arg->f6i = f6i; if (f6i->nh) { /* fib6_nh_mtu_change only returns 0, so this is safe */ return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_mtu_change, arg); } return fib6_nh_mtu_change(f6i->fib6_nh, arg); } void rt6_mtu_change(struct net_device *dev, unsigned int mtu) { struct rt6_mtu_change_arg arg = { .dev = dev, .mtu = mtu, }; fib6_clean_all(dev_net(dev), rt6_mtu_change_route, &arg); } static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_PREF] = { .type = NLA_U8 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_EXPIRES] = { .type = NLA_U32 }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_IP_PROTO] = { .type = NLA_U8 }, [RTA_SPORT] = { .type = NLA_U16 }, [RTA_DPORT] = { .type = NLA_U16 }, [RTA_NH_ID] = { .type = NLA_U32 }, [RTA_FLOWLABEL] = { .type = NLA_BE32 }, }; static int rtm_to_fib6_multipath_config(struct fib6_config *cfg, struct netlink_ext_ack *extack, bool newroute) { struct rtnexthop *rtnh; int remaining; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; if (!rtnh_ok(rtnh, remaining)) { NL_SET_ERR_MSG(extack, "Invalid nexthop configuration - no valid nexthops"); return -EINVAL; } do { bool has_gateway = cfg->fc_flags & RTF_GATEWAY; int attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs; attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { if (nla_len(nla) < sizeof(cfg->fc_gateway)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_GATEWAY"); return -EINVAL; } has_gateway = true; } } if (newroute && (cfg->fc_nh_id || !has_gateway)) { NL_SET_ERR_MSG(extack, "Device only routes can not be added for IPv6 using the multipath API."); return -EINVAL; } rtnh = rtnh_next(rtnh, &remaining); } while (rtnh_ok(rtnh, remaining)); return lwtunnel_valid_encap_type_attr(cfg->fc_mp, cfg->fc_mp_len, extack); } static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config *cfg, struct netlink_ext_ack *extack) { bool newroute = nlh->nlmsg_type == RTM_NEWROUTE; struct nlattr *tb[RTA_MAX+1]; struct rtmsg *rtm; unsigned int pref; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); if (rtm->rtm_tos) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): option not available for IPv6"); goto errout; } if (tb[RTA_FLOWLABEL]) { NL_SET_ERR_MSG_ATTR(extack, tb[RTA_FLOWLABEL], "Flow label cannot be specified for this operation"); goto errout; } *cfg = (struct fib6_config){ .fc_table = rtm->rtm_table, .fc_dst_len = rtm->rtm_dst_len, .fc_src_len = rtm->rtm_src_len, .fc_flags = RTF_UP, .fc_protocol = rtm->rtm_protocol, .fc_type = rtm->rtm_type, .fc_nlinfo.portid = NETLINK_CB(skb).portid, .fc_nlinfo.nlh = nlh, .fc_nlinfo.nl_net = sock_net(skb->sk), }; if (rtm->rtm_type == RTN_UNREACHABLE || rtm->rtm_type == RTN_BLACKHOLE || rtm->rtm_type == RTN_PROHIBIT || rtm->rtm_type == RTN_THROW) cfg->fc_flags |= RTF_REJECT; if (rtm->rtm_type == RTN_LOCAL) cfg->fc_flags |= RTF_LOCAL; if (rtm->rtm_flags & RTM_F_CLONED) cfg->fc_flags |= RTF_CACHE; cfg->fc_flags |= (rtm->rtm_flags & RTNH_F_ONLINK); if (tb[RTA_NH_ID]) { if (tb[RTA_GATEWAY] || tb[RTA_OIF] || tb[RTA_MULTIPATH] || tb[RTA_ENCAP]) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); goto errout; } cfg->fc_nh_id = nla_get_u32(tb[RTA_NH_ID]); } if (tb[RTA_GATEWAY]) { cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]); cfg->fc_flags |= RTF_GATEWAY; } if (tb[RTA_VIA]) { NL_SET_ERR_MSG(extack, "IPv6 does not support RTA_VIA attribute"); goto errout; } if (tb[RTA_DST]) { int plen = (rtm->rtm_dst_len + 7) >> 3; if (nla_len(tb[RTA_DST]) < plen) goto errout; nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen); } if (tb[RTA_SRC]) { int plen = (rtm->rtm_src_len + 7) >> 3; if (nla_len(tb[RTA_SRC]) < plen) goto errout; nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen); } if (tb[RTA_PREFSRC]) cfg->fc_prefsrc = nla_get_in6_addr(tb[RTA_PREFSRC]); if (tb[RTA_OIF]) cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]); if (tb[RTA_PRIORITY]) cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]); if (tb[RTA_METRICS]) { cfg->fc_mx = nla_data(tb[RTA_METRICS]); cfg->fc_mx_len = nla_len(tb[RTA_METRICS]); } if (tb[RTA_TABLE]) cfg->fc_table = nla_get_u32(tb[RTA_TABLE]); if (tb[RTA_MULTIPATH]) { cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]); cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); err = rtm_to_fib6_multipath_config(cfg, extack, newroute); if (err < 0) goto errout; } if (tb[RTA_PREF]) { pref = nla_get_u8(tb[RTA_PREF]); if (pref != ICMPV6_ROUTER_PREF_LOW && pref != ICMPV6_ROUTER_PREF_HIGH) pref = ICMPV6_ROUTER_PREF_MEDIUM; cfg->fc_flags |= RTF_PREF(pref); } if (tb[RTA_ENCAP]) cfg->fc_encap = tb[RTA_ENCAP]; if (tb[RTA_ENCAP_TYPE]) { cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; } if (tb[RTA_EXPIRES]) { unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ); if (addrconf_finite_timeout(timeout)) { cfg->fc_expires = jiffies_to_clock_t(timeout * HZ); cfg->fc_flags |= RTF_EXPIRES; } } err = 0; errout: return err; } struct rt6_nh { struct fib6_info *fib6_info; struct fib6_config r_cfg; struct list_head list; }; static int ip6_route_info_append(struct list_head *rt6_nh_list, struct fib6_info *rt, struct fib6_config *r_cfg) { struct rt6_nh *nh; list_for_each_entry(nh, rt6_nh_list, list) { /* check if fib6_info already exists */ if (rt6_duplicate_nexthop(nh->fib6_info, rt)) return -EEXIST; } nh = kzalloc(sizeof(*nh), GFP_KERNEL); if (!nh) return -ENOMEM; nh->fib6_info = rt; memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg)); list_add_tail(&nh->list, rt6_nh_list); return 0; } static void ip6_route_mpath_notify(struct fib6_info *rt, struct fib6_info *rt_last, struct nl_info *info, __u16 nlflags) { /* if this is an APPEND route, then rt points to the first route * inserted and rt_last points to last route inserted. Userspace * wants a consistent dump of the route which starts at the first * nexthop. Since sibling routes are always added at the end of * the list, find the first sibling of the last route appended */ rcu_read_lock(); if ((nlflags & NLM_F_APPEND) && rt_last && READ_ONCE(rt_last->fib6_nsiblings)) { rt = list_first_or_null_rcu(&rt_last->fib6_siblings, struct fib6_info, fib6_siblings); } if (rt) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); rcu_read_unlock(); } static bool ip6_route_mpath_should_notify(const struct fib6_info *rt) { bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); bool should_notify = false; struct fib6_info *leaf; struct fib6_node *fn; rcu_read_lock(); fn = rcu_dereference(rt->fib6_node); if (!fn) goto out; leaf = rcu_dereference(fn->leaf); if (!leaf) goto out; if (rt == leaf || (rt_can_ecmp && rt->fib6_metric == leaf->fib6_metric && rt6_qualify_for_ecmp(leaf))) should_notify = true; out: rcu_read_unlock(); return should_notify; } static int ip6_route_multipath_add(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; struct rt6_nh *nh, *nh_safe; struct fib6_config r_cfg; struct rtnexthop *rtnh; LIST_HEAD(rt6_nh_list); struct rt6_nh *err_nh; struct fib6_info *rt; __u16 nlflags; int remaining; int attrlen; int replace; int nhn = 0; int err; err = fib6_config_validate(cfg, extack); if (err) return err; replace = (cfg->fc_nlinfo.nlh && (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE)); nlflags = replace ? NLM_F_REPLACE : NLM_F_CREATE; if (info->nlh && info->nlh->nlmsg_flags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; /* Parse a Multipath Entry and build a list (rt6_nh_list) of * fib6_info structs per nexthop */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) r_cfg.fc_ifindex = rtnh->rtnh_ifindex; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { r_cfg.fc_gateway = nla_get_in6_addr(nla); r_cfg.fc_flags |= RTF_GATEWAY; } r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla) r_cfg.fc_encap_type = nla_get_u16(nla); } r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); rt = ip6_route_info_create(&r_cfg, GFP_KERNEL, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto cleanup; } err = ip6_route_info_create_nh(rt, &r_cfg, GFP_KERNEL, extack); if (err) { rt = NULL; goto cleanup; } rt->fib6_nh->fib_nh_weight = rtnh->rtnh_hops + 1; err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg); if (err) { fib6_info_release(rt); goto cleanup; } rtnh = rtnh_next(rtnh, &remaining); } /* for add and replace send one notification with all nexthops. * Skip the notification in fib6_add_rt2node and send one with * the full route when done */ info->skip_notify = 1; /* For add and replace, send one notification with all nexthops. For * append, send one notification with all appended nexthops. */ info->skip_notify_kernel = 1; err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, list) { err = __ip6_ins_rt(nh->fib6_info, info, extack); if (err) { if (replace && nhn) NL_SET_ERR_MSG_MOD(extack, "multipath route replace failed (check consistency of installed routes)"); err_nh = nh; goto add_errout; } /* save reference to last route successfully inserted */ rt_last = nh->fib6_info; /* save reference to first route for notification */ if (!rt_notif) rt_notif = nh->fib6_info; /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, * we have already failed to add the first nexthop: * fib6_add_rt2node() has rejected it; when replacing, old * nexthops have been replaced by first new, the rest should * be added to it. */ if (cfg->fc_nlinfo.nlh) { cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; } nhn++; } /* An in-kernel notification should only be sent in case the new * multipath route is added as the first route in the node, or if * it was appended to it. We pass 'rt_notif' since it is the first * sibling and might allow us to skip some checks in the replace case. */ if (ip6_route_mpath_should_notify(rt_notif)) { enum fib_event_type fib_event; if (rt_notif->fib6_nsiblings != nhn - 1) fib_event = FIB_EVENT_ENTRY_APPEND; else fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib6_multipath_entry_notifiers(info->nl_net, fib_event, rt_notif, nhn - 1, extack); if (err) { /* Delete all the siblings that were just added */ err_nh = NULL; goto add_errout; } } /* success ... tell user about new route */ ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags); goto cleanup; add_errout: /* send notification for routes that were added so that * the delete notifications sent by ip6_route_del are * coherent */ if (rt_notif) ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags); /* Delete routes that were already added */ list_for_each_entry(nh, &rt6_nh_list, list) { if (err_nh == nh) break; ip6_route_del(&nh->r_cfg, extack); } cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, list) { fib6_info_release(nh->fib6_info); list_del(&nh->list); kfree(nh); } return err; } static int ip6_route_multipath_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_config r_cfg; struct rtnexthop *rtnh; int last_err = 0; int remaining; int attrlen; int err; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; /* Parse a Multipath Entry */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) r_cfg.fc_ifindex = rtnh->rtnh_ifindex; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { r_cfg.fc_gateway = nla_get_in6_addr(nla); r_cfg.fc_flags |= RTF_GATEWAY; } } err = ip6_route_del(&r_cfg, extack); if (err) last_err = err; rtnh = rtnh_next(rtnh, &remaining); } return last_err; } static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib6_config cfg; int err; err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_nh_id) { rcu_read_lock(); err = !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id); rcu_read_unlock(); if (err) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); return -EINVAL; } } if (cfg.fc_mp) { return ip6_route_multipath_del(&cfg, extack); } else { cfg.fc_delete_all_nh = 1; return ip6_route_del(&cfg, extack); } } static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib6_config cfg; int err; err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; if (cfg.fc_mp) return ip6_route_multipath_add(&cfg, extack); else return ip6_route_add(&cfg, GFP_KERNEL, extack); } /* add the overhead of this fib6_nh to nexthop_len */ static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg) { int *nexthop_len = arg; *nexthop_len += nla_total_size(0) /* RTA_MULTIPATH */ + NLA_ALIGN(sizeof(struct rtnexthop)) + nla_total_size(16); /* RTA_GATEWAY */ if (nh->fib_nh_lws) { /* RTA_ENCAP_TYPE */ *nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); /* RTA_ENCAP */ *nexthop_len += nla_total_size(2); } return 0; } static size_t rt6_nlmsg_size(struct fib6_info *f6i) { struct fib6_info *sibling; struct fib6_nh *nh; int nexthop_len; if (f6i->nh) { nexthop_len = nla_total_size(4); /* RTA_NH_ID */ nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); goto common; } rcu_read_lock(); retry: nh = f6i->fib6_nh; nexthop_len = 0; if (READ_ONCE(f6i->fib6_nsiblings)) { rt6_nh_nlmsg_size(nh, &nexthop_len); list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, fib6_siblings) { rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); if (!READ_ONCE(f6i->fib6_nsiblings)) goto retry; } } rcu_read_unlock(); nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); common: return NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(16) /* RTA_SRC */ + nla_total_size(16) /* RTA_DST */ + nla_total_size(16) /* RTA_GATEWAY */ + nla_total_size(16) /* RTA_PREFSRC */ + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(4) /* RTA_IIF */ + nla_total_size(4) /* RTA_OIF */ + nla_total_size(4) /* RTA_PRIORITY */ + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ + nla_total_size(sizeof(struct rta_cacheinfo)) + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ + nla_total_size(1) /* RTA_PREF */ + nexthop_len; } static int rt6_fill_node_nexthop(struct sk_buff *skb, struct nexthop *nh, unsigned char *flags) { if (nexthop_is_multipath(nh)) { struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; if (nexthop_mpath_fill_node(skb, nh, AF_INET6)) goto nla_put_failure; nla_nest_end(skb, mp); } else { struct fib6_nh *fib6_nh; fib6_nh = nexthop_fib6_nh(nh); if (fib_nexthop_info(skb, &fib6_nh->nh_common, AF_INET6, flags, false) < 0) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct fib6_info *rt, struct dst_entry *dst, struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags) { struct rt6_info *rt6 = dst_rt6_info(dst); struct rt6key *rt6_dst, *rt6_src; u32 *pmetrics, table, rt6_flags; unsigned char nh_flags = 0; struct nlmsghdr *nlh; struct rtmsg *rtm; long expires = 0; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; if (rt6) { rt6_dst = &rt6->rt6i_dst; rt6_src = &rt6->rt6i_src; rt6_flags = rt6->rt6i_flags; } else { rt6_dst = &rt->fib6_dst; rt6_src = &rt->fib6_src; rt6_flags = rt->fib6_flags; } rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; rtm->rtm_dst_len = rt6_dst->plen; rtm->rtm_src_len = rt6_src->plen; rtm->rtm_tos = 0; if (rt->fib6_table) table = rt->fib6_table->tb6_id; else table = RT6_TABLE_UNSPEC; rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; rtm->rtm_type = rt->fib6_type; rtm->rtm_flags = 0; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->fib6_protocol; if (rt6_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; if (dest) { if (nla_put_in6_addr(skb, RTA_DST, dest)) goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) if (nla_put_in6_addr(skb, RTA_DST, &rt6_dst->addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { if (nla_put_in6_addr(skb, RTA_SRC, src)) goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && nla_put_in6_addr(skb, RTA_SRC, &rt6_src->addr)) goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE if (ipv6_addr_is_multicast(&rt6_dst->addr)) { int err = ip6mr_get_route(net, skb, rtm, portid); if (err == 0) return 0; if (err < 0) goto nla_put_failure; } else #endif if (nla_put_u32(skb, RTA_IIF, iif)) goto nla_put_failure; } else if (dest) { struct in6_addr saddr_buf; if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 && nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } if (rt->fib6_prefsrc.plen) { struct in6_addr saddr_buf; saddr_buf = rt->fib6_prefsrc.addr; if (nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } pmetrics = dst ? dst_metrics_ptr(dst) : rt->fib6_metrics->metrics; if (rtnetlink_put_metrics(skb, pmetrics) < 0) goto nla_put_failure; if (nla_put_u32(skb, RTA_PRIORITY, rt->fib6_metric)) goto nla_put_failure; /* For multipath routes, walk the siblings list and add * each as a nexthop within RTA_MULTIPATH. */ if (rt6) { struct net_device *dev; if (rt6_flags & RTF_GATEWAY && nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway)) goto nla_put_failure; dev = dst_dev(dst); if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex)) goto nla_put_failure; if (lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; } else if (READ_ONCE(rt->fib6_nsiblings)) { struct fib6_info *sibling; struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common, rt->fib6_nh->fib_nh_weight, AF_INET6, 0) < 0) goto nla_put_failure; rcu_read_lock(); list_for_each_entry_rcu(sibling, &rt->fib6_siblings, fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, AF_INET6, 0) < 0) { rcu_read_unlock(); goto nla_put_failure; } } rcu_read_unlock(); nla_nest_end(skb, mp); } else if (rt->nh) { if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id)) goto nla_put_failure; if (nexthop_is_blackhole(rt->nh)) rtm->rtm_type = RTN_BLACKHOLE; if (READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode) && rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0) goto nla_put_failure; rtm->rtm_flags |= nh_flags; } else { if (fib_nexthop_info(skb, &rt->fib6_nh->nh_common, AF_INET6, &nh_flags, false) < 0) goto nla_put_failure; rtm->rtm_flags |= nh_flags; } if (rt6_flags & RTF_EXPIRES) { expires = dst ? READ_ONCE(dst->expires) : rt->expires; expires -= jiffies; } if (!dst) { if (READ_ONCE(rt->offload)) rtm->rtm_flags |= RTM_F_OFFLOAD; if (READ_ONCE(rt->trap)) rtm->rtm_flags |= RTM_F_TRAP; if (READ_ONCE(rt->offload_failed)) rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED; } if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt6_flags))) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int fib6_info_nh_uses_dev(struct fib6_nh *nh, void *arg) { const struct net_device *dev = arg; if (nh->fib_nh_dev == dev) return 1; return 0; } static bool fib6_info_uses_dev(const struct fib6_info *f6i, const struct net_device *dev) { if (f6i->nh) { struct net_device *_dev = (struct net_device *)dev; return !!nexthop_for_each_fib6_nh(f6i->nh, fib6_info_nh_uses_dev, _dev); } if (f6i->fib6_nh->fib_nh_dev == dev) return true; if (READ_ONCE(f6i->fib6_nsiblings)) { const struct fib6_info *sibling; rcu_read_lock(); list_for_each_entry_rcu(sibling, &f6i->fib6_siblings, fib6_siblings) { if (sibling->fib6_nh->fib_nh_dev == dev) { rcu_read_unlock(); return true; } if (!READ_ONCE(f6i->fib6_nsiblings)) break; } rcu_read_unlock(); } return false; } struct fib6_nh_exception_dump_walker { struct rt6_rtnl_dump_arg *dump; struct fib6_info *rt; unsigned int flags; unsigned int skip; unsigned int count; }; static int rt6_nh_dump_exceptions(struct fib6_nh *nh, void *arg) { struct fib6_nh_exception_dump_walker *w = arg; struct rt6_rtnl_dump_arg *dump = w->dump; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int i, err; bucket = fib6_nh_get_excptn_bucket(nh, NULL); if (!bucket) return 0; for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { if (w->skip) { w->skip--; continue; } /* Expiration of entries doesn't bump sernum, insertion * does. Removal is triggered by insertion, so we can * rely on the fact that if entries change between two * partial dumps, this node is scanned again completely, * see rt6_insert_exception() and fib6_dump_table(). * * Count expired entries we go through as handled * entries that we'll skip next time, in case of partial * node dump. Otherwise, if entries expire meanwhile, * we'll skip the wrong amount. */ if (rt6_check_expired(rt6_ex->rt6i)) { w->count++; continue; } err = rt6_fill_node(dump->net, dump->skb, w->rt, &rt6_ex->rt6i->dst, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(dump->cb->skb).portid, dump->cb->nlh->nlmsg_seq, w->flags); if (err) return err; w->count++; } bucket++; } return 0; } /* Return -1 if done with node, number of handled routes on partial dump */ int rt6_dump_route(struct fib6_info *rt, void *p_arg, unsigned int skip) { struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg; struct fib_dump_filter *filter = &arg->filter; unsigned int flags = NLM_F_MULTI; struct net *net = arg->net; int count = 0; if (rt == net->ipv6.fib6_null_entry) return -1; if ((filter->flags & RTM_F_PREFIX) && !(rt->fib6_flags & RTF_PREFIX_RT)) { /* success since this is not a prefix route */ return -1; } if (filter->filter_set && ((filter->rt_type && rt->fib6_type != filter->rt_type) || (filter->dev && !fib6_info_uses_dev(rt, filter->dev)) || (filter->protocol && rt->fib6_protocol != filter->protocol))) { return -1; } if (filter->filter_set || !filter->dump_routes || !filter->dump_exceptions) { flags |= NLM_F_DUMP_FILTERED; } if (filter->dump_routes) { if (skip) { skip--; } else { if (rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq, flags)) { return 0; } count++; } } if (filter->dump_exceptions) { struct fib6_nh_exception_dump_walker w = { .dump = arg, .rt = rt, .flags = flags, .skip = skip, .count = 0 }; int err; rcu_read_lock(); if (rt->nh) { err = nexthop_for_each_fib6_nh(rt->nh, rt6_nh_dump_exceptions, &w); } else { err = rt6_nh_dump_exceptions(rt->fib6_nh, &w); } rcu_read_unlock(); if (err) return count + w.count; } return -1; } static int inet6_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; rtm = nlmsg_payload(nlh, sizeof(*rtm)); if (!rtm) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for get route request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get route request"); return -EINVAL; } if (rtm->rtm_flags & ~RTM_F_FIB_MATCH) { NL_SET_ERR_MSG_MOD(extack, "Invalid flags for get route request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG_MOD(extack, "rtm_src_len and rtm_dst_len must be 128 for IPv6"); return -EINVAL; } if (tb[RTA_FLOWLABEL] && (nla_get_be32(tb[RTA_FLOWLABEL]) & ~IPV6_FLOWLABEL_MASK)) { NL_SET_ERR_MSG_ATTR(extack, tb[RTA_FLOWLABEL], "Invalid flow label"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_SRC: case RTA_DST: case RTA_IIF: case RTA_OIF: case RTA_MARK: case RTA_UID: case RTA_SPORT: case RTA_DPORT: case RTA_IP_PROTO: case RTA_FLOWLABEL: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request"); return -EINVAL; } } return 0; } static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; int err, iif = 0, oif = 0; struct fib6_info *from; struct dst_entry *dst; struct rt6_info *rt; struct sk_buff *skb; struct rtmsg *rtm; struct flowi6 fl6 = {}; __be32 flowlabel; bool fibmatch; err = inet6_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); fibmatch = !!(rtm->rtm_flags & RTM_F_FIB_MATCH); if (tb[RTA_SRC]) { if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) goto errout; fl6.saddr = *(struct in6_addr *)nla_data(tb[RTA_SRC]); } if (tb[RTA_DST]) { if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr)) goto errout; fl6.daddr = *(struct in6_addr *)nla_data(tb[RTA_DST]); } if (tb[RTA_IIF]) iif = nla_get_u32(tb[RTA_IIF]); if (tb[RTA_OIF]) oif = nla_get_u32(tb[RTA_OIF]); if (tb[RTA_MARK]) fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]); if (tb[RTA_UID]) fl6.flowi6_uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else fl6.flowi6_uid = iif ? INVALID_UID : current_uid(); if (tb[RTA_SPORT]) fl6.fl6_sport = nla_get_be16(tb[RTA_SPORT]); if (tb[RTA_DPORT]) fl6.fl6_dport = nla_get_be16(tb[RTA_DPORT]); if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], &fl6.flowi6_proto, AF_INET6, extack); if (err) goto errout; } flowlabel = nla_get_be32_default(tb[RTA_FLOWLABEL], 0); fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, flowlabel); if (iif) { struct net_device *dev; int flags = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(net, iif); if (!dev) { rcu_read_unlock(); err = -ENODEV; goto errout; } fl6.flowi6_iif = iif; if (!ipv6_addr_any(&fl6.saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; dst = ip6_route_input_lookup(net, dev, &fl6, NULL, flags); rcu_read_unlock(); } else { fl6.flowi6_oif = oif; dst = ip6_route_output(net, NULL, &fl6); } rt = dst_rt6_info(dst); if (rt->dst.error) { err = rt->dst.error; ip6_rt_put(rt); goto errout; } if (rt == net->ipv6.ip6_null_entry) { err = rt->dst.error; ip6_rt_put(rt); goto errout; } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { ip6_rt_put(rt); err = -ENOBUFS; goto errout; } skb_dst_set(skb, &rt->dst); rcu_read_lock(); from = rcu_dereference(rt->from); if (from) { if (fibmatch) err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); else err = rt6_fill_node(net, skb, from, dst, &fl6.daddr, &fl6.saddr, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } else { err = -ENETUNREACH; } rcu_read_unlock(); if (err < 0) { kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; } void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int nlm_flags) { struct net *net = info->nl_net; struct sk_buff *skb; size_t sz; u32 seq; int err; err = -ENOBUFS; seq = info->nlh ? info->nlh->nlmsg_seq : 0; rcu_read_lock(); sz = rt6_nlmsg_size(rt); retry: skb = nlmsg_new(sz, GFP_ATOMIC); if (!skb) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, event, info->portid, seq, nlm_flags); if (err < 0) { kfree_skb(skb); /* -EMSGSIZE implies needed space grew under us. */ if (err == -EMSGSIZE) { sz = max(rt6_nlmsg_size(rt), sz << 1); goto retry; } goto errout; } rcu_read_unlock(); rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, GFP_ATOMIC); return; errout: rcu_read_unlock(); rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_rt_update(struct net *net, struct fib6_info *rt, struct nl_info *info) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (!skb) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, RTM_NEWROUTE, info->portid, seq, NLM_F_REPLACE); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, bool offload, bool trap, bool offload_failed) { struct sk_buff *skb; int err; if (READ_ONCE(f6i->offload) == offload && READ_ONCE(f6i->trap) == trap && READ_ONCE(f6i->offload_failed) == offload_failed) return; WRITE_ONCE(f6i->offload, offload); WRITE_ONCE(f6i->trap, trap); /* 2 means send notifications only if offload_failed was changed. */ if (net->ipv6.sysctl.fib_notify_on_flag_change == 2 && READ_ONCE(f6i->offload_failed) == offload_failed) return; WRITE_ONCE(f6i->offload_failed, offload_failed); if (!rcu_access_pointer(f6i->fib6_node)) /* The route was removed from the tree, do not send * notification. */ return; if (!net->ipv6.sysctl.fib_notify_on_flag_change) return; skb = nlmsg_new(rt6_nlmsg_size(f6i), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout; } err = rt6_fill_node(net, skb, f6i, NULL, NULL, NULL, 0, RTM_NEWROUTE, 0, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_ROUTE, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } EXPORT_SYMBOL(fib6_info_hw_flags_set); static int ip6_route_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (!(dev->flags & IFF_LOOPBACK)) return NOTIFY_OK; if (event == NETDEV_REGISTER) { net->ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = dev; net->ipv6.ip6_null_entry->dst.dev = dev; net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry->dst.dev = dev; net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev); net->ipv6.ip6_blk_hole_entry->dst.dev = dev; net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev); #endif } else if (event == NETDEV_UNREGISTER && dev->reg_state != NETREG_UNREGISTERED) { /* NETDEV_UNREGISTER could be fired for multiple times by * netdev_wait_allrefs(). Make sure we only call this once. */ in6_dev_put_clear(&net->ipv6.ip6_null_entry->rt6i_idev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES in6_dev_put_clear(&net->ipv6.ip6_prohibit_entry->rt6i_idev); in6_dev_put_clear(&net->ipv6.ip6_blk_hole_entry->rt6i_idev); #endif } return NOTIFY_OK; } /* * /proc */ #ifdef CONFIG_PROC_FS static int rt6_stats_seq_show(struct seq_file *seq, void *v) { struct net *net = (struct net *)seq->private; seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n", net->ipv6.rt6_stats->fib_nodes, net->ipv6.rt6_stats->fib_route_nodes, atomic_read(&net->ipv6.rt6_stats->fib_rt_alloc), net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, dst_entries_get_slow(&net->ipv6.ip6_dst_ops), net->ipv6.rt6_stats->fib_discarded_routes); return 0; } #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL static int ipv6_sysctl_rtcache_flush(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int delay; int ret; if (!write) return -EINVAL; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (ret) return ret; net = (struct net *)ctl->extra1; delay = net->ipv6.sysctl.flush_delay; fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } static struct ctl_table ipv6_route_table_template[] = { { .procname = "max_size", .data = &init_net.ipv6.sysctl.ip6_rt_max_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_thresh", .data = &ip6_dst_ops_template.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "flush", .data = &init_net.ipv6.sysctl.flush_delay, .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv6_sysctl_rtcache_flush }, { .procname = "gc_min_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_timeout", .data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_elasticity", .data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "mtu_expires", .data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "min_adv_mss", .data = &init_net.ipv6.sysctl.ip6_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_min_interval_ms", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "skip_notify_on_dev_down", .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) { struct ctl_table *table; table = kmemdup(ipv6_route_table_template, sizeof(ipv6_route_table_template), GFP_KERNEL); if (table) { table[0].data = &net->ipv6.sysctl.ip6_rt_max_size; table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh; table[2].data = &net->ipv6.sysctl.flush_delay; table[2].extra1 = net; table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout; table[5].data = &net->ipv6.sysctl.ip6_rt_gc_interval; table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity; table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires; table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[10].data = &net->ipv6.sysctl.skip_notify_on_dev_down; } return table; } size_t ipv6_route_sysctl_table_size(struct net *net) { /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) return 1; return ARRAY_SIZE(ipv6_route_table_template); } #endif static int __net_init ip6_route_net_init(struct net *net) { int ret = -ENOMEM; memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template, sizeof(net->ipv6.ip6_dst_ops)); if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0) goto out_ip6_dst_ops; net->ipv6.fib6_null_entry = fib6_info_alloc(GFP_KERNEL, true); if (!net->ipv6.fib6_null_entry) goto out_ip6_dst_entries; memcpy(net->ipv6.fib6_null_entry, &fib6_null_entry_template, sizeof(*net->ipv6.fib6_null_entry)); net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, sizeof(*net->ipv6.ip6_null_entry), GFP_KERNEL); if (!net->ipv6.ip6_null_entry) goto out_fib6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_null_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_null_entry->dst.rt_uncached); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_has_custom_rules = false; net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, sizeof(*net->ipv6.ip6_prohibit_entry), GFP_KERNEL); if (!net->ipv6.ip6_prohibit_entry) goto out_ip6_null_entry; net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_prohibit_entry->dst.rt_uncached); net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), GFP_KERNEL); if (!net->ipv6.ip6_blk_hole_entry) goto out_ip6_prohibit_entry; net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->dst.rt_uncached); #ifdef CONFIG_IPV6_SUBTREES net->ipv6.fib6_routes_require_src = 0; #endif #endif net->ipv6.sysctl.flush_delay = 0; net->ipv6.sysctl.ip6_rt_max_size = INT_MAX; net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2; net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ; net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ; net->ipv6.sysctl.ip6_rt_gc_elasticity = 9; net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ; net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; net->ipv6.sysctl.skip_notify_on_dev_down = 0; atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ); ret = 0; out: return ret; #ifdef CONFIG_IPV6_MULTIPLE_TABLES out_ip6_prohibit_entry: kfree(net->ipv6.ip6_prohibit_entry); out_ip6_null_entry: kfree(net->ipv6.ip6_null_entry); #endif out_fib6_null_entry: kfree(net->ipv6.fib6_null_entry); out_ip6_dst_entries: dst_entries_destroy(&net->ipv6.ip6_dst_ops); out_ip6_dst_ops: goto out; } static void __net_exit ip6_route_net_exit(struct net *net) { kfree(net->ipv6.fib6_null_entry); kfree(net->ipv6.ip6_null_entry); #ifdef CONFIG_IPV6_MULTIPLE_TABLES kfree(net->ipv6.ip6_prohibit_entry); kfree(net->ipv6.ip6_blk_hole_entry); #endif dst_entries_destroy(&net->ipv6.ip6_dst_ops); } static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS if (!proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops, sizeof(struct ipv6_route_iter))) return -ENOMEM; if (!proc_create_net_single("rt6_stats", 0444, net->proc_net, rt6_stats_seq_show, NULL)) { remove_proc_entry("ipv6_route", net->proc_net); return -ENOMEM; } #endif return 0; } static void __net_exit ip6_route_net_exit_late(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("ipv6_route", net->proc_net); remove_proc_entry("rt6_stats", net->proc_net); #endif } static struct pernet_operations ip6_route_net_ops = { .init = ip6_route_net_init, .exit = ip6_route_net_exit, }; static int __net_init ipv6_inetpeer_init(struct net *net) { struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); if (!bp) return -ENOMEM; inet_peer_base_init(bp); net->ipv6.peers = bp; return 0; } static void __net_exit ipv6_inetpeer_exit(struct net *net) { struct inet_peer_base *bp = net->ipv6.peers; net->ipv6.peers = NULL; inetpeer_invalidate_tree(bp); kfree(bp); } static struct pernet_operations ipv6_inetpeer_ops = { .init = ipv6_inetpeer_init, .exit = ipv6_inetpeer_exit, }; static struct pernet_operations ip6_route_net_late_ops = { .init = ip6_route_net_init_late, .exit = ip6_route_net_exit_late, }; static struct notifier_block ip6_route_dev_notifier = { .notifier_call = ip6_route_dev_notify, .priority = ADDRCONF_NOTIFY_PRIORITY - 10, }; void __init ip6_route_init_special_entries(void) { /* Registering of the loopback is done before this portion of code, * the loopback reference in rt6_info will not be taken, do it * manually for init_net */ init_net.ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #endif } #if IS_BUILTIN(CONFIG_IPV6) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) DEFINE_BPF_ITER_FUNC(ipv6_route, struct bpf_iter_meta *meta, struct fib6_info *rt) BTF_ID_LIST_SINGLE(btf_fib6_info_id, struct, fib6_info) static const struct bpf_iter_seq_info ipv6_route_seq_info = { .seq_ops = &ipv6_route_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct ipv6_route_iter), }; static struct bpf_iter_reg ipv6_route_reg_info = { .target = "ipv6_route", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__ipv6_route, rt), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &ipv6_route_seq_info, }; static int __init bpf_iter_register(void) { ipv6_route_reg_info.ctx_arg_info[0].btf_id = *btf_fib6_info_id; return bpf_iter_reg_target(&ipv6_route_reg_info); } static void bpf_iter_unregister(void) { bpf_iter_unreg_target(&ipv6_route_reg_info); } #endif #endif static const struct rtnl_msg_handler ip6_route_rtnl_msg_handlers[] __initconst_or_module = { {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWROUTE, .doit = inet6_rtm_newroute, .flags = RTNL_FLAG_DOIT_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELROUTE, .doit = inet6_rtm_delroute, .flags = RTNL_FLAG_DOIT_UNLOCKED}, {.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE, .doit = inet6_rtm_getroute, .flags = RTNL_FLAG_DOIT_UNLOCKED}, }; int __init ip6_route_init(void) { int ret; int cpu; ret = -ENOMEM; ip6_dst_ops_template.kmem_cachep = kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!ip6_dst_ops_template.kmem_cachep) goto out; ret = dst_entries_init(&ip6_dst_blackhole_ops); if (ret) goto out_kmem_cache; ret = register_pernet_subsys(&ipv6_inetpeer_ops); if (ret) goto out_dst_entries; ret = register_pernet_subsys(&ip6_route_net_ops); if (ret) goto out_register_inetpeer; ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; ret = fib6_init(); if (ret) goto out_register_subsys; ret = xfrm6_init(); if (ret) goto out_fib6_init; ret = fib6_rules_init(); if (ret) goto xfrm6_init; ret = register_pernet_subsys(&ip6_route_net_late_ops); if (ret) goto fib6_rules_init; ret = rtnl_register_many(ip6_route_rtnl_msg_handlers); if (ret < 0) goto out_register_late_subsys; ret = register_netdevice_notifier(&ip6_route_dev_notifier); if (ret) goto out_register_late_subsys; #if IS_BUILTIN(CONFIG_IPV6) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) ret = bpf_iter_register(); if (ret) goto out_register_late_subsys; #endif #endif for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); spin_lock_init(&ul->lock); } out: return ret; out_register_late_subsys: rtnl_unregister_all(PF_INET6); unregister_pernet_subsys(&ip6_route_net_late_ops); fib6_rules_init: fib6_rules_cleanup(); xfrm6_init: xfrm6_fini(); out_fib6_init: fib6_gc_cleanup(); out_register_subsys: unregister_pernet_subsys(&ip6_route_net_ops); out_register_inetpeer: unregister_pernet_subsys(&ipv6_inetpeer_ops); out_dst_entries: dst_entries_destroy(&ip6_dst_blackhole_ops); out_kmem_cache: kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); goto out; } void ip6_route_cleanup(void) { #if IS_BUILTIN(CONFIG_IPV6) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) bpf_iter_unregister(); #endif #endif unregister_netdevice_notifier(&ip6_route_dev_notifier); unregister_pernet_subsys(&ip6_route_net_late_ops); fib6_rules_cleanup(); xfrm6_fini(); fib6_gc_cleanup(); unregister_pernet_subsys(&ipv6_inetpeer_ops); unregister_pernet_subsys(&ip6_route_net_ops); dst_entries_destroy(&ip6_dst_blackhole_ops); kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/netprio_cgroup.c Priority Control Group * * Authors: Neil Horman <nhorman@tuxdriver.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/cgroup.h> #include <linux/rcupdate.h> #include <linux/atomic.h> #include <linux/sched/task.h> #include <net/rtnetlink.h> #include <net/pkt_cls.h> #include <net/sock.h> #include <net/netprio_cgroup.h> #include <linux/fdtable.h> /* * netprio allocates per-net_device priomap array which is indexed by * css->id. Limiting css ID to 16bits doesn't lose anything. */ #define NETPRIO_ID_MAX USHRT_MAX #define PRIOMAP_MIN_SZ 128 /* * Extend @dev->priomap so that it's large enough to accommodate * @target_idx. @dev->priomap.priomap_len > @target_idx after successful * return. Must be called under rtnl lock. */ static int extend_netdev_table(struct net_device *dev, u32 target_idx) { struct netprio_map *old, *new; size_t new_sz, new_len; /* is the existing priomap large enough? */ old = rtnl_dereference(dev->priomap); if (old && old->priomap_len > target_idx) return 0; /* * Determine the new size. Let's keep it power-of-two. We start * from PRIOMAP_MIN_SZ and double it until it's large enough to * accommodate @target_idx. */ new_sz = PRIOMAP_MIN_SZ; while (true) { new_len = (new_sz - offsetof(struct netprio_map, priomap)) / sizeof(new->priomap[0]); if (new_len > target_idx) break; new_sz *= 2; /* overflowed? */ if (WARN_ON(new_sz < PRIOMAP_MIN_SZ)) return -ENOSPC; } /* allocate & copy */ new = kzalloc(new_sz, GFP_KERNEL); if (!new) return -ENOMEM; if (old) memcpy(new->priomap, old->priomap, old->priomap_len * sizeof(old->priomap[0])); new->priomap_len = new_len; /* install the new priomap */ rcu_assign_pointer(dev->priomap, new); if (old) kfree_rcu(old, rcu); return 0; } /** * netprio_prio - return the effective netprio of a cgroup-net_device pair * @css: css part of the target pair * @dev: net_device part of the target pair * * Should be called under RCU read or rtnl lock. */ static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev) { struct netprio_map *map = rcu_dereference_rtnl(dev->priomap); int id = css->id; if (map && id < map->priomap_len) return map->priomap[id]; return 0; } /** * netprio_set_prio - set netprio on a cgroup-net_device pair * @css: css part of the target pair * @dev: net_device part of the target pair * @prio: prio to set * * Set netprio to @prio on @css-@dev pair. Should be called under rtnl * lock and may fail under memory pressure for non-zero @prio. */ static int netprio_set_prio(struct cgroup_subsys_state *css, struct net_device *dev, u32 prio) { struct netprio_map *map; int id = css->id; int ret; /* avoid extending priomap for zero writes */ map = rtnl_dereference(dev->priomap); if (!prio && (!map || map->priomap_len <= id)) return 0; ret = extend_netdev_table(dev, id); if (ret) return ret; map = rtnl_dereference(dev->priomap); map->priomap[id] = prio; return 0; } static struct cgroup_subsys_state * cgrp_css_alloc(struct cgroup_subsys_state *parent_css) { struct cgroup_subsys_state *css; css = kzalloc(sizeof(*css), GFP_KERNEL); if (!css) return ERR_PTR(-ENOMEM); return css; } static int cgrp_css_online(struct cgroup_subsys_state *css) { struct cgroup_subsys_state *parent_css = css->parent; struct net_device *dev; int ret = 0; if (css->id > NETPRIO_ID_MAX) return -ENOSPC; if (!parent_css) return 0; rtnl_lock(); /* * Inherit prios from the parent. As all prios are set during * onlining, there is no need to clear them on offline. */ for_each_netdev(&init_net, dev) { u32 prio = netprio_prio(parent_css, dev); ret = netprio_set_prio(css, dev, prio); if (ret) break; } rtnl_unlock(); return ret; } static void cgrp_css_free(struct cgroup_subsys_state *css) { kfree(css); } static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft) { return css->id; } static int read_priomap(struct seq_file *sf, void *v) { struct net_device *dev; rcu_read_lock(); for_each_netdev_rcu(&init_net, dev) seq_printf(sf, "%s %u\n", dev->name, netprio_prio(seq_css(sf), dev)); rcu_read_unlock(); return 0; } static ssize_t write_priomap(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { char devname[IFNAMSIZ + 1]; struct net_device *dev; u32 prio; int ret; if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2) return -EINVAL; dev = dev_get_by_name(&init_net, devname); if (!dev) return -ENODEV; rtnl_lock(); ret = netprio_set_prio(of_css(of), dev, prio); rtnl_unlock(); dev_put(dev); return ret ?: nbytes; } static int update_netprio(const void *v, struct file *file, unsigned n) { struct socket *sock = sock_from_file(file); if (sock) sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data, (unsigned long)v); return 0; } static void net_prio_attach(struct cgroup_taskset *tset) { struct task_struct *p; struct cgroup_subsys_state *css; cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; task_lock(p); iterate_fd(p->files, 0, update_netprio, v); task_unlock(p); } } static struct cftype ss_files[] = { { .name = "prioidx", .read_u64 = read_prioidx, }, { .name = "ifpriomap", .seq_show = read_priomap, .write = write_priomap, }, { } /* terminate */ }; struct cgroup_subsys net_prio_cgrp_subsys = { .css_alloc = cgrp_css_alloc, .css_online = cgrp_css_online, .css_free = cgrp_css_free, .attach = net_prio_attach, .legacy_cftypes = ss_files, }; static int netprio_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netprio_map *old; /* * Note this is called with rtnl_lock held so we have update side * protection on our rcu assignments */ switch (event) { case NETDEV_UNREGISTER: old = rtnl_dereference(dev->priomap); RCU_INIT_POINTER(dev->priomap, NULL); if (old) kfree_rcu(old, rcu); break; } return NOTIFY_DONE; } static struct notifier_block netprio_device_notifier = { .notifier_call = netprio_device_event }; static int __init init_cgroup_netprio(void) { register_netdevice_notifier(&netprio_device_notifier); return 0; } subsys_initcall(init_cgroup_netprio); |
| 303 330 28 195 298 4 2 332 4 302 9 31 32 31 18 19 19 19 359 5 5 305 9 26 26 12 3 12 4 25 25 17 8 26 26 26 16 8 5 5 5 1 27 304 5 13 1 13 13 332 304 304 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Definitions for the 'struct sk_buff' memory handlers. * * Authors: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Florian La Roche, <rzsfl@rz.uni-sb.de> */ #ifndef _LINUX_SKBUFF_H #define _LINUX_SKBUFF_H #include <linux/kernel.h> #include <linux/compiler.h> #include <linux/time.h> #include <linux/bug.h> #include <linux/bvec.h> #include <linux/cache.h> #include <linux/rbtree.h> #include <linux/socket.h> #include <linux/refcount.h> #include <linux/atomic.h> #include <asm/types.h> #include <linux/spinlock.h> #include <net/checksum.h> #include <linux/rcupdate.h> #include <linux/dma-mapping.h> #include <linux/netdev_features.h> #include <net/flow_dissector.h> #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> #include <linux/page_frag_cache.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> #endif #include <net/net_debug.h> #include <net/dropreason-core.h> #include <net/netmem.h> /** * DOC: skb checksums * * The interface for checksum offload between the stack and networking drivers * is as follows... * * IP checksum related features * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Drivers advertise checksum offload capabilities in the features of a device. * From the stack's point of view these are capabilities offered by the driver. * A driver typically only advertises features that it is capable of offloading * to its device. * * .. flat-table:: Checksum related device features * :widths: 1 10 * * * - %NETIF_F_HW_CSUM * - The driver (or its device) is able to compute one * IP (one's complement) checksum for any combination * of protocols or protocol layering. The checksum is * computed and set in a packet per the CHECKSUM_PARTIAL * interface (see below). * * * - %NETIF_F_IP_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv4. These are specifically * unencapsulated packets of the form IPv4|TCP or * IPv4|UDP where the Protocol field in the IPv4 header * is TCP or UDP. The IPv4 header may contain IP options. * This feature cannot be set in features for a device * with NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_IPV6_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with * NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_RXCSUM * - Driver (device) performs receive checksum offload. * This flag is only used to disable the RX checksum * feature for a device. The stack will accept receive * checksum indication in packets received on a device * regardless of whether NETIF_F_RXCSUM is set. * * Checksumming of received packets by device * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Indication of checksum verification is set in &sk_buff.ip_summed. * Possible values are: * * - %CHECKSUM_NONE * * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * * - %CHECKSUM_UNNECESSARY * * The hardware you're dealing with doesn't calculate the full checksum * (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums * for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY * if their checksums are okay. &sk_buff.csum is still undefined in this case * though. A driver or device must never modify the checksum field in the * packet even if checksum is verified. * * %CHECKSUM_UNNECESSARY is applicable to following protocols: * * - TCP: IPv6 and IPv4. * - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a * zero UDP checksum for either IPv4 or IPv6, the networking stack * may perform further validation in this case. * - GRE: only if the checksum is present in the header. * - SCTP: indicates the CRC in SCTP header has been validated. * - FCOE: indicates the CRC in FC frame has been validated. * * &sk_buff.csum_level indicates the number of consecutive checksums found in * the packet minus one that have been verified as %CHECKSUM_UNNECESSARY. * For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet * and a device is able to verify the checksums for UDP (possibly zero), * GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to * two. If the device were only able to verify the UDP checksum and not * GRE, either because it doesn't support GRE checksum or because GRE * checksum is bad, skb->csum_level would be set to zero (TCP checksum is * not considered in this case). * * - %CHECKSUM_COMPLETE * * This is the most generic way. The device supplied checksum of the _whole_ * packet as seen by netif_rx() and fills in &sk_buff.csum. This means the * hardware doesn't need to parse L3/L4 headers to implement this. * * Notes: * * - Even if device supports only some protocols, but is able to produce * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * * - %CHECKSUM_PARTIAL * * A checksum is set up to be offloaded to a device as described in the * output description for CHECKSUM_PARTIAL. This may occur on a packet * received directly from another Linux OS, e.g., a virtualized Linux kernel * on the same host, or it may be set in the input path in GRO or remote * checksum offload. For the purposes of checksum verification, the checksum * referred to by skb->csum_start + skb->csum_offset and any preceding * checksums in the packet are considered verified. Any checksums in the * packet that are after the checksum being offloaded are not considered to * be verified. * * Checksumming on transmit for non-GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * The stack requests checksum offload in the &sk_buff.ip_summed for a packet. * Values are: * * - %CHECKSUM_PARTIAL * * The driver is required to checksum the packet as seen by hard_start_xmit() * from &sk_buff.csum_start up to the end, and to record/write the checksum at * offset &sk_buff.csum_start + &sk_buff.csum_offset. * A driver may verify that the * csum_start and csum_offset values are valid values given the length and * offset of the packet, but it should not attempt to validate that the * checksum refers to a legitimate transport layer checksum -- it is the * purview of the stack to validate that csum_start and csum_offset are set * correctly. * * When the stack requests checksum offload for a packet, the driver MUST * ensure that the checksum is set correctly. A driver can either offload the * checksum calculation to the device, or call skb_checksum_help (in the case * that the device does not support offload for a particular checksum). * * %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of * %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate * checksum offload capability. * skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based * on network device checksumming capabilities: if a packet does not match * them, skb_checksum_help() or skb_crc32c_help() (depending on the value of * &sk_buff.csum_not_inet, see :ref:`crc`) * is called to resolve the checksum. * * - %CHECKSUM_NONE * * The skb was already checksummed by the protocol, or a checksum is not * required. * * - %CHECKSUM_UNNECESSARY * * This has the same meaning as CHECKSUM_NONE for checksum offload on * output. * * - %CHECKSUM_COMPLETE * * Not used in checksum output. If a driver observes a packet with this value * set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set. * * .. _crc: * * Non-IP checksum (CRC) offloads * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * .. flat-table:: * :widths: 1 10 * * * - %NETIF_F_SCTP_CRC * - This feature indicates that a device is capable of * offloading the SCTP CRC in a packet. To perform this offload the stack * will set csum_start and csum_offset accordingly, set ip_summed to * %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication * in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c. * A driver that supports both IP checksum offload and SCTP CRC32c offload * must verify which offload is configured for a packet by testing the * value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to * resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. * * * - %NETIF_F_FCOE_CRC * - This feature indicates that a device is capable of offloading the FCOE * CRC in a packet. To perform this offload the stack will set ip_summed * to %CHECKSUM_PARTIAL and set csum_start and csum_offset * accordingly. Note that there is no indication in the skbuff that the * %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports * both IP checksum offload and FCOE CRC offload must verify which offload * is configured for a packet, presumably by inspecting packet headers. * * Checksumming on output with GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * In the case of a GSO packet (skb_is_gso() is true), checksum offload * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as * part of the GSO operation is implied. If a checksum is being offloaded * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and * csum_offset are set to refer to the outermost checksum being offloaded * (two offloaded checksums are possible with UDP encapsulation). */ /* Don't change this without changing skb_csum_unnecessary! */ #define CHECKSUM_NONE 0 #define CHECKSUM_UNNECESSARY 1 #define CHECKSUM_COMPLETE 2 #define CHECKSUM_PARTIAL 3 /* Maximum value in skb->csum_level */ #define SKB_MAX_CSUM_LEVEL 3 #define SKB_DATA_ALIGN(X) ALIGN(X, SMP_CACHE_BYTES) #define SKB_WITH_OVERHEAD(X) \ ((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) /* For X bytes available in skb->head, what is the minimal * allocation needed, knowing struct skb_shared_info needs * to be aligned. */ #define SKB_HEAD_ALIGN(X) (SKB_DATA_ALIGN(X) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) #define SKB_MAX_ALLOC (SKB_MAX_ORDER(0, 2)) /* return minimum truesize of one skb containing X bytes of data */ #define SKB_TRUESIZE(X) ((X) + \ SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) struct net_device; struct scatterlist; struct pipe_inode_info; struct iov_iter; struct napi_struct; struct bpf_prog; union bpf_attr; struct skb_ext; struct ts_config; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { enum { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, BRNF_PROTO_PPPOE } orig_proto:8; u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; u8 sabotage_in_done:1; __u16 frag_max_size; int physinif; /* always valid & non-NULL from FORWARD on, for physdev match */ struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; struct in6_addr ipv6_daddr; /* after prerouting + nat detected: store original source * mac since neigh resolution overwrites it, only used while * skb is out in neigh layer. */ char neigh_header[8]; }; }; #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) /* Chain in tc_skb_ext will be used to share the tc chain with * ovs recirc_id. It will be set to the current chain by tc * and read by ovs to recirc_id. */ struct tc_skb_ext { union { u64 act_miss_cookie; __u32 chain; }; __u16 mru; __u16 zone; u8 post_ct:1; u8 post_ct_snat:1; u8 post_ct_dnat:1; u8 act_miss:1; /* Set if act_miss_cookie is used */ u8 l2_miss:1; /* Set by bridge upon FDB or MDB miss */ }; #endif struct sk_buff_head { /* These two members must be first to match sk_buff. */ struct_group_tagged(sk_buff_list, list, struct sk_buff *next; struct sk_buff *prev; ); __u32 qlen; spinlock_t lock; }; struct sk_buff; #ifndef CONFIG_MAX_SKB_FRAGS # define CONFIG_MAX_SKB_FRAGS 17 #endif #define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to * segment using its current segmentation instead. */ #define GSO_BY_FRAGS 0xFFFF typedef struct skb_frag { netmem_ref netmem; unsigned int len; unsigned int offset; } skb_frag_t; /** * skb_frag_size() - Returns the size of a skb fragment * @frag: skb fragment */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { return frag->len; } /** * skb_frag_size_set() - Sets the size of a skb fragment * @frag: skb fragment * @size: size of fragment */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { frag->len = size; } /** * skb_frag_size_add() - Increments the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { frag->len += delta; } /** * skb_frag_size_sub() - Decrements the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to subtract */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { frag->len -= delta; } /** * skb_frag_must_loop - Test if %p is a high memory page * @p: fragment's page */ static inline bool skb_frag_must_loop(struct page *p) { #if defined(CONFIG_HIGHMEM) if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || PageHighMem(p)) return true; #endif return false; } /** * skb_frag_foreach_page - loop over pages in a fragment * * @f: skb frag to operate on * @f_off: offset from start of f->netmem * @f_len: length from f_off to loop over * @p: (temp var) current page * @p_off: (temp var) offset from start of current page, * non-zero only on first page. * @p_len: (temp var) length in current page, * < PAGE_SIZE only on first and last page. * @copied: (temp var) length so far, excluding current p_len. * * A fragment can hold a compound page, in which case per-page * operations, notably kmap_atomic, must be called for each * regular page. */ #define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \ for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \ p_off = (f_off) & (PAGE_SIZE - 1), \ p_len = skb_frag_must_loop(p) ? \ min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \ copied = 0; \ copied < f_len; \ copied += p_len, p++, p_off = 0, \ p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ /** * struct skb_shared_hwtstamps - hardware time stamps * @hwtstamp: hardware time stamp transformed into duration * since arbitrary point in time * @netdev_data: address/cookie of network device driver used as * reference to actual hardware time stamp * * Software time stamps generated by ktime_get_real() are stored in * skb->tstamp. * * hwtstamps can only be compared against other hwtstamps from * the same device. * * This structure is attached to packets as part of the * &skb_shared_info. Use skb_hwtstamps() to get a pointer. */ struct skb_shared_hwtstamps { union { ktime_t hwtstamp; void *netdev_data; }; }; /* Definitions for tx_flags in struct skb_shared_info */ enum { /* generate hardware time stamp */ SKBTX_HW_TSTAMP_NOBPF = 1 << 0, /* generate software time stamp when queueing packet to NIC */ SKBTX_SW_TSTAMP = 1 << 1, /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, /* generate software time stamp on packet tx completion */ SKBTX_COMPLETION_TSTAMP = 1 << 3, /* determine hardware time stamp based on time or cycles */ SKBTX_HW_TSTAMP_NETDEV = 1 << 5, /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, /* used for bpf extension when a bpf program is loaded */ SKBTX_BPF = 1 << 7, }; #define SKBTX_HW_TSTAMP (SKBTX_HW_TSTAMP_NOBPF | SKBTX_BPF) #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP | \ SKBTX_BPF | \ SKBTX_COMPLETION_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ enum { /* use zcopy routines */ SKBFL_ZEROCOPY_ENABLE = BIT(0), /* This indicates at least one fragment might be overwritten * (as in vmsplice(), sendfile() ...) * If we need to compute a TX checksum, we'll need to copy * all frags to avoid possible bad checksum */ SKBFL_SHARED_FRAG = BIT(1), /* segment contains only zerocopy data and should not be * charged to the kernel memory. */ SKBFL_PURE_ZEROCOPY = BIT(2), SKBFL_DONT_ORPHAN = BIT(3), /* page references are managed by the ubuf_info, so it's safe to * use frags only up until ubuf_info is released */ SKBFL_MANAGED_FRAG_REFS = BIT(4), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) struct ubuf_info_ops { void (*complete)(struct sk_buff *, struct ubuf_info *, bool zerocopy_success); /* has to be compatible with skb_zcopy_set() */ int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); }; /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. * The zerocopy_success argument is true if zero copy transmit occurred, * false on data copy or out of memory error caused by data copy attempt. * The ctx field is used to track device context. * The desc field is used to track userspace buffer index. */ struct ubuf_info { const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; struct ubuf_info_msgzc { struct ubuf_info ubuf; union { struct { unsigned long desc; void *ctx; }; struct { u32 id; u16 len; u16 zerocopy:1; u32 bytelen; }; }; struct mmpin { struct user_struct *user; unsigned int num_pg; } mmp; }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) #define uarg_to_msgzc(ubuf_ptr) container_of((ubuf_ptr), struct ubuf_info_msgzc, \ ubuf) int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); /* Preserve some data across TX submission and completion. * * Note, this state is stored in the driver. Extending the layout * might need some special care. */ struct xsk_tx_metadata_compl { __u64 *tx_timestamp; }; /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ struct skb_shared_info { __u8 flags; __u8 meta_len; __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; struct sk_buff *frag_list; union { struct skb_shared_hwtstamps hwtstamps; struct xsk_tx_metadata_compl xsk_meta; }; unsigned int gso_type; u32 tskey; /* * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; union { struct { u32 xdp_frags_size; u32 xdp_frags_truesize; }; /* * Intermediate layers must ensure that destructor_arg * remains valid until skb destructor. */ void *destructor_arg; }; /* must be last field, see pskb_expand_head() */ skb_frag_t frags[MAX_SKB_FRAGS]; }; /** * DOC: dataref and headerless skbs * * Transport layers send out clones of payload skbs they hold for * retransmissions. To allow lower layers of the stack to prepend their headers * we split &skb_shared_info.dataref into two halves. * The lower 16 bits count the overall number of references. * The higher 16 bits indicate how many of the references are payload-only. * skb_header_cloned() checks if skb is allowed to add / write the headers. * * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr * (via __skb_header_release()). Any clone created from marked skb will get * &sk_buff.hdr_len populated with the available headroom. * If there's the only clone in existence it's able to modify the headroom * at will. The sequence of calls inside the transport layer is:: * * <alloc skb> * skb_reserve() * __skb_header_release() * skb_clone() * // send the clone down the stack * * This is not a very generic construct and it depends on the transport layers * doing the right thing. In practice there's usually only one payload-only skb. * Having multiple payload-only skbs with different lengths of hdr_len is not * possible. The payload-only skbs should never leave their owner. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) enum { SKB_FCLONE_UNAVAILABLE, /* skb has no fclone (from head_cache) */ SKB_FCLONE_ORIG, /* orig skb (from fclone_cache) */ SKB_FCLONE_CLONE, /* companion fclone skb (from fclone_cache) */ }; enum { SKB_GSO_TCPV4 = 1 << 0, /* This indicates the skb is from an untrusted source. */ SKB_GSO_DODGY = 1 << 1, /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 2, __SKB_GSO_TCP_FIXEDID = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, SKB_GSO_FCOE = 1 << 5, SKB_GSO_GRE = 1 << 6, SKB_GSO_GRE_CSUM = 1 << 7, SKB_GSO_IPXIP4 = 1 << 8, SKB_GSO_IPXIP6 = 1 << 9, SKB_GSO_UDP_TUNNEL = 1 << 10, SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, SKB_GSO_PARTIAL = 1 << 12, SKB_GSO_TUNNEL_REMCSUM = 1 << 13, SKB_GSO_SCTP = 1 << 14, SKB_GSO_ESP = 1 << 15, SKB_GSO_UDP = 1 << 16, SKB_GSO_UDP_L4 = 1 << 17, SKB_GSO_FRAGLIST = 1 << 18, SKB_GSO_TCP_ACCECN = 1 << 19, /* These indirectly map onto the same netdev feature. * If NETIF_F_TSO_MANGLEID is set it may mangle both inner and outer IDs. */ SKB_GSO_TCP_FIXEDID = 1 << 30, SKB_GSO_TCP_FIXEDID_INNER = 1 << 31, }; #if BITS_PER_LONG > 32 #define NET_SKBUFF_DATA_USES_OFFSET 1 #endif #ifdef NET_SKBUFF_DATA_USES_OFFSET typedef unsigned int sk_buff_data_t; #else typedef unsigned char *sk_buff_data_t; #endif enum skb_tstamp_type { SKB_CLOCK_REALTIME, SKB_CLOCK_MONOTONIC, SKB_CLOCK_TAI, __SKB_CLOCK_MAX = SKB_CLOCK_TAI, }; /** * DOC: Basic sk_buff geometry * * struct sk_buff itself is a metadata structure and does not hold any packet * data. All the data is held in associated buffers. * * &sk_buff.head points to the main "head" buffer. The head buffer is divided * into two parts: * * - data buffer, containing headers and sometimes payload; * this is the part of the skb operated on by the common helpers * such as skb_put() or skb_pull(); * - shared info (struct skb_shared_info) which holds an array of pointers * to read-only data in the (page, offset, length) format. * * Optionally &skb_shared_info.frag_list may point to another skb. * * Basic diagram may look like this:: * * --------------- * | sk_buff | * --------------- * ,--------------------------- + head * / ,----------------- + data * / / ,----------- + tail * | | | , + end * | | | | * v v v v * ----------------------------------------------- * | headroom | data | tailroom | skb_shared_info | * ----------------------------------------------- * + [page frag] * + [page frag] * + [page frag] * + [page frag] --------- * + frag_list --> | sk_buff | * --------- * */ /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list * @tstamp: Time we arrived/left * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp * @list: queue head * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header * @hdr_len: writable header length of cloned skb * @csum: Checksum (must include start/offset pair) * @csum_start: Offset from skb->head where checksumming should start * @csum_offset: Offset from csum_start where checksum should be stored * @priority: Packet queueing priority * @ignore_df: allow local fragmentation * @cloned: Head may be cloned (check refcnt to be sure) * @ip_summed: Driver fed us an IP checksum * @nohdr: Payload reference only, must not modify header * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs * @inner_protocol_type: whether the inner protocol is * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO * @remcsum_offload: remote checksum offload is enabled * @offload_fwd_mark: Packet was L2-forwarded in hardware * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress * @redirected: packet was redirected by packet classifier * @from_ingress: packet was redirected from the ingress path * @nf_skip_egress: packet shall skip nf egress - see netfilter_netdev.h * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_sk_redir: socket redirection information for skmsg * @_nfct: Associated connection, if any (with nfctinfo bits) * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @pp_recycle: mark the packet for recycling instead of freeing (implies * page_pool support on driver) * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport * ports. * @sw_hash: indicates hash was computed in software stack * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @encapsulation: indicates the inner headers in the skbuff are valid * @encap_hdr_csum: software checksum is needed * @csum_valid: checksum is already valid * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @csum_complete_sw: checksum was completed by software * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) * @unreadable: indicates that at least 1 of the fragments in this skb is * unreadable. * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required * @tstamp_type: When set, skb->tstamp has the * delivery_time clock base of skb->tstamp. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. * @secmark: security marking * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available * at the tail of an sk_buff * @vlan_all: vlan fields (proto & tci) * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) * @inner_ipproto: (aka @inner_protocol) stores ipproto when * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO; * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) * @inner_mac_header: Link layer header (encapsulation) * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header * @kcov_handle: KCOV remote handle for remote coverage collection * @tail: Tail pointer * @end: End pointer * @head: Head of buffer * @data: Data head pointer * @truesize: Buffer size * @users: User count - see {datagram,tcp}.c * @extensions: allocated extensions, valid if active_extensions is nonzero */ struct sk_buff { union { struct { /* These two members must be first to match sk_buff_head. */ struct sk_buff *next; struct sk_buff *prev; union { struct net_device *dev; /* Some protocols might use this space to store information, * while device pointer would be NULL. * UDP receive path is one user. */ unsigned long dev_scratch; }; }; struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; struct llist_node ll_node; }; struct sock *sk; union { ktime_t tstamp; u64 skb_mstamp_ns; /* earliest departure time */ }; /* * This is the control buffer. It is free to use for every * layer. Please put your private variables there. If you * want to keep them across layers you have to do a skb_clone() * first. This is owned by whoever has the skb queued ATM. */ char cb[48] __aligned(8); union { struct { unsigned long _skb_refdst; void (*destructor)(struct sk_buff *skb); }; struct list_head tcp_tsorted_anchor; #ifdef CONFIG_NET_SOCK_MSG unsigned long _sk_redir; #endif }; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) unsigned long _nfct; #endif unsigned int len, data_len; __u16 mac_len, hdr_len; /* Following fields are _not_ copied in __copy_skb_header() * Note that queue_mapping is here mostly to fill a hole. */ __u16 queue_mapping; /* if you move cloned around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define CLONED_MASK (1 << 7) #else #define CLONED_MASK 1 #endif #define CLONED_OFFSET offsetof(struct sk_buff, __cloned_offset) /* private: */ __u8 __cloned_offset[0]; /* public: */ __u8 cloned:1, nohdr:1, fclone:2, peeked:1, head_frag:1, pfmemalloc:1, pp_recycle:1; /* page_pool recycle indicator */ #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif /* Fields enclosed in headers group are copied * using a single memcpy() in __copy_skb_header() */ struct_group(headers, /* private: */ __u8 __pkt_type_offset[0]; /* public: */ __u8 pkt_type:3; /* see PKT_TYPE_MAX */ __u8 ignore_df:1; __u8 dst_pending_confirm:1; __u8 ip_summed:2; __u8 ooo_okay:1; /* private: */ __u8 __mono_tc_offset[0]; /* public: */ __u8 tstamp_type:2; /* See skb_tstamp_type */ #ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; #endif __u8 remcsum_offload:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 inner_protocol_type:1; __u8 l4_hash:1; __u8 sw_hash:1; #ifdef CONFIG_WIRELESS __u8 wifi_acked_valid:1; __u8 wifi_acked:1; #endif __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif #if IS_ENABLED(CONFIG_IP_VS) __u8 ipvs_property:1; #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) __u8 nf_trace:1; #endif #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; #endif __u8 redirected:1; #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif #ifdef CONFIG_NETFILTER_SKIP_EGRESS __u8 nf_skip_egress:1; #endif #ifdef CONFIG_SKB_DECRYPTED __u8 decrypted:1; #endif __u8 slow_gro:1; #if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; #endif __u8 unreadable:1; #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif u16 alloc_cpu; union { __wsum csum; struct { __u16 csum_start; __u16 csum_offset; }; }; __u32 priority; int skb_iif; __u32 hash; union { u32 vlan_all; struct { __be16 vlan_proto; __u16 vlan_tci; }; }; #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) union { unsigned int napi_id; unsigned int sender_cpu; }; #endif #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif union { __u32 mark; __u32 reserved_tailroom; }; union { __be16 inner_protocol; __u8 inner_ipproto; }; __u16 inner_transport_header; __u16 inner_network_header; __u16 inner_mac_header; __be16 protocol; __u16 transport_header; __u16 network_header; __u16 mac_header; #ifdef CONFIG_KCOV u64 kcov_handle; #endif ); /* end headers group */ /* These elements must be at the end, see alloc_skb() for details. */ sk_buff_data_t tail; sk_buff_data_t end; unsigned char *head, *data; unsigned int truesize; refcount_t users; #ifdef CONFIG_SKB_EXTENSIONS /* only usable after checking ->active_extensions != 0 */ struct skb_ext *extensions; #endif }; /* if you move pkt_type around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define PKT_TYPE_MAX (7 << 5) #else #define PKT_TYPE_MAX 7 #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) /* if you move tc_at_ingress or tstamp_type * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD #define SKB_TSTAMP_TYPE_MASK (3 << 6) #define SKB_TSTAMP_TYPE_RSHIFT (6) #define TC_AT_INGRESS_MASK (1 << 5) #else #define SKB_TSTAMP_TYPE_MASK (3) #define TC_AT_INGRESS_MASK (1 << 2) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel */ #define SKB_ALLOC_FCLONE 0x01 #define SKB_ALLOC_RX 0x02 #define SKB_ALLOC_NAPI 0x04 /** * skb_pfmemalloc - Test if the skb was allocated from PFMEMALLOC reserves * @skb: buffer */ static inline bool skb_pfmemalloc(const struct sk_buff *skb) { return unlikely(skb->pfmemalloc); } /* * skb might have a dst pointer attached, refcounted or not. * _skb_refdst low order bit is set if refcount was _not_ taken */ #define SKB_DST_NOREF 1UL #define SKB_DST_PTRMASK ~(SKB_DST_NOREF) /** * skb_dst - returns skb dst_entry * @skb: buffer * * Returns: skb dst_entry, regardless of reference taken or not. */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { /* If refdst was not refcounted, check we still are in a * rcu_read_lock section */ WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) && !rcu_read_lock_held() && !rcu_read_lock_bh_held()); return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK); } static inline void skb_dst_check_unset(struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE((skb->_skb_refdst & SKB_DST_PTRMASK) && !(skb->_skb_refdst & SKB_DST_NOREF)); } /** * skb_dstref_steal() - return current dst_entry value and clear it * @skb: buffer * * Resets skb dst_entry without adjusting its reference count. Useful in * cases where dst_entry needs to be temporarily reset and restored. * Note that the returned value cannot be used directly because it * might contain SKB_DST_NOREF bit. * * When in doubt, prefer skb_dst_drop() over skb_dstref_steal() to correctly * handle dst_entry reference counting. * * Returns: original skb dst_entry. */ static inline unsigned long skb_dstref_steal(struct sk_buff *skb) { unsigned long refdst = skb->_skb_refdst; skb->_skb_refdst = 0; return refdst; } /** * skb_dstref_restore() - restore skb dst_entry removed via skb_dstref_steal() * @skb: buffer * @refdst: dst entry from a call to skb_dstref_steal() */ static inline void skb_dstref_restore(struct sk_buff *skb, unsigned long refdst) { skb_dst_check_unset(skb); skb->_skb_refdst = refdst; } /** * skb_dst_set - sets skb dst * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was taken on dst and should * be released by skb_dst_drop() */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { skb_dst_check_unset(skb); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst; } /** * skb_dst_set_noref - sets skb dst, hopefully, without taking reference * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was not taken on dst. * If dst entry is cached, we do not take reference and dst_release * will be avoided by refdst_drop. If dst entry is not cached, we take * reference, so that last dst_release can destroy the dst immediately. */ static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { skb_dst_check_unset(skb); WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; } /** * skb_dst_is_noref - Test if skb dst isn't refcounted * @skb: buffer */ static inline bool skb_dst_is_noref(const struct sk_buff *skb) { return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. */ static inline bool skb_pkt_type_ok(u32 ptype) { return ptype <= PACKET_OTHERHOST; } /** * skb_napi_id - Returns the skb's NAPI id * @skb: buffer */ static inline unsigned int skb_napi_id(const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL return skb->napi_id; #else return 0; #endif } static inline bool skb_wifi_acked_valid(const struct sk_buff *skb) { #ifdef CONFIG_WIRELESS return skb->wifi_acked_valid; #else return 0; #endif } /** * skb_unref - decrement the skb's reference count * @skb: buffer * * Returns: true if we can free the skb. */ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; if (!IS_ENABLED(CONFIG_DEBUG_NET) && likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; return true; } static inline bool skb_data_unref(const struct sk_buff *skb, struct skb_shared_info *shinfo) { int bias; if (!skb->cloned) return true; bias = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; if (atomic_read(&shinfo->dataref) == bias) smp_rmb(); else if (atomic_sub_return(bias, &shinfo->dataref)) return false; return true; } void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason); static inline void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) { sk_skb_reason_drop(NULL, skb, reason); } /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason * @skb: buffer to free */ static inline void kfree_skb(struct sk_buff *skb) { kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } void skb_release_head_state(struct sk_buff *skb); void kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); static inline void kfree_skb_list(struct sk_buff *segs) { kfree_skb_list_reason(segs, SKB_DROP_REASON_NOT_SPECIFIED); } #ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); #else static inline void consume_skb(struct sk_buff *skb) { return kfree_skb(skb); } #endif void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize); struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); void skb_attempt_defer_free(struct sk_buff *skb); u32 napi_skb_cache_get_bulk(void **skbs, u32 n); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); struct sk_buff *slab_build_skb(void *data); /** * alloc_skb - allocate a network buffer * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, 0, NUMA_NO_NODE); } struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int max_page_order, int *errcode, gfp_t gfp_mask); struct sk_buff *alloc_skb_for_msg(struct sk_buff *first); /* Layout of fast clones : [skb1][skb2][fclone_ref] */ struct sk_buff_fclones { struct sk_buff skb1; struct sk_buff skb2; refcount_t fclone_ref; }; /** * skb_fclone_busy - check if fclone is busy * @sk: socket * @skb: buffer * * Returns: true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that didn't happen. */ static inline bool skb_fclone_busy(const struct sock *sk, const struct sk_buff *skb) { const struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); return skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) > 1 && READ_ONCE(fclones->skb2.sk) == sk; } /** * alloc_skb_fclone - allocate a network buffer from fclone cache * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); void skb_headers_offset_update(struct sk_buff *skb, int off); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority); struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone); static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, headroom, gfp_mask, false); } int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask); struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error); /** * skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error. */ static inline int skb_pad(struct sk_buff *skb, int pad) { return __skb_pad(skb, pad, true); } #define dev_kfree_skb(a) consume_skb(a) int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size, size_t max_frags); struct skb_seq_state { __u32 lower_offset; __u32 upper_offset; __u32 frag_idx; __u32 stepped_offset; struct sk_buff *root_skb; struct sk_buff *cur_skb; __u8 *frag_data; __u32 frag_off; }; void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st); unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st); void skb_abort_seq_read(struct skb_seq_state *st); int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len); unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config); /* * Packet hash types specify the type of hash in skb_set_hash. * * Hash types refer to the protocol layer addresses which are used to * construct a packet's hash. The hashes are used to differentiate or identify * flows of the protocol layer for the hash type. Hash types are either * layer-2 (L2), layer-3 (L3), or layer-4 (L4). * * Properties of hashes: * * 1) Two packets in different flows have different hash values * 2) Two packets in the same flow should have the same hash value * * A hash at a higher layer is considered to be more specific. A driver should * set the most specific hash possible. * * A driver cannot indicate a more specific hash than the layer at which a hash * was computed. For instance an L3 hash cannot be set as an L4 hash. * * A driver may indicate a hash level which is less specific than the * actual layer the hash was computed on. For instance, a hash computed * at L4 may be considered an L3 hash. This should only be done if the * driver can't unambiguously determine that the HW computed the hash at * the higher layer. Note that the "should" in the second property above * permits this. */ enum pkt_hash_types { PKT_HASH_TYPE_NONE, /* Undefined type */ PKT_HASH_TYPE_L2, /* Input: src_MAC, dest_MAC */ PKT_HASH_TYPE_L3, /* Input: src_IP, dst_IP */ PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */ }; static inline void skb_clear_hash(struct sk_buff *skb) { skb->hash = 0; skb->sw_hash = 0; skb->l4_hash = 0; } static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) { if (!skb->l4_hash) skb_clear_hash(skb); } static inline void __skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4) { skb->l4_hash = is_l4; skb->sw_hash = is_sw; skb->hash = hash; } static inline void skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) { /* Used by drivers to set hash from HW */ __skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4); } static inline void __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) { __skb_set_hash(skb, hash, true, is_l4); } u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb); static inline u32 __skb_get_hash_symmetric(const struct sk_buff *skb) { return __skb_get_hash_symmetric_net(NULL, skb); } void __skb_get_hash_net(const struct net *net, struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen); __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, const void *data, int hlen_proto); void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); struct bpf_flow_dissector; u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags); static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { return __skb_flow_dissect(NULL, skb, flow_dissector, target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, struct flow_keys *flow, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(NULL, skb, &flow_keys_dissector, flow, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys_basic(const struct net *net, const struct sk_buff *skb, struct flow_keys_basic *flow, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); /* Gets a skb connection tracking info, ctinfo map should be a * map of mapsize to translate enum ip_conntrack_info states * to user states. */ void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, bool post_ct, u16 zone); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); static inline __u32 skb_get_hash_net(const struct net *net, struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(net, skb); return skb->hash; } static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(NULL, skb); return skb->hash; } static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { struct flow_keys keys; __u32 hash = __get_hash_from_flowi6(fl6, &keys); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } return skb->hash; } __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { return skb->hash; } static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) { to->hash = from->hash; to->sw_hash = from->sw_hash; to->l4_hash = from->l4_hash; }; static inline int skb_cmp_decrypted(const struct sk_buff *skb1, const struct sk_buff *skb2) { #ifdef CONFIG_SKB_DECRYPTED return skb2->decrypted - skb1->decrypted; #else return 0; #endif } static inline bool skb_is_decrypted(const struct sk_buff *skb) { #ifdef CONFIG_SKB_DECRYPTED return skb->decrypted; #else return false; #endif } static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { #ifdef CONFIG_SKB_DECRYPTED to->decrypted = from->decrypted; #endif } #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->head + skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = offset; } #else static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end - skb->head; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = skb->head + offset; } #endif extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg, bool devmem); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); struct net_devmem_dmabuf_binding; int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length, struct net_devmem_dmabuf_binding *binding); int zerocopy_fill_skb_from_iter(struct sk_buff *skb, struct iov_iter *from, size_t length); static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len, NULL); } int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg, struct net_devmem_dmabuf_binding *binding); /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) { return &skb_shinfo(skb)->hwtstamps; } static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) { bool is_zcopy = skb && skb_shinfo(skb)->flags & SKBFL_ZEROCOPY_ENABLE; return is_zcopy ? skb_uarg(skb) : NULL; } static inline bool skb_zcopy_pure(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; } static inline bool skb_zcopy_managed(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAG_REFS; } static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, const struct sk_buff *skb2) { return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2); } static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); } static inline void skb_zcopy_init(struct sk_buff *skb, struct ubuf_info *uarg) { skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->flags |= uarg->flags; } static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, bool *have_ref) { if (skb && uarg && !skb_zcopy(skb)) { if (unlikely(have_ref && *have_ref)) *have_ref = false; else net_zcopy_get(uarg); skb_zcopy_init(skb, uarg); } } static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) { skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; } static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) { return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL; } static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) { return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); } static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); } } /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) { struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { if (!skb_zcopy_is_nouarg(skb)) uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } } void __skb_zcopy_downgrade_managed(struct sk_buff *skb); static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) { if (unlikely(skb_zcopy_managed(skb))) __skb_zcopy_downgrade_managed(skb); } /* Return true if frags in this skb are readable by the host. */ static inline bool skb_frags_readable(const struct sk_buff *skb) { return !skb->unreadable; } static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; } static inline void skb_poison_list(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET skb->next = SKB_LIST_POISON_NEXT; #endif } /* Iterate through singly-linked GSO fragments of an skb. */ #define skb_list_walk_safe(first, skb, next_skb) \ for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \ (skb) = (next_skb), (next_skb) = (skb) ? (skb)->next : NULL) static inline void skb_list_del_init(struct sk_buff *skb) { __list_del_entry(&skb->list); skb_mark_not_on_list(skb); } /** * skb_queue_empty - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. */ static inline int skb_queue_empty(const struct sk_buff_head *list) { return list->next == (const struct sk_buff *) list; } /** * skb_queue_empty_lockless - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. * This variant can be used in lockless contexts. */ static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list) { return READ_ONCE(list->next) == (const struct sk_buff *) list; } /** * skb_queue_is_last - check if skb is the last entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the last buffer on the list. */ static inline bool skb_queue_is_last(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->next == (const struct sk_buff *) list; } /** * skb_queue_is_first - check if skb is the first entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the first buffer on the list. */ static inline bool skb_queue_is_first(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->prev == (const struct sk_buff *) list; } /** * skb_queue_next - return the next packet in the queue * @list: queue head * @skb: current buffer * * Return the next packet in @list after @skb. It is only valid to * call this if skb_queue_is_last() evaluates to false. */ static inline struct sk_buff *skb_queue_next(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_last(list, skb)); return skb->next; } /** * skb_queue_prev - return the prev packet in the queue * @list: queue head * @skb: current buffer * * Return the prev packet in @list before @skb. It is only valid to * call this if skb_queue_is_first() evaluates to false. */ static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_first(list, skb)); return skb->prev; } /** * skb_get - reference buffer * @skb: buffer to reference * * Makes another reference to a socket buffer and returns a pointer * to the buffer. */ static inline struct sk_buff *skb_get(struct sk_buff *skb) { refcount_inc(&skb->users); return skb; } /* * If users == 1, we are the only owner and can avoid redundant atomic changes. */ /** * skb_cloned - is the buffer a clone * @skb: buffer to check * * Returns true if the buffer was generated with skb_clone() and is * one of multiple shared copies of the buffer. Cloned buffers are * shared data so must not be written to under normal circumstances. */ static inline int skb_cloned(const struct sk_buff *skb) { return skb->cloned && (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1; } static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /* This variant of skb_unclone() makes sure skb->truesize * and skb_end_offset() are not changed, whenever a new skb->head is needed. * * Indeed there is no guarantee that ksize(kmalloc(X)) == ksize(kmalloc(X)) * when various debugging features are in place. */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri); static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return __skb_unclone_keeptruesize(skb, pri); return 0; } /** * skb_header_cloned - is the header a clone * @skb: buffer to check * * Returns true if modifying the header part of the buffer requires * the data to be copied. */ static inline int skb_header_cloned(const struct sk_buff *skb) { int dataref; if (!skb->cloned) return 0; dataref = atomic_read(&skb_shinfo(skb)->dataref); dataref = (dataref & SKB_DATAREF_MASK) - (dataref >> SKB_DATAREF_SHIFT); return dataref != 1; } static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_header_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /** * __skb_header_release() - allow clones to use the headroom * @skb: buffer to operate on * * See "DOC: dataref and headerless skbs". */ static inline void __skb_header_release(struct sk_buff *skb) { skb->nohdr = 1; atomic_set(&skb_shinfo(skb)->dataref, 1 + (1 << SKB_DATAREF_SHIFT)); } /** * skb_shared - is the buffer shared * @skb: buffer to check * * Returns true if more than one person has a reference to this * buffer. */ static inline int skb_shared(const struct sk_buff *skb) { return refcount_read(&skb->users) != 1; } /** * skb_share_check - check if buffer is shared and if so clone it * @skb: buffer to check * @pri: priority for memory allocation * * If the buffer is shared the buffer is cloned and the old copy * drops a reference. A new clone with a single reference is returned. * If the buffer is not shared the original buffer is returned. When * being called from interrupt status or with spinlocks held pri must * be GFP_ATOMIC. * * NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /* * Copy shared buffers into a new sk_buff. We effectively do COW on * packets to handle cases where we have a local reader and forward * and a couple of other messy ones. The normal one is tcpdumping * a packet that's being forwarded. */ /** * skb_unshare - make a copy of a shared buffer * @skb: buffer to check * @pri: priority for memory allocation * * If the socket buffer is a clone then this function creates a new * copy of the data, drops a reference count on the old copy and returns * the new copy with the reference count at 1. If the buffer is not a clone * the original buffer is returned. When called with a spinlock held or * from interrupt state @pri must be %GFP_ATOMIC * * %NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_unshare(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, pri); /* Free our shared copy */ if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /** * skb_peek - peek at the head of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the head element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) { struct sk_buff *skb = list_->next; if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * __skb_peek - peek at the head of a non-empty &sk_buff_head * @list_: list to peek at * * Like skb_peek(), but the caller knows that the list is not empty. */ static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) { return list_->next; } /** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from * @list_: list to peek at * * Returns %NULL when the end of the list is met or a pointer to the * next element. The reference count is not incremented and the * reference is therefore volatile. Use with caution. */ static inline struct sk_buff *skb_peek_next(struct sk_buff *skb, const struct sk_buff_head *list_) { struct sk_buff *next = skb->next; if (next == (struct sk_buff *)list_) next = NULL; return next; } /** * skb_peek_tail - peek at the tail of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the tail element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_) { struct sk_buff *skb = READ_ONCE(list_->prev); if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * skb_queue_len - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. */ static inline __u32 skb_queue_len(const struct sk_buff_head *list_) { return list_->qlen; } /** * skb_queue_len_lockless - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. * This variant can be used in lockless contexts. */ static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_) { return READ_ONCE(list_->qlen); } /** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize * * This initializes only the list and queue length aspects of * an sk_buff_head object. This allows to initialize the list * aspects of an sk_buff_head without reinitializing things like * the spinlock. It can also be used for on-stack sk_buff_head * objects where the spinlock is known to not be used. */ static inline void __skb_queue_head_init(struct sk_buff_head *list) { list->prev = list->next = (struct sk_buff *)list; list->qlen = 0; } /* * This function creates a split out lock class for each invocation; * this is needed for now since a whole lot of users of the skb-queue * infrastructure in drivers have different locking usage (in hardirq) * than the networking core (in softirq only). In the long run either the * network layer or drivers should need annotation to consolidate the * main types of usage into 3 classes. */ static inline void skb_queue_head_init(struct sk_buff_head *list) { spin_lock_init(&list->lock); __skb_queue_head_init(list); } static inline void skb_queue_head_init_class(struct sk_buff_head *list, struct lock_class_key *class) { skb_queue_head_init(list); lockdep_set_class(&list->lock, class); } /* * Insert an sk_buff on a list. * * The "__skb_xxxx()" functions are the non-atomic ones that * can only be called with interrupts disabled. */ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { /* See skb_queue_empty_lockless() and skb_peek_tail() * for the opposite READ_ONCE() */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(((struct sk_buff_list *)next)->prev, newsk); WRITE_ONCE(((struct sk_buff_list *)prev)->next, newsk); WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *next) { struct sk_buff *first = list->next; struct sk_buff *last = list->prev; WRITE_ONCE(first->prev, prev); WRITE_ONCE(prev->next, first); WRITE_ONCE(last->next, next); WRITE_ONCE(next->prev, last); } /** * skb_queue_splice - join two skb lists, this is designed for stacks * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; } } /** * skb_queue_splice_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * The list at @list is reinitialised */ static inline void skb_queue_splice_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * skb_queue_splice_tail - join two skb lists, each list being a queue * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice_tail(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; } } /** * skb_queue_splice_tail_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void skb_queue_splice_tail_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * __skb_queue_after - queue a buffer at the list head * @list: list to use * @prev: place after this buffer * @newsk: buffer to queue * * Queue a buffer int the middle of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { __skb_insert(newsk, prev, ((struct sk_buff_list *)prev)->next, list); } void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); static inline void __skb_queue_before(struct sk_buff_head *list, struct sk_buff *next, struct sk_buff *newsk) { __skb_insert(newsk, ((struct sk_buff_list *)next)->prev, next, list); } /** * __skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_after(list, (struct sk_buff *)list, newsk); } void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk); /** * __skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the end of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_before(list, (struct sk_buff *)list, newsk); } void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk); /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list); static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; WRITE_ONCE(list->qlen, list->qlen - 1); next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; WRITE_ONCE(next->prev, prev); WRITE_ONCE(prev->next, next); } /** * __skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. This function does not take any locks * so must be used with appropriate locks held only. The head item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue(struct sk_buff_head *list); /** * __skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. This function does not take any locks * so must be used with appropriate locks held only. The tail item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek_tail(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list); static inline bool skb_is_nonlinear(const struct sk_buff *skb) { return skb->data_len; } static inline unsigned int skb_headlen(const struct sk_buff *skb) { return skb->len - skb->data_len; } static inline unsigned int __skb_pagelen(const struct sk_buff *skb) { unsigned int i, len = 0; for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); return len; } static inline unsigned int skb_pagelen(const struct sk_buff *skb) { return skb_headlen(skb) + __skb_pagelen(skb); } static inline void skb_frag_fill_netmem_desc(skb_frag_t *frag, netmem_ref netmem, int off, int size) { frag->netmem = netmem; frag->offset = off; skb_frag_size_set(frag, size); } static inline void skb_frag_fill_page_desc(skb_frag_t *frag, struct page *page, int off, int size) { skb_frag_fill_netmem_desc(frag, page_to_netmem(page), off, size); } static inline void __skb_fill_netmem_desc_noacc(struct skb_shared_info *shinfo, int i, netmem_ref netmem, int off, int size) { skb_frag_t *frag = &shinfo->frags[i]; skb_frag_fill_netmem_desc(frag, netmem, off, size); } static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc_noacc(shinfo, i, page_to_netmem(page), off, size); } /** * skb_len_add - adds a number to len fields of skb * @skb: buffer to add len to * @delta: number of bytes to add */ static inline void skb_len_add(struct sk_buff *skb, int delta) { skb->len += delta; skb->data_len += delta; skb->truesize += delta; } /** * __skb_fill_netmem_desc - initialise a fragment in an skb * @skb: buffer containing fragment to be initialised * @i: fragment index to initialise * @netmem: the netmem to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Initialises the @i'th fragment of @skb to point to &size bytes at * offset @off within @page. * * Does not take any additional reference on the fragment. */ static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { struct page *page; __skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size); if (netmem_is_net_iov(netmem)) { skb->unreadable = true; return; } page = netmem_to_page(netmem); /* Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). */ page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } static inline void skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { __skb_fill_netmem_desc(skb, i, netmem, off, size); skb_shinfo(skb)->nr_frags = i + 1; } /** * skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * As per __skb_fill_page_desc() -- initialises the @i'th fragment of * @skb to point to @size bytes at offset @off within @page. In * addition updates @skb such that @i is the last fragment. * * Does not take any additional reference on the fragment. */ static inline void skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } /** * skb_fill_page_desc_noacc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Variant of skb_fill_page_desc() which does not deal with * pfmemalloc, if page is not owned by us. */ static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i, struct page *page, int off, int size) { struct skb_shared_info *shinfo = skb_shinfo(skb); __skb_fill_page_desc_noacc(shinfo, i, page, off, size); shinfo->nr_frags = i + 1; } void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size, unsigned int truesize); static inline void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, unsigned int truesize) { skb_add_rx_frag_netmem(skb, i, page_to_netmem(page), off, size, truesize); } void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize); #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->head + skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data - skb->head; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb_reset_tail_pointer(skb); skb->tail += offset; } #else /* NET_SKBUFF_DATA_USES_OFFSET */ static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb->tail = skb->data + offset; } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ static inline void skb_assert_len(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET if (WARN_ONCE(!skb->len, "%s\n", __func__)) DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); #endif /* CONFIG_DEBUG_NET */ } #if defined(CONFIG_FAIL_SKB_REALLOC) void skb_might_realloc(struct sk_buff *skb); #else static inline void skb_might_realloc(struct sk_buff *skb) {} #endif /* * Add data to an sk_buff */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len); void *skb_put(struct sk_buff *skb, unsigned int len); static inline void *__skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; return tmp; } static inline void *__skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = __skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *__skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = __skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void __skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)__skb_put(skb, 1) = val; } static inline void *skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)skb_put(skb, 1) = val; } void *skb_push(struct sk_buff *skb, unsigned int len); static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->data -= len; skb->len += len; return skb->data; } void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->len -= len; if (unlikely(skb->len < skb->data_len)) { #if defined(CONFIG_DEBUG_NET) skb->len += len; pr_err("__skb_pull(len=%u)\n", len); skb_dump(KERN_ERR, skb, false); #endif BUG(); } return skb->data += len; } static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } void *skb_pull_data(struct sk_buff *skb, size_t len); void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb_might_realloc(skb); if (likely(len <= skb_headlen(skb))) return SKB_NOT_DROPPED_YET; if (unlikely(len > skb->len)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (unlikely(!__pskb_pull_tail(skb, len - skb_headlen(skb)))) return SKB_DROP_REASON_NOMEM; return SKB_NOT_DROPPED_YET; } static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) { if (!pskb_may_pull(skb, len)) return NULL; skb->len -= len; return skb->data += len; } void skb_condense(struct sk_buff *skb); /** * skb_headroom - bytes at buffer head * @skb: buffer to check * * Return the number of bytes of free space at the head of an &sk_buff. */ static inline unsigned int skb_headroom(const struct sk_buff *skb) { return skb->data - skb->head; } /** * skb_tailroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff */ static inline int skb_tailroom(const struct sk_buff *skb) { return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail; } /** * skb_availroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff * allocated by sk_stream_alloc() */ static inline int skb_availroom(const struct sk_buff *skb) { if (skb_is_nonlinear(skb)) return 0; return skb->end - skb->tail - skb->reserved_tailroom; } /** * skb_reserve - adjust headroom * @skb: buffer to alter * @len: bytes to move * * Increase the headroom of an empty &sk_buff by reducing the tail * room. This is only allowed for an empty buffer. */ static inline void skb_reserve(struct sk_buff *skb, int len) { skb->data += len; skb->tail += len; } /** * skb_tailroom_reserve - adjust reserved_tailroom * @skb: buffer to alter * @mtu: maximum amount of headlen permitted * @needed_tailroom: minimum amount of reserved_tailroom * * Set reserved_tailroom so that headlen can be as large as possible but * not larger than mtu and tailroom cannot be smaller than * needed_tailroom. * The required headroom should already have been reserved before using * this function. */ static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, unsigned int needed_tailroom) { SKB_LINEAR_ASSERT(skb); if (mtu < skb_tailroom(skb) - needed_tailroom) /* use at most mtu */ skb->reserved_tailroom = skb_tailroom(skb) - mtu; else /* use up to all available space */ skb->reserved_tailroom = needed_tailroom; } #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 static inline void skb_set_inner_protocol(struct sk_buff *skb, __be16 protocol) { skb->inner_protocol = protocol; skb->inner_protocol_type = ENCAP_TYPE_ETHER; } static inline void skb_set_inner_ipproto(struct sk_buff *skb, __u8 ipproto) { skb->inner_ipproto = ipproto; skb->inner_protocol_type = ENCAP_TYPE_IPPROTO; } static inline void skb_reset_inner_headers(struct sk_buff *skb) { skb->inner_mac_header = skb->mac_header; skb->inner_network_header = skb->network_header; skb->inner_transport_header = skb->transport_header; } static inline int skb_mac_header_was_set(const struct sk_buff *skb) { return skb->mac_header != (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_len(struct sk_buff *skb) { if (!skb_mac_header_was_set(skb)) { DEBUG_NET_WARN_ON_ONCE(1); skb->mac_len = 0; } else { skb->mac_len = skb->network_header - skb->mac_header; } } static inline unsigned char *skb_inner_transport_header(const struct sk_buff *skb) { return skb->head + skb->inner_transport_header; } static inline int skb_inner_transport_offset(const struct sk_buff *skb) { return skb_inner_transport_header(skb) - skb->data; } static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_transport_header))offset); skb->inner_transport_header = offset; } static inline void skb_set_inner_transport_header(struct sk_buff *skb, const int offset) { skb_reset_inner_transport_header(skb); skb->inner_transport_header += offset; } static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) { return skb->head + skb->inner_network_header; } static inline void skb_reset_inner_network_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_network_header))offset); skb->inner_network_header = offset; } static inline void skb_set_inner_network_header(struct sk_buff *skb, const int offset) { skb_reset_inner_network_header(skb); skb->inner_network_header += offset; } static inline bool skb_inner_network_header_was_set(const struct sk_buff *skb) { return skb->inner_network_header > 0; } static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) { return skb->head + skb->inner_mac_header; } static inline void skb_reset_inner_mac_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_mac_header))offset); skb->inner_mac_header = offset; } static inline void skb_set_inner_mac_header(struct sk_buff *skb, const int offset) { skb_reset_inner_mac_header(skb); skb->inner_mac_header += offset; } static inline bool skb_transport_header_was_set(const struct sk_buff *skb) { return skb->transport_header != (typeof(skb->transport_header))~0U; } static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->head + skb->transport_header; } static inline void skb_reset_transport_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->transport_header))offset); skb->transport_header = offset; } /** * skb_reset_transport_header_careful - conditionally reset transport header * @skb: buffer to alter * * Hardened version of skb_reset_transport_header(). * * Returns: true if the operation was a success. */ static inline bool __must_check skb_reset_transport_header_careful(struct sk_buff *skb) { long offset = skb->data - skb->head; if (unlikely(offset != (typeof(skb->transport_header))offset)) return false; if (unlikely(offset == (typeof(skb->transport_header))~0U)) return false; skb->transport_header = offset; return true; } static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { skb_reset_transport_header(skb); skb->transport_header += offset; } static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; } static inline void skb_reset_network_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->network_header))offset); skb->network_header = offset; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) { skb_reset_network_header(skb); skb->network_header += offset; } static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->head + skb->mac_header; } static inline int skb_mac_offset(const struct sk_buff *skb) { return skb_mac_header(skb) - skb->data; } static inline u32 skb_mac_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->network_header - skb->mac_header; } static inline void skb_unset_mac_header(struct sk_buff *skb) { skb->mac_header = (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->mac_header))offset); skb->mac_header = offset; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) { skb_reset_mac_header(skb); skb->mac_header += offset; } static inline void skb_pop_mac_header(struct sk_buff *skb) { skb->mac_header = skb->network_header; } static inline void skb_probe_transport_header(struct sk_buff *skb) { struct flow_keys_basic keys; if (skb_transport_header_was_set(skb)) return; if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); } static inline void skb_mac_header_rebuild(struct sk_buff *skb) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -skb->mac_len); memmove(skb_mac_header(skb), old_mac, skb->mac_len); } } /* Move the full mac header up to current network_header. * Leaves skb->data pointing at offset skb->mac_len into the mac_header. * Must be provided the complete mac header length. */ static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -full_mac_len); memmove(skb_mac_header(skb), old_mac, full_mac_len); __skb_push(skb, full_mac_len - skb->mac_len); } } static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); } static inline unsigned char *skb_checksum_start(const struct sk_buff *skb) { return skb->head + skb->csum_start; } static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; } static inline u32 skb_network_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->transport_header - skb->network_header; } static inline u32 skb_inner_network_header_len(const struct sk_buff *skb) { return skb->inner_transport_header - skb->inner_network_header; } static inline int skb_network_offset(const struct sk_buff *skb) { return skb_network_header(skb) - skb->data; } static inline int skb_inner_network_offset(const struct sk_buff *skb) { return skb_inner_network_header(skb) - skb->data; } static inline enum skb_drop_reason pskb_network_may_pull_reason(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, skb_network_offset(skb) + len); } static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_network_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } /* * CPUs often take a performance hit when accessing unaligned memory * locations. The actual performance hit varies, it can be small if the * hardware handles it or large if we have to take an exception and fix it * in software. * * Since an ethernet header is 14 bytes network drivers often end up with * the IP header at an unaligned offset. The IP header can be aligned by * shifting the start of the packet by 2 bytes. Drivers should do this * with: * * skb_reserve(skb, NET_IP_ALIGN); * * The downside to this alignment of the IP header is that the DMA is now * unaligned. On some architectures the cost of an unaligned DMA is high * and this cost outweighs the gains made by aligning the IP header. * * Since this trade off varies between architectures, we allow NET_IP_ALIGN * to be overridden. */ #ifndef NET_IP_ALIGN #define NET_IP_ALIGN 2 #endif /* * The networking layer reserves some headroom in skb data (via * dev_alloc_skb). This is used to avoid having to reallocate skb data when * the header has to grow. In the default case, if the header has to grow * 32 bytes or less we avoid the reallocation. * * Unfortunately this headroom changes the DMA alignment of the resulting * network packet. As for NET_IP_ALIGN, this unaligned DMA is expensive * on some architectures. An architecture can override this value, * perhaps setting it to a cacheline in size (since that will maintain * cacheline alignment of the DMA). It must be a power of 2. * * Various parts of the networking layer expect at least 32 bytes of * headroom, you should not reduce this. * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD #define NET_SKB_PAD max(32, L1_CACHE_BYTES) #endif int ___pskb_trim(struct sk_buff *skb, unsigned int len); static inline void __skb_set_length(struct sk_buff *skb, unsigned int len) { if (WARN_ON(skb_is_nonlinear(skb))) return; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void __skb_trim(struct sk_buff *skb, unsigned int len) { __skb_set_length(skb, len); } void skb_trim(struct sk_buff *skb, unsigned int len); static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) { if (skb->data_len) return ___pskb_trim(skb, len); __skb_trim(skb, len); return 0; } static inline int pskb_trim(struct sk_buff *skb, unsigned int len) { skb_might_realloc(skb); return (len < skb->len) ? __pskb_trim(skb, len) : 0; } /** * pskb_trim_unique - remove end from a paged unique (not cloned) buffer * @skb: buffer to alter * @len: new length * * This is identical to pskb_trim except that the caller knows that * the skb is not cloned so we should never get an error due to out- * of-memory. */ static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len) { int err = pskb_trim(skb, len); BUG_ON(err); } static inline int __skb_grow(struct sk_buff *skb, unsigned int len) { unsigned int diff = len - skb->len; if (skb_tailroom(skb) < diff) { int ret = pskb_expand_head(skb, 0, diff - skb_tailroom(skb), GFP_ATOMIC); if (ret) return ret; } __skb_set_length(skb, len); return 0; } /** * skb_orphan - orphan a buffer * @skb: buffer to orphan * * If a buffer currently has an owner then we call the owner's * destructor function and make the @skb unowned. The buffer continues * to exist but is no longer charged to its former owner. */ static inline void skb_orphan(struct sk_buff *skb) { if (skb->destructor) { skb->destructor(skb); skb->destructor = NULL; skb->sk = NULL; } else { BUG_ON(skb->sk); } } /** * skb_orphan_frags - orphan the frags contained in a buffer * @skb: buffer to orphan frags from * @gfp_mask: allocation mask for replacement pages * * For each frag in the SKB which needs a destructor (i.e. has an * owner) create a copy of that frag and release the original * page by calling the destructor. */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; if (skb_shinfo(skb)->flags & SKBFL_DONT_ORPHAN) return 0; return skb_copy_ubufs(skb, gfp_mask); } /* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } /** * __skb_queue_purge_reason - empty a list * @list: list to empty * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function does not take the * list lock and the caller must hold the relevant locks to use it. */ static inline void __skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason) { struct sk_buff *skb; while ((skb = __skb_dequeue(list)) != NULL) kfree_skb_reason(skb, reason); } static inline void __skb_queue_purge(struct sk_buff_head *list) { __skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } void skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason); static inline void skb_queue_purge(struct sk_buff_head *list) { skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } unsigned int skb_rbtree_purge(struct rb_root *root); void skb_errqueue_purge(struct sk_buff_head *list); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); /** * netdev_alloc_frag - allocate a page fragment * @fragsz: fragment size * * Allocates a frag from a page for receive buffer. * Uses GFP_ATOMIC allocations. */ static inline void *netdev_alloc_frag(unsigned int fragsz) { return __netdev_alloc_frag_align(fragsz, ~0u); } static inline void *netdev_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __netdev_alloc_frag_align(fragsz, -align); } struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask); /** * netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @length: length to allocate * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has unspecified headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. Although this function * allocates memory it can be called from an interrupt. */ static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb(dev, length, GFP_ATOMIC); } /* legacy helper around __netdev_alloc_skb() */ static inline struct sk_buff *__dev_alloc_skb(unsigned int length, gfp_t gfp_mask) { return __netdev_alloc_skb(NULL, length, gfp_mask); } /* legacy helper around netdev_alloc_skb() */ static inline struct sk_buff *dev_alloc_skb(unsigned int length) { return netdev_alloc_skb(NULL, length); } static inline struct sk_buff *__netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length, gfp_t gfp) { struct sk_buff *skb = __netdev_alloc_skb(dev, length + NET_IP_ALIGN, gfp); if (NET_IP_ALIGN && skb) skb_reserve(skb, NET_IP_ALIGN); return skb; } static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); } static inline void skb_free_frag(void *addr) { page_frag_free(addr); } void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); static inline void *napi_alloc_frag(unsigned int fragsz) { return __napi_alloc_frag_align(fragsz, ~0u); } static inline void *napi_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __napi_alloc_frag_align(fragsz, -align); } struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length); void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); /** * __dev_alloc_pages - allocate page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * @order: size of the allocation * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. * 1. This is for device Rx, therefore a cold page is preferred. * 2. The expectation is the user wants a compound page. * 3. If requesting a order 0 page it will not be compound * due to the check to see if order has a value in prep_new_page * 4. __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to * code in gfp_to_alloc_flags that should be enforcing this. */ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC; return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order); } #define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** * __dev_alloc_page - allocate a page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) { return __dev_alloc_pages_noprof(gfp_mask, 0); } #define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_page() dev_alloc_pages(0) /** * dev_page_is_reusable - check whether a page can be reused for network Rx * @page: the page to test * * A page shouldn't be considered for reusing/recycling if it was allocated * under memory pressure or at a distant memory node. * * Returns: false if this page should be returned to page allocator, true * otherwise. */ static inline bool dev_page_is_reusable(const struct page *page) { return likely(page_to_nid(page) == numa_mem_id() && !page_is_pfmemalloc(page)); } /** * skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page * @page: The page that was allocated from skb_alloc_page * @skb: The skb that may need pfmemalloc set */ static inline void skb_propagate_pfmemalloc(const struct page *page, struct sk_buff *skb) { if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } /** * skb_frag_off() - Returns the offset of a skb fragment * @frag: the paged fragment */ static inline unsigned int skb_frag_off(const skb_frag_t *frag) { return frag->offset; } /** * skb_frag_off_add() - Increments the offset of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) { frag->offset += delta; } /** * skb_frag_off_set() - Sets the offset of a skb fragment * @frag: skb fragment * @offset: offset of fragment */ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) { frag->offset = offset; } /** * skb_frag_off_copy() - Sets the offset of a skb fragment from another fragment * @fragto: skb fragment where offset is set * @fragfrom: skb fragment offset is copied from */ static inline void skb_frag_off_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->offset = fragfrom->offset; } /* Return: true if the skb_frag contains a net_iov. */ static inline bool skb_frag_is_net_iov(const skb_frag_t *frag) { return netmem_is_net_iov(frag->netmem); } /** * skb_frag_net_iov - retrieve the net_iov referred to by fragment * @frag: the fragment * * Return: the &struct net_iov associated with @frag. Returns NULL if this * frag has no associated net_iov. */ static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag) { if (!skb_frag_is_net_iov(frag)) return NULL; return netmem_to_net_iov(frag->netmem); } /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * * Return: the &struct page associated with @frag. Returns NULL if this frag * has no associated page. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { if (skb_frag_is_net_iov(frag)) return NULL; return netmem_to_page(frag->netmem); } /** * skb_frag_netmem - retrieve the netmem referred to by a fragment * @frag: the fragment * * Return: the &netmem_ref associated with @frag. */ static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag) { return frag->netmem; } int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, const struct bpf_prog *prog); /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns: the address of the data within @frag. The page must already * be mapped. */ static inline void *skb_frag_address(const skb_frag_t *frag) { if (!skb_frag_page(frag)) return NULL; return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } /** * skb_frag_address_safe - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns: the address of the data within @frag. Checks that the page * is mapped and returns %NULL otherwise. */ static inline void *skb_frag_address_safe(const skb_frag_t *frag) { struct page *page = skb_frag_page(frag); void *ptr; if (!page) return NULL; ptr = page_address(page); if (unlikely(!ptr)) return NULL; return ptr + skb_frag_off(frag); } /** * skb_frag_page_copy() - sets the page in a fragment from another fragment * @fragto: skb fragment where page is set * @fragfrom: skb fragment page is copied from */ static inline void skb_frag_page_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->netmem = fragfrom->netmem; } bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** * __skb_frag_dma_map - maps a paged fragment via the DMA API * @dev: the device to map the fragment to * @frag: the paged fragment to map * @offset: the offset within the fragment (starting at the * fragment's own offset) * @size: the number of bytes to map * @dir: the direction of the mapping (``PCI_DMA_*``) * * Maps the page associated with @frag to @device. */ static inline dma_addr_t __skb_frag_dma_map(struct device *dev, const skb_frag_t *frag, size_t offset, size_t size, enum dma_data_direction dir) { if (skb_frag_is_net_iov(frag)) { return netmem_to_net_iov(frag->netmem)->dma_addr + offset + frag->offset; } return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); } #define skb_frag_dma_map(dev, frag, ...) \ CONCATENATE(_skb_frag_dma_map, \ COUNT_ARGS(__VA_ARGS__))(dev, frag, ##__VA_ARGS__) #define __skb_frag_dma_map1(dev, frag, offset, uf, uo) ({ \ const skb_frag_t *uf = (frag); \ size_t uo = (offset); \ \ __skb_frag_dma_map(dev, uf, uo, skb_frag_size(uf) - uo, \ DMA_TO_DEVICE); \ }) #define _skb_frag_dma_map1(dev, frag, offset) \ __skb_frag_dma_map1(dev, frag, offset, __UNIQUE_ID(frag_), \ __UNIQUE_ID(offset_)) #define _skb_frag_dma_map0(dev, frag) \ _skb_frag_dma_map1(dev, frag, 0) #define _skb_frag_dma_map2(dev, frag, offset, size) \ __skb_frag_dma_map(dev, frag, offset, size, DMA_TO_DEVICE) #define _skb_frag_dma_map3(dev, frag, offset, size, dir) \ __skb_frag_dma_map(dev, frag, offset, size, dir) static inline struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy(skb, skb_headroom(skb), gfp_mask); } static inline struct sk_buff *pskb_copy_for_clone(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, skb_headroom(skb), gfp_mask, true); } /** * skb_clone_writable - is the header of a clone writable * @skb: buffer to check * @len: length up to which to write * * Returns true if modifying the header part of the cloned buffer * does not requires the data to be copied. */ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len) { return !skb_header_cloned(skb) && skb_headroom(skb) + len <= skb->hdr_len; } static inline int skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return skb_cloned(skb) && !skb_clone_writable(skb, write_len) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom, int cloned) { int delta = 0; if (headroom > skb_headroom(skb)) delta = headroom - skb_headroom(skb); if (delta || cloned) return pskb_expand_head(skb, ALIGN(delta, NET_SKB_PAD), 0, GFP_ATOMIC); return 0; } /** * skb_cow - copy header of skb when it is required * @skb: buffer to cow * @headroom: needed headroom * * If the skb passed lacks sufficient headroom or its data part * is shared, data is reallocated. If reallocation fails, an error * is returned and original skb is not changed. * * The result is skb with writable area skb->head...skb->tail * and at least @headroom of space at head. */ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_cloned(skb)); } /** * skb_cow_head - skb_cow but only making the head writable * @skb: buffer to cow * @headroom: needed headroom * * This function is identical to skb_cow except that we replace the * skb_cloned check by skb_header_cloned. It should be used when * you only need to push on some header and do not need to modify * the data. */ static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_header_cloned(skb)); } /** * skb_padto - pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int skb_padto(struct sk_buff *skb, unsigned int len) { unsigned int size = skb->len; if (likely(size >= len)) return 0; return skb_pad(skb, len - size); } /** * __skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * @free_on_error: free buffer on error * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ static inline int __must_check __skb_put_padto(struct sk_buff *skb, unsigned int len, bool free_on_error) { unsigned int size = skb->len; if (unlikely(size < len)) { len -= size; if (__skb_pad(skb, len, free_on_error)) return -ENOMEM; __skb_put(skb, len); } return 0; } /** * skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) __must_check; static inline bool skb_can_coalesce_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off) { if (skb_zcopy(skb)) return false; if (i) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return netmem == skb_frag_netmem(frag) && off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { return skb_can_coalesce_netmem(skb, i, page_to_netmem(page), off); } static inline int __skb_linearize(struct sk_buff *skb) { return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM; } /** * skb_linearize - convert paged skb to linear one * @skb: buffer to linarize * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize(struct sk_buff *skb) { return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0; } /** * skb_has_shared_frag - can any frag be overwritten * @skb: buffer to test * * Return: true if the skb has at least one frag that might be modified * by an external entity (as in vmsplice()/sendfile()) */ static inline bool skb_has_shared_frag(const struct sk_buff *skb) { return skb_is_nonlinear(skb) && skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; } /** * skb_linearize_cow - make sure skb is linear and writable * @skb: buffer to process * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize_cow(struct sk_buff *skb) { return skb_is_nonlinear(skb) || skb_cloned(skb) ? __skb_linearize(skb) : 0; } static __always_inline void __skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_sub(skb->csum, csum_partial(start, len, 0), off); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } /** * skb_postpull_rcsum - update checksum for received skb after pull * @skb: buffer to update * @start: start of data before pull * @len: length of data pulled * * After doing a pull on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = wsum_negate(csum_partial(start, len, wsum_negate(skb->csum))); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } static __always_inline void __skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_add(skb->csum, csum_partial(start, len, 0), off); } /** * skb_postpush_rcsum - update checksum for received skb after push * @skb: buffer to update * @start: start of data after push * @len: length of data pushed * * After doing a push on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum. */ static inline void skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { __skb_postpush_rcsum(skb, start, len, 0); } void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); /** * skb_push_rcsum - push skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_push on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_push unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len) { skb_push(skb, len); skb_postpush_rcsum(skb, skb->data, len); return skb->data; } int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim * @len: new length * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { skb_might_realloc(skb); if (likely(len >= skb->len)) return 0; return pskb_trim_rcsum_slow(skb, len); } static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; __skb_trim(skb, len); return 0; } static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; return __skb_grow(skb, len); } #define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) #define skb_rb_first(root) rb_to_skb(rb_first(root)) #define skb_rb_last(root) rb_to_skb(rb_last(root)) #define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) #define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_queue_walk_safe(queue, skb, tmp) \ for (skb = (queue)->next, tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_walk_from(queue, skb) \ for (; skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_rbtree_walk(skb, root) \ for (skb = skb_rb_first(root); skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from(skb) \ for (; skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from_safe(skb, tmp) \ for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \ skb = tmp) #define skb_queue_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_reverse_walk(queue, skb) \ for (skb = (queue)->prev; \ skb != (struct sk_buff *)(queue); \ skb = skb->prev) #define skb_queue_reverse_walk_safe(queue, skb, tmp) \ for (skb = (queue)->prev, tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) #define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) static inline bool skb_has_frag_list(const struct sk_buff *skb) { return skb_shinfo(skb)->frag_list != NULL; } static inline void skb_frag_list_init(struct sk_buff *skb) { skb_shinfo(skb)->frag_list = NULL; } #define skb_walk_frags(skb, iter) \ for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, int *err, long *timeo_p, const struct sk_buff *skb); struct sk_buff *__skb_try_recv_from_queue(struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); __poll_t datagram_poll_queue(struct file *file, struct socket *sock, struct poll_table_struct *wait, struct sk_buff_head *rcv_queue); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, struct iov_iter *to, int size); static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, struct msghdr *msg, int size) { return skb_copy_datagram_iter(from, offset, &msg->msg_iter, size); } int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, struct msghdr *msg); int skb_copy_and_crc32c_datagram_iter(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, u32 *crcp); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int skb_copy_datagram_from_iter_full(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len); int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); int skb_send_sock_locked_with_flags(struct sock *sk, struct sk_buff *skb, int offset, int len, int flags); int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen); void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_eth_pop(struct sk_buff *skb); int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len) { return copy_from_iter_full(data, len, &msg->msg_iter) ? 0 : -EFAULT; } static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) { return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; } __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); u32 skb_crc32c(const struct sk_buff *skb, int offset, int len, u32 crc); static inline void * __must_check __skb_header_pointer(const struct sk_buff *skb, int offset, int len, const void *data, int hlen, void *buffer) { if (likely(hlen - offset >= len)) return (void *)data + offset; if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) return NULL; return buffer; } static inline void * __must_check skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { return __skb_header_pointer(skb, offset, len, skb->data, skb_headlen(skb), buffer); } static inline void * __must_check skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) { if (likely(skb_headlen(skb) - offset >= len)) return skb->data + offset; return NULL; } /** * skb_needs_linearize - check if we need to linearize a given skb * depending on the given device features. * @skb: socket buffer to check * @features: net device features * * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or * 2. skb is fragmented and the device does not support SG. */ static inline bool skb_needs_linearize(struct sk_buff *skb, netdev_features_t features) { return skb_is_nonlinear(skb) && ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) || (skb_shinfo(skb)->nr_frags && !(features & NETIF_F_SG))); } static inline void skb_copy_from_linear_data(const struct sk_buff *skb, void *to, const unsigned int len) { memcpy(to, skb->data, len); } static inline void skb_copy_from_linear_data_offset(const struct sk_buff *skb, const int offset, void *to, const unsigned int len) { memcpy(to, skb->data + offset, len); } static inline void skb_copy_to_linear_data(struct sk_buff *skb, const void *from, const unsigned int len) { memcpy(skb->data, from, len); } static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb, const int offset, const void *from, const unsigned int len) { memcpy(skb->data + offset, from, len); } void skb_init(void); static inline ktime_t skb_get_ktime(const struct sk_buff *skb) { return skb->tstamp; } /** * skb_get_timestamp - get timestamp from a skb * @skb: skb to get stamp from * @stamp: pointer to struct __kernel_old_timeval to store stamp in * * Timestamps are stored in the skb as offsets to a base timestamp. * This function converts the offset back to a struct timeval and stores * it in stamp. */ static inline void skb_get_timestamp(const struct sk_buff *skb, struct __kernel_old_timeval *stamp) { *stamp = ns_to_kernel_old_timeval(skb->tstamp); } static inline void skb_get_new_timestamp(const struct sk_buff *skb, struct __kernel_sock_timeval *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_usec = ts.tv_nsec / 1000; } static inline void skb_get_timestampns(const struct sk_buff *skb, struct __kernel_old_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void skb_get_new_timestampns(const struct sk_buff *skb, struct __kernel_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline ktime_t net_timedelta(ktime_t t) { return ktime_sub(ktime_get_real(), t); } static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, u8 tstamp_type) { skb->tstamp = kt; if (kt) skb->tstamp_type = tstamp_type; else skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb, ktime_t kt, clockid_t clockid) { u8 tstamp_type = SKB_CLOCK_REALTIME; switch (clockid) { case CLOCK_REALTIME: break; case CLOCK_MONOTONIC: tstamp_type = SKB_CLOCK_MONOTONIC; break; case CLOCK_TAI: tstamp_type = SKB_CLOCK_TAI; break; default: WARN_ON_ONCE(1); kt = 0; } skb_set_delivery_time(skb, kt, tstamp_type); } DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); /* It is used in the ingress path to clear the delivery_time. * If needed, set the skb->tstamp to the (rcv) timestamp. */ static inline void skb_clear_delivery_time(struct sk_buff *skb) { if (skb->tstamp_type) { skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); else skb->tstamp = 0; } } static inline void skb_clear_tstamp(struct sk_buff *skb) { if (skb->tstamp_type) return; skb->tstamp = 0; } static inline ktime_t skb_tstamp(const struct sk_buff *skb) { if (skb->tstamp_type) return 0; return skb->tstamp; } static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) { if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp) return skb->tstamp; if (static_branch_unlikely(&netstamp_needed_key) || cond) return ktime_get_real(); return 0; } static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; } static inline void *skb_metadata_end(const struct sk_buff *skb) { return skb_mac_header(skb); } static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b, u8 meta_len) { const void *a = skb_metadata_end(skb_a); const void *b = skb_metadata_end(skb_b); u64 diffs = 0; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || BITS_PER_LONG != 64) goto slow; /* Using more efficient variant than plain call to memcmp(). */ switch (meta_len) { #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); fallthrough; case 24: diffs |= __it_diff(a, b, 64); fallthrough; case 16: diffs |= __it_diff(a, b, 64); fallthrough; case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); fallthrough; case 20: diffs |= __it_diff(a, b, 64); fallthrough; case 12: diffs |= __it_diff(a, b, 64); fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; default: slow: return memcmp(a - meta_len, b - meta_len, meta_len); } return diffs; } static inline bool skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { u8 len_a = skb_metadata_len(skb_a); u8 len_b = skb_metadata_len(skb_b); if (!(len_a | len_b)) return false; return len_a != len_b ? true : __skb_metadata_differs(skb_a, skb_b, len_a); } static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) { skb_shinfo(skb)->meta_len = meta_len; } static inline void skb_metadata_clear(struct sk_buff *skb) { skb_metadata_set(skb, 0); } struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING void skb_clone_tx_timestamp(struct sk_buff *skb); bool skb_defer_rx_timestamp(struct sk_buff *skb); #else /* CONFIG_NETWORK_PHY_TIMESTAMPING */ static inline void skb_clone_tx_timestamp(struct sk_buff *skb) { } static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) { return false; } #endif /* !CONFIG_NETWORK_PHY_TIMESTAMPING */ /** * skb_complete_tx_timestamp() - deliver cloned skb with tx timestamps * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers * must call this function to return the skb back to the stack with a * timestamp. * * @skb: clone of the original outgoing packet * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps); void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype); /** * skb_tstamp_tx - queue clone of skb with send time stamps * @orig_skb: the original outgoing packet * @hwtstamps: hardware time stamps, may be NULL if not available * * If the skb has a socket associated, then this function clones the * skb (thus sharing the actual data and optional structures), stores * the optional hardware time stamping information (if non NULL) or * generates a software time stamp (otherwise), then queues the clone * to the error queue of the socket. Errors are silently ignored. */ void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps); /** * skb_tx_timestamp() - Driver hook for transmit timestamping * * Ethernet MAC Drivers should call this function in their hard_xmit() * function immediately before giving the sk_buff to the MAC hardware. * * Specifically, one should make absolutely sure that this function is * called before TX completion of this packet can trigger. Otherwise * the packet could potentially already be freed. * * @skb: A socket buffer. */ static inline void skb_tx_timestamp(struct sk_buff *skb) { skb_clone_tx_timestamp(skb); if (skb_shinfo(skb)->tx_flags & (SKBTX_SW_TSTAMP | SKBTX_B |